Updated on 2025/04/02

写真a

 
KOYAMA Junji
 
Organization
Nagoya University Hospital Respiratory Medicine Assistant professor of hospital
Title
Assistant professor of hospital
External link

Degree 1

  1. 学士(医学) ( 2010.3   名古屋大学 ) 

Research Interests 1

  1. 肺癌

Research Areas 2

  1. Life Science / Respiratory medicine

  2. Life Science / Tumor diagnostics and therapeutics

Current Research Project and SDGs 2

  1. 胸部悪性腫瘍に対する薬物療法

  2. 胸部悪性腫瘍治療における機械学習の活用

Research History 1

  1. Nagoya University Hospital   Department of Respiratory Medicine   Assistant Professor

    2023.4

      More details

    Country:Japan

    researchmap

Education 2

  1. Nagoya University   Graduate School of Medicine

    2019.4 - 2023.3

      More details

    Country: Japan

    researchmap

  2. Nagoya University   School of Medicine   Department of Medicine

    2004.4 - 2010.3

      More details

    Country: Japan

    researchmap

Professional Memberships 6

  1. 日本呼吸器内視鏡学会

  2. 日本肺癌学会

  3. 日本臨床腫瘍学会

  4. 日本メディカルAI学会

  5. 日本呼吸器学会

▼display all

Awards 2

  1. The 26th Congress of the Asian Pacific Society of Respirology, Assembly Education Award

    2022.11  

     More details

  2. 第4回日本メディカルAI学会学術集会、優秀一般演題賞

    2022.6  

     More details

 

Papers 34

  1. Clinical benefit of PD-1/PD-L1 inhibitors for poor performance status patients with advanced non-small cell lung cancer Reviewed International journal

    Koyama, J; Morise, M; Tanaka, I; Hori, S; Matsuzawa, R; Ozone, S; Matsushita, A; Matsuo, M; Asano, S; Tanaka, T; Shima, K; Kimura, T; Sakamoto, K; Kondoh, Y; Hashimoto, N

    JOURNAL OF CHEMOTHERAPY     page: 1 - 10   2025.3

     More details

    Authorship:Lead author   Language:English  

    DOI: 10.1080/1120009X.2025.2481349

    Web of Science

    PubMed

  2. Comparison of immune checkpoint inhibitor plus chemotherapy or ipilimumab plus nivolumab-based therapy for NSCLC patients with PD-L1 TPS (1-49 %): TOPGAN2023-01. Reviewed International journal

    Hisashi Tanaka, Tomonori Makiguchi, Takehiro Tozuka, Yosuke Kawashima, Tomohiro Oba, Ryosuke Tsugitomi, Junji Koyama, Yuichi Tambo, Shinsuke Ogusu, Masafumi Saiki, Hiroshi Gyotoku, Tsukasa Hasegawa, Eisaku Miyauchi, Tomoaki Sonoda, Ryota Saito, Katsumi Nakatomi, Toshio Sakatani, Keita Kudo, Yuko Tsuchiya-Kawano, Makoto Nishio

    European journal of cancer (Oxford, England : 1990)   Vol. 213   page: 115117 - 115117   2024.12

     More details

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

    INTRODUCTION: Immune checkpoint inhibitors (ICIs) plus chemotherapy is now a standard treatment for non-small cell lung cancer (NSCLC). Whether ICI plus chemotherapy (ICI-chemo) or ipilimumab plus nivolumab (I-N)-based therapy is superior for patients with NSCLC with a programmed death-ligand 1 (PD-L1) tumor proportion score (TPS) of 1-49 % has not been evaluated. METHODS: This multicenter retrospective study included NSCLC patients with a TPS score of 1-49 %, who began first-line chemotherapy. Propensity score matching analysis was used to adjust for various confounders and evaluate treatment efficacy. RESULTS: A total of 401 patients were enrolled, of whom 308 received ICI-chemo and 93 received I-N-based therapy. The median OS was 21.0 months in the ICI-chemo group and 20.0 months in the I-N-based therapy group. After propensity score matching, there was no difference in OS or PFS between the ICI-chemo group and the I-N-based therapy group (OS: hazard ratios (HR), 0.83; 95 % confidence interval [CI], 0.54-1.26, PFS: HR, 0.72; 95 % CI, 0.52-1.00). Among PD-L1 TPS 25-49 %, there was a tendency for OS to be favorable for the ICI-chemo group (OS: HR, 0.30; 95 % CI, 0.09-0.85). Treatment discontinuation occurred for 26.2 % of the patients in the ICI-chemo group and 41.9 % in the I-N-based therapy group. CONCLUSIONS: Among PD-L1 TPS 1-49 %, there was no significant difference in survival outcomes between the ICI-chemo group and the I-N-based therapy group. Based on the results of a subgroup analysis, ICI-chemo may be superior for treating NSCLC with a TPS of 25-49 %.

