Language：English   Publishing type：Research paper (scientific journal)   Publisher：Springer Science and Business Media LLC  

DOI： 10.1007/s11547-024-01947-z

Web of Science

Scopus

PubMed

Other Link： https://link.springer.com/article/10.1007/s11547-024-01947-z/fulltext.html

Language：English   Publisher：Annals of Nuclear Medicine  

The article ‘Generative AI and large language models in nuclear medicine: current status and future prospects’, written by Kenji Hirata, Yusuke Matsui, Akira Yamada, Tomoyuki Fujioka, Masahiro Yanagawa, Takeshi Nakaura, Rintaro Ito, Daiju Ueda, Shohei Fujita, Fuminari Tatsugami, Yasutaka Fushimi, Takahiro Tsuboyama, Koji Kamagata, Taiki Nozaki, Noriyuki Fujima, Mariko Kawamura, Shinji Naganawa, was originally published under exclusive license to The Japanese Society of Nuclear Medicine. As a result of the subsequent decision to publish the article under the open access model, the article’s copyright notice was changed on 22 January 2025 to © The Author(s) 2025 and the article is now distributed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by/4.0/. The original article has been corrected.

DOI： 10.1007/s12149-025-02024-9

Open Access

Web of Science

Scopus

PubMed

Language：English   Publishing type：Research paper (scientific journal)   Publisher：Japanese Society for Magnetic Resonance in Medicine  

PURPOSE: The purpose of this study was to assess the extent to which improvement in sleep with lemborexant contributed to changes in interstitial fluid dynamics. METHODS: The 3 methods including diffusion tensor image analysis along the perivascular space (DTI-ALPS), dynamic contrast-enhanced method to assess tissue vascular permeability (Ktrans), and choroid plexus volume (CPV) were used. Correlations between these imaging indices and sleep parameters (latency to persistent sleep [LPS], wake after sleep onset [WASO], total sleep time [TST], and sleep efficiency [SE]) were evaluated using Pearson correlation analysis. Additionally, multiple regression analysis and linear mixed model analysis were employed to assess the relationship between baseline sleep status and imaging parameter changes. MRI and sleep assessments were performed before treatment initiation (week 0, w0) and at 12 weeks after lemborexant administration (week 12, w12). RESULTS: The ALPS-index was inversely correlated with LPS and positively correlated with TST and SE at w0. In multiple regression analysis, ALPS-index was lower when sleep parameters other than LPS were poor at w0. A linear mixed model analysis suggested that poor sleep status in LPS and SE at w0 may have an effect on greater ALPS-index. In the evaluation of Ktrans measurement, the single regression analysis showed a statistically significant correlation between the reduction in Ktrans and the shortening in LPS. Examination of CPV and sleep parameters showed a significant negative correlation between TST and CPV at w0 and w12. Multiple regression analysis also showed that TST of w12 had a significant effect on CPV at w12. CONCLUSION: Our results suggested that poor sleep status is related to the greater change of ALPS-index and CPV improvement after lemborexant administration may be related to in part to sleep parameter improvement.

DOI： 10.2463/mrms.mp.2024-0176

Web of Science

PubMed

CiNii Research

Language：English   Publisher：European Radiology  

Objectives: Chest wall infiltration in primary lung cancer affects the surgical and therapeutic strategies. This study evaluates the efficacy of the chest wall vessel involvement in subpleural lung cancer (CWVI)　on ultra-high-resolution CT (UHR-CT) for detecting chest wall invasion. Materials and methods: A retrospective analysis of lung cancer cases with confirmed pleural and chest wall invasion was conducted from November 2019 to April 2022. Seventy-seven patients (mean ± standard deviation age 70 ± 8 years, 64 males) who underwent preoperative contrast-enhanced UHR-CT were included. They were grouped into 51 non-chest wall infiltration (pl1 and pl2) and 26 chest wall infiltration (pl3). Clinical, histopathological, and UHR-CT findings were reviewed. Results: Upper lobe tumors exhibited a higher chest wall invasion rate (p < 0.001). Rib destruction was evident in five patients with chest wall invasion but none with pleural invasion (p < 0.001). CWVI was present in 19 of 26 patients with chest wall invasion and 2 of 51 patients with pleural invasion (p < 0.001). The maximum tumor diameter (Dmax), arch distance which means the interface length between the primary tumor and the chest wall (Adist), and the ratio of Dmax to Adist were higher in chest wall invasion cases (all p < 0.001). After excluding patients with rib destruction, in multivariate logistic regression analysis, only CWVI was a significant predictor for chest wall invasion (odds ratio 29.22 (95% confidence interval 9.13–262.90), p < 0.001). Conclusion: CWVI on UHR-CT can help diagnose lung cancer infiltrating the chest wall, offering a potential tool for clinical decision-making. Key Points: Question Chest wall infiltration in primary lung cancer has implications for the treatment plan, but diagnosis is often difficult with conventional CT. Findings Chest wall vessel involvement in subpleural lung cancer on ultra-high-resolution CT is a valuable predictor for diagnosing chest wall infiltration. Clinical relevance The delineation of chest wall vessels with contrast-enhanced ultra-high-resolution CT may improve the diagnosis of chest wall infiltration and allow accurate staging and optimal treatment options for subpleural primary lung cancer.

DOI： 10.1007/s00330-025-11382-x

Open Access

Web of Science

Scopus

PubMed

Language：English   Publishing type：Research paper (scientific journal)  

Ventricular tachycardia (VT) is a severe arrhythmia commonly treated with implantable cardioverter defibrillators, antiarrhythmic drugs and catheter ablation (CA). Although CA is effective in reducing recurrent VT, its impact on survival remains uncertain, especially in patients with extensive scarring. Stereotactic arrhythmia radioablation (STAR) has emerged as a novel treatment for VT in patients unresponsive to CA, leveraging techniques from stereotactic body radiation therapy used in cancer treatments. Recent clinical trials and case series have demonstrated the short-term efficacy and safety of STAR, although long-term outcomes remain unclear. Imaging techniques, such as electroanatomical mapping, contrast-enhanced magnetic resonance imaging and nuclear imaging, play a crucial role in treatment planning by identifying VT substrates and guiding target delineation. However, challenges persist owing to the complex anatomy and variability in target volume definitions. Advances in imaging and artificial intelligence are expected to improve the precision and efficacy of STAR. The exact mechanisms underlying the antiarrhythmic effects of STAR, including potential fibrosis and improvement in cardiac conduction, are still being explored. Despite its potential, STAR should be cautiously applied in prospective clinical trials, with a focus on optimizing dose delivery and understanding long-term outcomes. Collaborative efforts are necessary to standardize treatment strategies and enhance the quality of life for patients with refractory VT.

DOI： 10.1093/jrr/rrae090

Web of Science

Scopus

PubMed

Language：English   Publisher：Japanese Society for Magnetic Resonance in Medicine  

<p>Purpose: A cyst-like structure near superior sagittal sinus (Arachnoid Cuff Exit Site cysts: ACES cysts) has been reported in MRI. The purpose of this study was to investigate the association between presence of ACES cysts and cognitive function, as assessed using mini-mental state examination (MMSE) scores.</p><p>Methods: We retrospectively analyzed patients who underwent head MRI for dementia screening. Differences in patient ages and MMSE scores between patients with and without ACES cysts were examined using the Mann-Whitney <i>U</i> test. Correlations between patient ages and MMSE scores were examined for patients with and without ACES cysts using Spearman’s rank correlation coefficient. Multivariate logistic regression analysis was performed to examine the influence of presence or absence of ACES cysts on MMSE score.</p><p>Results: A total of 112 patients (male: 28, female: 84) were included for the analysis. The patient ages ranged from 66 to 94 years (median: 83 years). MMSE scores ranged from 6 to 30 (median: 24). ACES cysts were detected in 57 patients (50.9%). There was no significant difference in patient ages between the patients with and without ACES cysts (<i>P</i> = 0.058). The patients with ACES cysts showed significantly lower MMSE scores compared to the patients without ACES cysts (<i>P</i> < 0.001). In the patients with ACES cysts, there was no significant correlation between patient ages and MMSE scores (<i>ρ</i> = −0.178, <i>P</i> = 0.185), whereas a significant negative correlation was observed in the patients without ACES cysts (<i>ρ </i>= −0.347, <i>P</i> = 0.001). The presence of ACES cysts was determined as an independent predictor for the lower MMSE score (odds ratio = 15.2, 95% confidence interval = 5.59–41.4, <i>P</i> < 0.001).</p><p>Conclusion: The presence of the ACES cysts showed significant association with lower MMSE score. ACES cysts might be involved in the pathological processes affecting cognitive function.</p>

DOI： 10.2463/mrms.mp.2024-0138

Web of Science

PubMed

CiNii Research

Language：English   Publishing type：Research paper (scientific journal)  

This review explores the potential applications of Large Language Models (LLMs) in nuclear medicine, especially nuclear medicine examinations such as PET and SPECT, reviewing recent advancements in both fields. Despite the rapid adoption of LLMs in various medical specialties, their integration into nuclear medicine has not yet been sufficiently explored. We first discuss the latest developments in nuclear medicine, including new radiopharmaceuticals, imaging techniques, and clinical applications. We then analyze how LLMs are being utilized in radiology, particularly in report generation, image interpretation, and medical education. We highlight the potential of LLMs to enhance nuclear medicine practices, such as improving report structuring, assisting in diagnosis, and facilitating research. However, challenges remain, including the need for improved reliability, explainability, and bias reduction in LLMs. The review also addresses the ethical considerations and potential limitations of AI in healthcare. In conclusion, LLMs have significant potential to transform existing frameworks in nuclear medicine, making it a critical area for future research and development.

DOI： 10.1007/s12149-024-01981-x

Web of Science

Scopus

PubMed

Language：English   Publishing type：Research paper (scientific journal)   Publisher：Japanese Society for Magnetic Resonance in Medicine  

The integration of deep learning (DL) in breast MRI has revolutionized the field of medical imaging, notably enhancing diagnostic accuracy and efficiency. This review discusses the substantial influence of DL technologies across various facets of breast MRI, including image reconstruction, classification, object detection, segmentation, and prediction of clinical outcomes such as response to neoadjuvant chemotherapy and recurrence of breast cancer. Utilizing sophisticated models such as convolutional neural networks, recurrent neural networks, and generative adversarial networks, DL has improved image quality and precision, enabling more accurate differentiation between benign and malignant lesions and providing deeper insights into disease behavior and treatment responses. DL's predictive capabilities for patient-specific outcomes also suggest potential for more personalized treatment strategies. The advancements in DL are pioneering a new era in breast cancer diagnostics, promising more personalized and effective healthcare solutions. Nonetheless, the integration of this technology into clinical practice faces challenges, necessitating further research, validation, and development of legal and ethical frameworks to fully leverage its potential.

