Machine learning analysis of pathological images to predict 1-year progression-free survival of immunotherapy in patients with small-cell lung cancer
Background In small-cell lung cancer (SCLC), the tumor immune microenvironment (TIME) could be a promising biomarker for immunotherapy, but objectively evaluating TIME remains challenging. Hence, we aimed to develop a predictive biomarker of immunotherapy efficacy through a machine learning analysis...
Saved in:
| Main Authors: | , , , , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMJ Publishing Group
2024-02-01
|
| Series: | Journal for ImmunoTherapy of Cancer |
| Online Access: | https://jitc.bmj.com/content/12/2/e007987.full |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1823861407380144128 |
|---|---|
| author | Hirotaka Matsumoto Hiroaki Akamatsu Nobuyuki Yamamoto Yuki Sato Daichi Fujimoto Yoshihiko Taniguchi Motohiro Tamiya Yasuhiro Koh Junya Fukuoka Hisashi Tanaka Naoki Furuya Ryota Shibaki Tsukasa Nozawa Akira Sano Yuka Kitamura Takashi Kijima Toshihide Yokoyama Satoru Miura Akito Hata Jun Sugisaka |
| author_facet | Hirotaka Matsumoto Hiroaki Akamatsu Nobuyuki Yamamoto Yuki Sato Daichi Fujimoto Yoshihiko Taniguchi Motohiro Tamiya Yasuhiro Koh Junya Fukuoka Hisashi Tanaka Naoki Furuya Ryota Shibaki Tsukasa Nozawa Akira Sano Yuka Kitamura Takashi Kijima Toshihide Yokoyama Satoru Miura Akito Hata Jun Sugisaka |
| author_sort | Hirotaka Matsumoto |
| collection | DOAJ |
| description | Background In small-cell lung cancer (SCLC), the tumor immune microenvironment (TIME) could be a promising biomarker for immunotherapy, but objectively evaluating TIME remains challenging. Hence, we aimed to develop a predictive biomarker of immunotherapy efficacy through a machine learning analysis of the TIME.Methods We conducted a biomarker analysis in a prospective study of patients with extensive-stage SCLC who received chemoimmunotherapy as the first-line treatment. We trained a model to predict 1-year progression-free survival (PFS) using pathological images (H&E, programmed cell death-ligand 1 (PD-L1), and double immunohistochemical assay (cluster of differentiation 8 (CD8) and forkhead box P3 (FoxP3)) and patient information. The primary outcome was the mean area under the curve (AUC) of machine learning models in predicting the 1-year PFS.Results We analyzed 100,544 patches of pathological images from 78 patients. The mean AUC values of patient information, pathological image, and combined models were 0.789 (range 0.571–0.982), 0.782 (range 0.750–0.911), and 0.868 (range 0.786–0.929), respectively. The PFS was longer in the high efficacy group than in the low efficacy group in all three models (patient information model, HR 0.468, 95% CI 0.287 to 0.762; pathological image model, HR 0.334, 95% CI 0.117 to 0.628; combined model, HR 0.353, 95% CI 0.195 to 0.637). The machine learning analysis of the TIME had better accuracy than the human count evaluations (AUC of human count, CD8-positive lymphocyte: 0.681, FoxP3-positive lymphocytes: 0.626, PD-L1 score: 0.567).Conclusions The spatial analysis of the TIME using machine learning predicted the immunotherapy efficacy in patients with SCLC, thus supporting its role as an immunotherapy biomarker. |
| format | Article |
| id | doaj-art-6255e060953c4901b89e6055b35b9eff |
| institution | Kabale University |
| issn | 2051-1426 |
| language | English |
| publishDate | 2024-02-01 |
| publisher | BMJ Publishing Group |
| record_format | Article |
| series | Journal for ImmunoTherapy of Cancer |
