LLM-Guided Diagnostic Evidence Alignment for Medical Vision-Language Pretraining under Limited Pairing
Institute of Intelligent Information Processing, Shanxi University（山西大学智能信息处理研究所）；Alliance Manchester Business School, The University of Manchester（曼彻斯特大学阿利安斯商学院）；Department of Computer Science and Engineering, The Hong Kong University of Science and Technology（香港科技大学计算机科学与工程系）
Most existing CLIP-style medical vision--language pretraining methods rely on global or local alignment with substantial paired data. However, global alignment is easily dominated by non-diagnostic information, while local alignment fails to integrate key diagnostic evidence. As a result, learning reliable diagnostic representations becomes difficult, which limits their applicability in medical scenarios with limited paired data. To address this issue, we propose an LLM-Guided Diagnostic Evidence Alignment method (LGDEA), which shifts the pretraining objective toward evidence-level alignment that is more consistent with the medical diagnostic process. Specifically, we leverage LLMs to extract key diagnostic evidence from radiology reports and construct a shared diagnostic evidence space, enabling evidence-aware cross-modal alignment and allowing LGDEA to effectively exploit abundant unpaired medical images and reports, thereby substantially alleviating the reliance on paired data. Extensive experimental results demonstrate that our method achieves consistent and significant improvements on phrase grounding, image--text retrieval, and zero-shot classification, and even rivals pretraining methods that rely on substantial paired data.
Reconstruction of Patient-Specific Confounders in AI-based Radiologic Image Interpretation using Generative Pretraining
Else Kroener Fresenius Center for Digital Health (EKFZ)（埃尔泽·克勒纳·菲森纽斯数字健康中心（EKFZ））；Technical University Dresden（德累斯顿工业大学）；University Hospital Aachen（亚琛大学医院）；UC Berkeley（加州大学伯克利分校）；University Hospital Zurich（苏黎世大学医院）；University of Zurich（苏黎世大学）；Center for Artificial Intelligence in Medicine and Imaging (AIMI)（医学与成像人工智能中心（AIMI））；Stanford University（斯坦福大学）；University Hospital Dresden（德累斯顿大学医院）；National Center for Tumor Diseases (NCT)（国家肿瘤疾病中心（NCT））
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）
Stanford University（斯坦福大学）；Stanford Medical Center（斯坦福医学中心）；Stanford Health Care（斯坦福医疗保健系统）；Stanford Center for Artificial Intelligence in Medicine and Imaging（斯坦福医学与影像人工智能中心）；Prealize Health；Stanford School of Medicine（斯坦福医学院）；Human-Centered Artificial Intelligence Institute, Stanford University（斯坦福大学以人为本人工智能研究所）；Clinical Excellence Research Center, Stanford School of Medicine（斯坦福医学院临床卓越研究中心）
MedKCO: Medical Vision-Language Pretraining via Knowledge-Driven Cognitive Orchestration
School of Computer Science and Engineering, Southeast University, China（东南大学计算机科学与工程学院）；Key Laboratory of New Generation Artificial Intelligence Technology and Its Interdisciplinary Applications, Ministry of Education, China（教育部新一代人工智能技术及其交叉应用重点实验室）；School of Computer Science and Engineering, Nanjing University of Science and Technology, China（南京理工大学计算机科学与工程学院）
