awesome-multimodal-in-medical-imaging

awesome-multimodal-in-medical-imaging

医学影像多模态学习应用资源集锦

该项目汇集医学影像多模态学习应用资源,涵盖数据集、综述、报告生成、视觉问答和视觉语言模型等。内容包括大语言模型相关论文,并提供最新论文和代码链接。资源库定期更新,收录超过100篇高质量论文,为医学影像多模态研究提供重要参考。

医学影像多模态学习报告生成视觉问答视觉语言模型Github开源项目

Maintenance PR's Welcome Awesome

Awesome-Multimodal-Applications-In-Medical-Imaging

This repository includes resources on several applications of multi-modal learning in medical imaging, including papers related to <b>large language models (LLM)</b>. Papers involving LLM are bold.

Contributing

Please feel free to send me pull requests or email to add links or to discuss with me about this area. Markdown format:

- [**Name of Conference or Journal + Year**] Paper Name. [[pdf]](link) [[code]](link)

News

Citation

@article{xia2024cares, title={CARES: A Comprehensive Benchmark of Trustworthiness in Medical Vision Language Models}, author={Xia, Peng and Chen, Ze and Tian, Juanxi and Gong, Yangrui and Hou, Ruibo and Xu, Yue and Wu, Zhenbang and Fan, Zhiyuan and Zhou, Yiyang and Zhu, Kangyu and others}, journal={arXiv preprint arXiv:2406.06007}, year={2024} } @article{xia2024rule, title={RULE: Reliable Multimodal RAG for Factuality in Medical Vision Language Models}, author={Xia, Peng and Zhu, Kangyu and Li, Haoran and Zhu, Hongtu and Li, Yun and Li, Gang and Zhang, Linjun and Yao, Huaxiu}, journal={arXiv preprint arXiv:2407.05131}, year={2024} }

Overview


Data Source

Image-Caption Datasets

datasetdomainimagetextsourcelanguage
ROCOmultiple87K87Kresearch papersEn
MedICaTmultiple217K217Kresearch papersEn
PMC-OAmultiple1.6M1.6Mresearch papersEn
ChiMed-VLmultiple580K580Kresearch papersEn/zh
FFA-IRfundus1M10Kmedical reportsEn/zh
PadChestcxr160K109Kmedical reportsSp
MIMIC-CXRcxr377K227Kmedical reportsEn
OpenPathhistology208K208Ksocial mediaEn
Quilt-1Mhistology1M1Mresearch papers<br>social mediaEn
Harvard-FairVLMedfundus10k10Kmedical reportsEn

Visual Question Answering Datasets

datasetdomainimageQA Itemslanguage
VQA-RADradiology3153kEn
SLAKEradiology64214kEn/zh
Path-VQAhistology5k32MEn
VQA-Medradiology4.5k5.5kEn
PMC-VQAmultiple149k227kEn
OmniMedVQAmultiple118k128kEn
ProbMedradiology6k57kEn

Survey

  • [arXiv 2022] Visual Attention Methods in Deep Learning: An In-Depth Survey [pdf]
  • [arXiv 2022] Vision+X: A Survey on Multimodal Learning in the Light of Data [pdf]
  • [arXiv 2023] Vision Language Models for Vision Tasks: A Survey [pdf] [code]
  • [arXiv 2023] A Systematic Review of Deep Learning-based Research on Radiology Report Generation [pdf] [code]
  • [Artif Intell Med 2023] Medical Visual Question Answering: A Survey [pdf]
  • [arXiv 2023] Medical Vision Language Pretraining: A survey [pdf]
  • [arXiv 2023] CLIP in Medical Imaging: A Comprehensive Survey [pdf] [code]
  • [arXiv 2024] Vision-Language Models for Medical Report Generation and Visual Question Answering: A Review [pdf] [code]

Medical Report Generation

2018

  • [EMNLP 2018] Automated Generation of Accurate & Fluent Medical X-ray Reports [pdf] [code]
  • [ACL 2018] On the Automatic Generation of Medical Imaging Reports [pdf] [code]
  • [NeurIPS 2018] Hybrid Retrieval-Generation Reinforced Agent for Medical Image Report Generation [pdf]