| spelling | doaj-art-6255e060953c4901b89e6055b35b9eff2025-02-09T15:10:08ZengBMJ Publishing GroupJournal for ImmunoTherapy of Cancer2051-14262024-02-0112210.1136/jitc-2023-007987Machine learning analysis of pathological images to predict 1-year progression-free survival of immunotherapy in patients with small-cell lung cancerHirotaka Matsumoto0Hiroaki Akamatsu1Nobuyuki Yamamoto2Yuki Sato3Daichi Fujimoto4Yoshihiko Taniguchi5Motohiro Tamiya6Yasuhiro Koh7Junya Fukuoka8Hisashi Tanaka9Naoki Furuya10Ryota Shibaki11Tsukasa Nozawa12Akira Sano13Yuka Kitamura14Takashi Kijima15Toshihide Yokoyama16Satoru Miura17Akito Hata18Jun Sugisaka19Department of Respiratory Medicine, Hyogo Prefectural Amagasaki General Medical Center, Hyogo, JapanInternal Medicine Ⅲ, Wakayama Medical University, Wakayama, Japan2 Department of Surgery, Kansai Medical University, Hirakata, Osaka, JapanDepartment of Respiratory Medicine, Kobe City Medical Center General Hospital, Hyogo, JapanInternal Medicine Ⅲ, Wakayama Medical University, Wakayama, JapanDepartment of Internal Medicine, NHO Kinki Chuo Chest Medical Center, Osaka, JapanDepartment of Thoracic Oncology, Osaka International Cancer Institute, Osaka, JapanCenter for Biomedical Sciences, Wakayama Medical University, Wakayama, JapanDepartment of pathology informatics, Nagasaki University Graduate School of Biomedical Sciences, Nagasaki, JapanDepartment of Respiratory Medicine, Hirosaki University Graduate School of Medicine, Hirosaki, Aomori, JapanDivision of Respiratory Medicine, Department of Internal Medicine, St. Marianna University School of Medicine, Kanagawa, JapanInternal Medicine Ⅲ, Wakayama Medical University, Wakayama, JapanExaWizards Inc, Tokyo, JapanExaWizards Inc, Tokyo, JapanDepartment of pathology informatics, Nagasaki University Graduate School of Biomedical Sciences, Nagasaki, JapanDepartment of Respiratory Medicine and Hematology, Hyogo Medical University, Hyogo, JapanDepartment of Respiratory Medicine, Kurashiki Central Hospital, Okayama, JapanDepartment of Internal Medicine, Niigata Cancer Center Hospital, Niigata, JapanDivision of Thoracic Oncology, Kobe Minimally Invasive Cancer Center, Hyogo, JapanDepartment of Pulmonary Medicine, Sendai Kousei Hospital, Miyagi, JapanBackground In small-cell lung cancer (SCLC), the tumor immune microenvironment (TIME) could be a promising biomarker for immunotherapy, but objectively evaluating TIME remains challenging. Hence, we aimed to develop a predictive biomarker of immunotherapy efficacy through a machine learning analysis of the TIME.Methods We conducted a biomarker analysis in a prospective study of patients with extensive-stage SCLC who received chemoimmunotherapy as the first-line treatment. We trained a model to predict 1-year progression-free survival (PFS) using pathological images (H&E, programmed cell death-ligand 1 (PD-L1), and double immunohistochemical assay (cluster of differentiation 8 (CD8) and forkhead box P3 (FoxP3)) and patient information. The primary outcome was the mean area under the curve (AUC) of machine learning models in predicting the 1-year PFS.Results We analyzed 100,544 patches of pathological images from 78 patients. The mean AUC values of patient information, pathological image, and combined models were 0.789 (range 0.571–0.982), 0.782 (range 0.750–0.911), and 0.868 (range 0.786–0.929), respectively. The PFS was longer in the high efficacy group than in the low efficacy group in all three models (patient information model, HR 0.468, 95% CI 0.287 to 0.762; pathological image model, HR 0.334, 95% CI 0.117 to 0.628; combined model, HR 0.353, 95% CI 0.195 to 0.637). The machine learning analysis of the TIME had better accuracy than the human count evaluations (AUC of human count, CD8-positive lymphocyte: 0.681, FoxP3-positive lymphocytes: 0.626, PD-L1 score: 0.567).Conclusions The spatial analysis of the TIME using machine learning predicted the immunotherapy efficacy in patients with SCLC, thus supporting its role as an immunotherapy biomarker.https://jitc.bmj.com/content/12/2/e007987.full |
| spellingShingle | Hirotaka Matsumoto Hiroaki Akamatsu Nobuyuki Yamamoto Yuki Sato Daichi Fujimoto Yoshihiko Taniguchi Motohiro Tamiya Yasuhiro Koh Junya Fukuoka Hisashi Tanaka Naoki Furuya Ryota Shibaki Tsukasa Nozawa Akira Sano Yuka Kitamura Takashi Kijima Toshihide Yokoyama Satoru Miura Akito Hata Jun Sugisaka Machine learning analysis of pathological images to predict 1-year progression-free survival of immunotherapy in patients with small-cell lung cancer Journal for ImmunoTherapy of Cancer |