Generative Text-Guided 3D Vision-Language Pretraining for Unified Medical Image Segmentation
University of Science and Technology of China（中国科学技术大学）；Institute of Artificial Intelligence, Hefei Comprehensive National Science Center（合肥综合性国家科学中心人工智能研究院）；Imperial College London（帝国理工学院）
Comparative Study of Anatomical and Learned Features in AI Models for Structural Brain MRI
Center for Data Science, New York University（纽约大学数据科学中心）；NYU Grossman School of Medicine（纽约大学格罗斯曼医学院）；Courant Institute of Mathematical Sciences, NYU（纽约大学柯朗数学科学研究所）
From Generic to Specialized: A Subspecialty Diagnostic System Powered by Self-Supervised Learning for Cervical Histopathology
Tsinghua University（清华大学）；Ningbo Clinical Pathology Diagnosis Center（宁波市临床病理诊断中心）；University of Oxford（牛津大学）；Research Institute of Tsinghua University in Shenzhen（清华大学深圳研究院）；Greater Bay Area National Center of Technology Innovation（粤港澳大湾区国家技术创新中心）；Zhejiang University School of Medicine（浙江大学医学院）；Hangzhou Adicon Clinical Laboratories Co., Ltd.（杭州艾迪康医学检验中心有限公司）；Wuhan University of Science and Technology（武汉科技大学）；Guangdong Women and Children Hospital（广东省妇幼保健院）；Maternal and Child Health Hospital of Hubei Province（湖北省妇幼保健院）；Shenzhen Shengqiang Technology Co., Ltd.（深圳盛强科技有限公司）；Pengcheng Laboratory（鹏城实验室）；Jinfeng Laboratory（金凤实验室）；The 920th Hospital of the Joint Logistics Support Force of PLA（中国人民解放军联勤保障部队第九二〇医院）；The Integrated Engineering Research Center of Cell Biological Medicine of State and Regions（细胞生物医学国家与区域整合工程研究中心）；Fuzhou University（福州大学）
Institute of AI for Health, Helmholtz Munich, Germany International School of Medicine, Istanbul Medipol University, T\"urkiye Munich Leukemia Laboratory, Germany Department of Medicine III, Ludwig-Maximilian-University Hospital, Germany Department of Physics, University of Munich, Germany Munich Center for Machine Learning (MCML), Germany DKTK, German Cancer Consortium, Germany
Shanghai Jiao Tong University（上海交通大学）；Shanghai AI Laboratory（上海人工智能实验室）；Ruijin Hospital, Shanghai Jiao Tong University School of Medicine（上海交通大学医学院附属瑞金医院）
PRISM2: Unlocking Multi-Modal General Pathology AI with Clinical Dialogue
Paige, NYC, NY United States（美国纽约市帕伊公司）；Microsoft Research, Cambridge, MA United States（微软研究院）；Memorial Sloan Kettering Cancer Center, NYC, NY United States（纪念斯隆凯特林癌症中心）；University of Yale, New Haven, CT United States（耶鲁大学）
EyeMVP: OCT-Informed Fundus Representation Learning via Paired CFP--OCT Pretraining
Shenzhen International Graduate School, Tsinghua University（清华大学深圳国际研究生院）；Beijing Tongren Eye Center, Beijing Tongren Hospital, Capital Medical University（首都医科大学附属北京同仁医院北京同仁眼科中心）；Liangxiang Hospital of Beijing Fangshan District, Capital Medical University（首都医科大学北京市房山区良乡医院）；The Third People's Hospital of Dalian（大连市第三人民医院）；National Clinical Research Center for Endocrine and Metabolic Diseases, The Second Xiangya Hospital of Central South University（中南大学湘雅二医院国家内分泌代谢病临床医学研究中心）；The Central Hospital of Baoji City（宝鸡市中心医院）；Wuxi No.2 People's Hospital, Affiliated Wuxi Clinical College of Nantong University（南通大学附属无锡临床学院无锡市第二人民医院）；Shenzhen Eye Hospital, Southern Medical University（南方医科大学深圳眼科医院）；Beijing Friendship Hospital, Capital Medical University（首都医科大学附属北京友谊医院）
