{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,9]],"date-time":"2026-07-09T22:22:30Z","timestamp":1783635750060,"version":"3.55.0"},"reference-count":78,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,5,22]],"date-time":"2026-05-22T00:00:00Z","timestamp":1779408000000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"funder":[{"DOI":"10.13039\/100022955","name":"Fundamental Research Funds for the Provincial Universities of Zhejiang Province","doi-asserted-by":"publisher","award":["GK259909299001-006"],"award-info":[{"award-number":["GK259909299001-006"]}],"id":[{"id":"10.13039\/100022955","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012165","name":"Key Technologies Research and Development Program","doi-asserted-by":"publisher","award":["2023YFC2706400"],"award-info":[{"award-number":["2023YFC2706400"]}],"id":[{"id":"10.13039\/501100012165","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Knowledge-Based Systems"],"published-print":{"date-parts":[[2026,8]]},"DOI":"10.1016\/j.knosys.2026.116261","type":"journal-article","created":{"date-parts":[[2026,5,21]],"date-time":"2026-05-21T15:14:38Z","timestamp":1779376478000},"page":"116261","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":1,"special_numbering":"C","title":["PathLens: A lightweight multimodal reasoner for in-depth pathology insights"],"prefix":"10.1016","volume":"348","author":[{"given":"Zhu","family":"Zhu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Huangwei","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhenyu","family":"Yan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Donghao","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yueyi","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuqi","family":"Zhan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Weihao","family":"Cheng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Manli","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Weizhong","family":"Gu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yifei","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Feiwei","family":"Qin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gang","family":"Yu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"issue":"8","key":"10.1016\/j.knosys.2026.116261_b1","first-page":"1136","article-title":"Real-world deployment of a fine-tuned pathology foundation model for lung cancer biomarker detection","volume":"31","author":"Campanella","year":"2025","journal-title":"Nature Med."},{"key":"10.1016\/j.knosys.2026.116261_b2","doi-asserted-by":"crossref","first-page":"692","DOI":"10.1038\/s41416-024-02726-3","article-title":"A non-invasive artificial intelligence model for identifying axillary pathological complete response to neoadjuvant chemotherapy in breast cancer: a secondary analysis to multicenter clinical trial","volume":"131","author":"Zhu","year":"2024","journal-title":"Br. J. Cancer"},{"key":"10.1016\/j.knosys.2026.116261_b3","series-title":"Multimodal feature prototype learning for interpretable and discriminative cancer survival prediction","author":"Jiang","year":"2025"},{"key":"10.1016\/j.knosys.2026.116261_b4","series-title":"Towards accurate and interpretable neuroblastoma diagnosis via contrastive Multi-scale pathological image analysis","author":"Zhu","year":"2025"},{"issue":"8","key":"10.1016\/j.knosys.2026.116261_b5","doi-asserted-by":"crossref","DOI":"10.1016\/j.patter.2025.101286","article-title":"GastritisMIL: An interpretable deep learning model for the comprehensive histological assessment of chronic gastritis","volume":"6","author":"Xia","year":"2025","journal-title":"Patterns"},{"key":"10.1016\/j.knosys.2026.116261_b6","doi-asserted-by":"crossref","first-page":"5493","DOI":"10.1038\/s41467-025-60307-1","article-title":"Deep learning quantifies pathologists\u2019 visual patterns for whole slide image diagnosis","volume":"16","author":"Nan","year":"2025","journal-title":"Nat. Commun."},{"key":"10.1016\/j.knosys.2026.116261_b7","doi-asserted-by":"crossref","DOI":"10.1016\/j.media.2025.103708","article-title":"DIOR-ViT: Differential ordinal learning vision transformer for cancer classification in pathology images","volume":"105","author":"Lee","year":"2025","journal-title":"Med. Image Anal."