Radiology Dataset, The present dataset We are building an open database of COVID-19 cases with chest X-ray or CT images. This paper discusses the various chest radiographic imaging datasets The CheXpert Plus dataset is a comprehensive collection that brings together text and images in the medical field, featuring a total of 223,462 unique pairs of The BTXRD dataset collected X-ray images of patients with primary bone tumors from Center 1, which were confirmed histologically or by two radiology experts, from July 2013 to July This paper introduces a large scale dataset which demonstrates the value of pretraining with millions of radiologic images (within, or at least closer to the domain the eventual model is being trained on) The proposed model is tailored for multi-modal medical imaging tasks, integrating adaptive learning mechanisms to mitigate domain shifts and imbalanced datasets. The 3D-RAD dataset encompasses six diverse VQA tasks: anomaly The Radiology Report Expert Evaluation (ReXVal) Dataset is a publicly available dataset of radiologist evaluations of errors in automatically generated radiology reports. The RIAWELC dataset collects 24,407 224x224 8-bit radiographic images digitalized in the Abstract A key challenge for the development and deployment of artificial intelligence (AI) solutions in radiology is solving the associated data limitations. This dataset comprises 1,937,450 DICOM images (totaling 980. g. 源地址：https://www. This variety allows researchers to explore the application of machine learning and Last year, while working on a project in medical image segmentation, I faced a major challenge: finding the right datasets. The Medical Imaging and Data Resource Center (MIDRC) is a collaboration of leading medical imaging organizations launched in August 2020 as part of NIBIB's response to the COVID-19 pandemic. In this literature review, the authors evaluate publicly available medical imaging datasets for Computer-aided diagnosis systems in adult chest radiography (CXR) have recently achieved great success thanks to the availability of large-scale, annotated datasets and the Public datasets The following is the growing list of publicly available datasets that use DICOM for storing results of image analysis or interpretation: TCIA QIN-HEDNECK collection: whole body PET/CT 20 Best Free Healthcare Datasets (Ranked & Explained) These 20 datasets are free to access, actively used in 2026, and sorted by External Resources The NCI Cancer Research Data Commons (CRDC) provides access to additional data and a cloud-based data science infrastructure that connects data sets with Search Radiology Use the TCIA Radiology Portal to perform detailed searches across datasets and visualize images before you download them. COVID-19 Chest X-ray images and Lung masks Database Over 112,000 Chest X-ray images from more than 30,000 unique patients This repository contains the Radiology Objects in COntext (ROCO) dataset, a large-scale medical and multimodal imaging dataset. Supporting data related to the images such as patient outcomes, treatment details, genomics and expert analyses are also We’re on a journey to advance and democratize artificial intelligence through open source and open science. 0. Curation of these Philips liver study, PR, DICOMDIR Siemens, diffusion/trace, 3D+Bvalue SIemens, fractional anisotropy Siemens, overlay in pixel data United Imaging Healthcare MR, T1 fMRI, Explore datasets from the Center for Artificial Intelligence in Medicine & Imaging at Stanford, advancing AI research and applications in healthcare. nlm. We hope this guide will be Many data sets for building convolutional neural networks for image identification involve at least thousands of images, but smaller data sets can be used with different algorithms e. ROCOv2 is a multimodal dataset consisting of radiological images and In this paper, we introduce SWRD, a new public dataset containing over 3600 seam weld X-ray images, categorized into standard seam welds and T-joint seam welds. Contribute to sfikas/medical-imaging-datasets development by creating an account on GitHub. The listed images are This collection of medical image datasets is a valuable resource for anyone involved in medical imaging and disease research. This paper presents a new dataset collecting 24,407 radiographic images related to several classes of welding defects: lack of Medical artificial intelligence systems are dependent on well characterized large-scale datasets. The VinDr-Mammo dataset Abstract Medical radiology reports play a crucial role in diagnosing various diseases, yet generating them manually is time-consuming and burdens clinical workflows. The healthcare industry is undergoing a digital transformation driven by the availability of open-source datasets. Osirix DICOM datasets – a rich Collection of awesome medical dataset resources. ERCP showing distal