DOI： 10.2463/mrms.rev.2024-0056

Web of Science

PubMed

CiNii Research

Language：English   Publishing type：Research paper (scientific journal)   Publisher：Springer Science and Business Media LLC  

Abstract

Interventional oncology provides image-guided therapies, including transarterial tumor embolization and percutaneous tumor ablation, for malignant tumors in a minimally invasive manner. As in other medical fields, the application of artificial intelligence (AI) in interventional oncology has garnered significant attention. This narrative review describes the current state of AI applications in interventional oncology based on recent literature. A literature search revealed a rapid increase in the number of studies relevant to this topic recently. Investigators have attempted to use AI for various tasks, including automatic segmentation of organs, tumors, and treatment areas; treatment simulation; improvement of intraprocedural image quality; prediction of treatment outcomes; and detection of post-treatment recurrence. Among these, the AI-based prediction of treatment outcomes has been the most studied. Various deep and conventional machine learning algorithms have been proposed for these tasks. Radiomics has often been incorporated into prediction and detection models. Current literature suggests that AI is potentially useful in various aspects of interventional oncology, from treatment planning to post-treatment follow-up. However, most AI-based methods discussed in this review are still at the research stage, and few have been implemented in clinical practice. To achieve widespread adoption of AI technologies in interventional oncology procedures, further research on their reliability and clinical utility is necessary. Nevertheless, considering the rapid research progress in this field, various AI technologies will be integrated into interventional oncology practices in the near future.

DOI： 10.1007/s11604-024-01668-3

PubMed

Other Link： https://link.springer.com/article/10.1007/s11604-024-01668-3/fulltext.html

Language：English   Publisher：Japanese Journal of Radiology  

Medicine and deep learning-based artificial intelligence (AI) engineering represent two distinct fields each with decades of published history. The current rapid convergence of deep learning and medicine has led to significant advancements, yet it has also introduced ambiguity regarding data set terms common to both fields, potentially leading to miscommunication and methodological discrepancies. This narrative review aims to give historical context for these terms, accentuate the importance of clarity when these terms are used in medical deep learning contexts, and offer solutions to mitigate misunderstandings by readers from either field. Through an examination of historical documents, including articles, writing guidelines, and textbooks, this review traces the divergent evolution of terms for data sets and their impact. Initially, the discordant interpretations of the word ‘validation’ in medical and AI contexts are explored. We then show that in the medical field as well, terms traditionally used in the deep learning domain are becoming more common, with the data for creating models referred to as the ‘training set’, the data for tuning of parameters referred to as the ‘validation (or tuning) set’, and the data for the evaluation of models as the ‘test set’. Additionally, the test sets used for model evaluation are classified into internal (random splitting, cross-validation, and leave-one-out) sets and external (temporal and geographic) sets. This review then identifies often misunderstood terms and proposes pragmatic solutions to mitigate terminological confusion in the field of deep learning in medicine. We support the accurate and standardized description of these data sets and the explicit definition of data set splitting terminologies in each publication. These are crucial methods for demonstrating the robustness and generalizability of deep learning applications in medicine. This review aspires to enhance the precision of communication, thereby fostering more effective and transparent research methodologies in this interdisciplinary field.

DOI： 10.1007/s11604-024-01608-1

Web of Science

Scopus

PubMed

Language：English   Publishing type：Research paper (scientific journal)  

PURPOSE: The diploic veins have been suggested to be involved in the excretion of cerebrospinal fluid and intracranial waste products; however, to date, there have been no reports evaluating the space surrounding the diploic veins. Therefore, we aimed to visualize the distribution of gadolinium-based contrast agent (GBCA) in the space surrounding the diploic veins and to evaluate the spatial characteristics. MATERIALS AND METHODS: Ninety-eight participants (aged 14-84 years) were scanned 4 h after intravenous GBCA injection at Nagoya University Hospital between April 2021 and December 2022. The volume of the space surrounding the diploic veins where the GBCA was distributed was measured using contrast-enhanced T1-weighted images with the application of three-axis motion-sensitized driven equilibrium. The parasagittal dura (PSD) volume adjacent to the superior sagittal sinus was also measured using the same images. Both volumes were corrected for intracranial volume. The correlation between age and the corrected volume was examined using Spearman's rank correlation coefficient; the relationship between the corrected volume and sex was assessed using the Mann-Whitney U test. RESULTS: A significant weak negative correlation was observed between the volume of the space surrounding the diploic veins and age (r = -0.330, p < 0.001). Furthermore, there was a significant weak positive correlation between the PSD volume and age (r = 0.385, p < 0.001). Both volumes were significantly greater in men than in women. There was no correlation between the volume of the space surrounding the diploic veins and the volume of the PSD. CONCLUSION: The volume of the space surrounding the diploic veins was measurable and, in contrast to the volume of the PSD, was greater in younger participants. This space may be related to intracranial excretory mechanisms and immune responses during youth, requiring further research.

DOI： 10.1007/s11604-024-01572-w

Web of Science

Scopus

PubMed

Language：English   Publishing type：Research paper (scientific journal)   Publisher：Springer Science and Business Media LLC  

DOI： 10.1007/s11547-024-01861-4

Web of Science

Scopus

PubMed

Other Link： https://link.springer.com/article/10.1007/s11547-024-01861-4/fulltext.html

Language：English   Publishing type：Research paper (scientific journal)  

The advent of Deep Learning (DL) has significantly propelled the field of diagnostic radiology forward by enhancing image analysis and interpretation. The introduction of the Transformer architecture, followed by the development of Large Language Models (LLMs), has further revolutionized this domain. LLMs now possess the potential to automate and refine the radiology workflow, extending from report generation to assistance in diagnostics and patient care. The integration of multimodal technology with LLMs could potentially leapfrog these applications to unprecedented levels.However, LLMs come with unresolved challenges such as information hallucinations and biases, which can affect clinical reliability. Despite these issues, the legislative and guideline frameworks have yet to catch up with technological advancements. Radiologists must acquire a thorough understanding of these technologies to leverage LLMs' potential to the fullest while maintaining medical safety and ethics. This review aims to aid in that endeavor.

DOI： 10.1007/s11604-024-01552-0

Web of Science

Scopus

PubMed

Language：English   Publishing type：Research paper (scientific journal)   Publisher：Elsevier BV  

DOI： 10.1016/j.diii.2024.06.002

Scopus

PubMed

Language：English   Publishing type：Research paper (scientific journal)   Publisher：Japanese Society for Magnetic Resonance in Medicine  

PURPOSE: The endolymph of the inner ear, vital for balance and hearing, has long been considered impermeable to intravenously administered gadolinium-based contrast agents (GBCAs) due to the tight blood-endolymph barrier. However, anecdotal observations suggested potential GBCA entry in delayed heavily T2-weighted 3D-real inversion recovery (IR) MRI scans. This study systematically investigated GBCA distribution in the endolymph using this 3D-real IR sequence. METHODS: Forty-one patients suspected of endolymphatic hydrops (EHs) underwent pre-contrast, 4-h, and 24-h post-contrast 3D-real IR imaging. Signal intensity in cerebrospinal fluid (CSF), perilymph, and endolymph was measured and analyzed for temporal dynamics of GBCA uptake, correlations between compartments, and the influence of age and presence of EH. RESULTS: Endolymph showed a delayed peak GBCA uptake at 24h, contrasting with peaks in perilymph and CSF at 4h. Weak to moderate positive correlations between endolymph and CSF contrast effect were observed at both 4 (r = 0.483) and 24h (r = 0.585), suggesting possible inter-compartmental interactions. Neither the presence of EH nor age significantly influenced endolymph enhancement. However, both perilymph and CSF contrast effects significantly correlated with age at both time points. CONCLUSION: This study provides the first in vivo systematic confirmation of GBCA entering the endolymph following intravenous administration. Notably, endolymph uptake peaked at 24h, significantly later than perilymph and CSF. The lack of a link between endolymph contrast and both perilymph and age suggests distinct uptake mechanisms. These findings shed light on inner ear fluid dynamics and their potential implications in Ménière's disease and other inner ear disorders.

DOI： 10.2463/mrms.mp.2024-0011

Web of Science

PubMed

CiNii Research

Language：English   Publishing type：Research paper (scientific journal)   Publisher：Japanese Society for Magnetic Resonance in Medicine  

More than 5 years have passed since the Diffusion Tensor Image Analysis ALong the Perivascular Space (DTI-ALPS) method was proposed with the intention of evaluating the glymphatic system. This method is handy due to its noninvasiveness, provision of a simple index in a straightforward formula, and the possibility of retrospective analysis. Therefore, the ALPS method was adopted to evaluate the glymphatic system for many disorders in many studies. The purpose of this review is to look back and discuss the ALPS method at this moment.The ALPS-index was found to be an indicator of a number of conditions related to the glymphatic system. Thus, although this was expected in the original report, the results of the ALPS method are often interpreted as uniquely corresponding to the function of the glymphatic system. However, a number of subsequent studies have pointed out the problems on the data interpretation. As they rightly point out, a higher ALPS-index indicates predominant Brownian motion of water molecules in the radial direction at the lateral ventricular body level, no more and no less. Fortunately, the term "ALPS-index" has become common and is now known as a common term by many researchers. Therefore, the ALPS-index should simply be expressed as high or low, and whether it reflects a glymphatic system is better to be discussed carefully. In other words, when a decreased ALPS-index is observed, it should be expressed as "decreased ALPS-index" and not directly as "glymphatic dysfunction". Recently, various methods have been proposed to evaluate the glymphatic system. It has become clear that these methods also do not seem to reflect the entirety of the extremely complex glymphatic system. This means that it would be desirable to use various methods in combination to evaluate the glymphatic system in a comprehensive manner.

