{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,16]],"date-time":"2026-03-16T07:09:19Z","timestamp":1773644959197,"version":"3.50.1"},"reference-count":43,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,3,16]],"date-time":"2026-03-16T00:00:00Z","timestamp":1773619200000},"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. Bioinform."],"abstract":"<jats:sec>\n                    <jats:title>Objective<\/jats:title>\n                    <jats:p>Quantitative analysis of tumor-infiltrating lymphocytes (TILs) is crucial in computational pathology studies of lung adenocarcinoma. However, acquiring large-scale, fully annotated datasets remains a major obstacle for the supervised learning approaches that currently dominate high-precision modeling. To address this data bottleneck, we developed a fully automated pipeline for the precise annotation of tissue contours, tumor parenchyma, and lymphocytes in whole-slide images (WSIs).<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>\n                      This study utilized WSI data from The Cancer Genome Atlas (TCGA) cohort, with comprehensive manual annotations performed by two pathologists using QuPath software, with all annotations subsequently reviewed by a third senior pathologist. The resulting training dataset comprised over 20,000 annotated units. These annotated data were used to train three core modules consisting of an OpenCV-based image processing pipeline for tissue contour detection, a lightweight U\n                      <jats:sup>2<\/jats:sup>\n                      -NetP model for tumor parenchyma segmentation, and a YOLOv7 object detection framework for TILs identification within stromal regions. The pipeline was rigorously validated on both an independent internal cohort and an external hospital cohort, and its outputs were benchmarked against semi-quantitative assessments from expert pathologists.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>The pipeline demonstrated robust and generalizable performance. For tissue contour detection, the OpenCV-based pipeline achieved a Dice coefficient of 90.90% on the test set. For the core learning-based tasks, the tumor parenchyma segmentation model achieved a Dice coefficient of 87.17% on the internal test set and maintained consistent accuracy on the external cohort, with Dice coefficients ranging from 0.8509 to 0.9178. In the particularly challenging task of lymphocyte detection, the YOLOv7-based model attained an F1-score of 78.84% and mAP@0.5 of 81.16% on the test set, with performance sustained on external data. Critically, the automated TILs quantifications showed excellent agreement with independent pathologist assessments (ICC &amp;gt;0.96). The implementation of optimized lightweight architectures enables the pipeline to serve as an accessible solution for large-scale WSIs analysis in computational pathology.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>This study has successfully developed a fully automated annotation pipeline for lung adenocarcinoma WSIs. By generating high-quality annotations of stromal TILs, this pipeline establishes a reliable data foundation for subsequent computational pathology research and facilitates the advancement of artificial intelligence applications in pathology.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fbinf.2026.1764743","type":"journal-article","created":{"date-parts":[[2026,3,16]],"date-time":"2026-03-16T06:36:41Z","timestamp":1773643001000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["An integrated automated deep learning framework for annotating tumor-infiltrating lymphocytes in lung adenocarcinoma pathology"],"prefix":"10.3389","volume":"6","author":[{"given":"Xia","family":"Li","sequence":"first","affiliation":[{"name":"Department of Pathology, the First Affiliated Hospital of Guangxi Medical University","place":["Nanning, Guangxi, China"]}]},{"given":"Kang-Lai","family":"Wei","sequence":"additional","affiliation":[{"name":"Department of Pathology, the Second Affiliated Hospital of Guangxi Medical University","place":["Nanning, Guangxi, China"]}]},{"given":"Zhao-Quan","family":"Huang","sequence":"additional","affiliation":[{"name":"Department of Pathology, the First Affiliated Hospital of Guangxi Medical University","place":["Nanning, Guangxi, China"]}]},{"given":"Zi-Yan","family":"Huang","sequence":"additional","affiliation":[{"name":"Health Management Department, the