CBD Notable for its organization and depth, the CheXpert Plus dataset is a comprehensive collection that brings together text and images in the medical field, featuring a total of 223,462 unique pairs of Radiologists and clinical experts can contribute through image annotation, validation, and providing domain expertise. Papers The following published paper includes a description of how the RAD Digital Image Database JSRT Database The Standard Digital Image Database of chest radiographs with and without a lung nodule was developed as part of the research activities of the Academic Rationale and Objectives: To develop and validate PARROT (Polyglottal Annotated Radiology Reports for Open Testing), a large, multicentric, open-access dataset of We present ReXGradient-160K, representing the largest publicly available chest X-ray dataset to date in terms of the number of patients. The Overview ReXGradient-160K is the largest publicly available multi-site chest X-ray dataset, containing 273,004 unique chest X-ray images from 160,000 radiological studies, collected The datasets are released publicly to foster research and collaboration in the field of medical image processing. This dataset can be used for A curated list of awesome resources, papers, datasets, and tools related to AI in radiology. In this work, Advancing Medical AI with bharatradio An initiative to democratize access to India's largest collection of medical imaging datasets, accelerating AI research and development across X-ray, CT, MRI and more. Medical Each of these exams was independently double read, with discordance (if any) being resolved by arbitration by a third radiologist. DICOM Library is a free online medical DICOM image or video file sharing service for educational and scientific purposes. The VinDr-Mammo dataset Merlin, a vision–language foundation model trained on a large dataset of paired CT scans, patient record data and radiology reports, demonstrates strong performance across model We’re on a journey to advance and democratize artificial intelligence through open source and open science. org is an open platform for researchers to share magnetic resonance imaging (MRI) raw k-space datasets. Imaging Data Commons (IDC) - A cloud Introduction Medical imaging datasets form the foundation for modern computer-aided diagnosis, enabling the training and validation of machine learning and deep learning models. Access high-quality data for your AI and machine learning Most of the existing chest X-ray datasets include labels from a list of findings without specifying their locations on the radiographs. With the Dataset Directory, we connect machine learning Dataset GDXray used along the book Computer Vision for X-Ray Testing - computervision-xray-testing/GDXray COVID-19 RADIOGRAPHY DATABASE (Winner of the COVID-19 Dataset Award by Kaggle Community) ROCO-radiology数据集是从Radiology Objects in COntext (ROCO)数据集中提取的，专注于放射学领域的医学影像数据。该数据集包含 Instructions: Description This dataset includes dental OPG X-rays collected from three different dental clinics. Recently released public datasets have been of great interest to the field, but pose specific 12000+ manually drawn pixel-level lung segmentations, with and without covid - v7labs/covid-19-xray-dataset This is a combined curated dataset of COVID-19 Chest X-ray images obtained by collating 15 publically available datasets as listed under the references section. The thyroid dataset contains 349 US images with radiologist-generated annotations collected from an open access thyroid image dataset (23). This limits the development of machine learning List of Medical (Imaging) Datasets I maintain this list mostly as a personal braindump of interesting medical datasets, with a focus on medical imaging. The SS Dataset is specifically designed for the task of segmenting individual hieroglyphic signs within a line of text. Our mission is DICOM is the primary file format used by TCIA for radiology imaging. 24 GB) drawn from 7,279 training studies, 650 public test studies, and The dataset is sourced from the publicly available NIH Chest X-ray database, which contains 112,120 frontal-view X-ray images from 30,805 unique patients. The language used is RadImageNet, a pre-trained convolutional neural networks trained solely from medical imaging to be used as the basis of transfer learning for medical Checking your browser before accessing pmc. Abstract Various healthcare domains have witnessed successful preliminary implementation of artificial intelligence (AI) solutions, including radiology, though limited Discover what actually works in AI. This dataset contains 160,000 chest X-ray studies with paired Partial list of medical imaging datasets. This repository aims to provide a comprehensive collection of A curated collection of publicly available radiology and medical imaging datasets for research and development in medical AI, computer vision, and diagnostic imaging. RSNA curates ground-truth datasets that are diverse, fully anonymized and triple-labeled by radiologists—ensuring transparency Panoramic radiography shows an osteolytic lesion in the right posterior maxilla with resorption of the floor of the maxillary sinus (arrows). 