Two-Stage Deep Learning Framework for Quality Assessment of Left Atrial Late Gadolinium Enhanced MRI Images
Kahlert School of Computing, University of Utah（犹他大学卡勒特计算学院）；Department of Biomedical Engineering, University of Utah（犹他大学生物医学工程系）；Nora Eccles Harrison Cardiovascular Research and Training Institute, University of Utah（犹他大学诺拉·埃克尔斯·哈里森心血管研究与培训研究所）；Department of Biomedical Engineering, Johns Hopkins（约翰斯·霍普金斯大学生物医学工程系）；Division of Cardiology, University of Utah（犹他大学心脏病学系）；Department of Radiology and Imaging Sciences, University of Utah（犹他大学放射学与影像科学系）；Scientific Computing and Imaging Institute, University of Utah（犹他大学科学计算与成像研究所）
Patient Pose Assessment Using a CT-Based Framework for Synthetic Data Generation
Institute for Neuro- and Bioinformatics, University of Lübeck（吕贝克大学神经与生物信息学研究所）；University Medical Center Schleswig-Holstein（石勒苏益格-荷尔斯泰因大学医学中心）；IMAGE Information Systems Europe GmbH（IMAGE信息系统欧洲有限公司）；Pattern Recognition Company GmbH（模式识别有限公司）
Symmetry Interactive Transformer with CNN Framework for Diagnosis of Alzheimer's Disease Using Structural MRI
College of Electronics and Information Engineering, Sichuan University, China（四川大学电子信息工程学院）；Tri-Institutional Center for Translational Research in Neuroimaging and Data Science (GSU, Georgia Tech, Emory), Atlanta, USA（跨机构神经影像与数据科学转化研究中心）；College of Information and Electrical Engineering, China Agricultural University, China（中国农业大学信息与电气工程学院）；School of Biomedical Engineering and Imaging Sciences, King's College London, UK（伦敦国王学院生物医学工程与影像科学学院）
Demographic-Aware Self-Supervised Anomaly Detection Pretraining for Equitable Rare Cardiac Diagnosis
Shanghai Jiao Tong University（上海交通大学）；Shanghai AI Laboratory（上海人工智能实验室）；National University of Defense Technology（国防科技大学）；Ruijin Hospital, Shanghai Jiao Tong University School of Medicine（瑞金医院，上海交通大学医学院）；Renji Hospital, Shanghai Jiao Tong University School of Medicine（仁济医院，上海交通大学医学院）
Visual Prompt Engineering for Vision Language Models in Radiology
Division of Medical Image Computing, German Cancer Research Center, Heidelberg, Germany（德国癌症研究中心医学图像计算部）；Faculty of Mathematics and Computer Science, Heidelberg University, Heidelberg, Germany（海德堡大学数学与计算机科学学院）；Medical Faculty Heidelberg, University of Heidelberg, Heidelberg, Germany（海德堡大学医学学院）
Symmetry Awareness Encoded Deep Learning Framework for Brain Imaging Analysis
School of Computer Science, University of Sydney（悉尼大学计算机科学学院）；Brain and Mind Centre, University of Sydney（悉尼大学脑与心智中心）；Sydney Neuroimaging Analysis Centre（悉尼神经影像分析中心）；School of Mathematics and Statistics, University of Sydney（悉尼大学数学与统计学院）；I-MED Radiology Network（I-MED放射学网络）
OmniMRI: A Unified Vision--Language Foundation Model for Generalist MRI Interpretation
Athinoula A. Martinos Center for Biomedical Imaging（阿提诺拉A.马丁诺斯生物医学成像中心）；Harvard Medical School（哈佛医学院）；Massachusetts General Hospital（麻省总医院）；University Campus Bio-Medico of Rome（罗马生物医学大学校园）
A Non-contrast Head CT Foundation Model for Comprehensive Neuro-Trauma Triage
Siemens Healthineers（西门子医疗）；New York University（纽约大学）；University of Maryland Medical Center（马里兰大学医学中心）；Vancouver General Hospital（温哥华总医院）；Northwell Health（诺斯韦尔健康）；UCHealth Memorial Hospital（UCHealth纪念医院）；Siemens SRL（西门子罗马尼亚有限责任公司）；Transilvania University of Braşov（布拉索夫特兰西瓦尼亚大学）