DOI： 10.2463/mrms.rev.2023-0175

Web of Science

Scopus

PubMed

CiNii Research

Language：English   Publishing type：Research paper (scientific journal)   Publisher：Oxford University Press (OUP)  

Abstract

This review provides an overview of the application of artificial intelligence (AI) in radiation therapy (RT) from a radiation oncologist’s perspective. Over the years, advances in diagnostic imaging have significantly improved the efficiency and effectiveness of radiotherapy. The introduction of AI has further optimized the segmentation of tumors and organs at risk, thereby saving considerable time for radiation oncologists. AI has also been utilized in treatment planning and optimization, reducing the planning time from several days to minutes or even seconds. Knowledge-based treatment planning and deep learning techniques have been employed to produce treatment plans comparable to those generated by humans. Additionally, AI has potential applications in quality control and assurance of treatment plans, optimization of image-guided RT and monitoring of mobile tumors during treatment. Prognostic evaluation and prediction using AI have been increasingly explored, with radiomics being a prominent area of research. The future of AI in radiation oncology offers the potential to establish treatment standardization by minimizing inter-observer differences in segmentation and improving dose adequacy evaluation. RT standardization through AI may have global implications, providing world-standard treatment even in resource-limited settings. However, there are challenges in accumulating big data, including patient background information and correlating treatment plans with disease outcomes. Although challenges remain, ongoing research and the integration of AI technology hold promise for further advancements in radiation oncology.

DOI： 10.1093/jrr/rrad090

Web of Science

Scopus

PubMed

Language：English   Publishing type：Research paper (scientific journal)  

An artificial intelligence (AI) system that reconstructs virtual 3D thin-section CT (TSCT) images from conventional CT images by applying deep learning was developed. The aim of this study was to investigate whether virtual and real TSCT could measure the solid size of early-stage lung adenocarcinoma. The pair of original thin-CT and simulated thick-CT from the training data with TSCT images (thickness, 0.5-1.0 mm) of 2700 pulmonary nodules were used to train the thin-CT generator in the generative adversarial network (GAN) framework and develop a virtual TSCT AI system. For validation, CT images of 93 stage 0-I lung adenocarcinomas were collected, and virtual TSCTs were reconstructed from conventional 5-mm thick-CT images using the AI system. Two radiologists measured and compared the solid size of tumors on conventional CT and virtual and real TSCT. The agreement between the two observers showed an almost perfect agreement on the virtual TSCT for solid size measurements (intraclass correlation coefficient = 0.967, P < 0.001, respectively). The virtual TSCT had a significantly stronger correlation than that of conventional CT (P = 0.003 and P = 0.001, respectively). The degree of agreement between the clinical T stage determined by virtual TSCT and the clinical T stage determined by real TSCT was excellent in both observers (k = 0.882 and k = 0.881, respectively). The AI system developed in this study was able to measure the solid size of early-stage lung adenocarcinoma on virtual TSCT as well as on real TSCT.

DOI： 10.1038/s41598-023-48755-5

Web of Science

Scopus

PubMed

Language：English   Publishing type：Research paper (scientific journal)   Publisher：Japanese Society for Magnetic Resonance in Medicine  

Postsurgery intracranial air usually diminishes, presumably merging with cerebrospinal fluid (CSF) and venous circulation. Our study presents two transsphenoidal surgery cases, highlighting potential air absorption by arachnoid granulation (AG)-an underexplored phenomenon. AG has long been deemed pivotal for CSF absorption, but recent perspectives suggest a significant role in waste clearance, neuroinflammation, and neuroimmunity. These cases may stimulate renewed research on the multifaceted role of AG in neurofluid dynamics and potentially elucidate further AG functions.

DOI： 10.2463/mrms.bc.2023-0122

Web of Science

PubMed

CiNii Research

Language：English   Publisher：Japanese Society for Magnetic Resonance in Medicine  

<p>Due primarily to the excellent soft tissue contrast depictions provided by MRI, the widespread application of head and neck MRI in clinical practice serves to assess various diseases. Artificial intelligence (AI)-based methodologies, particularly deep learning analyses using convolutional neural networks, have recently gained global recognition and have been extensively investigated in clinical research for their applicability across a range of categories within medical imaging, including head and neck MRI. Analytical approaches using AI have shown potential for addressing the clinical limitations associated with head and neck MRI. In this review, we focus primarily on the technical advancements in deep-learning-based methodologies and their clinical utility within the field of head and neck MRI, encompassing aspects such as image acquisition and reconstruction, lesion segmentation, disease classification and diagnosis, and prognostic prediction for patients presenting with head and neck diseases. We then discuss the limitations of current deep-learning-based approaches and offer insights regarding future challenges in this field.</p>

DOI： 10.2463/mrms.rev.2023-0047

PubMed

CiNii Research

Language：English   Publisher：Radiologia Medica  

Although there is no solid agreement for artificial intelligence (AI), it refers to a computer system with intelligence similar to that of humans. Deep learning appeared in 2006, and more than 10 years have passed since the third AI boom was triggered by improvements in computing power, algorithm development, and the use of big data. In recent years, the application and development of AI technology in the medical field have intensified internationally. There is no doubt that AI will be used in clinical practice to assist in diagnostic imaging in the future. In qualitative diagnosis, it is desirable to develop an explainable AI that at least represents the basis of the diagnostic process. However, it must be kept in mind that AI is a physician-assistant system, and the final decision should be made by the physician while understanding the limitations of AI. The aim of this article is to review the application of AI technology in diagnostic imaging from PubMed database while particularly focusing on diagnostic imaging in thorax such as lesion detection and qualitative diagnosis in order to help radiologists and clinicians to become more familiar with AI in thorax.

DOI： 10.1007/s11547-023-01691-w

Scopus

PubMed

Language：English   Publisher：Annals of Nuclear Medicine  

The radiopharmaceutical 2-[fluorine-18]fluoro-2-deoxy-d-glucose (FDG) has been dominantly used in positron emission tomography (PET) scans for over 20 years, and due to its vast utility its applications have expanded and are continuing to expand into oncology, neurology, cardiology, and infectious/inflammatory diseases. More recently, the addition of artificial intelligence (AI) has enhanced nuclear medicine diagnosis and imaging with FDG-PET, and new radiopharmaceuticals such as prostate-specific membrane antigen (PSMA) and fibroblast activation protein inhibitor (FAPI) have emerged. Nuclear medicine therapy using agents such as [177Lu]-dotatate surpasses conventional treatments in terms of efficacy and side effects. This article reviews recently established evidence of FDG and non-FDG drugs and anticipates the future trajectory of nuclear medicine.

DOI： 10.1007/s12149-023-01865-6

Web of Science

Scopus

PubMed

Language：English   Publisher：NMR in Biomedicine  

In the current study, we assessed changes in interstitial fluid dynamics resulting after whole-brain radiotherapy using the diffusion-weighted image analysis along the perivascular space (DWI-ALPS) method, which is a simplified variation of the diffusion tensor image ALPS (DTI-ALPS) method using diffusion-weighted imaging (DWI) with orthogonal motion-probing gradients (MPGs). This retrospective study included 47 image sets from 22 patients who underwent whole-brain radiotherapy for brain tumors. The data for the normal control group comprised 105 image sets from 105 participants with no pathological changes. DWI was performed with the three MPGs applied in an orthogonal direction to the imaging plane, and apparent diffusion coefficient images for the x-, y-, and z-axes were retrospectively generated. The ALPS index was calculated to quantify interstitial fluid dynamics. The independent t-test was used to compare the ALPS index between normal controls and patients who underwent whole-brain radiotherapy. Patients were compared in all age groups and individual age groups (20–39, 40–59, and 60–84 years). We also examined the correlation between biologically equivalent doses (BEDs) and the ALPS index, as well as the correlation between white matter hyperintensity and the ALPS index. In the comparison of all age groups, the ALPS index was significantly lower (p < 0.001) in the postradiation group (1.32 ± 0.16) than in the control group (1.44 ± 0.17), suggesting that interstitial fluid dynamics were altered in patients following whole-brain radiotherapy. Significant age group differences were found (40–59 years: p < 0.01; 60–84 years: p < 0.001), along with a weak negative correlation between BEDs (r = −0.19) and significant correlations between white matter hyperintensity and the ALPS index (r = −0.46 for periventricular white matter, r = −0.38 for deep white matter). It was concluded that the ALPS method using DWI with orthogonal MPGs suggest alteration in interstitial fluid dynamics in patients after whole-brain radiotherapy. Further systematic prospective studies are required to investigate their association with cognitive symptoms.

DOI： 10.1002/nbm.5030

Web of Science

Scopus

PubMed

Language：English   Publisher：Japanese Journal of Radiology  

In this review, we address the issue of fairness in the clinical integration of artificial intelligence (AI) in the medical field. As the clinical adoption of deep learning algorithms, a subfield of AI, progresses, concerns have arisen regarding the impact of AI biases and discrimination on patient health. This review aims to provide a comprehensive overview of concerns associated with AI fairness; discuss strategies to mitigate AI biases; and emphasize the need for cooperation among physicians, AI researchers, AI developers, policymakers, and patients to ensure equitable AI integration. First, we define and introduce the concept of fairness in AI applications in healthcare and radiology, emphasizing the benefits and challenges of incorporating AI into clinical practice. Next, we delve into concerns regarding fairness in healthcare, addressing the various causes of biases in AI and potential concerns such as misdiagnosis, unequal access to treatment, and ethical considerations. We then outline strategies for addressing fairness, such as the importance of diverse and representative data and algorithm audits. Additionally, we discuss ethical and legal considerations such as data privacy, responsibility, accountability, transparency, and explainability in AI. Finally, we present the Fairness of Artificial Intelligence Recommendations in healthcare (FAIR) statement to offer best practices. Through these efforts, we aim to provide a foundation for discussing the responsible and equitable implementation and deployment of AI in healthcare.

DOI： 10.1007/s11604-023-01474-3

Scopus

PubMed

Language：English   Publisher：Diagnostic and Interventional Imaging  

Recent advances in artificial intelligence (AI) for cardiac computed tomography (CT) have shown great potential in enhancing diagnosis and prognosis prediction in patients with cardiovascular disease. Deep learning, a type of machine learning, has revolutionized radiology by enabling automatic feature extraction and learning from large datasets, particularly in image-based applications. Thus, AI-driven techniques have enabled a faster analysis of cardiac CT examinations than when they are analyzed by humans, while maintaining reproducibility. However, further research and validation are required to fully assess the diagnostic performance, radiation dose-reduction capabilities, and clinical correctness of these AI-driven techniques in cardiac CT. This review article presents recent advances of AI in the field of cardiac CT, including deep-learning-based image reconstruction, coronary artery motion correction, automatic calcium scoring, automatic epicardial fat measurement, coronary artery stenosis diagnosis, fractional flow reserve prediction, and prognosis prediction, analyzes current limitations of these techniques and discusses future challenges.