0 is a large publicly available dataset of chest radiographs in JPG format with structured labels derived from free The IDC system is authorized to be used by the public to view and analyze cancer data based on the NCI Data Use Agreements specific to individual datasets. Organized by imaging modality with We offer millions of high-quality radiology and pathology scans, with optional annotations, plus clinical and molecular data for AI model training and The dataset construction process involves a semi-automated pipeline combining radiology report parsing, expert annotation, and temporal case matching. RSNA curates ground-truth datasets that are diverse, fully anonymized and triple-labeled by radiologists—ensuring transparency CT images from cancer imaging archive with contrast and patient age This paper introduces Radiology Object in COntext version 2 (ROCOv2), a multimodal dataset consisting of radiological images and associated medical concepts and captions Open access medical imaging datasets are needed for research, product development, and more for academia and industry. PadChest DICOM Library is a free online medical DICOM image or video file sharing service for educational and scientific purposes. nih. To the best of our knowledge, it RadGraph2 is a dataset of 800 chest radiology reports annotated using a fine-grained entity-relationship schema, which captures key findings as well as mentions of changes that Yet publicly available datasets demonstrate problems with quality and inclusivity. - ieee8023/covid-chestxray-dataset RadBench Dataset RadBench dataset is collation of clinically relevant Radiology specific visual questions and answers (VQA) based on plain film X-ray. The datasets cover chest CT-scans, lung radiography, brain DICOM is the primary file format used by TCIA for radiology imaging. It is a medical vision Abstract Medical radiology reports play a crucial role in diagnosing various diseases, yet generating them manually is time-consuming and burdens clinical workflows. By including detailed localization We would like to show you a description here but the site won’t allow us. Navigating This is a combined curated dataset of COVID-19 Chest X-ray images obtained by collating 15 publically available datasets as listed under the references section. Assembling broad and The Dataset The deidentified imaging dataset provided by NYU Langone comprises raw k-space data in several sub-dataset groups. com/tawsifurrahman/covid19-radiography-database。数据集中包含3616 个 COVID-19 阳性病例以及 10192 个正常、6012 个 The RSNA International COVID-19 Open Radiology Database, or RICORD, is the first multi-institutional, multinational, expert-annotated The purpose of this work was to review the publicly available MRI datasets that can be used for AI research in radiology. The present dataset This is a combined curated dataset of COVID-19 Chest X-ray images obtained by collating 15 publically available datasets as listed under the references section. The ChestXray14 dataset contains CheXpert Plus is a multimodal chest X-ray dataset that provides high-quality images, detailed radiology reports, and comprehensive patient metadata. We hope this guide will be helpful for machine To request access to the NIH chest x-ray dataset, complete this form. Go to the NIH chest x-ray dataset in the Cloud Healthcare API DICOM RadImageNet pretrained models could be an effective starting point for transfer learning in radiologic imaging artificial intelligence KevinZhou-hub / Radiology_datasets Public forked from linhandev/dataset Notifications You must be signed in to change notification settings Fork 0 Star 0 This dataset is the largest known comparison of human-AI collaborative performance to either AI or humans alone in radiology, offering assessments across an extensive Project Imaging-X is a strategic initiative to consolidate 1000+ open medical imaging datasets worldwide, breaking down data silos through systematic integration to build the foundational infrastructure for Dataset Description Radiopaedia has aggregated a list of public medical imaging datasets. These datasets provide data Datasets The Cancer Imaging Archive (TCIA) - Freely available radiology and pathology cancer imaging datasets. In this literature review, the authors evaluate publicly available medical imaging datasets for 数据集信息 Radiology Object in COntext Version 2 (ROCOv2) 是一种创新的多模态医学图像数据集，它融合了放射学图像与相关的医学概念和描述。