},{"key":"10.1016\/j.knosys.2026.116261_b8","doi-asserted-by":"crossref","DOI":"10.1016\/j.media.2022.102415","article-title":"DDTNet: A dense dual-task network for tumor-infiltrating lymphocyte detection and segmentation in histopathological images of breast cancer","volume":"78","author":"Zhang","year":"2022","journal-title":"Med. Image Anal."},{"key":"10.1016\/j.knosys.2026.116261_b9","series-title":"PathVQA: 30000+ questions for medical visual question answering","author":"He","year":"2020"},{"issue":"3","key":"10.1016\/j.knosys.2026.116261_b10","first-page":"2647","article-title":"Explainable AI (XAI) in healthcare: Enhancing trust and transparency in critical decision-making","volume":"23","author":"Adeniran","year":"2024","journal-title":"World J. Adv. Res. Rev."},{"key":"10.1016\/j.knosys.2026.116261_b11","series-title":"Proceedings of the International Conference on Machine Learning","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021"},{"issue":"9","key":"10.1016\/j.knosys.2026.116261_b12","doi-asserted-by":"crossref","first-page":"2307","DOI":"10.1038\/s41591-023-02504-3","article-title":"A visual\u2013language foundation model for pathology image analysis using medical Twitter","volume":"29","author":"Huang","year":"2023","journal-title":"Nature Med."},{"key":"10.1016\/j.knosys.2026.116261_b13","doi-asserted-by":"crossref","first-page":"524","DOI":"10.1038\/s43588-025-00818-5","article-title":"Cost-effective instruction learning for pathology vision and language analysis","volume":"5","author":"Chen","year":"2025","journal-title":"Nat. Comput. Sci."},{"key":"10.1016\/j.knosys.2026.116261_b14","series-title":"REALM: An MLLM-Agent framework for open world 3D reasoning segmentation and editing on Gaussian splatting","author":"Shi","year":"2025"},{"key":"10.1016\/j.knosys.2026.116261_b15","series-title":"Sci-mind: cognitively-inspired adversarial debate for autonomous mathematical modeling","author":"Jia","year":"2026"},{"issue":"7","key":"10.1016\/j.knosys.2026.116261_b16","doi-asserted-by":"crossref","DOI":"10.1016\/j.isci.2025.112980","article-title":"Comprehensive application of artificial intelligence in colorectal cancer: A review","volume":"28","author":"Sun","year":"2025","journal-title":"IScience"},{"key":"10.1016\/j.knosys.2026.116261_b17","series-title":"Geodesic prototype matching via diffusion maps for interpretable Fine-Grained recognition","author":"Jia","year":"2025"},{"key":"10.1016\/j.knosys.2026.116261_b18","series-title":"Cotbox-ttt: grounding medical VQA with visual Chain-of-Thought boxes during Test-Time training","author":"Qian","year":"2025"},{"key":"10.1016\/j.knosys.2026.116261_b19","series-title":"Skincare: a multimodal dermatology dataset annotated with medical caption and Chain-of-Thought reasoning","author":"Shen","year":"2025"},{"issue":"1","key":"10.1016\/j.knosys.2026.116261_b20","doi-asserted-by":"crossref","first-page":"e58","DOI":"10.1016\/S2589-7500(23)00219-4","article-title":"Operational greenhouse-gas emissions of deep learning in digital pathology: a modelling study","volume":"6","author":"Vafaei Sadr","year":"2024","journal-title":"Lancet Digit. Health"},{"key":"10.1016\/j.knosys.2026.116261_b21","series-title":"Proceedings of the Forty-Second International Conference on Machine Learning","article-title":"HealthGPT: A medical large vision-language model for unifying comprehension and generation via heterogeneous knowledge adaptation","author":"Lin","year":"2025"},{"key":"10.1016\/j.knosys.2026.116261_b22","series-title":"Trustworthy and fair SkinGPT-R1 for democratizing dermatological reasoning across diverse ethnicities","author":"Shen","year":"2026"},{"key":"10.1016\/j.knosys.2026.116261_b23","series-title":"Beyond the individual: virtualizing multi-disciplinary reasoning for clinical intake via collaborative agents","author":"Chen","year":"2026"},{"key":"10.1016\/j.knosys.2026.116261_b24","series-title":"Medcollab: causal-driven multi-agent collaboration for full-cycle clinical diagnosis