{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,10]],"date-time":"2026-10-10T04:49:25Z","timestamp":1791607765641,"version":"4.3.4"},"reference-count":37,"publisher":"MDPI AG","issue":"19","license":[{"start":{"date-parts":[[2026,10,8]],"date-time":"2026-10-08T00:00:00Z","timestamp":1791417600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"},{"start":{"date-parts":[[2026,10,8]],"date-time":"2026-10-08T00:00:00Z","timestamp":1791417600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"National Natural Science Foundation of China","award":["82002813"],"award-info":[{"award-number":["82002813"]}],"id":[{"id":"https:\/\/ror.org\/01h0zpd94","id-type":"ROR","asserted-by":"crossref"}]},{"name":"National Natural Science Foundation of China","award":["82472971"],"award-info":[{"award-number":["82472971"]}],"id":[{"id":"https:\/\/ror.org\/01h0zpd94","id-type":"ROR","asserted-by":"crossref"}]},{"name":"National Natural Science Foundation of China","award":["82202909"],"award-info":[{"award-number":["82202909"]}],"id":[{"id":"https:\/\/ror.org\/01h0zpd94","id-type":"ROR","asserted-by":"crossref"}]},{"award":["82002813"],"award-info":[{"award-number":["82002813"]}],"id":[{"id":"https:\/\/ror.org\/01h0zpd94","id-type":"ROR","asserted-by":"publisher"}]},{"award":["82472971"],"award-info":[{"award-number":["82472971"]}],"id":[{"id":"https:\/\/ror.org\/01h0zpd94","id-type":"ROR","asserted-by":"publisher"}]},{"award":["82202909"],"award-info":[{"award-number":["82202909"]}],"id":[{"id":"https:\/\/ror.org\/01h0zpd94","id-type":"ROR","asserted-by":"publisher"}]},{"name":"Tianjin Key Medical Discipline Construction Project","award":["TJYXZDXK-3-016C"],"award-info":[{"award-number":["TJYXZDXK-3-016C"]}]},{"name":"Tianjin Health Technology Project","award":["TJWJ2021QN010"],"award-info":[{"award-number":["TJWJ2021QN010"]}]},{"name":"Special Fund for pharmacy, examination and imaging of Tianjin Medical University Cancer Institute and Hospital","award":["Y2309"],"award-info":[{"award-number":["Y2309"]}],"id":[{"id":"https:\/\/ror.org\/0152hn881","id-type":"ROR","asserted-by":"crossref"}]},{"award":["Y2309"],"award-info":[{"award-number":["Y2309"]}],"id":[{"id":"https:\/\/ror.org\/0152hn881","id-type":"ROR","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Cancers"],"abstract":"<jats:p>Accurate subtyping of lymphomas is critical for guiding treatment decisions and predicting patient outcomes, yet it remains challenging due to overlapping morphological features. This study aimed to develop and validate a deep learning-based diagnostic system, designated BH-LymphDS, to accurately differentiate the three most prevalent lymphoma subtypes: Diffuse Large B-cell Lymphoma (DLBCL), Follicular Lymphoma (FL), and Hodgkin Lymphoma (HL). The system integrates a Swin Transformer backbone with a clustering-constrained attention multiple instance learning (CLAM) algorithm and a k-nearest neighbors (KNN) classifier, supporting weakly supervised learning directly from whole-slide images without manual region-level annotation. A total of 1910 whole-slide images (WSIs) from diagnostic biopsies were utilized for model development\u2014the largest cohort to date in this field. The performance of nine distinct deep learning architectures was systematically compared. Model efficacy was rigorously evaluated through five-fold cross-validation and further validated on independent external datasets from TCIA and TCGA. Additionally, a comparative analysis was conducted against the diagnostic performance of three experienced hematopathologists. In the internal testing cohort, BH-LymphDS achieved a micro-average AUC of 0.955 and an accuracy of 92.5%. During cross-validation, the system attained a superior micro-average F1-score (0.871) compared to the average of the three hematopathologists (0.851). The Swin Transformer emerged as the optimal backbone, and gradient-weighted class activation mapping (GradCAM) confirmed that the model\u2019s decisions were based on legitimate morphological features such as nuclear atypia and cellular growth patterns. Our findings demonstrate that an advanced AI system can satisfy the rigorous requirements for accurate lymphoma subclassification on histopathological slides. The BH-LymphDS shows strong potential as a reliable auxiliary diagnostic tool to enhance clinical workflow efficiency and diagnostic consistency.