    DOI: 10.1016/j.ejca.2024.115117

    Web of Science

    Scopus

    PubMed

    researchmap

  3. Artificial intelligence-based personalized survival prediction using clinical and radiomics features in patients with advanced non-small cell lung cancer. Reviewed International journal Open Access

    Junji Koyama, Masahiro Morise, Taiki Furukawa, Shintaro Oyama, Reiko Matsuzawa, Ichidai Tanaka, Keiko Wakahara, Hideo Yokota, Tomoki Kimura, Yoshimune Shiratori, Yasuhiro Kondoh, Naozumi Hashimoto, Makoto Ishii

    BMC cancer   Vol. 24 ( 1 ) page: 1417 - 1417   2024.11

     More details

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

    BACKGROUND: Multiple first-line treatment options have been developed for advanced non-small cell lung cancer (NSCLC) in each subgroup determined by predictive biomarkers, specifically driver oncogene and programmed cell death ligand-1 (PD-L1) status. However, the methodology for optimal treatment selection in individual patients is not established. This study aimed to develop artificial intelligence (AI)-based personalized survival prediction model according to treatment selection. METHODS: The prediction model was built based on random survival forest (RSF) algorithm using patient characteristics, anticancer treatment histories, and radiomics features of the primary tumor. The predictive accuracy was validated with external test data and compared with that of cox proportional hazard (CPH) model. RESULTS: A total of 459 patients (training, n = 299; test, n = 160) with advanced NSCLC were enrolled. The algorithm identified following features as significant factors associated with survival: age, sex, performance status, Brinkman index, comorbidity of chronic obstructive pulmonary disease, histology, stage, driver oncogene status, tumor PD-L1 expression, administered anticancer agent, six markers of blood test (sodium, lactate dehydrogenase, etc.), and three radiomics features associated with tumor texture, volume, and shape. The C-index of RSF model for test data was 0.841, which was higher than that of CPH model (0.775, P < 0.001). Furthermore, the RSF model enabled to identify poor survivor treated with pembrolizumab because of tumor PD-L1 high expression and those treated with driver oncogene targeted therapy according to driver oncogene status. CONCLUSIONS: The proposed AI-based algorithm accurately predicted the survival of each patient with advanced NSCLC. The AI-based methodology will contribute to personalized medicine. TRIAL REGISTRATION: The trial design was retrospectively registered study performed in accordance with the Declaration of Helsinki and approved by the Institutional Review Board of Nagoya University Graduate School of Medicine (approval: 2020 - 0287).

    DOI: 10.1186/s12885-024-13190-w

    Open Access

    Web of Science

    Scopus

    PubMed

    researchmap

  4. Bronchial occlusion with endobronchial Watanabe spigots using a two-scope technique for massive haemoptysis. Reviewed International journal Open Access

    Tomoya Baba, Takayasu Ito, Yoshiki Sato, Shunsaku Hayai, Junji Koyama, Shota Nakamura, Yoshiyuki Tokuda, Toyofumi Fengshi Chen-Yoshikawa, Makoto Ishii

    Respirology case reports   Vol. 12 ( 6 ) page: e01405   2024.6

     More details

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

    Massive haemoptysis is a life-threatening condition whose cause needs to be identified rapidly so that prompt interventions can ensue. Bronchial occlusion with endobronchial Watanabe spigots (EWSs) may be useful when endovascular treatment or surgery proves to be difficult. An 84-year-old woman developed massive haemoptysis during percutaneous mitral valve repair for refractory heart failure due to severe mitral regurgitation (MR). Interventional radiology (IVR) and surgery were contraindicated, and bronchial occlusion with EWSs was attempted to control bleeding. The bleeding was so persistent that it was difficult to secure the visual field without aspiration with a bronchoscope. Herein, we report a two-scope technique, also used in cryobiopsy of peripheral lung lesions, to control bleeding and perform bronchial occlusion with EWSs.

    DOI: 10.1002/rcr2.1405

    Web of Science

    Scopus

    PubMed

    researchmap

  5. Artificial intelligence in a prediction model for postendoscopic retrograde cholangiopancreatography pancreatitis. Reviewed International journal

    Hidekazu Takahashi, Eizaburo Ohno, Taiki Furukawa, Kentaro Yamao, Takuya Ishikawa, Yasuyuki Mizutani, Tadashi Iida, Yoshimune Shiratori, Shintaro Oyama, Junji Koyama, Kensaku Mori, Yuichiro Hayashi, Masahiro Oda, Takahisa Suzuki, Hiroki Kawashima

    Digestive endoscopy : official journal of the Japan Gastroenterological Endoscopy Society   Vol. 36 ( 4 ) page: 463 - 472   2024.4

