Multimodal large language models (MLLMs) show promising performance on medical visual question answering (VQA) and report generation, but these generation and explanation abilities do not reliably transfer to disease-specific classification. We evaluated MLLM architectures on knee osteoarthritis (OA) radiograph classification, which remains underrepresented in existing medical MLLM benchmarks, even though knee OA affects an estimated 300 to 400 million people worldwide. Through systematic ablation studies manipulating the vision encoder, the connector, and the large language model (LLM) across diverse training strategies, we measured each component's contribution to diagnostic accuracy. In our classification task, a trained vision encoder alone could outperform full MLLM pipelines in classification accuracy and fine-tuning the LLM provided no meaningful improvement over prompt-based guidance. And LoRA fine-tuning on a small, class-balanced dataset (500 images) gave better results than training on a much larger but class-imbalanced set (5,778 images), indicating that data balance and quality can matter more than raw scale for this task. These findings suggest that for domain-specific medical classification, LLMs are more effective as interpreters and report generators rather than as primary classifiers. Therefore, the MLLM architecture appears less suitable for medical image diagnostic classification tasks that demand high certainty. We recommend prioritizing vision encoder optimization and careful dataset curation when developing clinically applicable systems.
Simple Methods for Scanner Drift Normalization Validated for Automatic Segmentation of Knee Magnetic Resonance Imaging - with data from the Osteoarthritis Initiative
Biomediq A/S（Biomediq公司）；University of Copenhagen（哥本哈根大学）
Improved-Mask R-CNN: Towards an Accurate Generic MSK MRI instance segmentation platform (Data from the Osteoarthritis Initiative)
Schulich School of Engineering, University of Calgary（卡尔加里大学舒立克工程学院）；Department of Radiology & Diagnostic Imaging, University of Alberta（阿尔伯塔大学放射与诊断成像系）；Alberta Machine Intelligence Institute (AMII), University of Alberta（阿尔伯塔大学阿尔伯塔机器智能研究所（AMII））；Mechanical and Manufacturing Engineering, University of Calgary（卡尔加里大学机械与制造工程系）
Automated anomaly-aware 3D segmentation of bones and cartilages in knee MR images from the Osteoarthritis Initiative
The University of Queensland（昆士兰大学）；Australian e-Health Research Centre（澳大利亚电子健康研究中心）；Commonwealth Scientific and Industrial Research Organisation（联邦科学与工业研究组织）
Quantifying Radiographic Knee Osteoarthritis Severity using Deep Convolutional Neural Networks
Insight Centre for Data Analytics, Dublin City University（都柏林城市大学数据洞察中心）；School of Health and Human Performance, Dublin City University（都柏林城市大学健康与人体表现学院）
Self-Supervised Learning for Knee Osteoarthritis: Diagnostic Limitations and Prognostic Value of Hospital Data
Department of Physics, J.K. Institute of Science（物理系，J.K. 科学研究所）；World Scientific University（世界科学大学）；University of Intelligent Studies（智能研究大学）；Center for Data Science, New York University（数据科学中心，纽约大学）；Bernard and Irene Schwartz Center for Biomedical Imaging, New York University Langone Health（伯纳德和艾琳·施瓦茨生物医学成像中心，纽约大学朗格尼健康中心）；Department of Radiology, New York University Langone Health（放射学系，纽约大学朗格尼健康中心）；Perlmutter Cancer Center, New York University Langone Health（珀尔马特癌症中心，纽约大学朗格尼健康中心）
Unsupervised Domain Adaptation for Automated Knee Osteoarthritis Phenotype Classification