<\/jats:p>","DOI":"10.3390\/cancers18193237","type":"journal-article","created":{"date-parts":[[2026,10,8]],"date-time":"2026-10-08T11:26:53Z","timestamp":1791458813000},"page":"3237","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Deep Learning on Histopathological Images Enables Accurate Diagnosis of Common B-Cell and Hodgkin Lymphoma"],"prefix":"10.3390","volume":"18","author":[{"given":"Peisen","family":"Zhang","sequence":"first","affiliation":[{"name":"Tianjin Key Laboratory of Integrated Design and Online Monitoring for Light Industry & Food Machinery and Equipment, Tianjin University of Science and Technology, Tianjin 300222, China"}],"role":[{"vocabulary":"crossref","role":"author"},{"role":"conceptualization","vocabulary":"credit"},{"role":"methodology","vocabulary":"credit"},{"role":"software","vocabulary":"credit"},{"role":"formal-analysis","vocabulary":"credit"},{"role":"visualization","vocabulary":"credit"}]},{"given":"Changjiang","family":"Yan","sequence":"additional","affiliation":[{"name":"Tianjin Key Laboratory of Integrated Design and Online Monitoring for Light Industry & Food Machinery and Equipment, Tianjin University of Science and Technology, Tianjin 300222, China"}],"role":[{"vocabulary":"crossref","role":"author"},{"role":"methodology","vocabulary":"credit"},{"role":"formal-analysis","vocabulary":"credit"},{"role":"data-curation","vocabulary":"credit"},{"role":"visualization","vocabulary":"credit"}]},{"given":"Meilin","family":"Sun","sequence":"additional","affiliation":[{"name":"Department of Pathology, Tianjin Medical University Cancer Institute & Hospital, National Clinical Research Center for Cancer, Tianjin\u2019s Clinical Research Center for Cancer, Key Laboratory of Cancer Prevention and Therapy, Tianjin 300060, China"}],"role":[{"vocabulary":"crossref","role":"author"},{"role":"validation","vocabulary":"credit"},{"role":"investigation","vocabulary":"credit"},{"role":"writing-review-editing","vocabulary":"credit"}]},{"given":"Shaojie","family":"Ding","sequence":"additional","affiliation":[{"name":"Department of Pathology, Tianjin Medical University Cancer Institute & Hospital, National Clinical Research Center for Cancer, Tianjin\u2019s Clinical Research Center for Cancer, Key Laboratory of Cancer Prevention and Therapy, Tianjin 300060, China"}],"role":[{"vocabulary":"crossref","role":"author"},{"role":"validation","vocabulary":"credit"},{"role":"investigation","vocabulary":"credit"}]},{"given":"Lingmei","family":"Li","sequence":"additional","affiliation":[{"name":"Department of Pathology, Tianjin Medical University Cancer Institute & Hospital, National Clinical Research Center for Cancer, Tianjin\u2019s Clinical Research Center for Cancer, Key Laboratory of Cancer Prevention and Therapy, Tianjin 300060, China"}],"role":[{"vocabulary":"crossref","role":"author"},{"role":"validation","vocabulary":"credit"},{"role":"writing-review-editing","vocabulary":"credit"}]},{"given":"Wenfeng","family":"Cao","sequence":"additional","affiliation":[{"name":"Department of Pathology, Tianjin Medical University Cancer Institute & Hospital, National Clinical Research Center for Cancer, Tianjin\u2019s Clinical Research Center for Cancer, Key Laboratory of Cancer Prevention and Therapy, Tianjin 300060, China"}],"role":[{"vocabulary":"crossref","role":"author"},{"role":"supervision","vocabulary":"credit"},{"role":"resources","vocabulary":"credit"}]},{"given":"Lu","family":"Cao","sequence":"additional","affiliation":[{"name":"Department of Pathology, Tianjin Medical University Cancer Institute & Hospital, National Clinical Research Center for Cancer, Tianjin\u2019s Clinical Research Center for Cancer, Key Laboratory of Cancer Prevention and Therapy, Tianjin 