Despite significant progress in applying large language models (LLMs) to the medical domain, several limitations still prevent them from practical applications. Among these are the constraints on model size and the lack of cohort-specific labeled datasets. In this work, we investigated the potential of improving a lightweight LLM, such as Llama 3.1-8B, through fine-tuning with datasets using synthetic labels. Two tasks are jointly trained by combining their respective instruction datasets. When the quality of the task-specific synthetic labels is relatively high (e.g., generated by GPT4- o), Llama 3.1-8B achieves satisfactory performance on the open-ended disease detection task, with a micro F1 score of 0.91. Conversely, when the quality of the task-relevant synthetic labels is relatively low (e.g., from the MIMIC-CXR dataset), fine-tuned Llama 3.1-8B is able to surpass its noisy teacher labels (micro F1 score of 0.67 v.s. 0.63) when calibrated against curated labels, indicating the strong inherent underlying capability of the model. These findings demonstrate the potential of fine-tuning LLMs with synthetic labels, offering a promising direction for future research on LLM specialization in the medical domain.
Leveraging Prompt-Learning for Structured Information Extraction from Crohn's Disease Radiology Reports in a Low-Resource Language
Faculty of Data and Decision Sciences, Technion - Israel Institute of Technology(以色列理工学院数据与决策科学学院);Shaare Zedek Medical Center(沙雷泽德克医疗中心);Faculty of Biomedical Engineering, Technion - Israel Institute of Technology(以色列理工学院生物医学工程学院);Hospital for Sick Children(病童医院)
提出SMP-BERT提示学习方法,利用报告结构从希伯来语克罗恩病放射学报告中提取结构化信息,显著优于传统微调,尤其在罕见病症检测上(AUC 0.99 vs 0.94,F1 0.84 vs 0.34),推动低资源语言的AI诊断。
ChatRadio-Valuer: A Chat Large Language Model for Generalizable Radiology Report Generation Based on Multi-institution and Multi-system Data
Northwestern Polytechnical University(西北工业大学);The Second Xiangya Hospital, Central South University(中南大学湘雅二医院);Clinical Research Center for Medical Imaging in Hunan Province(湖南省医学影像临床研究中心);Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences(中国科学院深圳先进技术研究院);Institute of Medical Research, Northwestern Polytechnical University(西北工业大学医学研究院);Glasgow College, University of Electronic Science and Technology of China(电子科技大学格拉斯哥学院);Central South University(中南大学)
Reinforcement Learning Improves LLM Accuracy and Reasoning in Disease Classification from Radiology Reports
Department of Population Health Sciences, Weill Cornell Medicine, New York, NY(人口健康科学系,韦尔·柯林斯医学中心,纽约,NY);Department of Radiology, Weill Cornell Medicine, New York, NY(放射科,韦尔·柯林斯医学中心,纽约,NY);Department of Radiology, Thomas Jefferson University, Philadelphia, PA(放射科,托马斯·杰斐逊大学,费城,PA)
Potential of Multimodal Large Language Models for Data Mining of Medical Images and Free-text Reports
Institute of Medical Research, Northwestern Polytechnical University(西北工业大学医学研究院);School of Computing, University of Georgia(佐治亚大学计算学院);School of Life Science and Technology, University of Electronic Science and Technology of China(电子科技大学生命科学与技术学院);School of Automation, Northwestern Polytechnical University(西北工业大学自动化学院);School of Electronics and Information, Northwestern Polytechnical University(西北工业大学电子信息学院);School of Biomedical Engineering, ShanghaiTech University(上海科技大学生物医学工程学院);Lingang Laboratory(临港实验室)
Merlin: A Computed Tomography Vision-Language Foundation Model and Dataset
Stanford University(斯坦福大学);Stanford Center for Artificial Intelligence in Medicine and Imaging(斯坦福大学医学与成像人工智能中心);Department of Electrical Engineering(电气工程系);University of California Berkeley(加州大学伯克利分校);Department of Radiology(放射科);University of Wisconsin-Madison(威斯康星大学麦迪逊分校);Hospital Israelita Albert Einstein(以色列特医院阿尔伯特·爱因斯坦医院)
Agent-Based Uncertainty Awareness Improves Automated Radiology Report Labeling with an Open-Source Large Language Model
Faculty of Biomedical Engineering, Technion - Israel Institute of Technology(以色列理工学院 生物医学工程学院);Faculty of Data and Decision Sciences, Technion - Israel Institute of Technology(以色列理工学院 数据与决策科学学院);Juliet Keidan Institute of Pediatric Gastroenterology Hepatology and Nutrition, Shaare Zedek Medical Center, The Hebrew University School of Medicine(沙尔泽德克医疗中心 朱丽叶·凯丹儿科胃肠病学、肝病学与营养学研究所;希伯来大学医学院);The Eisenberg R&D Authority, Shaare Zedek Medical Center, The Hebrew University of Jerusalem(沙尔泽德克医疗中心 艾森伯格研发管理局;耶路撒冷希伯来大学)