DOI： 10.1016/j.diii.2023.06.011

Scopus

PubMed

Language：English   Publisher：Radiologia Medica  

This review outlines the current status and challenges of the clinical applications of artificial intelligence in liver imaging using computed tomography or magnetic resonance imaging based on a topic analysis of PubMed search results using latent Dirichlet allocation. LDA revealed that “segmentation,” “hepatocellular carcinoma and radiomics,” “metastasis,” "fibrosis," and "reconstruction" were current main topic keywords. Automatic liver segmentation technology using deep learning is beginning to assume new clinical significance as part of whole-body composition analysis. It has also been applied to the screening of large populations and the acquisition of training data for machine learning models and has resulted in the development of imaging biomarkers that have a significant impact on important clinical issues, such as the estimation of liver fibrosis, recurrence, and prognosis of malignant tumors. Deep learning reconstruction is expanding as a new technological clinical application of artificial intelligence and has shown results in reducing contrast and radiation doses. However, there is much missing evidence, such as external validation of machine learning models and the evaluation of the diagnostic performance of specific diseases using deep learning reconstruction, suggesting that the clinical application of these technologies is still in development.

DOI： 10.1007/s11547-023-01638-1

Web of Science

Scopus

PubMed

Language：English   Publishing type：Research paper (scientific journal)  

The concept of the glymphatic system was proposed more than a decade ago as a mechanism for interstitial fluid flow and waste removal in the central nervous system. The function of the glymphatic system has been shown to be particularly activated during sleep. Dysfunction of the glymphatic system has been implicated in several neurodegenerative diseases. Noninvasive in vivo imaging of the glymphatic system is expected to be useful in elucidating the pathophysiology of these diseases. Currently, magnetic resonance imaging is the most commonly used technique to evaluate the glymphatic system in humans, and a large number of studies have been reported. This review provides a comprehensive overview of investigations of the human glymphatic system function using magnetic resonance imaging. The studies can be divided into 3 categories, including imaging without gadolinium-based contrast agents (GBCAs), imaging with intrathecal administration of GBCAs, and imaging with intravenous administration of GBCAs. The purpose of these studies has been to examine not only the interstitial fluid movement in the brain parenchyma, but also the fluid dynamics in the perivascular and subarachnoid spaces, as well as the parasagittal dura and meningeal lymphatics. Recent research has even extended to include the glymphatic system of the eye and the inner ear. This review serves as an important update and a useful guide for future research directions.

DOI： 10.1097/RLI.0000000000000969

PubMed

Language：English   Publishing type：Research paper (scientific journal)   Publisher：Japanese Society for Magnetic Resonance in Medicine  

PURPOSE: To investigate the characteristics of the putative meningeal lymphatics located at the posterior wall of the sigmoid sinus (PML-PSS) in human subjects imaged before and after intravenous administration (IV) of a gadolinium-based contrast agent (GBCA). The appearance of the PML-PSS and the enhancement of the perivascular space of the basal ganglia (PVS-BG) were analyzed for an association with gender, age, and clearance of the GBCA from the cerebrospinal fluid (CSF). METHODS: Forty-two patients with suspected endolymphatic hydrops were included. Heavily T2-weighted 3D-fluid attenuated inversion recovery (hT2w-3D-FLAIR) and 3D-real inversion recovery (IR) images were obtained at pre-administration, immediately post-administration, and at 4 and 24 hours after IV-GBCA. The appearance of the PML-PSS and the presence of enhancement in the PVS-BG were analyzed for a relationship with age, gender, contrast enhancement of the CSF at 4 hours after IV-GBCA, and the washout ratio of the GBCA in the CSF from 4 to 24 hours after IV-GBCA. RESULTS: The PML-PSS and PVS-BG were seen in 23 of 42 and 21 of 42 cases, respectively, at 4 hours after IV-GBCA. In all PML-PSS positive cases, hT2w-3D-FLAIR signal enhancement was highest at 4 hours after IV-GBCA. A multivariate analysis between gender, age, CSF signal elevation at 4 hours, and washout ratio indicated that only the washout ratio was independently associated with the enhancement of the PML-PSS or PVS-BG. The odds ratios (95% CIs; P value) were 4.09 × 10-5 (2.39 × 10-8 - 0.07; 0.0078) for the PML-PSS and 1.7 × 10-4 (1.66 × 10-7 - 0.174; 0.014) for the PVS-BG. CONCLUSION: The PML-PSS had the highest signal enhancement at 4 hours after IV-GBCA. When the PML-PSS was seen, there was also often enhancement of the PVS-BG at 4 hours after IV-GBCA. Both observed enhancements were associated with delayed GBCA excretion from the CSF.

DOI： 10.2463/mrms.mp.2022-0110

PubMed

CiNii Research

Language：English   Publishing type：Research paper (scientific journal)   Publisher：Japanese Society for Magnetic Resonance in Medicine  

PURPOSE: Peripheral retinal leakage (PRL) of contrast medium from the ora serrata (i.e., the peripheral part of the retina) was recently reported in normal eyes using ultra-widefield fluorescein angiography. We occasionally see PRL of gadolinium-based contrast agents (GBCAs) in the vitreous from the temporal and inferior sides of the ora serrata on MR images of subjects without ophthalmic disease. In this study, we retrospectively evaluated these MR images to determine if PRL was associated with aging. We also evaluated whether the initial leakage appeared in the temporal and inferior sides, and whether there was uniform distribution within the vitreous after 24 hours. METHODS: In 127 subjects (9 volunteers, 85 patients with sudden deafness, and 33 patients with a suspicion of endolymphatic hydrops), pre- and post-contrast-enhanced heavily T2-weighted 3D-fluid attenuated inversion recovery (FLAIR) images were obtained. The presence or absence of PRL was subjectively evaluated. For patients with a suspicion of endolymphatic hydrops, 3D-real inversion recovery (IR) images were also obtained at pre-, 10 mins, 4 hours, and 24 hours after intravenous administration (IV) of GBCA. Four circular ROIs were placed in the vitreous humor and the signal intensity was measured. RESULTS: In the cases with PRL (n = 88) and without PRL (n = 47), the median age was 59 and 47 years, respectively (P = 0.001). At 4 hours after IV-GBCA, the mean signal increase in the inferior temporal ROI was greater than all the other ROIs. At 24 hours after IV-GBCA, no significant difference in signal intensity was observed for the four ROIs. CONCLUSION: PRL of GBCA is age-dependent and occurs mainly from the inferior temporal side of the ora serrata. The contrast effect was uniformly distributed at 24 hours after IV-GBCA. Future observations in a variety of diseases will determine the clinical significance of these findings.

DOI： 10.2463/mrms.mp.2021-0100

Web of Science

Scopus

PubMed

CiNii Research

Language：English   Publishing type：Research paper (scientific journal)   Publisher：Japanese Society for Magnetic Resonance in Medicine  

It has been reported that perivenous cystic structures near the parasagittal dura are associated with the leakage of gadolinium-based contrast agents at 4 hours after intravenous administration. The origin of such cystic structures remains unknown. While reading many cases of MR cisternography, we noticed that some of the cystic structures appeared to connect to the perivenous subpial space. This new imaging finding might facilitate future research of the waste clearance system for the central nervous system.

DOI： 10.2463/mrms.bc.2021-0141

Web of Science

Scopus

PubMed

CiNii Research

Language：English   Publishing type：Research paper (scientific journal)   Publisher：Japanese Society for Magnetic Resonance in Medicine  

Interest in interstitial fluid dynamics has increased since the proposal of the glymphatic system hypothesis. Abnormal dynamics of the interstitial fluid have been pointed out to be an important factor in various pathological statuses. In this article, we propose the concept of central nervous system interstitial fluidopathy as a disease or condition in which abnormal interstitial fluid dynamics is one of the important factors for the development of a pathological condition. We discuss the aspects of interstitial fluidopathy in various diseases, including Alzheimer's disease, Parkinson's disease, normal pressure hydrocephalus, and cerebral small vessel disease. We also discuss a method called "diffusion tensor image analysis along the perivascular space" using MR diffusion images, which is used to evaluate the degree of interstitial fluidopathy or the activity of the glymphatic system.

DOI： 10.2463/mrms.rev.2022-0012

PubMed

CiNii Research

Language：English   Publishing type：Research paper (scientific journal)  

PURPOSE: The purpose of this study was to evaluate the interstitial fluid status in a wide range of age groups using diffusion-weighted image analysis along the perivascular space (DWI-ALPS) method, which is a simplified variation of diffusion tensor image analysis along the perivascular space (DTI-ALPS). MATERIALS AND METHODS: This retrospective study included data from 128 patients who underwent clinical magnetic resonance imaging (MRI) studies, including DWI, and were found to have no abnormal findings in the brain on MRI. Three motion-probing gradients of the DWI were applied in an orthogonal direction to the imaging plane. Apparent diffusion coefficient images in the x-, y-, and z-axes were retrospectively generated, and composite color images were created to locate the projection and association fiber area on the slice including the body of the lateral ventricle. ALPS indices were calculated, and correlations with age were evaluated using linear and second-degree regression analysis. Linear regression analysis was also performed for a subgroup of patients older than 40 years. In addition, an analysis of variance (ANOVA) test among the generations was performed. RESULTS: The linear regression analysis between age and the ALPS index showed a correlation coefficient of -0.20 for all age group and -0.51 for the subgroup older than 40 years. The second-degree regression analysis showed a correlation coefficient of 0.39. ANOVA showed that the 40's generation showed a statistically significant higher value of ALPS index compared to all other generations except for the 30's generation. While, the 70's generation showed a statistically significant lower value of the ALPS index compared to all other generations. CONCLUSIONS: The analysis of the DWI-APLS method showed a correlation between age and the ALPS index in second-degree distribution which peaked in the 40's generation. This finding in normal subjects may be fundamental in the analysis of disease cases. We tried to evaluate the glymphatic system status in a wide range of age groups using diffusion-weighted image analysis along the perivascular space (DWI-ALPS) method, and the results showed a correlation between age and the ALPS index in second-degree distribution which peaked in the 40's generation.