300060, China"}],"role":[{"vocabulary":"crossref","role":"author"},{"role":"conceptualization","vocabulary":"credit"},{"role":"resources","vocabulary":"credit"},{"role":"writing-original-draft","vocabulary":"credit"},{"role":"writing-review-editing","vocabulary":"credit"},{"role":"project-administration","vocabulary":"credit"},{"role":"funding-acquisition","vocabulary":"credit"}]}],"member":"1968","published-online":{"date-parts":[[2026,10,8]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"2008","DOI":"10.1200\/JCO.2016.71.2083","article-title":"Impact of expert pathologic review of lymphoma diagnosis: Study of patients from the French Lymphopath Network","volume":"35","author":"Laurent","year":"2017","journal-title":"J. Clin. Oncol."},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Munir, F., Hardit, V., Sheikh, I.N., AlQahtani, S., He, J., Cuglievan, B., Hosing, C., Tewari, P., and Khazal, S. (2023). Classical Hodgkin Lymphoma: From Past to Future\u2014A Comprehensive Review of Pathophysiology and Therapeutic Advances. Int. J. Mol. Sci., 24.","DOI":"10.3390\/ijms241210095"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"83","DOI":"10.1038\/s41572-019-0132-x","article-title":"Follicular lymphoma","volume":"5","author":"Carbone","year":"2019","journal-title":"Nat. Rev. Dis. Primers"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"296","DOI":"10.1002\/ajh.24937","article-title":"Follicular lymphoma: 2018 update on diagnosis and management","volume":"93","author":"Freedman","year":"2018","journal-title":"Am. J. Hematol."},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Perry, C., Greenberg, O., Haberman, S., Herskovitz, N., Gazy, I., Avinoam, A., Paz-Yaacov, N., Hershkovitz, D., and Avivi, I. (2023). Image-based deep learning detection of high-grade B-cell lymphomas directly from hematoxylin and eosin images. Cancers, 15.","DOI":"10.3390\/cancers15215205"},{"key":"ref_6","first-page":"3602","article-title":"Diffuse large B-cell lymphoma: 10 years\u2019 real-world clinical experience with rituximab plus cyclophosphamide, doxorubicin, vincristine and prednisolone","volume":"15","author":"Horvat","year":"2018","journal-title":"Oncol. Lett."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"109","DOI":"10.1186\/s13000-023-01375-z","article-title":"Artificial intelligence in diagnostic pathology","volume":"18","author":"Shafi","year":"2023","journal-title":"Diagn. Pathol."},{"key":"ref_8","first-page":"e92058","article-title":"AI in Digital Pathology for Diffuse Large B-cell Lymphoma: A Systematic Review of Diagnosis and Classification","volume":"17","author":"Tomalieh","year":"2025","journal-title":"Cureus"},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Carreras, J., Ikoma, H., Kikuti, Y.Y., Nagase, S., Ito, A., Orita, M., Tomita, S., Tanigaki, Y., Nakamura, N., and Masugi, Y. (2025). Histological Image Classification Between Follicular Lymphoma and Reactive Lymphoid Tissue Using Deep Learning and Explainable Artificial Intelligence (XAI). Cancers, 17.","DOI":"10.3390\/cancers17152428"},{"key":"ref_10","unstructured":"Fernandez-Pol, S., Natkunam, Y., Vrabac, D., Rojansky, R., Advani, R., Rajpurkar, P., and Ng Andrew, Y. (2024, December 20). H&E and Immunohistochemical Stain Images of 209 Cases of Diffuse Large B-Cell Lymphoma Linked with Cytogenetic Features and Clinical Outcomes. The Cancer Imaging Archive 2022. Available online: https:\/\/www.cancerimagingarchive.net\/collection\/dlbcl-morphology\/."},{"key":"ref_11","unstructured":"Contributors, M. (2024, December 28). OpenMMLab\u2019s Pre-Training Toolbox and Benchmark. Available online: https:\/\/github.com\/open-mmlab\/mmpretrain."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"555","DOI":"10.1038\/s41551-020-00682-w","article-title":"Data-efficient and weakly supervised computational pathology on whole-slide images","volume":"5","author":"Lu","year":"2021","journal-title":"Nat. Biomed. Eng."