{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,5]],"date-time":"2026-11-05T15:43:46Z","timestamp":1793893426902,"version":"4.8.0"},"reference-count":30,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2025,8,6]],"date-time":"2025-08-06T00:00:00Z","timestamp":1754438400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Immunol."],"abstract":"<jats:sec>\n                    <jats:title>Introduction<\/jats:title>\n                    <jats:p>Programmed cell death ligand-1 (PD-L1) combined positive score (CPS) evaluation plays a pivotal role in predicting immunotherapy efficacy for gastric cancer. However, manual CPS assessment suffers from significant inter-observer variability among pathologists, leading to clinical inconsistencies. To address this limitation, we developed a deep learning-based artificial intelligence (AI) system that automates PD-L1 CPS quantification for patients with gastric cancer (GC) using whole slide images (WSIs).<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>We developed a deep learning-based artificial intelligence (AI) system that automates PD-L1 CPS quantification for patients with gastric cancer (GC) using whole slide images (WSIs). Our pipeline firstly employs a dual-network architecture for tumor region detection: MobileNet for patch-level classification and U-Net for pixel-level segmentation. Followed by a YOLO-based cell detection model to compute PD-L1 expression on different cells for CPS calculation. A total of 308 GC WSIs were included, including 210 in the internal cohort and 98 in the external cohort. Within the internal cohort, 100 WSIs were utilized for the model development, while the remaining 110 WSIs served as an internal testing set for comparative analysis between AI-derived CPS values and pathologist-derived reference standards.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>The AI-derived CPS demonstrated strong concordance with expert pathologists\u2019 consensus in internal cohort (Cohen\u2019s kappa = 0.782). Furthermore, the AI-based CPS prediction pipeline was evaluated for its performance in the external cohort, and showed robust performance (Cohen\u2019s kappa = 0.737).<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Discussion<\/jats:title>\n                    <jats:p>Our system provides a standardized decision-support tool for immunotherapy stratification in GC management, demonstrating potential to improve CPS assessment reproducibility.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fimmu.2025.1614099","type":"journal-article","created":{"date-parts":[[2025,8,6]],"date-time":"2025-08-06T04:12:35Z","timestamp":1754453555000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":9,"title":["Automated interpretation of PD-L1 CPS based on multi-AI models integration strategy in gastric cancer"],"prefix":"10.3389","volume":"16","author":[{"given":"Ting","family":"Han","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Meng","family":"Zhuo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ziyu","family":"Song","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Peilin","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shiting","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wei","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuanyuan","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hong","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dadong","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaolin","family":"Lin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zebing","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiuying","family":"Xiao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2025,8,6]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","DOI":"10.3322\/caac.21834","article-title":"Global cancer statistics 2022: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries","volume":"74","author":"Bray","year":"2024","journal-title":"CA Cancer J Clin"},{"key":"B2","doi-asserted-by":"publisher","DOI":"10.1016\/S2468-1253(23)00366-7","article-title":"Global, regional, and national lifetime risks of developing and dying from gastrointestinal cancers in 185 countries: a population-based systematic analysis of GLOBOCAN","volume":"9","author":"Wang","year":"2024","journal-title":"Lancet Gastroenterol Hepatol"},{"key":"B3","article-title":"Nivolumab (NIVO) plus chemotherapy (chemo) vs chemo as first-line (1L) treatment for advanced gastric cancer\/gastroesophageal junction cancer\/esophageal adenocarcinoma (GC\/GEJC\/EAC): 3-year follow-up from Check-Mate 649","volume":"34","author":"Janjigian","year":"2023","journal-title":"Ann Oncol"},{"key":"B4","doi-asserted-by":"publisher","DOI":"10.1001\/jama.2023.19918","article-title":"Sintilimab plus chemotherapy for unresectable gastric or gastroesophageal junction cancer: the ORIENT-16 randomized clinical trial[J","volume":"330","author":"Xu","year":"2023","journal-title":"JAMA"},{"key":"B5","doi-asserted-by":"publisher","first-page":"286","DOI":"10.1200\/JCO.2023.41.4_suppl.286","article-title":"Rationale 305: Phase 3 study of tislelizumab+chemotherapy vs placebo+chemotherapy as first-line treatment of advanced gastric or gastroesophageal junction adenocarcinoma","volume":"41","author":"Moehler","year":"2023","journal-title":"J Clin Oncol"},{"key":"B6","doi-asserted-by":"publisher","first-page":"1247","DOI":"10.3390\/diagnostics14121247","article-title":"Predictive factors of immunotherapy in gastric cancer: A 2024 update","volume":"14","author":"Bintintan","year":"2024","journal-title":"Diagnostics (Basel)"},{"key":"B7","doi-asserted-by":"publisher","DOI":"10.3389\/fonc.2021.646355","article-title":"Appropriate PD-L1 cutoff value for gastric cancer immunotherapy: A systematic review and meta-analysis","volume":"11","author":"Xie","year":"2021","journal-title":"Front Oncol"},{"key":"B8","doi-asserted-by":"publisher","DOI":"10.1080\/14737140.2023.2238896","article-title":"Predictive value of PD-L1 expression in response to immune checkpoint inhibitors for gastric cancer treatment: a systematic review and meta-analysis","volume":"23","author":"Noori","year":"2023","journal-title":"Expert Rev Anticancer Ther"},{"key":"B9","doi-asserted-by":"publisher","first-page":"100154","DOI":"10.1016\/j.modpat.2023.100154","article-title":"High interobserver variability among pathologists using combined positive score to evaluate PD-L1 expression in gastric, gastroesophageal junction, and esophageal adenocarcinoma","volume":"36","author":"Robert","year":"2023","journal-title":"Mod Pathol"},{"key":"B10","doi-asserted-by":"publisher","first-page":"654","DOI":"10.1038\/s41467-024-44824-z","article-title":"Segment anything in medical images","volume":"15","author":"Ma","year":"2024","journal-title":"Nat Commun"},{"key":"B11","doi-asserted-by":"publisher","DOI":"10.1001\/jama.2017.14585","article-title":"Diagnostic assessment of deep learning algorithms for detection of lymph node metastases in women with breast cancer","volume":"318","author":"Ehteshami Bejnordi","year":"2017","journal-title":"JAMA"},{"key":"B12","doi-asserted-by":"publisher","DOI":"10.1038\/s41591-024-02993-w","article-title":"Prediction of recurrence risk in endometrial cancer with multimodal deep learning","volume":"30","author":"Volinsky-Fremond","year":"2024","journal-title":"Nat Med"},{"key":"B13","doi-asserted-by":"publisher","DOI":"10.1038\/s41416-020-01122-x","article-title":"Deep learning in cancer pathology: a new generation of clinical biomarkers","volume":"124","author":"Echle","year":"2021","journal-title":"Br J Cancer"},{"key":"B14","doi-asserted-by":"publisher","DOI":"10.3389\/fimmu.2022.893198","article-title":"Artificial intelligence-assisted score analysis for predicting the expression of the immunotherapy biomarker PD-L1 in lung cancer","volume":"13","author":"Cheng","year":"2022","journal-title":"Front Immunol"},{"key":"B15","doi-asserted-by":"publisher","DOI":"10.1038\/s41379-021-00904-9","article-title":"Artificial intelligence-assisted system for precision diagnosis of PD-L1 expression in non-small cell lung cancer","volume":"35","author":"Wu","year":"2022","journal-title":"Mod Pathol"},{"key":"B16","doi-asserted-by":"crossref","first-page":"81","DOI":"10.1111\/his.15176","article-title":"An artificial intelligence-powered PD-L1 combined positive score (CPS) analyser in urothelial carcinoma alleviating interobserver and intersite variability","volume":"85","author":"Lee","year":"2024","journal-title":"Histopathology"},{"key":"B17","doi-asserted-by":"publisher","DOI":"10.1111\/his.15205","article-title":"Artificial intelligence enhances whole-slide interpretation of PD-L1 CPS in triple-negative breast cancer: A multi-institutional ring