Location-Aware Pretraining for Medical Difference Visual Question Answering
Department of Electrical and Computer Engineering, Carnegie Mellon University, Kigali, Rwanda（电气与计算机工程系，卡内基梅隆大学，刚果（金）基利齐）；University of Melbourne, Melbourne, Australia（墨尔本大学，墨尔本，澳大利亚）
PathFLIP: Fine-grained Language-Image Pretraining for Versatile Computational Pathology
Harbin Institute of Technology, Shenzhen, School of Computer Science and Technology（哈尔滨工业大学（深圳）计算机科学与技术学院）；National University of Singapore, Department of Electronic and Computer Engineering（新加坡国立大学电子与计算机工程系）
From Pretraining to Privacy: Federated Ultrasound Foundation Model with Self-Supervised Learning
FNii-Shenzhen, The Chinese University of Hong Kong, Shenzhen（深圳FNii，香港中文大学（深圳））；School of Science and Engineering, The Chinese University of Hong Kong, Shenzhen（科学与工程学院，香港中文大学（深圳））；West China Hospital of Sichuan University, Chengdu（四川大学华西医院）；School of Computer Science, University College Dublin, Ireland（计算机科学学院，都柏林大学（爱尔兰））；College of Computer Science and Software Engineering, Shenzhen University, Shenzhen（计算机科学与软件工程学院，深圳大学）；South China Hospital, Health Science Center, Shenzhen University, Shenzhen（南方医院，深圳大学健康科学中心）；School of Computer Science, Nanjing University of Posts and Telecommunications, Nanjing（计算机科学学院，南京邮电大学）；Affiliated Hospital of North Sichuan Medical College, Sichuan（北川医学院附属医院）；North Sichuan Medical College, Sichuan（北川医学院）；Shenzhen Research Institute of Big Data, Shenzhen（深圳大数据研究院）；Bio-Computing Research Center, Harbin Institute of Technology, Shenzhen（生物计算研究中心，哈尔滨工业大学（深圳））；School of Computer Science, Wuhan University, Wuhan（计算机科学学院，武汉大学）；Computer Science Program, Computer, E（计算机科学项目，计算机）
CLIP-IT: CLIP-based Pairing for Histology Images Classification
LIVIA, ILLS, Dept. of Systems Engineering, ETS Montreal, Canada（LIVIA、ILLs、系统工程系、蒙特利尔大学ETSMontreal加拿大）；Dept. of Computer Engineering, University of Cagliari, Italy（计算机工程系、卡利亚里大学意大利）；Goodman Cancer Research, Centre, Dept. of Oncology, McGill University, Canada（Goodman癌症研究中心、肿瘤学系、麦吉尔大学加拿大）
HecVL: Hierarchical Video-Language Pretraining for Zero-shot Surgical Phase Recognition
University of Strasbourg（斯特拉斯堡大学）；CNRS（法国国家科学研究中心）；INSERM（法国国家健康与医学研究院）；ICube（ICube实验室）；IHU Strasbourg（斯特拉斯堡大学医院研究所）；Technische Universität München（慕尼黑工业大学）
MedVista3D: Vision-Language Modeling for Reducing Diagnostic Errors in 3D CT Disease Detection, Understanding and Reporting
Department of Biomedical Engineering（生物医学工程系）；Georgia Institute of Technology（佐治亚理工学院）；Department of Machine Learning（机器学习系）；Department of Radiation Oncology（放射肿瘤科）；Emory University School of Medicine（埃默里大学医学院）；University of Southern California（南加州大学）
传统的计算机视觉模型被训练来预测一组固定的预定义类别。最近，自然语言已被证明是一个更广泛和更丰富的监督来源，提供更精细的描述视觉概念比监督的“黄金”标签。以前的作品，如CLIP，使用一个简单的预训练任务来预测图像和文本标题之间的配对。然而，CLIP是数据饥渴的，需要超过4亿个图像文本对进行训练。我们提出了一种数据高效的对比蒸馏方法，使用软标签从嘈杂的图像-文本对中学习。我们的模型从预训练的图像和句子编码器中传输知识，仅用3 M图像文本对就实现了强大的性能，比CLIP小133倍。相对于ResNet 50图像编码器和DeCLUTR文本编码器，我们的方法在ImageNet 21 k +1 k上的一般零样本学习的SoTA超过了73%。在Google Open Images的zero-shot评估中，我们也以10.5%的优势击败了CLIP（19，958类）。