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"646","DOI":"10.1016\/j.cell.2011.02.013","article-title":"Hallmarks of cancer: The next generation","volume":"144","author":"Hanahan","year":"2011","journal-title":"Cell"},{"key":"ref_14","first-page":"528","article-title":"LymphoML: An interpretable artificial intelligence-based method identifies morphologic features that correlate with lymphoma subtype","volume":"225","author":"Shankar","year":"2023","journal-title":"Mach. Learn. Health"},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"100359","DOI":"10.1016\/j.jpi.2023.100359","article-title":"Multimodal Gated Mixture of Experts Using Whole Slide Image and Flow Cytometry for Multiple Instance Learning Classification of Lymphoma","volume":"15","author":"Hashimoto","year":"2024","journal-title":"J. Pathol. Inform."},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Steinbuss, G., Kriegsmann, M., Zgorzelski, C., Brobeil, A., Goeppert, B., Dietrich, S., Mechtersheimer, G., Kriegsmann, K., and Spaargaren, M. (2021). Deep learning for the classification of non-Hodgkin lymphoma on histopathological images. Cancers, 13.","DOI":"10.3390\/cancers13102419"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"307","DOI":"10.21037\/atm.2019.06.29","article-title":"Deep convolutional neural network Inception-v3 model for differential diagnosing of lymph node in cytological images: A pilot study","volume":"7","author":"Guan","year":"2019","journal-title":"Ann. Transl. Med."},{"key":"ref_18","first-page":"153","article-title":"Automated diagnosis of lymphoma with digital pathology images using deep learning","volume":"49","author":"Belousova","year":"2019","journal-title":"Ann. Clin. Lab. Sci."},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Hamdi, M., Senan, E.M., Jadhav, M.E., Olayah, F., Awaji, B., and Alalayah, K.M. (2023). Hybrid Models Based on Fusion Features of a CNN and Handcrafted Features for Accurate Histopathological Image Analysis for Diagnosing Malignant Lymphomas. Diagnostics, 13.","DOI":"10.3390\/diagnostics13132258"},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Rajadurai, S., Perumal, K., Ijaz, M.F., and Chowdhary, C.L. (2024). PrecisionLymphoNet: Advancing Malignant Lymphoma Diagnosis via Ensemble Transfer Learning with CNNs. Diagnostics, 14.","DOI":"10.3390\/diagnostics14050469"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"1183","DOI":"10.1007\/s40031-024-01135-7","article-title":"Gradient Propagation Based DenseNet121 with ResNet50 Feature Extraction for Lymphoma Classification","volume":"106","author":"Srinivasan","year":"2024","journal-title":"J. Inst. Eng. (India) Ser. B"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"20537","DOI":"10.1007\/s00521-024-10229-8","article-title":"A new approach for automatic classification of non-Hodgkin lymphoma using deep learning and classical learning methods on histopathological images","volume":"36","year":"2024","journal-title":"Neural Comput. Appl."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"44709","DOI":"10.1109\/ACCESS.2019.2908724","article-title":"A deep learning approach for breast invasive ductal carcinoma detection and lymphoma multi-classification in histological images","volume":"7","author":"Brancati","year":"2019","journal-title":"IEEE Access"},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"4241","DOI":"10.1002\/mp.14357","article-title":"Classification of digital pathological images of non-Hodgkin\u2019s lymphoma subtypes based on the fusion of transfer learning and principal component analysis","volume":"47","author":"Zhang","year":"2020","journal-title":"Med. Phys."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"20569","DOI":"10.1007\/s00521-023-08810-8","article-title":"The use of generative adversarial networks for multi-site one-class follicular lymphoma classification","volume":"35","author":"Somaratne","year":"2023","journal-title":"Neural Comput. Appl."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"1300","DOI":"10.1038\/s41374-020-0442-3","article-title":"Deep learning shows the capability of high-level computer-aided diagnosis in malignant lymphoma","volume":"100","author":"Miyoshi","year":"2020","journal-title":"Lab. Investig."