study","volume":"85","author":"Li","year":"2024","journal-title":"Histopathology"},{"key":"B18","doi-asserted-by":"publisher","first-page":"108827","DOI":"10.1016\/j.patcog.2022.108827","article-title":"GasHis-Transformer: A multi-scale visual transformer approach for gastric histopathological image detection","volume":"130","author":"Chen","year":"2021","journal-title":"Pattern Recognit"},{"key":"B19","doi-asserted-by":"crossref","DOI":"10.1109\/CVPR.2018.00474","article-title":"MobileNetV2: Inverted residuals and linear bottlenecks","volume-title":"2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Sandler","year":"2018"},{"key":"B20","doi-asserted-by":"crossref","first-page":"1800","DOI":"10.1109\/CVPR.2017.195","article-title":"Xception: Deep learning with depthwise separable convolutions","volume-title":"2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Chollet","year":"2017"},{"key":"B21","article-title":"YOLOX: Exceeding YOLO Series in 2021","volume-title":"arXiv; 2021","author":"Ge","year":"2021"},{"key":"B22","doi-asserted-by":"publisher","DOI":"10.1016\/j.jtho.2016.11.2228","article-title":"PD-L1 immunohistochemistry assays for lung cancer: results from phase 1 of the blueprint PD-L1 IHC assay comparison project","volume":"12","author":"Hirsch","year":"2017","journal-title":"J Thorac Oncol"},{"key":"B23","doi-asserted-by":"publisher","first-page":"292","DOI":"10.3390\/cancers13020292","article-title":"PD-L1 testing and squamous cell carcinoma of the head and neck: A multicenter study on the diagnostic reproducibility of different protocols","volume":"13","author":"Crosta","year":"2021","journal-title":"Cancers (Basel)"},{"key":"B24","doi-asserted-by":"publisher","DOI":"10.1038\/s41571-019-0252-y","article-title":"Artificial intelligence in digital pathology - new tools for diagnosis and precision oncology","volume":"16","author":"Bera","year":"2019","journal-title":"Nat Rev Clin Oncol"},{"key":"B25","doi-asserted-by":"publisher","first-page":"45938","DOI":"10.1038\/srep45938","article-title":"Relevance of deep learning to facilitate the diagnosis of HER2 status in breast cancer","volume":"7","author":"Vandenberghe","year":"2017","journal-title":"Sci Rep"},{"key":"B26","doi-asserted-by":"publisher","first-page":"100054","DOI":"10.1016\/j.modpat.2022.100054","article-title":"The role of artificial intelligence in accurate interpretation of HER2 immunohistochemical scores 0 and 1+ in breast cancer","volume":"36","author":"Wu","year":"2023","journal-title":"Mod Pathol"},{"key":"B27","doi-asserted-by":"publisher","first-page":"3213","DOI":"10.1038\/s41598-017-03405-5","article-title":"An advanced deep learning approach for ki-67 stained hotspot detection and proliferation rate scoring for prognostic evaluation of breast cancer","volume":"7","author":"Saha","year":"2017","journal-title":"Sci Rep"},{"key":"B28","doi-asserted-by":"publisher","first-page":"15907","DOI":"10.1038\/s41598-021-95372-1","article-title":"Automated tumor proportion score analysis for PD-L1 (22C3) expression in lung squamous cell carcinoma","volume":"11","author":"Liu","year":"2021","journal-title":"Sci Rep"},{"key":"B29","doi-asserted-by":"publisher","first-page":"167","DOI":"10.3390\/cancers16010167","article-title":"AI-powered segmentation of invasive carcinoma regions in breast cancer immunohistochemical whole-slide images","volume":"16","author":"Liu","year":"2023","journal-title":"Cancers (Basel)"},{"key":"B30","doi-asserted-by":"publisher","first-page":"65","DOI":"10.1186\/s13000-020-00957-5","article-title":"Automated quantitative analysis of Ki-67 staining and HE images recognition and registration based on whole tissue sections in breast carcinoma","volume":"15","author":"Feng","year":"2020","journal-title":"Diagn Pathol"}],"container-title":["Frontiers in Immunology"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fimmu.2025.1614099\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,6]],"date-time":"2025-08-06T04:12:36Z","timestamp":1754453556000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fimmu.2025.1614099\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,6]]},"references-count":30,"alternative-id":["10.3389\/fimmu.2025.1614099"],"URL":"https:\/\/doi.org\/10.3389\/fimmu.2025.1614099","relation":{},"ISSN":["1664-3224"],"issn-type":[{"value":"1664-3224","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,8,6]]},"article-number":"1614099"}}