2019

  • [AAAI 2019] Knowledge-Driven Encode, Retrieve, Paraphrase for Medical Image Report Generation [pdf]
  • [ICDM 2019] Automatic Generation of Medical Imaging Diagnostic Report with Hierarchical Recurrent Neural Network [pdf]
  • [MICCAI 2019] Automatic Radiology Report Generation based on Multi-view Image Fusion and Medical Concept Enrichment [pdf]

2020

  • [AAAI 2020] When Radiology Report Generation Meets Knowledge Graph [pdf]
  • [EMNLP 2020] Generating Radiology Reports via Memory-driven Transformer [pdf] [code]
  • [ACCV 2020] Hierarchical X-Ray Report Generation via Pathology tags and Multi Head Attention [pdf] [code]

2021

  • [NeurIPS 2021 D&B] FFA-IR: Towards an Explainable and Reliable Medical Report Generation Benchmark [pdf] [code]
  • [ACL 2021] Competence-based Multimodal Curriculum Learning for Medical Report Generation [pdf]
  • [CVPR 2021] Exploring and Distilling Posterior and Prior Knowledge for Radiology Report Generation [pdf]
  • [MICCAI 2021] AlignTransformer: Hierarchical Alignment of Visual Regions and Disease Tags for Medical Report Generation [pdf]
  • [NAACL-HLT 2021] Improving Factual Completeness and Consistency of Image-to-Text Radiology Report Generation [pdf] [code]
  • [MICCAI 2021] RATCHET: Medical Transformer for Chest X-ray Diagnosis and Reporting [pdf][code]
  • [MICCAI 2021] Trust It or Not: Confidence-Guided Automatic Radiology Report Generation [pdf]
  • [MICCAI 2021] Surgical Instruction Generation with Transformers [pdf]
  • [MICCAI 2021] Class-Incremental Domain Adaptation with Smoothing and Calibration for Surgical Report Generation [pdf] [code]
  • [ACL 2021] Cross-modal Memory Networks for Radiology Report Generation [pdf] [code]

2022

  • [CVPR 2022] Cross-modal Clinical Graph Transformer for Ophthalmic Report Generation [pdf]
  • [Nature Machine Intelligence 2022] Generalized Radiograph Representation Learning via Cross-supervision between Images and Free-text Radiology Reports [pdf] [code]
  • [MICCAI 2022] A Self-Guided Framework for Radiology Report Generation [pdf]
  • [MICCAI 2022] A Medical Semantic-Assisted Transformer for Radiographic Report Generation [pdf]
  • [MIDL 2022] Representative Image Feature Extraction via Contrastive Learning Pretraining for Chest X-ray Report Generation [pdf]
  • [MICCAI 2022] RepsNet: Combining Vision with Language for Automated Medical Reports [pdf] [code]
  • [ICML 2022] Improving Radiology Report Generation Systems by Removing Hallucinated References to Non-existent Priors [pdf]
  • [TNNLS 2022] Hybrid Reinforced Medical Report Generation with M-Linear Attention and Repetition Penalty [pdf]
  • [MedIA 2022] CAMANet: Class Activation Map Guided Attention Network for Radiology Report Generation [pdf]
  • [MedIA 2022] Knowledge matters: Chest radiology report generation with general and specific knowledge [pdf] [code]
  • [MICCAI 2022] Lesion Guided Explainable Few Weak-shot Medical Report Generation [pdf] [code]
  • [BMVC 2022] On the Importance of Image Encoding in

编辑推荐精选

AEE

AEE

AI Excel全自动制表工具

AEE 在线 AI 全自动 Excel 编辑器,提供智能录入、自动公式、数据整理、图表生成等功能,高效处理 Excel 任务,提升办公效率。支持自动高亮数据、批量计算、不规则数据录入,适用于企业、教育、金融等多场景。

UI-TARS-desktop

UI-TARS-desktop

基于 UI-TARS 视觉语言模型的桌面应用,可通过自然语言控制计算机进行多模态操作。

UI-TARS-desktop 是一款功能强大的桌面应用,基于 UI-TARS(视觉语言模型)构建。它具备自然语言控制、截图与视觉识别、精确的鼠标键盘控制等功能,支持跨平台使用(Windows/MacOS),能提供实时反馈和状态显示,且数据完全本地处理,保障隐私安全。该应用集成了多种大语言模型和搜索方式,还可进行文件系统操作。适用于需要智能交互和自动化任务的场景,如信息检索、文件管理等。其提供了详细的文档,包括快速启动、部署、贡献指南和 SDK 使用说明等,方便开发者使用和扩展。

