datasets
Training and evaluation data, with the modality, task and licence stated up front. Listed live from the Hugging Face Hub.
KiTS-Challenge-ImagingGuided-Lensless-Polarization-Imaging-stageI
Stage I reconstructions for evaluation (UPLight & ZJU-RGB-P)
This dataset accompanies Guided Lensless Polarization Imaging (CVPR 2026 Findings). It provides FISTA Stage-I outputs, RGB guidance images, and ground-truth polarization stacks for two public evaluation sets used in the paper.
Layout
UPLight (~1,991 scenes)
Folder
Description
UPLight/fista_grayscale/
3-channel grayscale polarization FISTA reconstructions
UPLight/fista_color/… See the full description on the dataset page: https://huggingface.co/datasets/noakraicer/Guided-Lensless-Polarization-Imaging-stageI.alive-medical-imaging
ALIVE Medical Imaging QA Dataset
Lecture-derived question-answer corpus, retrieval index, and source
materials for the ALIVE (Avatar-Lecture Interactive Video Engine)
system. The dataset was built from 23 recorded lectures of an
undergraduate medical imaging course and is the corpus used to
fine-tune the ALIVE language model and to evaluate its retrieval and
answer-generation behavior.
Layout
huggingface/
├── data/ question-answer pairs (Alpaca-style… See the full description on the dataset page: https://huggingface.co/datasets/zabir1996/alive-medical-imaging.imaging-101
Imaging-101: Benchmark Data & Fixtures
Observation data and evaluation fixtures for the Imaging-101 benchmark -- 57 expert-verified computational imaging tasks for evaluating LLM coding agents.
Paper: Imaging-101: Benchmarking LLM Agents for Scientific Computational Imaging Problems (ICCP 2026)
Website: starpacker.github.io/agent-imaging-website
GitHub: github.com/HeSunPU/imaging-101
What is in this dataset?
Directory
Contents
Format
tasks/<task>/data/… See the full description on the dataset page: https://huggingface.co/datasets/starpacker52/imaging-101.mimic-medical-imaging-qa
MIMIC Medical Imaging QA Dataset
5,207 Bloom's-taxonomy-stratified question--answer pairs derived from 23 medical imaging lectures (RPI BMED 2300). The dataset supports the paper "MIMIC: A Course-Derivation Pipeline and Benchmark for Slide-Anchored Tutoring with a Domain-Adapted Large Language Model" and was used to fine-tune MIMIC-LM, a domain-adapted Llama-3.1-8B-Instruct model for grounded medical imaging instruction.
License
The benchmark annotations, dataset… See the full description on the dataset page: https://huggingface.co/datasets/zabir1996/mimic-medical-imaging-qa.Project-Imaging-X
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 next-generation medical AI models.
Challenge: Medical imaging lacks large-scale unified datasets due to clinical expertise requirements and privacy constraints, limiting the development of powerful medical foundation models.
Solution: We surveyed 1000+… See the full description on the dataset page: https://huggingface.co/datasets/General-Medical-AI/Project-Imaging-X.Project-Imaging-X
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 next-generation medical AI models.
Challenge: Medical imaging lacks large-scale unified datasets due to clinical expertise requirements and privacy constraints, limiting the development of powerful medical foundation models.
Solution: We surveyed 1000+… See the full description on the dataset page: https://huggingface.co/datasets/Fadil369/Project-Imaging-X.medical-ehr-imagingGraptoloidea-Specimens-Imaging
Dataset Card for Graptoloidea Specimens Imaging
Dataset Summary
This dataset offers a detailed examination of Graptoloidea specimens, featuring attributes like image file paths, suborder, infraorder, family (including subfamily), tagged species names, geological stages, mean age values, and locality details (with coordinates and horizon information), complemented by original reference citations for each specimen. It serves as a comprehensive resource for paleontological… See the full description on the dataset page: https://huggingface.co/datasets/LeoZhangzaolin/Graptoloidea-Specimens-Imaging.Project-Imaging-X
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 next-generation medical AI models.
Challenge: Medical imaging lacks large-scale unified datasets due to clinical expertise requirements and privacy constraints, limiting the development of powerful medical foundation models.
Solution: We surveyed 1000+… See the full description on the dataset page: https://huggingface.co/datasets/lingcarzy/Project-Imaging-X.medical-imaging-combinedProject-Imaging-X
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 next-generation medical AI models.
Challenge: Medical imaging lacks large-scale unified datasets due to clinical expertise requirements and privacy constraints, limiting the development of powerful medical foundation models.