     More details

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

    OBJECTIVES: In this study we aimed to develop an artificial intelligence-based model for predicting postendoscopic retrograde cholangiopancreatography (ERCP) pancreatitis (PEP). METHODS: We retrospectively reviewed ERCP patients at Nagoya University Hospital (NUH) and Toyota Memorial Hospital (TMH). We constructed two prediction models, a random forest (RF), one of the machine-learning algorithms, and a logistic regression (LR) model. First, we selected features of each model from 40 possible features. Then the models were trained and validated using three fold cross-validation in the NUH cohort and tested in the TMH cohort. The area under the receiver operating characteristic curve (AUROC) was used to assess model performance. Finally, using the output parameters of the RF model, we classified the patients into low-, medium-, and high-risk groups. RESULTS: A total of 615 patients at NUH and 544 patients at TMH were enrolled. Ten features were selected for the RF model, including albumin, creatinine, biliary tract cancer, pancreatic cancer, bile duct stone, total procedure time, pancreatic duct injection, pancreatic guidewire-assisted technique without a pancreatic stent, intraductal ultrasonography, and bile duct biopsy. In the three fold cross-validation, the RF model showed better predictive ability than the LR model (AUROC 0.821 vs. 0.660). In the test, the RF model also showed better performance (AUROC 0.770 vs. 0.663, P = 0.002). Based on the RF model, we classified the patients according to the incidence of PEP (2.9%, 10.0%, and 23.9%). CONCLUSION: We developed an RF model. Machine-learning algorithms could be powerful tools to develop accurate prediction models.

    DOI: 10.1111/den.14622

    Web of Science

    Scopus

    PubMed

    researchmap

▼display all

MISC 71

  1. Prognostic impact of bone metastases in osimertinib-treated patients with EGFR-mutated NSCLC

    Tanaka, I; Gen, S; Hori, K; Morise, M; Koyama, J; Kodama, Y; Matsui, A; Miyazawa, A; Hase, T; Hibino, Y; Yokoyama, T; Kimura, T; Yoshida, N; Sato, M; Ishii, M

    CANCER SCIENCE   Vol. 116   page: 329 - 329   2025.1

     More details

  2. EGFR遺伝子変異を有する非小細胞肺癌患者の骨転移が、オシメルチニブの治療効果に与える影響 多施設共同後ろ向きコホート研究(Prognostic impact of bone metastases in osimertinib-treated patients with EGFR-mutated NSCLC)

    田中 一大, 玄 崇永, 堀 和美, 森瀬 昌宏, 神山 潤二, 小玉 勇太, 松井 彰, 宮沢 亜矢子, 長谷 哲成, 日比野 佳孝, 横山 俊彦, 木村 智樹, 吉田 憲生, 佐藤 光夫, 石井 誠

    日本癌学会総会記事   Vol. 83回   page: P - 1216   2024.9

     More details

    Language:English   Publisher:(一社)日本癌学会  

    researchmap

  3. NSCC-NOSに対するPD-1/PD-L1阻害剤一次治療

    平野 達也, 森瀬 昌宏, 堀 翔, 橋本 賢彦, 大曽根 祥子, 速井 俊策, 神山 潤二, 田中 一大, 佐藤 光夫, 木村 智樹, 近藤 康博, 石井 誠

    日本呼吸器学会誌   Vol. 13 ( 増刊 ) page: 295 - 295   2024.3

     More details

    Language:Japanese   Publisher:(一社)日本呼吸器学会  

    researchmap

  4. EBUS-TBNAとEBUS-MFBにより適正な診断が得られた悪性末梢神経鞘腫術後縦隔リンパ節転移の1例

    佐藤 智則, 伊藤 貴康, 馬場 智也, 神山 潤二, 松井 利憲, 森瀬 昌宏, 若原 恵子, 石井 誠, 中黒 匡人

    気管支学   Vol. 46 ( 1 ) page: 64 - 64   2024.1

     More details

    Language:Japanese   Publisher:(一社)日本呼吸器内視鏡学会  

    researchmap

  5. 2スコープ法を活用したEWSによる気管支充填術が有効であった大量喀血の1例

    馬場 智也, 伊藤 貴康, 佐藤 圭樹, 速井 俊策, 神山 潤二, 森瀬 昌宏, 若原 恵子, 石井 誠, 中村 彰太, 芳川 豊史, 徳田 順之

    気管支学   Vol. 46 ( 1 ) page: 65 - 65   2024.1

     More details

    Language:Japanese   Publisher:(一社)日本呼吸器内視鏡学会  

    researchmap

▼display all

Industrial property rights 1

  1. 情報処理装置、情報処理方法、および、コンピュータプログラム

    神山潤二, 古川大記, 森瀬昌宏, 横田秀夫

     More details

    Application no:PCT/JP2023/008495  Date applied:2023.3

    Announcement no:WO2023/176576  Date announced:2023.9

 

Teaching Experience (On-campus) 2

  1. 基本的臨床技能実習

    2024

     詳細を見る

    胸部X-P読影

  2. 基本的臨床技能実習

    2023

     詳細を見る

    胸部X-P読影