数据集导航

医疗数据集导航 - 全部数据集（第 163 页）

汇集 20 大疾病系统 5035 个医疗数据集，支持搜索与分类筛选，助力医疗AI研发选型

共 5035 个数据集 · 第 163 / 168 页
数据集名称 系统分类 病种 数据模态 任务类型 描述 来源 原始地址 操作
Derm1M医学文本与大模型多模态皮肤病分类1029761 image-text pairs aligned with clinical ontology knowledge for dermatology, ICCV 2025GitHubhttps://arxiv.org/pdf/2503.14911访问
GEMeX呼吸道疾病多模态胸部X光问答151025 images and 1605575 QA, large-scale groundable explainable medical VQA for chest X-ray diagnosis ICCV 2025Hugging Facehttps://arxiv.org/pdf/2411.16778访问
Surg-396K医学文本与大模型多模态手术问答41400 images from EndoVis/CoPESD/Cholec80, 396000 image-text pairs, 5 dialogue types, 7 surgical tasks 2025GitHubhttps://arxiv.org/abs/2501.11347访问
AbdomenAtlas 3.0消化系统疾病多模态腹部CT报告生成9262 3D CT scans with paired reports, 8562 tumor instances, 3D abdominal CT report generation/tumor segmentation ICCV 20GitHubhttps://arxiv.org/pdf/2501.04678访问
HuatuoGPT-o1 Dataset医学文本与大模型文本医学推理40K medically verified complex reasoning questions based on MedQA-USMLE and MedMCQA 2024GitHubhttps://arxiv.org/pdf/2412.18925访问
PubMedVision眼病多模态视觉问答1.3M VQA samples from 915K PubMed medical images, medical visual knowledge injection 2024Hugging Facehttps://arxiv.org/abs/2406.19280访问
PMC-VQA眼病多模态视觉问答226946 QA pairs, visual instruction tuning for medical VQA 2024Hugging Facehttps://huggingface.co/datasets/RadGenome/PMC-VQA访问
VQARad眼病多模态视觉问答315 images, 3515 QA, radiology visual question answering 2023OSFhttps://osf.io/89kps/访问
Asclepius医学文本与大模型多模态视觉问答3232 QA pairs, 15 medical specialties, 3 categories 8 sub-categories clinical tasks, spectrum evaluation ACL 2025GitHubhttps://arxiv.org/abs/2402.11217访问
HLS-CMDS Heart and Lung Sounds Dataset心血管系统疾病音频心肺音分类Heart and Lung Sounds Dataset Recorded from a Clinical Manikin using Digital Stethoscope 2025UCIhttp://archive.ics.uci.edu/dataset/1202/hls-cmds:+heart+and+lung+sounds+dataset+recorded+from+a+cli访问
RecGym Gym Workouts Recognition Dataset通用医学数据集运动识别Gym workouts with IMU and Capacitive sensors, 10 volunteers, fitness recommendation 2025UCIhttps://www.archive.ics.uci.edu/dataset/1128/recgym访问
BEED Bangalore EEG Epilepsy Dataset神经系统疾病癫痫检测Comprehensive EEG collection for epileptic seizure detection, 256Hz, 10-20 system, 8K instances 2024UCIhttps://archive-beta.ics.uci.edu/访问
Neurofibromatosis Type 1 Clinical Symptoms医学文本与大模型疾病分类National NF1 database with 331 probands with tumors, familial and sporadic casesUCIhttps://www.archive.ics.uci.edu/datasets?Keywords=diagnosis访问
Visible Human Project通用医学数据集解剖图谱Complete, anatomically detailed, 3D representations of human male and female bodies, NLMdata.govhttps://www.nlm.nih.gov/research/visible/visible_human.html访问
PLACES Local Data for Better Health Place Data 2024通用医学数据集公共卫生CDC PLACES local health data, place-level estimates for 2024 releasedata.govhttps://catalog.data.gov/dataset/places-local-data-for-better-health-place-data-2024-release-88989访问
BIOMEDICA Index眼病多模态生物医学检索Large-scale vision-language dataset from open scientific literature, hybrid vector-text database for biomedical generaliarXivhttps://arxiv.org/html/2503.22727v1访问
TITAN医学文本与大模型病理图像病理分类Published in Nature Medicine, TCGA-UT-8K pathology ROI classification benchmark, foundation model for computational pathGitHubhttps://github.com/mahmoodlab/TITAN访问
TCGA-UT-8K医学文本与大模型病理图像病理分类Pathology ROI classification benchmark released with TITAN, Nature Medicine 2025GitHubhttps://github.com/mahmoodlab/TITAN访问
CT-RATE呼吸道疾病CT异常分类25,692 non-contrast chest CT volumes expanded to 50,188, 21,304 patients, radiology reports, multi-abnormality labelsHugging Facehttps://huggingface.co/datasets/ibrahimhamamci/CT-RATE访问
BCNB Early Breast Cancer Core-Needle Biopsy WSI肿瘤病理图像乳腺癌研究1058 WSIs with clinical characteristics, tumor regions annotated, breast cancer core-needle biopsyGitHubhttps://bupt-ai-cz.github.io/BCNB/访问
BCI Breast Cancer Immunohistochemical Image Generation神经系统疾病病理图像图像转换4870 registered HE-IHC image pairs, four HER2 expression levelsGitHubhttps://bupt-ai-cz.github.io/BCI/访问
MultiModel Breast Cancer MSI Dataset肿瘤乳腺癌分类MultiModel Breast Cancer MSI Dataset 2025Kagglehttps://www.kaggle.com/datasets/vishwamalani/breast-cancer-dataset访问
LUNA25 Lung Nodule Analysis 2025呼吸道疾病CT肺结节分割Chest CT scans (MHA format), CSV files with lesion center coordinates, point-prompted segmentation 2025Grand Challengehttps://deepwiki.com/bowang-lab/MedSAM2/4.1-medical-imaging-datasets访问
ISIC 2020 SIIM-ISIC Melanoma皮肤与结缔组织疾病黑色素瘤检测~33,000 dermoscopic images, benign/malignant binary classificationKagglehttps://www.kaggle.com/c/siim-isic-melanoma-classification访问
HCC-TACE-Seg消化系统疾病CT肝癌分割HCC patients pre-TACE CT, tumour + liver segmentationTCIAhttps://www.cancerimagingarchive.net/collection/hcc-tace-seg/访问
Multi-phase CT liver-tumor differential diagnosis消化系统疾病CT肝肿瘤鉴别Multi-phase CT, multi-class liver tumors with diagnosis labels 2025Nature Sci Datahttps://www.nature.com/articles/s41597-025-06343-4访问
Lung-PET-CT-Dx呼吸道疾病肺癌诊断355 subjects, CT + PET/CT DICOM, tumour bounding boxes + clinical dataTCIAhttps://www.cancerimagingarchive.net/collection/lung-pet-ct-dx/访问
RSNA 2023 Screening Mammography肿瘤乳腺癌筛查~54k FFDM DICOM images, Australia + US, cancer label + path follow-up 2023Kaggle/RSNAhttps://www.rsna.org/artificial-intelligence/ai-image-challenge/screening-mammography-breast-cancer-detection-ai-challenge访问
VinDr-Mammo通用医学数据集乳腺病变检测5,000 four-view FFDM exams, BI-RADS + lesion annotations 2023PhysioNethttps://www.nature.com/articles/s41597-023-02100-7访问
PolypGen消化系统疾病息肉分割1,537 images + 2,225 seq + 4,275 neg frames, pixel-level polyp masks, 6 centres 2023GitHubhttps://github.com/DebeshJha/PolypGen访问