DOI： 10.1007/s11604-022-01275-0

Web of Science

Scopus

PubMed

Language：English  

DOI： 10.1007/s11547-022-01486-5

Web of Science

Scopus

PubMed

Language：English   Publishing type：Research paper (scientific journal)  

PURPOSE: The diffusion tensor image analysis along the perivascular space (DTI-ALPS) method was developed to evaluate the brain's glymphatic function or interstitial fluid dynamics. This study aimed to evaluate the reproducibility of the DTI-ALPS method and the effect of modifications in the imaging method and data evaluation. MATERIALS AND METHODS: Seven healthy volunteers were enrolled in this study. Image acquisition was performed for this test-retest study using a fixed imaging sequence and modified imaging methods which included the placement of region of interest (ROI), imaging plane, head position, averaging, number of motion-proving gradients, echo time (TE), and a different scanner. The ALPS-index values were evaluated for the change of conditions listed above. RESULTS: This test-retest study by a fixed imaging sequence showed very high reproducibility (intraclass coefficient = 0.828) for the ALPS-index value. The bilateral ROI placement showed higher reproducibility. The number of averaging and the difference of the scanner did not influence the ALPS-index values. However, modification of the imaging plane and head position impaired reproducibility, and the number of motion-proving gradients affected the ALPS-index value. The ALPS-index values from 12-axis DTI and 3-axis diffusion-weighted image (DWI) showed good correlation (r = 0.86). Also, a shorter TE resulted in a larger value of the ALPS-index. CONCLUSION: ALPS index was robust under the fixed imaging method even when different scanners were used. ALPS index was influenced by the imaging plane, the number of motion-proving gradient axes, and TE in the imaging sequence. These factors should be uniformed in the planning ALPS method studies. The possibility to develop a 3-axis DWI-ALPS method using three axes of the motion-proving gradient was also suggested.

DOI： 10.1007/s11604-021-01187-5

Web of Science

Scopus

PubMed

Language：English   Publishing type：Research paper (scientific journal)  

PURPOSE: The purpose of the study is to evaluate the associations between intratumoral or peritumoral textural features derived from pretreatment magnetic resonance imaging (MRI) and recurrence-free survival (RFS) in triple-negative breast cancer (TNBC) patients. METHODS: Forty-three patients with TNBC who underwent preoperative MRI between February 2008 and March 2014 were included. We performed two-dimensional texture analysis on the intratumoral or peritumoral region of interest (ROI) on axial of T2-weighted image (T2WI), dynamic contrast-enhanced (DCE)-MRI and DCE-MRI subtraction images. We also analyzed histopathological data. Cox proportional hazards models were used to investigate associations with survival outcomes. RESULTS: Twelve of the 43 patients (27.9%) had recurrence disease, at a median of 32.5 months follow-up (1.4-61.5 months). In univariate analysis, nine texture features in T2WI and DCE-MRI subtraction images were significantly associated with RFS. In multivariate analysis, intratumoral difference entropy in DCE-MRI subtraction images in the initial phase (hazard ratio 11.71; 95% confidence interval (CI) [1.41, 97.00]; p value 0.023) and, peritumoral difference variance in DCE-MRI subtraction images in the delayed phase (hazard ratio 9.60; 95% CI [1.98, 46.51]; p value 0.005), were both independently associated with RFS. Moreover, multivariate analysis revealed the presence of lymphovascular invasion as independently associated with RFS (hazard ratio 8.13; 95% CI [2.16, 30.30]; p value 0.002). CONCLUSIONS: At pretreatment MRI, an intratumoral and peritumoral quantitative approach using texture analysis has the potential to serve as a prognostic marker in patients with TNBC.

DOI： 10.1007/s12282-021-01294-1

Web of Science

Scopus

PubMed

Language：English   Publisher：Radiologia Medica  

Breast magnetic resonance imaging (MRI) is the most sensitive imaging modality for breast cancer diagnosis and is widely used clinically. Dynamic contrast-enhanced MRI is the basis for breast MRI, but ultrafast images, T2-weighted images, and diffusion-weighted images are also taken to improve the characteristics of the lesion. Such multiparametric MRI with numerous morphological and functional data poses new challenges to radiologists, and thus, new tools for reliable, reproducible, and high-volume quantitative assessments are warranted. In this context, radiomics, which is an emerging field of research involving the conversion of digital medical images into mineable data for clinical decision-making and outcome prediction, has been gaining ground in oncology. Recent development in artificial intelligence has promoted radiomics studies in various fields including breast cancer treatment and numerous studies have been conducted. However, radiomics has shown a translational gap in clinical practice, and many issues remain to be solved. In this review, we will outline the steps of radiomics workflow and investigate clinical application of radiomics focusing on breast MRI based on published literature, as well as current discussion about limitations and challenges in radiomics.

DOI： 10.1007/s11547-021-01423-y

Web of Science

Scopus

PubMed

Language：English   Publishing type：Research paper (scientific journal)   Publisher：Japanese Society for Magnetic Resonance in Medicine  

PURPOSE: To evaluate the relationship between the size of the venous structures related to the inner ear and the degree of endolymphatic hydrops (EH). METHODS: Thirty-four patients with a suspicion of EH underwent whole brain MR imaging including the inner ear. Images were obtained pre- and post-administration, and at 4 and 24 hours after the intravenous administration of a gadolinium-based contrast agent (IV-GBCA). The cross-sectional areas (CSA) of the internal jugular vein (IJV), superior petrosal sinus (SPS), and inferior petrosal sinus (IPS) were measured on the magnetization prepared rapid acquisition of gradient echo (MPRAGE) images obtained immediately after the IV-GBCA. The grade of EH was determined on the hybrid of reversed image of positive endolymph signal and native image of positive perilymph signal (HYDROPS) images obtained at 4 hours after IV-GBCA as no, mild, and significant EH according to the previously proposed grading system for the cochlea and vestibule, respectively. The ipsilateral CSA was compared between groups with each level of EH grade. P < 0.05 was considered statistically significant. RESULTS: There were no statistically significant differences between EH grades for the CSA of the IJV or that of the IPS in either the cochlea or the vestibule. The CSA of the SPS in the groups with significant EH was significantly smaller than that in the group with no EH, for both the cochlea (P < 0.01) and the vestibule (P < 0.05). In an ROC analysis to predict significant EH, the cut-off CSA value in the SPS was 3.905 mm2 for the cochlea (AUC: 0.8762, 95% confidence interval [CI]: 0.7952‒0.9572) and 3.805 mm2 for the vestibule (AUC: 0.7727, 95% CI: 0.6539‒0.8916). CONCLUSION: In the ears with significant EH in the cochlea or vestibule, the CSA of the ipsilateral SPS was smaller than in the ears without EH.

DOI： 10.2463/mrms.mp.2021-0010

Web of Science

Scopus

PubMed

CiNii Research

Language：English   Publishing type：Research paper (scientific journal)   Publisher：Japanese Society for Magnetic Resonance in Medicine  

In this study, we present images acquired by a fast-imaging method for the evaluation of endolymphatic hydrops after intravenous administration of a single dose of gadolinium-based contrast agent. We utilized the hybrid of reversed image of MR cisternography and a positive perilymph signal by heavily T2- weighted 3D-fluid attenuated inversion recovery-multiplied by T2 (HYDROPS2-Mi2) method combined with deep learning reconstruction denoising. The scan time for the fast protocol was approximately 5 mins, which is far shorter than previously reported scan times. The fast acquisition provides similar image quality and less motion artifacts compared to the longer method.

DOI： 10.2463/mrms.ici.2021-0022

Web of Science

Scopus

PubMed

CiNii Research

Language：Japanese   Publisher：MEDICAL IMAGING AND INFORMATION SCIENCES  

<p>There have been many studies on the use of AI for the diagnosis of COVID-19 pneumonia. Although these AIs have high performance, there are several points that need to be considered when using them in clinical practice. In this paper, we comprehensively reviewed the AI studies for COVID-19 pneumonia that were registered in PubMed until December 2020. The performance and problems of these AIs were presented.</p>

DOI： 10.11318/mii.38.32

CiNii Research

Language：English   Publishing type：Research paper (scientific journal)  

The accuracy of brain age estimates from magnetic resonance (MR) images has improved with the advent of deep learning artificial intelligence (AI) models. However, most previous studies on predicting age emphasized aging from childhood to adulthood and old age, and few studies have focused on early brain development in children younger than 2 years of age. Here, we performed brain age estimates based on MR images in children younger than 2 years of age using deep learning. Our AI model, developed with one slice each of raw T1- and T2-weighted images from each subject, estimated brain age with a mean absolute error of 8.2 weeks (1.9 months). The estimates of our AI model were close to those of human specialists. The AI model also estimated the brain age of subjects with a myelination delay as significantly younger than the chronological age. These results indicate that the prediction accuracy of our AI model approached that of human specialists and that our simple method requiring less data and preprocessing facilitates a radiological assessment of brain development, such as monitoring maturational changes in myelination.

DOI： 10.1016/j.mri.2021.03.004

Web of Science

Scopus

PubMed

Language：English   Publishing type：Research paper (scientific journal)   Publisher：Springer Science and Business Media LLC  

<title>Abstract</title><sec>
<title>Purpose</title>
To visualize and analyze the dynamics of cerebrospinal fluid (CSF) motion in the cranium, we evaluated the distribution of motion-related signal dephasing by CSF on Diffusion ANalysis of fluid DYnamics with Incremental Strength of Motion proving gradient (DANDYISM) method, a composite imaging method using various low <italic>b</italic> values.



</sec><sec>
<title>Materials and methods</title>
This study examined ten subjects aged 25–58. We acquired DWIs on a 3T clinical scanner with <italic>b</italic> values 0, 50, 100, 200, 300, 500, 700, and 1000 s/mm² in total imaging time of 4 min. We constructed DANDYISM images and evaluated the CSF area distribution with decreased motion-dephasing signal using a scoring method.


</sec><sec>
<title>Results</title>
The DANDYISM images showed statistically significant higher CSF scores in the ventral posterior fossa, suprasellar cistern, and Sylvian vallecula compared to the lateral ventricle and frontal and parietal CSF spaces, indicating greater CSF movement in the former areas.


</sec><sec>
<title>Conclusion</title>
The results indicated prominent CSF motions in the ventral portion of the posterior fossa, suprasellar cistern, and Sylvian fissure but smaller motions in the lateral ventricles and parietal subarachnoid space. This method may provide information of CSF dynamics in the clinical settings within short imaging time.