| title | Machine learning analysis of pathological images to predict 1-year progression-free survival of immunotherapy in patients with small-cell lung cancer |
| title_full | Machine learning analysis of pathological images to predict 1-year progression-free survival of immunotherapy in patients with small-cell lung cancer |
| title_fullStr | Machine learning analysis of pathological images to predict 1-year progression-free survival of immunotherapy in patients with small-cell lung cancer |
| title_full_unstemmed | Machine learning analysis of pathological images to predict 1-year progression-free survival of immunotherapy in patients with small-cell lung cancer |
| title_short | Machine learning analysis of pathological images to predict 1-year progression-free survival of immunotherapy in patients with small-cell lung cancer |
| title_sort | machine learning analysis of pathological images to predict 1 year progression free survival of immunotherapy in patients with small cell lung cancer |
| url | https://jitc.bmj.com/content/12/2/e007987.full |
| work_keys_str_mv | AT hirotakamatsumoto machinelearninganalysisofpathologicalimagestopredict1yearprogressionfreesurvivalofimmunotherapyinpatientswithsmallcelllungcancer AT hiroakiakamatsu machinelearninganalysisofpathologicalimagestopredict1yearprogressionfreesurvivalofimmunotherapyinpatientswithsmallcelllungcancer AT nobuyukiyamamoto machinelearninganalysisofpathologicalimagestopredict1yearprogressionfreesurvivalofimmunotherapyinpatientswithsmallcelllungcancer AT yukisato machinelearninganalysisofpathologicalimagestopredict1yearprogressionfreesurvivalofimmunotherapyinpatientswithsmallcelllungcancer AT daichifujimoto machinelearninganalysisofpathologicalimagestopredict1yearprogressionfreesurvivalofimmunotherapyinpatientswithsmallcelllungcancer AT yoshihikotaniguchi machinelearninganalysisofpathologicalimagestopredict1yearprogressionfreesurvivalofimmunotherapyinpatientswithsmallcelllungcancer AT motohirotamiya machinelearninganalysisofpathologicalimagestopredict1yearprogressionfreesurvivalofimmunotherapyinpatientswithsmallcelllungcancer AT yasuhirokoh machinelearninganalysisofpathologicalimagestopredict1yearprogressionfreesurvivalofimmunotherapyinpatientswithsmallcelllungcancer AT junyafukuoka machinelearninganalysisofpathologicalimagestopredict1yearprogressionfreesurvivalofimmunotherapyinpatientswithsmallcelllungcancer AT hisashitanaka machinelearninganalysisofpathologicalimagestopredict1yearprogressionfreesurvivalofimmunotherapyinpatientswithsmallcelllungcancer AT naokifuruya machinelearninganalysisofpathologicalimagestopredict1yearprogressionfreesurvivalofimmunotherapyinpatientswithsmallcelllungcancer AT ryotashibaki machinelearninganalysisofpathologicalimagestopredict1yearprogressionfreesurvivalofimmunotherapyinpatientswithsmallcelllungcancer AT tsukasanozawa machinelearninganalysisofpathologicalimagestopredict1yearprogressionfreesurvivalofimmunotherapyinpatientswithsmallcelllungcancer AT akirasano machinelearninganalysisofpathologicalimagestopredict1yearprogressionfreesurvivalofimmunotherapyinpatientswithsmallcelllungcancer AT yukakitamura machinelearninganalysisofpathologicalimagestopredict1yearprogressionfreesurvivalofimmunotherapyinpatientswithsmallcelllungcancer AT takashikijima machinelearninganalysisofpathologicalimagestopredict1yearprogressionfreesurvivalofimmunotherapyinpatientswithsmallcelllungcancer AT toshihideyokoyama machinelearninganalysisofpathologicalimagestopredict1yearprogressionfreesurvivalofimmunotherapyinpatientswithsmallcelllungcancer AT satorumiura machinelearninganalysisofpathologicalimagestopredict1yearprogressionfreesurvivalofimmunotherapyinpatientswithsmallcelllungcancer AT akitohata machinelearninganalysisofpathologicalimagestopredict1yearprogressionfreesurvivalofimmunotherapyinpatientswithsmallcelllungcancer AT junsugisaka machinelearninganalysisofpathologicalimagestopredict1yearprogressionfreesurvivalofimmunotherapyinpatientswithsmallcelllungcancer |