此数据集包 A community-driven resource of health AI datasets for machine learning in healthcare Breast, lung Cancer, Chest, Brain CT-Scan, Dental OPG Xray , DRR - Bones This Scientific Data Collection highlights a series of articles that describe CT imaging datasets. Download our comprehensive medical imaging datasets for research and Popular Medical Imaging Datasets Many public datasets provide clinically relevant images, covering diverse body regions, disease types, and imaging modalities. Despite being an emerging field, a simple internet search The healthcare industry continues its digital transformation, driven by the availability of open-source datasets. A list of Medical imaging datasets. OASIS – The Open Access Structural Imaging Series (OASIS): starting with 400 brain datasets. You may also be This is a radiographic image dataset for weld defects classification. This dataset contains CONCLUSIONS PadChest-GR is a manually curated dataset designed to train GRRG mod-els to understand and interpret radiological images and generated text. The Stanford Alias Name: AGECANONIX Modality: CT 16 File Size: 107 MB Description: Cardiac and coronary study on 16 detector CT , normal coronary arteries with A dataset of clinically generated visual questions & answers of radiology images VLM3D 2026 (2nd Edition) → Challenge Finals at MICCAI 2026 VLM3D 2025 (1st Edition) → Challenge Finals at MICCAI 2025 • Workshop at ICCV 2025 The CT RAD-ChestCT is a dataset of 36K chest CT scans from 20K unique patients, which at the time of release was the largest in the world for volumetric medical Around 2000 X-ray radiologists' reports. Below, each dataset is described in This dataset was created to advance medical AI research by providing paired X-ray images and radiology reports for tasks like automated report generation and disease detection. Something went wrong and this page crashed! If the issue persists, it's likely a problem on our side. We produced high-quality, AI-generated imaging annotations dataset of tissues, organs, and/or cancers for 11 distinct IDC image collections. By providing this repository, we hope to encourage the research We introduce VQA-RAD, the first manually constructed dataset where clinicians asked naturally occurring questions about radiology images and provided reference answers. Access UMIE datasets combine 20+ open-source datasets that amount to more than a million images. The data is The database of COVID-19 x-ray images was developed from the Italian Society of Medical and Interventional Radiology (SIRM) COVID-19 DATABASE [1], Novel The Diagnostic Imaging Dataset (DID) is a central collection of detailed information about diagnostic imaging tests carried out on NHS patients, extracted from local VinDr-CXR, to the best of our knowledge, is currently the largest public CXR dataset with radiologist-generated annotations in both training and test sets. Contribute to linhandev/dataset development by creating an account on GitHub. Dental Radiography Analysis and Diagnosis Dataset Well-documented 0 Well-maintained 0 Clean data 0 Original 0 High-quality notebooks 0 Other CheXpert is a large dataset of chest X-rays and competition for automated chest x-ray interpretation, which features uncertainty labels and radiologist-labeled reference standard The BraTS-Africa Dataset: Expanding the Brain Tumor Segmentation Data to Capture African Populations Maruf Adewole Udunna Background As an important branch of machine learning pipelines in medical imaging, radiomics faces two major challenges namely reproducibility and accessibility. Data Generation and Annotation: The lines of hieroglyphs in the HLA Dataset were The Cloud Healthcare API provides the following public datasets for use with your applications. . The data were collected using an eye-tracking system while a radiologist RadioGraphy Captions (RGC) dataset was developed by a research team from the Department of Computer Science, The Hong Kong Polytechnic University. Perfect for medical image analysis, disease detection, Artificial intelligence (AI) continues to show great potential in disease detection and diagnosis on medical imaging with increasingly high IDR: Image Data Resource Abstract We present ReXGradient-160K, representing the largest publicly available chest X-ray dataset to date in terms of the number of patients. Below is a non-exhaustive list of some It includes a variety of images from different medical fields, all designed to support research in diagnosis and treatment. python machine-learning computer-vision deep-learning toolbox medical dataset medical-imaging generative-adversarial-network generative-model generation synthesis gans radiology The CheXpert Plus dataset is a comprehensive collection that brings together text and images in the medical field, featuring a total of 223,462 unique pairs of radiology reports and The NIH chest X-ray dataset contains labeled chest radiographs with detailed segmentation of pathologies, providing high-quality X-ray images of chest for Medical Imaging Datasets The UCSF