First Affiliated Hospital of Guangxi Medical University","place":["Nanning, Guangxi, China"]}]}],"member":"1965","published-online":{"date-parts":[[2026,3,16]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"1804","DOI":"10.1039\/d2lc00817c","article-title":"Red blood cell rosetting enables size-based separation of specific lymphocyte subsets from blood in a microfluidic device","volume":"23","author":"Abhishek","year":"2023","journal-title":"Lab. Chip"},{"key":"B2","first-page":"2017","article-title":"Attention is all you need","volume-title":"Advances in neural information processing systems (NeurIPS)","author":"Vaswani","year":"2017"},{"key":"B3","doi-asserted-by":"publisher","first-page":"10076","DOI":"10.1109\/TPAMI.2024.3435571","article-title":"Medical image segmentation review: the success of U-Net","volume":"46","author":"Azad","year":"2024","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"B4","doi-asserted-by":"publisher","first-page":"23","DOI":"10.1038\/s41379-021-00919-2","article-title":"Digital pathology and artificial intelligence in translational medicine and clinical practice","volume":"35","author":"Baxi","year":"2022","journal-title":"Mod. Pathol."},{"key":"B5","doi-asserted-by":"publisher","first-page":"1162","DOI":"10.1038\/s41416-022-01875-7","article-title":"Tumour immune microenvironment in resected thymic carcinomas as a predictor of clinical outcome","volume":"127","author":"Bocchialini","year":"2022","journal-title":"Br. J. Cancer"},{"key":"B6","doi-asserted-by":"publisher","first-page":"2425","DOI":"10.1109\/TNNLS.2021.3106641","article-title":"Hierarchical regression and classification for accurate object detection","volume":"34","author":"Cao","year":"2023","journal-title":"IEEE Trans. Neural Netw. Learn Syst."},{"key":"B7","article-title":"YOLOv7: trainable bag-of-freebies sets new state-of-the-art for real-time object detectors","author":"Chien-Yao Wang","year":"2023"},{"key":"B8","doi-asserted-by":"publisher","first-page":"102231","DOI":"10.1016\/j.compmedimag.2023.102231","article-title":"Labeling confidence for uncertainty-aware histology image classification","volume":"107","author":"Del Amor","year":"2023","journal-title":"Comput. Med. Imaging Graph"},{"key":"B9","doi-asserted-by":"publisher","first-page":"194","DOI":"10.1016\/j.wasman.2023.05.039","article-title":"Real-time construction demolition waste detection using state-of-the-art deep learning methods; single-stage vs two-stage detectors","volume":"167","author":"Demetriou","year":"2023","journal-title":"Waste Manag."},{"key":"B10","doi-asserted-by":"publisher","first-page":"1345","DOI":"10.1038\/s41467-025-56546-x","article-title":"Spatially mapping the tumour immune microenvironments of non-small cell lung cancer","volume":"16","author":"Desharnais","year":"2025","journal-title":"Nat. Commun."},{"key":"B11","doi-asserted-by":"publisher","first-page":"33","DOI":"10.1038\/s41698-022-00277-5","article-title":"Image analysis reveals molecularly distinct patterns of TILs in NSCLC associated with treatment outcome","volume":"6","author":"Ding","year":"2022","journal-title":"NPJ Precis. Oncol."},{"key":"B12","doi-asserted-by":"publisher","first-page":"102056","DOI":"10.1016\/j.compmedimag.2022.102056","article-title":"Improved-mask R-CNN: towards an accurate generic MSK MRI instance segmentation platform (data from the osteoarthritis initiative)","volume":"97","author":"Felfeliyan","year":"2022","journal-title":"Comput. Med. Imaging Graph"},{"key":"B13","doi-asserted-by":"publisher","first-page":"180","DOI":"10.1186\/s13058-024-01932-4","article-title":"Characterization of tumor-infiltrating lymphocytes and their spatial distribution in triple-negative breast cancer","volume":"26","author":"Han","year":"2024","journal-title":"Breast Cancer Res."},{"key":"B14","volume-title":"Deep learning","author":"Ian Goodfellow","year":"2016"},{"key":"B15","doi-asserted-by":"publisher","first-page":"6558","DOI":"10.1109\/TNNLS.2021.3082496","article-title":"Learning from crowds with multiple noisy label distribution propagation","volume":"33","author":"Jiang","year":"2022","journal-title":"IEEE Trans. Neural Netw. Learn Syst."},{"key":"B16","doi-asserted-by":"publisher","first-page":"2011","DOI":"10.1038\/s41379-022-01137-0","article-title":"Intratumoral spatial heterogeneity of tumor-infiltrating lymphocytes is a significant factor for precisely stratifying prognostic immune subgroups of microsatellite instability-high colorectal carcinomas","volume":"35","author":"Jung","year":"2022","journal-title":"Mod. Pathol."