Wan2.1

Wan2.1

开源且先进的大规模视频生成模型项目

Wan2.1 是一个开源且先进的大规模视频生成模型项目,支持文本到图像、文本到视频、图像到视频等多种生成任务。它具备丰富的配置选项,可调整分辨率、扩散步数等参数,还能对提示词进行增强。使用了多种先进技术和工具,在视频和图像生成领域具有广泛应用前景,适合研究人员和开发者使用。

爱图表

爱图表

全流程 AI 驱动的数据可视化工具,助力用户轻松创作高颜值图表

爱图表(aitubiao.com)就是AI图表,是由镝数科技推出的一款创新型智能数据可视化平台,专注于为用户提供便捷的图表生成、数据分析和报告撰写服务。爱图表是中国首个在图表场景接入DeepSeek的产品。通过接入前沿的DeepSeek系列AI模型,爱图表结合强大的数据处理能力与智能化功能,致力于帮助职场人士高效处理和表达数据,提升工作效率和报告质量。

Qwen2.5-VL

Qwen2.5-VL

一款强大的视觉语言模型,支持图像和视频输入

Qwen2.5-VL 是一款强大的视觉语言模型,支持图像和视频输入,可用于多种场景,如商品特点总结、图像文字识别等。项目提供了 OpenAI API 服务、Web UI 示例等部署方式,还包含了视觉处理工具,有助于开发者快速集成和使用,提升工作效率。

HunyuanVideo

HunyuanVideo

HunyuanVideo 是一个可基于文本生成高质量图像和视频的项目。

HunyuanVideo 是一个专注于文本到图像及视频生成的项目。它具备强大的视频生成能力,支持多种分辨率和视频长度选择,能根据用户输入的文本生成逼真的图像和视频。使用先进的技术架构和算法,可灵活调整生成参数,满足不同场景的需求,是文本生成图像视频领域的优质工具。

WebUI for Browser Use

WebUI for Browser Use

一个基于 Gradio 构建的 WebUI,支持与浏览器智能体进行便捷交互。

WebUI for Browser Use 是一个强大的项目,它集成了多种大型语言模型,支持自定义浏览器使用,具备持久化浏览器会话等功能。用户可以通过简洁友好的界面轻松控制浏览器智能体完成各类任务,无论是数据提取、网页导航还是表单填写等操作都能高效实现,有利于提高工作效率和获取信息的便捷性。该项目适合开发者、研究人员以及需要自动化浏览器操作的人群使用,在 SEO 优化方面,其关键词涵盖浏览器使用、WebUI、大型语言模型集成等,有助于提高网页在搜索引擎中的曝光度。

xiaozhi-esp32

xiaozhi-esp32

基于 ESP32 的小智 AI 开发项目,支持多种网络连接与协议,实现语音交互等功能。

xiaozhi-esp32 是一个极具创新性的基于 ESP32 的开发项目,专注于人工智能语音交互领域。项目涵盖了丰富的功能,如网络连接、OTA 升级、设备激活等,同时支持多种语言。无论是开发爱好者还是专业开发者,都能借助该项目快速搭建起高效的 AI 语音交互系统,为智能设备开发提供强大助力。

olmocr

olmocr

一个用于 OCR 的项目,支持多种模型和服务器进行 PDF 到 Markdown 的转换,并提供测试和报告功能。

olmocr 是一个专注于光学字符识别(OCR)的 Python 项目,由 Allen Institute for Artificial Intelligence 开发。它支持多种模型和服务器,如 vllm、sglang、OpenAI 等,可将 PDF 文件的页面转换为 Markdown 格式。项目还提供了测试框架和 HTML 报告生成功能,方便用户对 OCR 结果进行评估和分析。适用于科研、文档处理等领域,有助于提高工作效率和准确性。

飞书多维表格

飞书多维表格

飞书多维表格 ×DeepSeek R1 满血版

飞书多维表格联合 DeepSeek R1 模型,提供 AI 自动化解决方案,支持批量写作、数据分析、跨模态处理等功能,适用于电商、短视频、影视创作等场景,提升企业生产力与创作效率。关键词:飞书多维表格、DeepSeek R1、AI 自动化、批量处理、企业协同工具。

下拉加载更多