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"102752","DOI":"10.1016\/j.media.2023.102752","article-title":"Case-based similar image retrieval for weakly annotated large histopathological images of malignant lymphoma using deep metric learning","volume":"85","author":"Hashimoto","year":"2023","journal-title":"Med. Image Anal."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"28","DOI":"10.1136\/jcp-2023-209186","article-title":"Lymphoma triage from H&E using AI for improved clinical management","volume":"78","author":"Tsakiroglou","year":"2023","journal-title":"J. Clin. Pathol."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"e5900850","DOI":"10.1097\/01.HS9.0000976224.59008.50","article-title":"Predicting cell of origin from digitized images of hematoxylin and eosin-stained slides of diffuse large b-cell lymphomas using a cell-based deep-learning model","volume":"7","author":"Yuce","year":"2023","journal-title":"HemaSphere"},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Nambiar, N., Rajesh, V., Nair, A., Nambiar, S., Nair, R., Uthamanthil, R., Lotodo, T., Mittal, S., and Kussick, S. (2024). An AI based, open access screening tool for early diagnosis of Burkitt lymphoma. Front. Med., 11.","DOI":"10.3389\/fmed.2024.1345611"},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"6004","DOI":"10.1038\/s41467-020-19817-3","article-title":"A deep learning diagnostic platform for diffuse large B-cell lymphoma with high accuracy across multiple hospitals","volume":"11","author":"Li","year":"2020","journal-title":"Nat. Commun."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"743","DOI":"10.1093\/ajcp\/aqaa001","article-title":"Improving augmented human intelligence to distinguish Burkitt lymphoma from diffuse large B-cell lymphoma cases","volume":"153","author":"Mohlman","year":"2020","journal-title":"Am. J. Clin. Pathol."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"63","DOI":"10.1038\/s41746-020-0272-0","article-title":"Accurate diagnosis of lymphoma on whole-slide histopathology images using deep learning","volume":"3","author":"Syrykh","year":"2020","journal-title":"npj Digit. Med."},{"key":"ref_34","unstructured":"Rony, J., Belharbi, S., Dolz, J., Ben Ayed, I., McCaffrey, L., and Granger, E. (2019). Deep weakly-supervised learning methods for classification and localization in histology images: A survey. arXiv."},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"5562","DOI":"10.1109\/JBHI.2024.3407878","article-title":"A vision transformer-based framework for knowledge transfer from multi-modal to mono-modal lymphoma subtyping models","volume":"28","author":"Guetarni","year":"2024","journal-title":"IEEE J. Biomed. Health Inform."},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"pgaf137","DOI":"10.1093\/pnasnexus\/pgaf137","article-title":"AI system for diagnosing mucosa-associated lymphoid tissue lymphoma and diffuse large B cell lymphoma using ImageNet and hematoxylin and eosin-stained specimens","volume":"4","author":"Yamaguchi","year":"2025","journal-title":"PNAS Nexus"},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"e62851","DOI":"10.2196\/62851","article-title":"Artificial Intelligence in Lymphoma Histopathology: Systematic Review","volume":"27","author":"Fu","year":"2025","journal-title":"J. Med. Internet Res."}],"container-title":["Cancers"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2072-6694\/18\/19\/3237\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,10]],"date-time":"2026-10-10T04:20:27Z","timestamp":1791606027000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2072-6694\/18\/19\/3237"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10,8]]},"references-count":37,"journal-issue":{"issue":"19","published-online":{"date-parts":[[2026,10]]}},"alternative-id":["cancers18193237"],"URL":"https:\/\/doi.org\/10.3390\/cancers18193237","relation":{},"ISSN":["2072-6694"],"issn-type":[{"value":"2072-6694","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,10,8]]}}}