</sec>

DOI： 10.1007/s11604-020-01075-4

Web of Science

Scopus

PubMed

Other Link： http://link.springer.com/article/10.1007/s11604-020-01075-4/fulltext.html

Language：Japanese   Publishing type：Research paper (scientific journal)  

BACKGROUND: To investigate the correlation between iodine-related attenuation in contrast-enhanced dual-energy computed tomography (DE-CT) and the postoperative prognosis of surgically resected solid-type small-sized lung cancers. METHODS: We retrospectively reviewed the DE-CT findings and postoperative course of solid-type lung cancers ≤3 cm in diameter. After injection of iodinated contrast media, arterial phases were scanned using 140-kVp and 80-kVp tube voltages. Three-dimensional iodine-related attenuation (3D-IRA) of primary tumors at the arterial phase was computed using the "lung nodule" application software. The corrected 3D-IRA normalized to the patient's body weight and contrast medium concentration was then calculated. RESULTS: A total of 120 resected solid-type lung cancers ≤3 cm in diameter were selected for analysis (82 males and 38 females; mean age, 67 years). During the observation period (median, 47 months), 32 patients showed postoperative recurrence. Recurrent tumors had significantly lower 3D-IRA and corrected 3D-IRA at early phase compared to non-recurrent tumors (p = 0.046 and p = 0.027, respectively). The area under the receiver operating characteristic curve for postoperative recurrence was 0.624 for the corrected 3D-IRA at early phase (p = 0.025), and the cutoff value was 5.88. Kaplan-Meier curves for disease-free survival indicated that patients showing tumors with 3D-IRA > 5.88 had a significantly better prognosis than those with tumors showing 3D-IRA < 5.88 (p = 0.017). CONCLUSIONS: The 3D-IRA of small-sized solid-type lung cancers on contrast-enhanced DE-CT was significantly associated with postoperative prognosis, and low 3D-IRA tumors showed a higher TNM stage and a significantly poorer prognosis.

DOI： 10.1186/s40644-020-00368-1

Web of Science

Scopus

PubMed

Language：English   Publishing type：Research paper (scientific journal)   Publisher：Japanese Society for Magnetic Resonance in Medicine  

<p>Purpose: Decrease in signal of the cerebrospinal fluid (CSF) on low b-value diffusion weighted image (DWI) due to non-uniform flow can provide additional information regarding CSF motion. The purpose of the current study was to evaluate whether arterial pulsations constitute the driving force of CSF motion.</p><p>Methods: We evaluated the CSF signals within the Sylvian fissure on low b-value DWI in 19 patients with unilateral middle cerebral artery (MCA) occlusion. DWI with b-value of 500 s/mm² was evaluated for a decrease in CSF signal within the Sylvian fissure including the Sylvian vallecula and lower, middle, and higher Sylvian fissures and graded as follows: the same as contralateral side; smaller signal decrease than that on contralateral side; and no signal decrease. MR angiography (MRA) findings of MCA were graded as follows: the same as contralateral, lower signal than contralateral signal, and no signal. In 15 patients, regional cerebral blood flow (rCBF) was evaluated using single-photon emission computed tomography (SPECT) studies and graded as >90%, 90%–70%, and <70% rCBF compared to contralateral. The correlations between the gradings were evaluated using G likelihood-ratio test.</p><p>Results: There was no statistically significant correlation between the MRA and low b-value DWI gradings of CSF in all areas. There were statistically significant correlations between the decreases in CBF on SPECT and CSF signals in the middle Sylvian fissure.</p><p>Conclusion: The driving force of CSF pulsation in the Sylvian sinus may be related to the pulsations of the cerebral hemisphere rather than direct arterial pulsations.</p>

DOI： 10.2463/mrms.mp.2020-0121

Web of Science

Scopus

PubMed

CiNii Research

Language：English   Publishing type：Research paper (scientific journal)   Publisher：Japanese Society for Magnetic Resonance in Medicine  

PURPOSE: To investigate the association between signal changes over time in perivenous cystic structures near the superior sagittal sinus and leakage of a gadolinium-based contrast agent (GBCA) into the subarachnoid space in patients with suspected endolymphatic hydrops. METHODS: Fifty-one cystic structures in 27 cases were evaluated. The signal intensity of the cystic structures was measured on 3D real inversion recovery (3D-real IR) images obtained at pre-, and at 10 min, 4 hrs and 24 hrs post-intravenous administration (IV) of GBCA. Signal enhancement of the cystic structures from the pre-contrast images at each time point was compared in subjects with leakage (positive) versus those without leakage (negative) using an ANOVA. Fisher's exact probability test was used to compare the maximum contrast-enhanced time point between positive and negative groups. We used 5% as a threshold to determine statistical significance. RESULTS: In leakage positive subjects, mean signal enhancement of the cysts was significantly greater at 4 and 24 hrs compared to 10 min. However, although there was a trend of an increase from 4 to 24 hrs, the difference was not significant. In the leakage negative group, mean signal enhancement of the cysts was significantly higher at 4 hrs compared to 10 min and 24 hrs. There was no significant difference between 10 min and 24 hrs. In the positive group, the maximum signal increase was found in 10/38 and 28/38 cysts at 4 and 24 hrs after IV-GBCA, respectively. In the leakage negative group, the maximum signal increase was found in 10/13 and 3/13 cysts at 4 and 24 hrs, respectively (P = 0.0019). CONCLUSION: There was an association between signal changes over time after IV-GBCA in perivenous cystic structures and leakage of GBCA. Further research to clarify the impact of cystic structures on the function of the waste clearance system of the brain is warranted.

DOI： 10.2463/mrms.mp.2020-0138

Web of Science

Scopus

PubMed

CiNii Research

Language：English   Publishing type：Research paper (scientific journal)   Publisher：Japanese Society for Magnetic Resonance in Medicine  

PURPOSE: The purpose of this retrospective study was to investigate the relationship between the number and size of cystic structures around the cortical veins near the superior sagittal sinus and the leakage of gadolinium-based contrast agent (GBCA) around the cortical veins. METHODS: Of 190 patients (91 male and 99 female), that were scanned at 4 h after an intravenous injection of GBCA as a diagnostic examination for endolymphatic hydrops, 6 patients with GBCA leakage were younger than the previously proposed threshold age of 37.3 years for leakage. Six age-matched patients without leakage were also included for reference. In addition, we included 8 cases without leakage that were older than the hypothesized threshold of 37.3 years, as well as 8 age-matched patients with GBCA leakage into the cerebrospinal fluid space. The number of cysts was counted and the sizes were measured in these 28 patients (age: 32-60 years old, 13 men and 15 women). RESULTS: The mean number of cysts surrounding the cortical veins in the parasagittal region was 4.29 ± 1.77 vs. 1.79 ± 1.05 (P = 0.0001) in the subjects with and without GBCA leakage, respectively. The mean size of the largest cysts was at 8.89 ± 3.49 mm vs. 5.69 ± 2.29 (P = 0.009) in the subjects with and without GBCA leakage, respectively. CONCLUSION: The number and size of the perivenous cystic structures near the superior sagittal sinus is greater in subjects with GBCA leakage into the subarachnoid space compared with those without leakage. Future research regarding the histological and functional details of these parasagittal cystic structures is needed.

DOI： 10.2463/mrms.mp.2020-0062

Web of Science

Scopus

PubMed

CiNii Research

Language：English   Publishing type：Research paper (scientific journal)   Publisher：Japanese Society for Magnetic Resonance in Medicine  

PURPOSE: To evaluate the feasibility for the detection of slight contrast effects after intravenous administration of single dose gadolinium-based contrast agent (IV-SD-GBCA), the time course of the GBCA distribution up to 24 h was examined in various fluid spaces and brain parenchyma using 3D-real IR imaging and MR fingerprinting (MRF). METHODS: Twenty-four patients with a suspicion of endolymphatic hydrops were scanned at pre-administration and at 10 min, 4 and 24 h post-IV-SD-GBCA. 3D-real IR images and MRF at the level of the internal auditory canal were obtained. The signal intensity on the 3D-real IR image of the cerebrospinal fluid (CSF) in the cerebellopontine angle cistern (CPA), Sylvian fissure (Syl), lateral ventricle (LV), and cochlear perilymph (CPL) was measured. The T1 and T2 values of cerebellar gray (GM) and white matter (WM) were measured using MRF. Each averaged value at the various time points was compared using an analysis of variance. RESULTS: The signal intensity on the 3D-real IR image in each CSF region peaked at 4 h, and was decreased significantly by 24 h (P< 0.05). All patients had a maximum signal intensity at 4 h in the CPA, and Syl. The mean CPL signal intensity peaked at 4 h and decreased significantly by 24 h (P < 0.05). All patients but two had a maximum signal intensity at 4 h. Regarding the T1 value in the cerebellar WM and GM, the T1 value at 10 min post-IV-GBCA was significantly decreased compared to the pre-contrast scan, but no significant difference was observed at the other time points. There was no significant change in T2 in the gray or white matter at any of the time points. CONCLUSION: Time course of GBCA after IV-SD-GBCA could be evaluated by 3D-real IR imaging in CSF spaces and in the brain by MRF.

DOI： 10.2463/mrms.mp.2020-0030

Web of Science

Scopus

PubMed

CiNii Research

Language：English   Publishing type：Research paper (scientific journal)  

We retrospectively evaluated the frequency of unexpected accumulation of radioactive iodine on the post-therapy whole-body scan (Rx-WBS) after radioactive iodine (RAI) ablation therapy in patients with differentiated thyroid cancer (DTC). We searched our institutional database for Rx-WBSs of DTC patients who underwent RAI ablation or adjuvant therapy between 2012 and 2019. Patients with distant metastasis diagnosed by CT or PET/CT before therapy, and those had previously received RAI therapy were excluded. In total, 293 patients (201 female and 92 male, median age 54 years) were selected. Two nuclear medicine physicians interpreted the Rx-WBS images by determining the visual intensity of radioiodine uptake by the thyroid bed, cervical and mediastinal lymph nodes, lungs, and bone. Clinical features of the patients with and without the metastatic accumulation were compared by chi-square test and median test. Logistic regression analyses were performed to compare the association between the presence of metastatic accumulation and these clinical factors. Eighty-four of 293 patients (28.7%) showed metastatic accumulation. Patients with metastatic RAI accumulation showed a significantly higher frequency of pathological N1 (pN1) and serum thyroglobulin (Tg) > 1.5 ng/ml under TSH stimulation (p = 0.035 and p = 0.031, respectively). Logistic regression analysis indicated that a serum Tg > 1.5 ng/ml was significantly correlated with the presence of metastatic accumulation (odds ratio = 1.985; p = 0.033). In conclusion, Patients with Tg > 1.5 ng/ml were more likely to show metastatic accumulation. In addition, the presence of lymph node metastasis at the initial thyroid surgery was also associated with this unexpected metastatic accumulation.