},{"key":"B17","doi-asserted-by":"publisher","first-page":"110680","DOI":"10.1016\/j.compbiomed.2025.110680","article-title":"HVUNet: a hybrid vision transformer-based UNet for accurate detection and localization in histopathology images","volume":"196","author":"Kanadath","year":"2025","journal-title":"Comput. Biol. Med."},{"key":"B18","doi-asserted-by":"publisher","first-page":"1601773","DOI":"10.3389\/fimmu.2025.1601773","article-title":"Tumor-infiltrating lymphocytes in cancer immunotherapy: from chemotactic recruitment to translational modeling","volume":"16","author":"Kraja","year":"2025","journal-title":"Front. Immunol."},{"key":"B19","doi-asserted-by":"publisher","first-page":"6240","DOI":"10.1038\/s41467-025-61349-1","article-title":"Automated cell annotation and classification on histopathology for spatial biomarker discovery","volume":"16","author":"Li","year":"2025","journal-title":"Nat. Commun."},{"key":"B20","doi-asserted-by":"crossref","DOI":"10.1109\/CVPR.2017.106","article-title":"Feature pyramid networks for object detection","author":"Lin","year":"2017"},{"key":"B21","doi-asserted-by":"publisher","first-page":"e004440","DOI":"10.1136\/jitc-2021-004440","article-title":"Role of tumor infiltrating lymphocytes and spatial immune heterogeneity in sensitivity to PD-1 axis blockers in non-small cell lung cancer","volume":"10","author":"Lopez de Rodas","year":"2022","journal-title":"J. Immunother. Cancer"},{"key":"B22","doi-asserted-by":"publisher","first-page":"1679365","DOI":"10.3389\/fimmu.2025.1679365","article-title":"Advancing immunotherapy for esophageal cancer: decoding the roles of PD-L1, TME, and tumor-intrinsic biomarkers","volume":"16","author":"Ma","year":"2025","journal-title":"Front. Immunol."},{"key":"B23","doi-asserted-by":"publisher","first-page":"170","DOI":"10.1016\/j.media.2016.06.037","article-title":"Image analysis and machine learning in digital pathology: challenges and opportunities","volume":"33","author":"Madabhushi","year":"2016","journal-title":"Med. Image Anal."},{"key":"B24","doi-asserted-by":"publisher","first-page":"100086","DOI":"10.1016\/j.modpat.2022.100086","article-title":"Annotating for artificial intelligence applications in digital pathology: a practical guide for pathologists and researchers","volume":"36","author":"Montezuma","year":"2023","journal-title":"Mod. Pathol."},{"key":"B25","doi-asserted-by":"publisher","first-page":"259","DOI":"10.1038\/s41586-023-05881-4","article-title":"Foundation models for generalist medical artificial intelligence","volume":"616","author":"Moor","year":"2023","journal-title":"Nature"},{"key":"B26","doi-asserted-by":"publisher","first-page":"91","DOI":"10.1186\/s40478-025-02007-x","article-title":"Identification and characterization of tertiary lymphoid structures in brain metastases","volume":"13","author":"Mughal","year":"2025","journal-title":"Acta Neuropathol. Commun."},{"key":"B27","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1186\/s13073-021-01010-w","article-title":"A lepidic gene signature predicts patient prognosis and sensitivity to immunotherapy in lung adenocarcinoma","volume":"14","author":"Nguyen","year":"2022","journal-title":"Genome Med."},{"key":"B28","doi-asserted-by":"publisher","first-page":"104980","DOI":"10.1016\/j.critrevonc.2025.104980","article-title":"Predictive models for immune checkpoint inhibitor response in cancer: a review of current approaches and future directions","volume":"216","author":"Oisakede","year":"2025","journal-title":"Crit. Rev. Oncol. Hematol."},{"key":"B29","doi-asserted-by":"publisher","first-page":"eadv4049","DOI":"10.1126\/scirobotics.adv4049","article-title":"Extending robot minds through collective learning","volume":"10","author":"Prorok","year":"2025","journal-title":"Sci. Robot."},{"key":"B30","doi-asserted-by":"publisher","first-page":"108547","DOI":"10.1016\/j.compbiomed.2024.108547","article-title":"GMIM: self-supervised pre-training for 3D medical image segmentation with adaptive and hierarchical masked image modeling","volume":"176","author":"Qi","year":"2024","journal-title":"Comput. Biol. Med."