Radious: Unveiling the Enigma of Dental Radiology with BEIT Adaptor and Mask2Former in Semantic Segmentation
Gilan University of Medical Sciences(吉兰医科大学);University of Tehran(德黑兰大学);Hamedan University of Technology(哈马丹工业大学);Shahid Beheshti University of Medical Sciences(沙希德·贝赫什提医科大学)
MAC-RRG: Iterative Multi-Agent Collaboration for X-ray Radiology Report Generation
Anhui University(安徽大学);The First Affiliated Hospital of Anhui Medical University(安徽医科大学第一附属医院);Harbin Institute of Technology, Shenzhen(哈尔滨工业大学(深圳));Peng Cheng Laboratory(鹏城实验室)
CBM-RAG: Demonstrating Enhanced Interpretability in Radiology Report Generation with Multi-Agent RAG and Concept Bottleneck Models
German Research Center for Artificial Intelligence (DFKI)(德国人工智能研究中心);Saarland University(萨尔兰大学);University of Oldenburg(奥尔登堡大学);Dhaka Medical College Hospital(达卡医学院医院)
Multi-Label Annotation of Chest Abdomen Pelvis Computed Tomography Text Reports Using Deep Learning
Duke University School of Medicine(杜克大学医学院);Duke University(杜克大学);University of Girona(赫罗纳大学);South China University of Technology(华南理工大学);University of Arizona College of Medicine(亚利桑那大学医学院)
Radiology Text Analysis System (RadText): Architecture and Evaluation
The University of Texas at Austin(德克萨斯大学奥斯汀分校);Weill Cornell Medicine(威尔康奈尔医学院);National Center for Biotechnology Information (NCBI), National Library of Medicine (NLM), National Institutes of Health (NIH)(美国国立卫生研究院国家医学图书馆国家生物技术信息中心)
Enhanced Contrastive Learning with Multi-view Longitudinal Data for Chest X-ray Report Generation
School of Computer Science and Technology, Xidian University(西安电子科技大学计算机科学与技术学院);Xi’an Key Laboratory of Big Data and Intelligent Vision(西安大数据与智能视觉重点实验室);Key Laboratory of Collaborative Intelligence Systems, Ministry of Education, Xidian University(教育部协同智能系统重点实验室);Warren Alpert Medical School, Brown University(布朗大学沃伦·阿尔佩特医学学院)
XMACNet: An Explainable Lightweight Attention based CNN with Multi Modal Fusion for Chili Disease Classification
Vellore Institute of Technology(韦洛尔理工学院);Angel College of Engineering and Technology(安吉尔工程技术学院);Vel Tech Rangarajan Dr.Sagunthala R&D Institute of Science and Technology(Vel Tech朗加拉詹·萨贡塔拉博士科技研究院);Bannari Amman Institute of Technology(班纳里·安曼理工学院)
Human-AI Interaction (HAIx) Lab, Indian Institute of Technology Gandhinagar(人类-人工智能交互实验室,印度理工学院冈丁加尔);Department of Computer Science and Engineering, Madhav Institute of Technology and Science Deemed University (MITS-DU)(计算机科学与工程系,马达夫技术与科学 deemed 大学(MITS-DU));Multimedia and Information Security Research Group, Department of Computer Science and Engineering, ABV-Indian Institute of Information Technology and Management(多媒体与信息安全研究组,计算机科学与工程系,ABV-印度信息科技与管理学院)
Residual GRU+MHSA: A Lightweight Hybrid Recurrent Attention Model for Cardiovascular Disease Detection
George Mason University(乔治·马歇尔大学);University of Southern Queensland(南方昆士兰大学);University of Aveiro(阿维罗大学);Edinburgh Napier University(爱丁堡纳皮尔大学);Northwood High School(北伍德高中)
Radiology Report Generation Using Transformers Conditioned with Non-imaging Data
Centre for Computational Imaging and Simulation Technologies in Biomedicine(生物医学计算成像与模拟技术中心);Leeds Institute for Cardiovascular and Metabolic Medicine(利兹心血管与代谢医学研究所);School of Medicine(医学院);School of Computing, University of Leeds(利兹大学计算机学院)
本文提出一种多模态 Transformer 网络,整合胸部 X 射线图像与患者人口统计信息生成放射报告,实验证明加入非影像数据有效提升了生成质量。
Automated Plant Disease and Pest Detection System Using Hybrid Lightweight CNN-MobileViT Models for Diagnosis of Indigenous Crops
Department of Computer Science \& Engineering;Department of Information Technology Mekelle University - Mekelle Institute of Technology, Ethiopia Email
Lunguage: A Benchmark for Structured and Sequential Chest X-ray Interpretation
KAIST(韩国科学技术院);Ghent University(根特大学);Seoul National University Hospital(首尔国立大学医院);Seoul Medical Center(首尔医院);Yeungnam University College of Medicine(延世大学医学院);Microsoft Research Health Futures(微软研究院健康未来)