Solution: We surveyed 1000+… See the full description on the dataset page: https://huggingface.co/datasets/sunli1201/Project-Imaging-X.medical-imaging-combined
Combined Medical Imaging Dataset
Dataset Description
Combined medical imaging dataset with 6793 samples in Alpaca instruction format.
Dataset Statistics
Total Samples: 6793
Training Samples: 5434
Validation Samples: 1359
Modality Distribution
X-ray: 2691 samples
CT: 2257 samples
Unknown: 1329 samples
MRI: 369 samples
Ultrasound: 147 samples
Source Distribution
ROCO: 5000 samples
VQA-RAD: 1793 samples
Sources
ROCO… See the full description on the dataset page: https://huggingface.co/datasets/robailleo/medical-imaging-combined.medical-imaging
X-ray Reports Dataset
This dataset contains high-quality (“A-grade”) anonymized X-ray images paired with radiology reports. It has been carefully curated, cleaned, and verified to ensure accuracy, completeness, and compliance with privacy standards (e.g., HIPAA/GDPR), making it suitable for high-stakes or research-grade model training.
Contact
For queries or collaborations related to this dataset, contact:
anoushka@kgen.io
abhishek.vadapalli@kgen.io
Supported… See the full description on the dataset page: https://huggingface.co/datasets/HumynLabs/medical-imaging.multi-camera-hsi-rgb-super-resolutionThis is a sample multi-camera dataset acquired by two sensors:
Ultris SR5 Camera - a hyperspectral imaging (HSI) sensor.
Raspberry Pi High Quality Camera - a classical RGB color sensor.
The dataset is used for pedagogical purpose in the course of Computer Vision (code 5PMSIVV3) at Grenoble INP Phelma, the application being RGB-guided HSI super-resolution.
The dataset was made possible thanks to the Multi-camera Imaging Research and Acquisition (MIRA) Platform of GIPSA-Lab, Grenoble, France.… See the full description on the dataset page: https://huggingface.co/datasets/mira-imaging/multi-camera-hsi-rgb-super-resolution.medical-imaging-combined
Combined Medical Imaging Dataset
Dataset Description
Combined medical imaging dataset with 1893 samples in Alpaca instruction format.
Dataset Statistics
Total Samples: 1893
Training Samples: 1514
Validation Samples: 379
Modality Distribution
X-ray: 1806 samples
CT: 48 samples
Unknown: 32 samples
MRI: 5 samples
Ultrasound: 2 samples
Source Distribution
VQA-RAD: 1793 samples
ROCO: 100 samples
Sources
ROCO (Radiology Objects… See the full description on the dataset page: https://huggingface.co/datasets/alvinl29/medical-imaging-combined.OpenHotelsSample
OpenHotels Representative Sample
This repository contains a representative sample of OpenHotels for review and inspection. It mirrors the full OpenHotels release structure: image files are stored in tar shards under shards/, and metadata files describe the gallery, non-object query images, object-centric query images, and hotel classes.
The sample is intended for data-quality inspection, not benchmark reporting. Use the full OpenHotels dataset for final evaluation.… See the full description on the dataset page: https://huggingface.co/datasets/imagingforgood/OpenHotelsSample.3D_imaging_of_an_entire_T1D_pancreasTitle: 3D imaging of an entire pancreas shows inverse proportions of extra islet vs islet associated β cells in late onset type 1 diabetes
Abstract: Residual β-cell function can positively affect diabetes regulation in type 1 diabetes (T1D), but details on residual β-cell mass distribution in T1D is largely lacking in a whole organ context. Implementing an optical 3D imaging pipeline, we generated a complete account of the remaining β-cells throughout an entire human late onset T1D pancreas at… See the full description on the dataset page: https://huggingface.co/datasets/JLehrstrand/3D_imaging_of_an_entire_T1D_pancreas.fetch_huggingface_9025_medical-chest-imaging
Chest X-Ray Diagnostics
Chest X-ray images labeled for image classification of thoracic conditions. Intended for research purposes.
License
Released under CC BY-NC 4.0. Non-commercial use only.
medical-imaging-it-glossary
Medical Imaging IT Glossary — PACS, RIS, DICOM, HL7 (ES/EN)
A structured, bilingual (Spanish/English) reference glossary of standards,
systems, protocols and operational concepts used in medical imaging IT and
teleradiology: 53 terms across 23 categories, covering DICOM services and
data hierarchy, HL7 v2/FHIR message types, PACS/RIS/VNA systems, imaging
modalities (CT, MRI, US, PET, mammography, etc.), interoperability profiles
(IHE), and relevant Mexican/international… See the full description on the dataset page: https://huggingface.co/datasets/NODARISHUB/medical-imaging-it-glossary.medical-imaging-combined
Combined Medical Imaging Dataset
Dataset Description
Combined medical imaging dataset with 6793 samples in Alpaca instruction format.