},{"key":"B31","doi-asserted-by":"publisher","first-page":"354","DOI":"10.1016\/j.jconrel.2024.11.020","article-title":"Toward precision medicine: end-to-end design and construction of integrated microneedle-based theranostic systems","volume":"377","author":"Qin","year":"2025","journal-title":"J. Control Release"},{"key":"B32","article-title":"Path aggregation network for instance segmentation","author":"Shu Liu","year":"2018"},{"key":"B33","doi-asserted-by":"publisher","first-page":"231","DOI":"10.1007\/978-1-0716-4184-2_12","article-title":"Cancer-associated lymphoid aggregates in histology images: manual and deep learning-based quantification approaches","volume":"2864","author":"Silina","year":"2025","journal-title":"Methods Mol. Biol."},{"key":"B34","doi-asserted-by":"publisher","first-page":"273","DOI":"10.1016\/j.wasman.2024.12.014","article-title":"AI-based plastic waste sorting method utilizing object detection models for enhanced classification","volume":"193","author":"Son","year":"2025","journal-title":"Waste Manag."},{"key":"B35","doi-asserted-by":"publisher","first-page":"244","DOI":"10.1097\/JTO.0b013e318206a221","article-title":"International association for the study of lung cancer\/american thoracic society\/european respiratory society international multidisciplinary classification of lung adenocarcinoma","volume":"6","author":"Travis","year":"2011","journal-title":"J. Thorac. Oncol."},{"key":"B36","doi-asserted-by":"publisher","first-page":"1639","DOI":"10.1109\/TIP.2020.3044220","article-title":"EnAET: a self-trained framework for semi-supervised and supervised learning with ensemble transformations","volume":"30","author":"Wang","year":"2021","journal-title":"IEEE Trans. Image Process"},{"key":"B37","doi-asserted-by":"publisher","first-page":"e2302175","DOI":"10.1002\/advs.202302175","article-title":"Cell granularity reflects immune cell function and enables selection of lymphocytes with superior attributes for immunotherapy","volume":"10","author":"Wu","year":"2023","journal-title":"Adv. Sci. (Weinh)"},{"key":"B38","doi-asserted-by":"publisher","first-page":"111","DOI":"10.1186\/s12967-025-07608-7","article-title":"Focal hotspot and diffuse immune subtypes of tumor-infiltrating lymphocytes: AI-powered spatial clustering classification and its clinical relevance to HER2 expression in triple-negative breast cancer","volume":"24","author":"Xie","year":"2025","journal-title":"J. Transl. Med."},{"key":"B39","doi-asserted-by":"publisher","first-page":"107726","DOI":"10.1016\/j.compbiomed.2023.107726","article-title":"Reversed domain adaptation for nuclei segmentation-based pathological image classification","volume":"168","author":"Xu","year":"2024","journal-title":"Comput. Biol. Med."},{"key":"B40","doi-asserted-by":"crossref","first-page":"107404","DOI":"10.1016\/j.patcog.2020.107404","article-title":"U2-Net: going deeper with nested U-Structure for salient object detection","volume":"106","author":"Xuebin","year":"2020","journal-title":"Pattern Recognit."},{"key":"B41","doi-asserted-by":"publisher","first-page":"2811","DOI":"10.1109\/TIP.2025.3561679","article-title":"Ray-aided quadruple affiliation network for calculating tumor-stroma ratios in breast cancers","volume":"34","author":"Yang","year":"2025","journal-title":"IEEE Trans. Image Process"},{"key":"B42","doi-asserted-by":"publisher","first-page":"1286986","DOI":"10.3389\/fimmu.2023.1286986","article-title":"Modulation of natural killer cell exhaustion in the lungs: the key components from lung microenvironment and lung tumor microenvironment","volume":"14","author":"Zhang","year":"2023","journal-title":"Front. Immunol."},{"key":"B43","doi-asserted-by":"publisher","first-page":"104699","DOI":"10.1016\/j.compbiomed.2021.104699","article-title":"Sharp U-Net: Depthwise convolutional network for biomedical image segmentation","volume":"136","author":"Zunair","year":"2021","journal-title":"Comput. Biol. Med."}],"container-title":["Frontiers in Bioinformatics"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fbinf.2026.1764743\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,16]],"date-time":"2026-03-16T06:36:43Z","timestamp":1773643003000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fbinf.2026.1764743\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,16]]},"references-count":43,"alternative-id":["10.3389\/fbinf.2026.1764743"],"URL":"https:\/\/doi.org\/10.3389\/fbinf.2026.1764743","relation":{},"ISSN":["2673-7647"],"issn-type":[{"value":"2673-7647","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3,16]]},"article-number":"1764743"}}