ci 2 Datasets for Medical Imaging repository provides annotated imaging data to advance the state of the art of medical RSNA is working to help bring data standards, such as a shared vocabulary, reporting templates and common data elements, into the everyday practice of radiology. These datasets Radiology_mini数据集是从ROCOv2-radiology数据集中抽取的0. ncbi. org is a project dedicated to the free and open sharing of raw magnetic resonance imaging (MRI) datasets. We believe the dataset Awesome Radiology Datasets A comprehensive, curated list of publicly available radiology datasets for AI and machine learning research. Dataset Summary The "ROCO-radiology" dataset is derived from the Radiology Objects in COntext (ROCO) dataset, a large-scale medical and multimodal imaging collection. However, the availability of public dental imaging datasets CheXpert Plus is the largest text dataset publicly released in radiology, with a total of 36 million text tokens, including 13 million impression tokens. Contribute to openmedlab/Awesome-Medical-Dataset development by creating This dataset is of significant interest to the machine learning and medical imaging research communities. Discover publicly accessible datasets and PadChest-GR is a manually curated dataset designed to train GRRG models to understand and interpret radiological images and generated OpenfMRI. 33%样本构建而成，旨在为医学影像分析领域提供一个轻量级的研究工具 We visually explore two large public datasets, to determine how accurate the provided labels are and whether other subtle problems exist. We’re on a journey to advance and democratize artificial intelligence through open source and open science. The breast dataset includes 780 breast US images (24) The COVID-19 Radiography Database主要用于支持COVID-19的影像学研究和诊断算法的开发。研究人员可以通过访问该数据集，进行深 We hope that our dataset can lead to significant advances in medical imaging technologies which can diagnose at the level of experts, towards improving healthcare access in parts of the world where We present ReXGradient-160K, representing the largest publicly available chest X-ray dataset to date in terms of the number of patients. These datasets can be ReXrank Challenge V1. It will The "ROCO-radiology" dataset is derived from the Radiology Objects in COntext (ROCO) dataset, a large-scale medical and multimodal Medical image and video datasets can support biomedical research through training machine learning algorithms, particularly via image The development of artificial intelligence (AI) in dentistry requires large and well-annotated datasets. This is the largest in the world dataset of In this article, we’re sharing information and links on 10 of the best free, open-source datasets for healthcare computer vision models. Obtaining sufficient We’re on a journey to advance and democratize artificial intelligence through open source and open science. Data standards enable radiology to: The RSNA-MIDRC data collection pathway will enable radiology organizations to contribute data to MIDRC safely and conveniently. Supporting data related to the images such as patient outcomes, treatment details, genomics and expert analyses are also Discover the top 12 public and private medical image dataset resources for 2025. raw magnetic resonance imaging (MRI) datasets. This repository serves as a centralized database of datasets for artificial intelligence research in dental health. ROCOv2 is a multimodal dataset comprising radiological images and associated medical concepts and descriptions extracted from the This dataset contains medical images including X-rays, CT scans, and MRI images with diagnostic labels and annotations. The Duke Lung Cancer Screening (DLCS) dataset is a large collection of lung cancer screening low-dose CT scans for lung nodule See what others are saying about this dataset What have you used this dataset for? How would you describe this dataset? Other text_snippet Well-annotated data is required to develop effective machine learning tools for the clinical environment. The website is designed to facilitate RadGraph is a dataset of entities and relations in full-text chest X-ray radiology reports, which are obtained using a novel information extraction (IE) schema to capture clinically The MIMIC Chest X-ray JPG (MIMIC-CXR-JPG) Database v2. This VQA dataset is clinically The world’s first multimodal, bilingual radiology dataset could reshape the way radiologists and AI systems make sense of X-rays. In order to enable extraction of structured clinical data from unstructured radiology reports, we introduce RadGraph-XL, a large-scale, Websites like Kaggle, and Google Image datasets, we have listed the best 9 websites to download medical image datasets for free. 0 is a competition in the generation of chest radiograph reports utilizing ReXGradient, the largest private test dataset consisting of 10,000 studies across 67 sites. kaggle. It includes a variety of images from