via IBIS-Structured argumentation","author":"Zhan","year":"2026"},{"key":"10.1016\/j.knosys.2026.116261_b25","series-title":"Fetalagents: a multi-agent system for fetal ultrasound image and video analysis","author":"Hu","year":"2026"},{"key":"10.1016\/j.knosys.2026.116261_b26","series-title":"International Conference on Learning Representations","article-title":"Multitask prompted training enables zero-shot task generalization","author":"Sanh","year":"2022"},{"key":"10.1016\/j.knosys.2026.116261_b27","series-title":"DeepSeekMath: Pushing the limits of mathematical reasoning in open language models","author":"Shao","year":"2024"},{"key":"10.1016\/j.knosys.2026.116261_b28","series-title":"Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 2: Short Papers)","first-page":"708","article-title":"Towards visual question answering on pathology images","author":"He","year":"2021"},{"issue":"4","key":"10.1016\/j.knosys.2026.116261_b29","doi-asserted-by":"crossref","first-page":"1886","DOI":"10.1109\/JBHI.2023.3294249","article-title":"K-PathVQA: Knowledge-aware multimodal representation for pathology visual question answering","volume":"28","author":"Naseem","year":"2024","journal-title":"IEEE J. Biomed. Health Inform."},{"key":"10.1016\/j.knosys.2026.116261_b30","series-title":"Interspeech 2024","first-page":"4034","article-title":"TM-PATHVQA: 90000+ textless multilingual questions for medical visual question answering","author":"Rajkhowa","year":"2024"},{"key":"10.1016\/j.knosys.2026.116261_b31","series-title":"18th European Conference on Computer Vision","first-page":"401","article-title":"WSI-VQA: Interpreting whole slide images by generative visual question answering","author":"Chen","year":"2024"},{"key":"10.1016\/j.knosys.2026.116261_b32","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"13183","article-title":"Quilt-LLaVA: Visual instruction tuning by extracting localized narratives from open-source histopathology videos","author":"Seyfioglu","year":"2024"},{"key":"10.1016\/j.knosys.2026.116261_b33","series-title":"18th European Conference on Computer Vision","first-page":"56","article-title":"PathMMU: A massive multimodal expert-level benchmark for understanding and reasoning in pathology","author":"Sun","year":"2024"},{"key":"10.1016\/j.knosys.2026.116261_b34","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"19764","article-title":"Visual language pretrained multiple instance Zero-Shot transfer for histopathology images","author":"Lu","year":"2023"},{"issue":"3","key":"10.1016\/j.knosys.2026.116261_b35","doi-asserted-by":"crossref","first-page":"863","DOI":"10.1038\/s41591-024-02856-4","article-title":"A visual-language foundation model for computational pathology","volume":"30","author":"Lu","year":"2024","journal-title":"Nature Med."},{"issue":"8035","key":"10.1016\/j.knosys.2026.116261_b36","doi-asserted-by":"crossref","first-page":"970","DOI":"10.1038\/s41586-024-07894-z","article-title":"A pathology foundation model for cancer diagnosis and prognosis prediction","volume":"634","author":"Wang","year":"2024","journal-title":"Nature"},{"issue":"8051","key":"10.1016\/j.knosys.2026.116261_b37","doi-asserted-by":"crossref","first-page":"769","DOI":"10.1038\/s41586-024-08378-w","article-title":"A vision-language foundation model for precision oncology","volume":"638","author":"Xiang","year":"2025","journal-title":"Nature"},{"key":"10.1016\/j.knosys.2026.116261_b38","series-title":"MMLNB: Multi-Modal learning for neuroblastoma subtyping classification assisted with textual description generation","author":"Chen","year":"2025"},{"key":"10.1016\/j.knosys.2026.116261_b39","series-title":"Directed ordinal diffusion regularization for Progression-Aware diabetic retinopathy grading","author":"Chen","year":"2026"},{"issue":"8033","key":"10.1016\/j.knosys.2026.116261_b40","doi-asserted-by":"crossref","first-page":"466","DOI":"10.1038\/s41586-024-07618-3","article-title":"A multimodal generative AI copilot for human pathology","volume":"634","author":"Lu","year":"2024","journal-title":"Nature"},{"key":"10.1016\/j.knosys.2026.116261_b41","series-title":"2024 IEEE