DOI： 10.18999/nagjms.82.2.205

Web of Science

Scopus

PubMed

Language：English   Publishing type：Research paper (scientific journal)  

Neurite orientation dispersion and density imaging (NODDI) is a novel diffusion method for evaluating tissue microstructure, and may provide additional information over conventional diffusion tensor imaging (DTI). We evaluated NODDI and DTI parameters in cases of tuberous sclerosis (TS) to assess microstructural changes in the white matter. Eleven cases of tuberous sclerosis and eight age-matched controls underwent NODDI and DTI. We performed qualitative analysis and tract-based spatial statistics (TBSS) analysis of the NODDI parameters (Ficv: intracellular volume fraction, Fiso: isotropic fraction, ODI: orientation dispersion index) as well as DTI parameters (MD: mean diffusivity, FA: fractional anisotropy). We also performed a correlation analysis between clinical symptoms and parameters. The qualitative analysis indicated that the Ficv had a lower value in TS cases particularly in the tubers adjacent to the white matter. The TBSS analysis showed that the TS cases had decreased Ficv in a greater area compared to the other parameters including MD. In particular, the Ficv was decreased in deep white matter, such as the superior longitudinal fascicles (SLF). The application of NODDI to TS cases revealed tissue microstructural changes, and particularly the Ficv could detect more widespread abnormalities in white matter structure compared to DTI parameters.

DOI： 10.1038/s41598-019-57306-w

Web of Science

Scopus

PubMed

Language：English   Publishing type：Research paper (scientific journal)   Publisher：Japanese Society for Magnetic Resonance in Medicine  

We currently obtain pre- and post-contrast enhanced whole brain 3D-real inversion recovery images for the evaluation of endolymphatic hydrops. We noticed that the space between the pial sheath surrounding the cortical veins and the cortical venous wall is enhanced and this enhancement seems to connect to the meningeal lymphatics along superior sagittal sinus. This new anatomical concept regarding the outflow from the glymphatic system might be important for the future research in neuroscience.

DOI： 10.2463/mrms.bc.2019-0099

Web of Science

Scopus

PubMed

CiNii Research

Language：Japanese   Publishing type：Research paper (scientific journal)  

OBJECTIVE: To evaluate the associations between computer-aided diagnosis (CAD)-generated kinetic volume parameters and survival in triple-negative breast cancer (TNBC) patients. METHODS: 40 patients with TNBC who underwent pre-operative MRI between March 2008 and March 2014 were included. We analyzed CAD-generated parameters on dynamic contrast-enhanced MRI, visual MRI assessment, and histopathological data. Cox proportional hazards models were used to determine associations with survival outcomes. RESULTS: 12 of the 40 (30.0%) patients experienced recurrence and 7 died of breast cancer after a median follow-up of 73.6 months. In multivariate analysis, higher percentage volume (%V) with more than 200% initial enhancement rate correlated with worse disease-specific survival (hazard ratio, 1.12; 95% confidence interval, 1.02-1.22; p-value, 0.014) and higher %V with more than 100% initial enhancement rate followed by persistent curve type at 30% threshold correlated with worse disease-specific survival (hazard ratio, 1.33; 95% confidence interval, 1.10-1.61; p-value, 0.004) and disease-free survival (hazard ratio, 1.27; 95% confidence interval, 1.12-1.43; p-value, 0.000). CONCLUSION: CAD-generated kinetic volume parameters may correlate with survival in TNBC patients. Further study would be necessary to validate our results on larger cohorts. ADVANCES IN KNOWLEDGE: CAD generated kinetic volume parameters on breast MRI can predict recurrence and survival outcome of patients in TNBC. Varying the enhancement threshold improved the predictive performance of CAD generated kinetic volume parameter.

DOI： 10.1259/bjr.20190712

Web of Science

Scopus

PubMed

Language：English   Publishing type：Research paper (scientific journal)   Publisher：Japanese Society for Magnetic Resonance in Medicine  

PURPOSE: It has been reported previously that intravenously administered gadolinium-based contrast agent (GBCA) leaks into the subarachnoid space around the cortical veins at 4 h after injection in all old people over 37 years, but not in younger people up to 37 years of age in 3D-real IR images. The purpose of this study was to investigate whether there was a strict threshold of 37 years of age for the leakage of the GBCA into the subarachnoid space. METHODS: The subjects included 190 patients, that were scanned for 3D-real IR images at 4 hours after intravenous injection of GBCA as a diagnostic test for endolymphatic hydrops. The patient's age ranged from 14 to 81 years. Two experienced neuroradiologists evaluated the images to determine whether the GBCA leakage around the cortical veins was positive or negative. Any discrepancies between the two observers were discussed and a consensus was obtained.A Mann-Whitney U test and receiver operating characteristic (ROC) curve analysis were used to compare the positive and the negative group and to set the age cut-off value for the prediction of GBCA leakage. RESULTS: The GBCA leakage around the cortical veins was negative in 35 patients and positive in 155 patients. The average age was 33 ± 11 years in the negative group, and 55 ± 12 years in the positive group (P < 0.01). In the ROC analysis for the age and leakage of the GBCA, an area under the curve was 0.905 and the cut-off age was 37.317 years (sensitivity of 0.942 and specificity of 0.771). CONCLUSION: Intravenously administered GBCA leaks into the subarachnoid space around the cortical veins in most patients over 37 years of age. However, it should be noted that it can be found occasionally in patients under 37 years of age.

DOI： 10.2463/mrms.mp.2019-0182

Web of Science

Scopus

PubMed

CiNii Research

Language：English   Publishing type：Research paper (scientific journal)  

The results of research on the use of artificial intelligence (AI) for medical imaging of the lungs of patients with coronavirus disease 2019 (COVID-19) has been published in various forms. In this study, we reviewed the AI for diagnostic imaging of COVID-19 pneumonia. PubMed, arXiv, medRxiv, and Google scholar were used to search for AI studies. There were 15 studies of COVID-19 that used AI for medical imaging. Of these, 11 studies used AI for computed tomography (CT) and 4 used AI for chest radiography. Eight studies presented independent test data, 5 used disclosed data, and 4 disclosed the AI source codes. The number of datasets ranged from 106 to 5941, with sensitivities ranging from 0.67-1.00 and specificities ranging from 0.81-1.00 for prediction of COVID-19 pneumonia. Four studies with independent test datasets showed a breakdown of the data ratio and reported prediction of COVID-19 pneumonia with sensitivity, specificity, and area under the curve (AUC). These 4 studies showed very high sensitivity, specificity, and AUC, in the range of 0.9-0.98, 0.91-0.96, and 0.96-0.99, respectively.

DOI： 10.5152/dir.2019.20294

Web of Science

Scopus

PubMed

Language：English   Publishing type：Research paper (scientific journal)   Publisher：LWW  

DOI： 10.1097/IAE.0000000000002611

Web of Science

Scopus

PubMed

Language：English   Publishing type：Research paper (scientific journal)   Publisher：LWW  

PURPOSE: This paper aims to explore the role of a metabolic parameter on F-FDG-PET/CT for clinical T-classification in early-stage adenocarcinoma. PATIENTS AND METHODS: One hundred six surgically resected pathological TNM stage (p-stage) 0/I lung adenocarcinomas were retrospectively reviewed. The solid size (SS) measured on thin-section CT and the pathological invasive size (IS) of tumors were recorded. The SUVmax and metabolic tumor volume with SUV ≥1.0 (MTV1.0) derived from PET/CT data were measured on a workstation, and the metabolic tumor diameter with SUV ≥1.0 (MTD1.0) was calculated automatically from MTV1.0. For the correlations between the IS and the SS, MTD1.0, or SUVmax, Pearson's correlation coefficients were compared using the Meng-Rosenthal-Rubin method. Additionally, the reproducibility between the clinical TNM stage (c-stage), based on the SS or MTD1.0, and the p-stage was analyzed using the kappa coefficient (k). RESULTS: For the correlations between the IS and the other parameters, Pearson correlation coefficient was 0.630 for the SS, 0.600 for the SUVmax, and 0.725 for MTD1.0. MTD1.0 correlated significantly and more strongly with the IS than the SS and the SUVmax did (P = 0.040, and P = 0.008, respectively). The reproducibility between p-stage and c-stage based on the SS was moderate (k = 0.529, P < 0.001), whereas that between p-stage and c-stage based on MTD1.0 was substantial (k = 0.676, P < 0.001). CONCLUSIONS: MTD1.0 on FDG-PET/CT was correlated significantly and more strongly with the pathological IS in lung adenocarcinomas than with the SS on thin-section CT. FDG-PET/CT could classify more precisely early-stage lung adenocarcinoma than the presently used T-classification based on thin-section CT findings.

DOI： 10.1097/RLU.0000000000002591

Web of Science

Scopus

PubMed

Language：English   Publishing type：Research paper (scientific journal)   Publisher：Radiological Society of North America  

Purpose To investigate the relationship between the postoperative prognosis of patients with part-solid non-small cell lung cancer and the solid component size acquired by using three-dimensional (3D) volumetry software on multidetector computed tomographic (CT) images. Materials and Methods A retrospective study by using preoperative multidetector CT data with 0.5-mm section thickness, clinical records, and pathologic reports of 96 patients with primary subsolid non-small cell lung cancer (47 men and 49 women; mean age ± standard deviation, 66 years ± 8) were reviewed. Two radiologists measured the two-dimensional (2D) maximal solid size of each nodule on an axial image (hereafter, 2D MSSA), the 3D maximal solid size on multiplanar reconstructed images (hereafter, 3D MSSMPR), and the 3D solid volume of greater than 0 HU (hereafter, 3D SV0HU) within each nodule. The correlations between the postoperative recurrence and the effects of clinical and pathologic characteristics, 2D MSSA, 3D MSSMPR, and 3D SV0HU as prognostic imaging biomarkers were assessed by using a Cox proportional hazards model. Results For the prediction of postoperative recurrence, the area under the receiver operating characteristics curve was 0.796 (95% confidence interval: 0.692, 0.900) for 2D MSSA, 0.776 (95% confidence interval: 0.667, 0.886) for 3D MSSMPR, and 0.835 (95% confidence interval: 0.749, 0.922) for 3D SV0HU. The optimal cutoff value for 3D SV0HU for predicting tumor recurrence was 0.54 cm3, with a sensitivity of 0.933 (95% confidence interval: 0.679, 0.998) and a specificity of 0.716 (95% confidence interval: 0.605, 0.811) for the recurrence. Significant predictive factors for disease-free survival were 3D SV0HU greater than or equal to 0.54 cm3 (hazard ratio, 6.61; P = .001) and lymphatic and/or vascular invasion derived from histopathologic analysis (hazard ratio, 2.96; P = .040). Conclusion The measurement of 3D SV0HU predicted the postoperative prognosis of patients with part-solid lung cancer more accurately than did 2D MSSA and 3D MSSMPR. © RSNA, 2018.