The Chinese University of Hong Kong（香港中文大学）；Shanghai Sixth People's Hospital Affiliated to Shanghai Jiao Tong University School of Medicine（上海交通大学医学院附属第六人民医院）
Stacked Ensemble of Fine-Tuned CNNs for Knee Osteoarthritis Severity Grading
Indian Institute of Technology Guwahati（印度理工学院瓜瓦提分校）；Indian Institute of Technology Kanpur（印度理工学院坎浦尔分校）；California State University, Northridge（加州州立大学北岭分校）
Key-Exchange Convolutional Auto-Encoder for Data Augmentation in Early Knee Osteoarthritis Detection
Massachusetts General Hospital（麻省总医院）；Harvard Medical School（哈佛医学院）；University Sorbonne Paris Nord（巴黎北部索邦大学）；Jiangsu Institute of Hematology（江苏血液学研究所）；The First Affiliated Hospital of Soochow University（苏州大学附属第一医院）；Henan University of Chinese Medicine（河南中医药大学）；German Cancer Research Center（德国癌症研究中心）；Athinoula A. Martinos Centre for Biomedical Imaging（阿西努拉·A.马蒂诺斯生物医学成像中心）；Geneva University Hospital（日内瓦大学医院）；IDP Institute（IDP研究所）；University of Orleans（奥尔良大学）
Joining Forces for Pathology Diagnostics with AI Assistance: The EMPAIA Initiative
Charité – Universitätsmedizin Berlin（柏林夏里特医学院）；Freie Universität Berlin（柏林自由大学）；Humboldt Universität zu Berlin（柏林洪堡大学）；Fraunhofer Institute for Digital Medicine MEVIS（弗劳恩霍夫数字医学MEVIS研究所）；Technische Universität Berlin（柏林工业大学）；QuIP GmbH（QuIP有限公司）；University Hospital RWTH Aachen（亚琛工业大学附属医院）
Reviewing Clinical Knowledge in Medical Large Language Models: Training and Beyond
School of Computer Science and Technology, Wuhan University of Science and Technology（计算机科学与技术学院，武汉科技大学）；Hubei Province Key Laboratory of Intelligent Information Processing and Real-time Industrial System（湖北省智能信息处理与实时工业系统重点实验室）；School of Computer Science and Technology, Huazhong University of Science and Technology（计算机科学与技术学院，华中科技大学）；School of Cyber Science and Engineering, Wuhan University（网络科学与工程学院，武汉大学）；Department of Computer Science, Vrije Universiteit Amsterdam（计算机科学系，阿姆斯特丹自由大学）
A multimodal vision foundation model for generalizable knee pathology
Beihang University（北京航空航天大学）；Peking University Third Hospital（北京大学第三医院）；Institute of Sports Medicine of Peking University（北京大学运动医学研究所）；Ministry of Education（教育部）
3D CNN-based classification using sMRI and MD-DTI images for Alzheimer disease studies
Lomonosov Moscow State University（莫斯科国立大学）；University of Bordeaux（波尔多大学）；Université Ibn Zhor（伊本·佐尔大学）；University Victor Segalen Bordeaux 2（维克多·瑟加兰-波尔多第二大学）
Class Balancing Diversity Multimodal Ensemble for Alzheimer's Disease Diagnosis and Early Detection
Unit of Computer Systems and Bioinformatics, Department of Engineering, Università Campus Bio-Medico di Roma（计算机系统与生物信息学单位，工程系，罗马生物医学大学）；Operative Research Unit of Neurology, Fondazione Policlinico Universitario Campus Bio-Medico（神经学操作研究单位，大学医学研究院生物医学 Campus）；Eustema S.p.A., Research and Development Centre（Eustema 公司，研发中心）；Department of Diagnostic and Intervention, Radiation Physics, Biomedical Engineering, Umeå University（诊断与介入部门，辐射物理，生物医学工程，乌梅大学）
POCOVID-Net: Automatic Detection of COVID-19 From a New Lung Ultrasound Imaging Dataset (POCUS)
ETH Zurich（苏黎世联邦理工学院）；Clinique des Grangettes（格兰奇诊所）；Biomedical Research Institute August Pi i Sunyer（奥古斯特·皮·苏涅尔生物医学研究所）；Technische Universität München（慕尼黑工业大学）
Efficient Large Scale Medical Image Dataset Preparation for Machine Learning Applications
German Cancer Research Center (DKFZ)（德国癌症研究中心（DKFZ））；University of Heidelberg（海德堡大学）；Goethe University Frankfurt（法兰克福歌德大学）；Charité - Universitätsmedizin Berlin（柏林夏里特医学院）