International Conference on Bioinformatics and Biomedicine","first-page":"3138","article-title":"PA-LLaVA: A large language-vision assistant for human pathology image understanding","author":"Dai","year":"2024"},{"key":"10.1016\/j.knosys.2026.116261_b42","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"10360","article-title":"CPath-Omni: A unified multimodal foundation model for patch and whole slide image analysis in computational pathology","author":"Sun","year":"2025"},{"key":"10.1016\/j.knosys.2026.116261_b43","series-title":"International Conference on Learning Representations","article-title":"Pathgen-1.6 m: 1.6 million pathology image-text pairs generation through multi-agent collaboration","author":"Sun","year":"2025"},{"key":"10.1016\/j.knosys.2026.116261_b44","series-title":"DeepSeek-R1: Incentivizing reasoning capability in LLMs via reinforcement learning","author":"DeepSeek-AI","year":"2025"},{"key":"10.1016\/j.knosys.2026.116261_b45","series-title":"Med-U1: Incentivizing unified medical reasoning in LLMs via large-scale reinforcement learning","author":"Zhang","year":"2025"},{"key":"10.1016\/j.knosys.2026.116261_b46","series-title":"Med-R1: Reinforcement learning for generalizable medical reasoning in vision-language models","author":"Lai","year":"2025"},{"key":"10.1016\/j.knosys.2026.116261_b47","series-title":"MedVLM-R1: Incentivizing medical reasoning capability of vision-language models (VLMs) via reinforcement learning","author":"Pan","year":"2025"},{"key":"10.1016\/j.knosys.2026.116261_b48","series-title":"Lingshu: A generalist foundation model for unified multimodal medical understanding and reasoning","author":"Team","year":"2025"},{"key":"10.1016\/j.knosys.2026.116261_b49","series-title":"PathVLM-R1: A reinforcement learning-driven reasoning model for pathology visual-language tasks","author":"Wu","year":"2025"},{"key":"10.1016\/j.knosys.2026.116261_b50","series-title":"Patho-R1: A multimodal reinforcement learning-based pathology expert reasoner","author":"Zhang","year":"2025"},{"key":"10.1016\/j.knosys.2026.116261_b51","series-title":"Group sequence policy optimization","author":"Zheng","year":"2025"},{"key":"10.1016\/j.knosys.2026.116261_b52","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","first-page":"5034","article-title":"PathAsst: A generative foundation AI assistant towards artificial general intelligence of pathology","volume":"Vol. 38","author":"Sun","year":"2024"},{"key":"10.1016\/j.knosys.2026.116261_b53","doi-asserted-by":"crossref","first-page":"277","DOI":"10.1038\/s43856-024-00709-2","article-title":"Development of a large-scale medical visual question-answering dataset","volume":"4","author":"Zhang","year":"2024","journal-title":"Commun. Med."},{"key":"10.1016\/j.knosys.2026.116261_b54","series-title":"Qwen2.5-VL technical report","author":"Bai","year":"2025"},{"key":"10.1016\/j.knosys.2026.116261_b55","series-title":"Health Insurance Portability and Accountability Act of 1996 (HIPAA)","author":"U.S. Department of Health and Human Services","year":"1996"},{"key":"10.1016\/j.knosys.2026.116261_b56","series-title":"Regulation (EU) 2016\/679 of the European Parliament and of the Council (General Data Protection Regulation)","author":"Parliament","year":"2016"},{"issue":"1","key":"10.1016\/j.knosys.2026.116261_b57","doi-asserted-by":"crossref","first-page":"119","DOI":"10.1038\/s41746-020-00323-1","article-title":"The future of digital health with federated learning","volume":"3","author":"Rieke","year":"2020","journal-title":"Npj Digit. Med."},{"key":"10.1016\/j.knosys.2026.116261_b58","series-title":"GPT-4 technical report","author":"OpenAI","year":"2023"},{"key":"10.1016\/j.knosys.2026.116261_b59","unstructured":"Anthropic, The Claude 3 Model Family, Technical Report, 2024, URL: https:\/\/www.anthropic.com\/news\/claude-3."