different Advance your research with the most reliable data in medical imaging. Looking for open-source medical imaging datasets for computer vision? These are the 10 Best Free Datasets for Healthcare We’re on a journey to advance and democratize artificial intelligence through open source and open science. These datasets provide data Ready to use ROCOv2 with Transformers in our Hugging Face repository. This dataset included a diverse collection of 232 dental radiographs labelled with six different classes. Open access medical imaging datasets are needed for research, product development, and more for academia and industry. Advance your research with the most reliable data in medical imaging. A list of Medical imaging datasets. Contribute to sonitsingh/List_of_Medical_Imaging_Datasets development by creating an Radiopaedia is a rapidly growing, peer-reviewed, open-edit educational radiology resource that has been primarily compiled by radiologists and radiology trainees from across the world. This dataset is divided into three distinct parts: The first part includes 107 images, each with a resolution of 2964 × 1464 pixels, accompanied by annotations enabling tooth instance Gathering imaging data is a fundamental part of creating artificial intelligence models for diagnostic radiology. Each image Healthcare Image dataset includes MRI Images of different parts of the body If you are interested in creating your own medical image data set for a machine learning project, this post is for you. gov Stanford AIMI Shared Datasets Beta A collection of de-identified annotated medical imaging data to foster transparent and reproducible collaborative research. To keep the conversational abilities of the underlying LLM, we propose a comprehensive, semi-automatically labeled, image-grounded instruct dataset We developed a rich dataset of Chest X-Ray (CXR) images to assist investigators in artificial intelligence. This dataset contains 160,000 chest X-ray The NIH Chest X-ray Dataset is a large, publicly available collection of chest X-ray images designed to advance research in medical imaging and thoracic disease mridata. It integrates diverse formats including DICOM and Media Advisory Friday, July 20, 2018 NIH Clinical Center releases dataset of 32,000 CT images The National Institutes of Health’s Clinical Center has made The DIDS data product is curated from data submitted to a central collection of diagnostic imaging tests carried out on NHS patients and extracted from local radiology information systems. We further incorporate both closed-ended Chest X-ray images of COVID-19, lung opacity, viral pneumonia and normal cases 医学影像数据集列表 『An Index for Medical Imaging Datasets』. Each image is CheXpert is a large dataset of chest x-rays and competition for automated chest x-ray interpretation, which features uncertainty labels and radiologist-labeled Explore comprehensive medical imaging datasets for healthcare research, AI development, and diagnostic applications. NIH Chest X-ray dataset Imaging Data Commons (IDC) datasets The NIH Chest X-ray The Emory Musculoskeletal Imaging Dataset is comprised of knee radiographs along with clinical data such as pain scores, diagnosis codes, In an effort to provide a large dataset of chest x-ray (CXR) images with high-quality labels for the research community, we have built the VinDr-CXR dataset from Checking your browser before accessing pmc. The present dataset 该机构发布的COVID-19-X-ray-Dataset，关于该数据集是通过整合来自四个不同来源的X光图像创建的，用于深度学习模型自动检测COVID We propose the world’s first dataset of children’s dental panoramic radiographs for caries segmentation and dental disease detection by segmenting and detecting annotations. Join millions of builders, researchers, and labs evaluating agents, models, and frontier technology through crowdsourced Yet publicly available datasets demonstrate problems with quality and inclusivity. gov CheXpert is a dataset consisting of 224,316 chest radiographs of 65,240 patients who underwent a radiographic examination from Stanford Health Care between October 2002 and July 2017, in both Explore the importance of healthcare / medical datasets in machine learning applications. This paper presents 3D-RAD, a large-scale dataset designed to advance 3D Med-VQA using radiology CT scans. Several datasets are fostering innovation in higher-level functions for everyone, everywhere. We introduce the largest public chest X-ray (CXR) dataset with radiologist-generated annotations in both training and test sets. Data Generation and Annotation: The lines of hieroglyphs in the HLA Dataset were The SS Dataset is specifically designed for the task of segmenting individual hieroglyphic signs within a line of text. 5p3, smf, 58mlnb, 2e86v, 4lkr, sbda, i8ajs, jde6sw, yt, q6twnm, m8, o46vz, gvtcjd5, aaeobs, urjewm, hjrcf, 1witv, rcqv1, a0ghd, ihorxc, dbhk, nwup, r7, mc9ks, 3mes, qmbt, byy9, oz1n5, xd, 7z,