Dataset Statistics
Total Samples: 6793
Training Samples: 5434
Validation Samples: 1359
Modality Distribution
X-ray: 2691 samples
CT: 2257 samples
Unknown: 1329 samples
MRI: 369 samples
Ultrasound: 147 samples
Source Distribution
ROCO: 5000 samples
VQA-RAD: 1793 samples
Sources
ROCO… See the full description on the dataset page: https://huggingface.co/datasets/teeyouteeyou/medical-imaging-combined.rsna-medcial-imaging-subsets
Medical Imaging Subsets (8-bit PNG/JPEG)
A curated collection of 58,666+ PNG/JPEG images from medical imaging competitions and public datasets, with windowing applied and labels preserved.
Sample Images
Top row: ICH with hemorrhage (CT), ICH without hemorrhage (CT), lumbar spine (MRI T2), breast cancer positive (mammogram). Bottom row: breast cancer negative (mammogram), SIIM-COVID19 negative (chest X-ray), SIIM-COVID19 positive (chest X-ray), Chaoyang colon… See the full description on the dataset page: https://huggingface.co/datasets/toufiqmusah/rsna-medcial-imaging-subsets.RadFAQs_Radiology_Imaging_Health_QA_Dataset
RadFAQs — Radiology & Imaging Health Q&A Dataset (Nepali)
Overview
This dataset (radfaqs_health_qa_nepali_all_nepali.jsonl) is a large, single-source collection of 1,235 instruction-following conversation pairs in Nepali, entirely focused on radiology and medical imaging — CT scans, MRI, X-rays, ultrasound, PET scans, bone density (DEXA) tests, echocardiograms, angiography, radiotherapy/brachytherapy, and related procedures. Each record is a single-turn human↔gpt… See the full description on the dataset page: https://huggingface.co/datasets/sabin1234/RadFAQs_Radiology_Imaging_Health_QA_Dataset.clinical-imaging-report-action-coherence-risk-v0.1What this repo is for
Detect when
imaging answers a question
but the system fails to
acknowledge and act
Common breaks
critical report not acknowledged
report late for urgent indication
action delayed after critical finding
negative result not integrated
Examples you can use
CTPA positive but anticoag not started
CT head bleed not escalated
CT perforation with delayed surgery
You use it to flag
missed diagnosis risk
treatment delay risk
healthcare-diagnostic-imaging-report-turnaround-coherence-risk-v0.1What this repo is for
Detect diagnostic delay risk early.
Tracks alignment between scan completion, reporting, validation, release, clinician notification, and clinical action.
Helps hospitals reduce missed results, prevent diagnostic delays, and stabilise care pathways.
High-Spatiotemporal-Resolution-Particle-ImagingBioDSBench-imaging101-format
BioDSBench (Imaging-101 Format)
This dataset packages 118 BioDSBench Python tasks in an imaging-101-like task-per-directory layout, aligned with the structure of imaging-101 benchmark tasks.
It is a re-formatted version of BioDSBench, restructured for compatibility with source-native LLM agent evaluation harnesses such as biodsbench-adapter.
Dataset Summary
118 biomedical Python data-science tasks across 13 PMIDs (biomedical publications)
Each task has:… See the full description on the dataset page: https://huggingface.co/datasets/starpacker52/BioDSBench-imaging101-format.robustness-of-transferability-estimation-metrics-for-medical-imagingThis repository contains the data splits of target datasets used in the following work:
@misc{claßen2026robustnesstransferabilityestimationmetrics,
title={Robustness of transferability estimation metrics for medical imaging},
author={Niclas Claßen and Théo Sourget and Dovile Juodelyte and Rob van der Goot and Veronika Cheplygina},
year={2026},
eprint={2608.09999},
archivePrefix={arXiv},
primaryClass={eess.IV},
url={https://arxiv.org/abs/2608.09999}… See the full description on the dataset page: https://huggingface.co/datasets/niclasclassen/robustness-of-transferability-estimation-metrics-for-medical-imaging.clinical-imaging-queue-treatment-delay-coherence-risk-v0.1What this repo is for
Detect when imaging queues
and treatment urgency
fall out of alignment
before
stroke delays
trauma bottlenecks
and preventable deterioration.
clinical-imaging-order-result-followup-coherence-risk-v0.1What this repo is for
Detect when
imaging results
and
clinical follow-up
fall out of alignment
before
missed findings
and delayed treatment.