},{"key":"10.1016\/j.knosys.2026.116261_b60","series-title":"Gemini: A family of highly capable multimodal models","author":"DeepMind","year":"2023"},{"key":"10.1016\/j.knosys.2026.116261_b61","series-title":"InternVL2.5: Scaling efficient vision-language models with advanced pretraining recipes","author":"Team","year":"2024"},{"key":"10.1016\/j.knosys.2026.116261_b62","series-title":"InternVL3: Exploring advanced training and test-time recipes for vision-language models","author":"Team","year":"2025"},{"key":"10.1016\/j.knosys.2026.116261_b63","series-title":"MedVLM-R1: Training medical vision-language models with reinforcement learning from clinical reasoning feedback","author":"Wang","year":"2025"},{"key":"10.1016\/j.knosys.2026.116261_b64","series-title":"Med-Gemma: Towards building a generalist biomedical language model","author":"Team","year":"2025"},{"key":"10.1016\/j.knosys.2026.116261_b65","series-title":"NeurIPS 2023 Datasets and Benchmarks Track","article-title":"LLaVA-Med: Training a large language-and-vision assistant for biomedicine in one day","author":"Li","year":"2023"},{"key":"10.1016\/j.knosys.2026.116261_b66","series-title":"HuatuoGPT-Vision: Towards injecting medical visual knowledge into multimodal LLMs at scale","author":"Chen","year":"2024"},{"key":"10.1016\/j.knosys.2026.116261_b67","series-title":"BiMediX2: Bio-medical expert LMM for diverse medical modalities","author":"Mullappilly","year":"2024"},{"key":"10.1016\/j.knosys.2026.116261_b68","series-title":"Med-Flamingo: A Multimodal Medical Few-shot Learner","first-page":"24995","volume":"Vol. 225","author":"Moor","year":"2023"},{"key":"10.1016\/j.knosys.2026.116261_b69","series-title":"GSCo: Towards generalizable AI in medicine via generalist supervision and curriculum optimization","author":"Fan","year":"2024"},{"key":"10.1016\/j.knosys.2026.116261_b70","series-title":"Improved baselines with visual instruction tuning","author":"Liu","year":"2023"},{"key":"10.1016\/j.knosys.2026.116261_b71","series-title":"LLaVA-OneVision: Easy visual task transfer","author":"Li","year":"2024"},{"key":"10.1016\/j.knosys.2026.116261_b72","series-title":"The Llama 3 herd of models","author":"Grattafiori","year":"2024"},{"key":"10.1016\/j.knosys.2026.116261_b73","series-title":"DeepSeek-VL2: Mixture-of-Experts vision-language models for efficient multimodal understanding","author":"DeepSeek AI","year":"2024"},{"key":"10.1016\/j.knosys.2026.116261_b74","series-title":"Qwen3 technical report","author":"Team","year":"2025"},{"key":"10.1016\/j.knosys.2026.116261_b75","series-title":"InternVL3.5: Advancing open-source multimodal models in versatility, reasoning, and efficiency","author":"Wang","year":"2025"},{"key":"10.1016\/j.knosys.2026.116261_b76","series-title":"PathGen-1.6M: 1.6 million pathology image\u2013text pairs generated via multi-agent collaboration","author":"Team","year":"2024"},{"key":"10.1016\/j.knosys.2026.116261_b77","series-title":"Expanding performance boundaries of open-source multimodal models with model, data, and test-time scaling","author":"Chen","year":"2024"},{"issue":"140","key":"10.1016\/j.knosys.2026.116261_b78","first-page":"1","article-title":"A technique for the measurement of attitudes","volume":"22","author":"Likert","year":"1932","journal-title":"Arch. Psychol."}],"container-title":["Knowledge-Based Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0950705126009871?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0950705126009871?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,7,9]],"date-time":"2026-07-09T22:06:21Z","timestamp":1783634781000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0950705126009871"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8]]},"references-count":78,"alternative-id":["S0950705126009871"],"URL":"https:\/\/doi.org\/10.1016\/j.knosys.2026.116261","relation":{},"ISSN":["0950-7051"],"issn-type":[{"value":"0950-7051","type":"print"}],"subject":[],"published":{"date-parts":[[2026,8]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"PathLens: A lightweight multimodal reasoner for in-depth pathology insights","name":"articletitle","label":"Article Title"},{"value":"Knowledge-Based Systems","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.knosys.2026.116261","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 The Authors. Published by Elsevier B.V.","name":"copyright","label":"Copyright"}],"article-number":"116261"}}