DOI： 10.1148/radiol.2018172319

Web of Science

Scopus

PubMed

Language：English   Publishing type：Research paper (scientific journal)   Publisher：Elsevier  

INTRODUCTION: We aimed to determine the concordance between the clinical stage (c-stage) and pathologic stage (p-stage) for patients with small-size lung cancer. Additionally we searched for prognostic factors other than the TNM stage. PATIENTS AND METHODS: We retrospectively reviewed the preoperative multidetector computed tomography (CT) and positron emission tomography/CT reports, surgical records, and pathologic reports of patients with primary lung cancer ≤ 3 cm. The Union for International Cancer Control TNM seventh edition classification of c-stage and p-stage were compared. The tumors were classified into multiple subgroups by concordance or discordance between the c-stage and p-stage. Disease-free survival (DFS) was assessed using survival analysis to assess the tumor characteristics that were predictive of prognosis. RESULTS: A total of 289 surgically resected primary lung cancers were evaluated. The concordance between c-stage and p-stage was 65.4%, with moderate reproducibility (kappa coefficient, 0.467). The upstaging rate from c-stage I to p-stage II-IV was 9.4%, and these patients had significantly worse DFS than those with a concordant stage I classification (P < .001). The main reason for upstaging was an underestimation of metastases to the hilar lymph nodes (n = 7) or mediastinal lymph nodes (n = 11). A multivariate Cox proportional hazards model showed that the significant predictive factors for DFS were p-stage (hazard ratio, 1.342; P = .003) and maximum standardized uptake value on positron emission tomography/CT (hazard ratio, 12.162; P = .001). CONCLUSION: The concordance rate between c-stage and p-stage for small primary lung cancers had moderate reproducibility. Discordance between c-stage I and p-stage II-IV significantly affected DFS. The maximum standardized uptake value of the primary lesion was an independent prognostic factor, and combining it with c-stage might improve the prediction of therapeutic outcomes.

DOI： 10.1016/j.cllc.2017.05.021

Web of Science

Scopus

PubMed

Language：English   Publishing type：Research paper (scientific journal)   Publisher：Elsevier  

PURPOSE: To compare dual-phase dual-energy CT (DE-CT) with FDG-PET/CT for predicting histopathological locoregional invasiveness of non-small cell lung cancers (NSCLCs). MATERIALS AND METHODS: We selected 63 consecutive patients with NSCLC lesions (37 males, 26 females; age range, 44-85 years; mean age, 69 years) who were evaluated preoperatively by both DE-CT and PET/CT at our institution. Postoperative microscopic invasiveness (lymphatic permeation, vascular invasion, and/or pleural involvement) was reviewed, and we defined locoregionally invasive tumors as those that had at least one positive finding of microscopic invasiveness. DE-CT scanning in the arterial and delayed phases was performed after injection of iodinated contrast media using 140-kVp and 80-kVp tube voltages. Three-dimensional iodine-related attenuation of primary tumors in the arterial and delayed phases was quantified automatically using "syngo Dual Energy Lung Nodules" application software, and the ratio of arterial phase to delayed phase enhancement (A/D ratio) was calculated. The A/D ratio and SUVmax on PET/CT were evaluated with respect to postoperative invasiveness by univariate logistic regression analysis. RESULTS: The A/D ratio was significantly correlated with lymphatic permeation, vascular invasion, and pleural involvement (p=0.011, p=0.021, and p=0.010, respectively). In contrast, the SUVmax was significantly correlated with pleural involvement (p=0.020) but not with lymphatic permeation or vascular invasion (p=0.088 and p=0.100, respectively). In the subgroup of patients with lesion diameters ≤2cm, the A/D ratio was significantly correlated with locoregional invasiveness (p=0.040), while the SUVmax was not (p=0.121). CONCLUSION: For the prediction of microscopic invasiveness of NSCLCs, the diagnostic performance of dual-phase DE-CT may be comparable to that of FDG-PET/CT.

DOI： 10.1016/j.ejrad.2017.08.010

Web of Science

Scopus

PubMed

Language：English   Publishing type：Research paper (scientific journal)   Publisher：Public Library of Science  

PURPOSE: We developed an original, computer-aided diagnosis (CAD) software that subtracts the initial thoracic vertebral three-dimensional computed tomography (3D-CT) image from the follow-up 3D-CT image. The aim of this study was to investigate the efficacy of this CAD software during screening for vertebral metastases on follow-up CT images of primary lung cancer patients. MATERIALS AND METHODS: The interpretation experiment included 30 sets of follow-up CT scans in primary lung cancer patients and was performed by two readers (readers A and B), who each had 2.5 years' experience reading CT images. In 395 vertebrae from C6 to L3, 46 vertebral metastases were identified as follows: osteolytic metastases (n = 17), osteoblastic metastases (n = 14), combined osteolytic and osteoblastic metastases (n = 6), and pathological fractures (n = 9). Thirty-six lesions were in the anterior component (vertebral body), and 10 lesions were in the posterior component (vertebral arch, transverse process, and spinous process). The area under the curve (AUC) by receiver operating characteristic (ROC) curve analysis and the sensitivity and specificity for detecting vertebral metastases were compared with and without CAD for each observer. RESULTS: Reader A detected 47 abnormalities on CT images without CAD, and 33 of them were true-positive metastatic lesions. Using CAD, reader A detected 57 abnormalities, and 38 were true positives. The sensitivity increased from 0.717 to 0.826, and on ROC curve analysis, AUC with CAD was significantly higher than that without CAD (0.849 vs. 0.902, p = 0.021). Reader B detected 40 abnormalities on CT images without CAD, and 36 of them were true-positive metastatic lesions. Using CAD, reader B detected 44 abnormalities, and 39 were true positives. The sensitivity increased from 0.783 to 0.848, and AUC with CAD was nonsignificantly higher than that without CAD (0.889 vs. 0.910, p = 0.341). Both readers detected more osteolytic and osteoblastic metastases with CAD than without CAD. CONCLUSION: Our temporal 3D-CT subtraction CAD software easily detected vertebral metastases on the follow-up CT images of lung cancer patients regardless of the osteolytic or osteoblastic nature of the lesions.

DOI： 10.1371/journal.pone.0170309

Web of Science

Scopus

PubMed

Language：English   Publishing type：Research paper (scientific journal)  

DOI： 10.1007/s12149-015-1025-z

PubMed

Language：English   Publishing type：Research paper (scientific journal)  

DOI： 10.1259/bjr.20150224

PubMed

Language：English   Publishing type：Research paper (scientific journal)  

DOI： 10.1016/j.lungcan.2014.09.006

PubMed

Language：English   Publishing type：Research paper (scientific journal)  

DOI： 10.1186/1470-7330-14-3

PubMed

Language：Japanese  

J-GLOBAL

J-GLOBAL

J-GLOBAL

Language：Japanese   Publisher：(公社)日本小児科学会  

J-GLOBAL

J-GLOBAL

Language：Japanese   Publisher：医用画像情報学会  

COVID-19が世界中に広まり、COVID-19肺炎の診断に胸部CTや胸部単純X線の有用性が報告され、この画像所見を用いたAI開発が初期の段階から積極的に行われた。高性能なAIが多数存在するが、臨床において用いる際には注意すべき点が複数存在する。COVID-19肺炎に対して開発・使用された画像診断に関連するAI研究について、PubMedに2020年12月までに登録されたものを抽出しレビューを行った。

J-GLOBAL

Language：Japanese   Publisher：(株)メディカルアイ  

J-GLOBAL

Language：Japanese   Publisher：(株)メディカルアイ  

J-GLOBAL

Language：Japanese  

J-GLOBAL

Language：Japanese   Publisher：(公社)日本医学放射線学会  

J-GLOBAL

Language：Japanese  

J-GLOBAL

J-GLOBAL

Language：Japanese   Publisher：(一社)日本小児神経学会  

J-GLOBAL

Language：Japanese  

J-GLOBAL

Other Link： https://search-tp.jamas.or.jp/index.php?module=Default&action=Link&pub_year=2020&ichushi_jid=J00235&link_issn=&doc_id=20200408090014&doc_link_id=10.15105%2FGZ.0000001656&url=https%3A%2F%2Fdoi.org%2F10.15105%2FGZ.0000001656&type=%88%E3%8F%91.jp_%83I%81%5B%83%8B%83A%83N%83Z%83X&icon=https%3A%2F%2Fjk04.jamas.or.jp%2Ficon%2F00024_2.gif

Language：Japanese   Publisher：(公社)日本医学放射線学会  

J-GLOBAL

Language：Japanese   Publisher：(NPO)日本肺癌学会  

J-GLOBAL

Language：Japanese   Publisher：(公社)日本医学放射線学会  

J-GLOBAL

Language：Japanese   Publisher：(株)インナービジョン  

2006年から始まった第三次AIブームによりAIの研究が加速度的に進み、現在ではスマートフォンのカメラや音声入力など身近なものに活用されている。放射線医学においては古くから人工知能(AI)を用いた研究が行われ、臨床にも応用されていた。最近では、さらに発展したAIを用いたCADの開発が盛んであり、世界中の研究者が開発を競っている。本稿では、加速度的に進歩するAIと放射線医学とのかかわりについて、主に胸部画像診断の観点から現在の状況と問題点についてまとめ、実際の研究例について提示する。(著者抄録)

J-GLOBAL

Language：Japanese   Publisher：(公社)日本医学放射線学会  

J-GLOBAL

Language：Japanese   Publisher：(公社)日本医学放射線学会  

J-GLOBAL

Language：Japanese   Publisher：(公社)日本医学放射線学会  

J-GLOBAL

Language：Japanese   Publisher：(公社)日本医学放射線学会  

J-GLOBAL

Language：Japanese   Publisher：(NPO)日本肺癌学会  

J-GLOBAL

Language：Japanese   Publisher：(一社)日本核医学会  

Language：Japanese   Publisher：(一社)日本核医学会  

Language：Japanese   Publisher：(一社)日本核医学会  

Language：Japanese   Publisher：(一社)日本核医学会  

Language：Japanese   Publisher：(公社)日本医学放射線学会  

J-GLOBAL

J-GLOBAL

J-GLOBAL

Language：Japanese   Publisher：(公社)日本医学放射線学会  

J-GLOBAL