datasets
Training and evaluation data, with the modality, task and licence stated up front. Listed live from the Hugging Face Hub.
multimodal-ct-radiology-reports
Perle AI Multi-phase CECT and CT with Radiology Reports
Summary
A de-identified CT dataset from Perle AI, paired with the original radiology reports. It supports work on multi-modal medical imaging: phase or pathology classification, report generation from images, and visual question answering.
The release has three configurations:
Config
Modality
Subjects
Pairing
cect_3phase
3-phase contrast-enhanced abdominal CT (DICOM)
5
per-subject text report +… See the full description on the dataset page: https://huggingface.co/datasets/Perle-ai/multimodal-ct-radiology-reports.Chameleon-Radiology-Reportsnervous-radio-8ab78b
nervous-radio-8ab78b
Synthetic products test data: 45 rows in data.csv.
All values are randomly generated fictional examples, not real observations, products, or user activity. Intended only for CSV loading and pipeline tests; not suitable for scientific or business conclusions. Columns are sampled independently and do not model real-world correlations.
Fields
sample_id: random identifier for this generated sample.
row_id: sequential row number starting at 1.… See the full description on the dataset page: https://huggingface.co/datasets/Velvet-Michael/nervous-radio-8ab78b.stereotactic-radiosurgery-k1-with-segmentation
🎯 Stereotactic Radiosurgery Dataset (SRS)
🏥 400 synthetic patient records describing the clinical, imaging, segmentation, and treatment-planning metadata of a stereotactic radiosurgery workflow, delivered as a single CSV with placeholder file paths.
⚠️ Disclaimer: This is a metadata-only synthetic dataset. It contains no real patients, no image files, and no segmentation files. Every record is generated; paths in the imaging and segmentation columns are placeholders that do… See the full description on the dataset page: https://huggingface.co/datasets/Taylor658/stereotactic-radiosurgery-k1-with-segmentation.Reportes-radiologicosimage-report-consistency-radiology-v01Image–Report Consistency Integrity v01
What this dataset is
This dataset evaluates whether a system can detect misalignment between imaging findings and radiology report language.
You give the model:
A description of imaging findings
An excerpt from a radiology report
You ask one question.
Do the words
faithfully reflect
the image
Why this matters
Radiology errors often occur after the image is seen.
Common failure patterns:
Reports overstating equivocal findings
Reports contradicting stated… See the full description on the dataset page: https://huggingface.co/datasets/ClarusC64/image-report-consistency-radiology-v01.diagnostic-scope-differential-control-radiology-v01Diagnostic Scope and Differential Control v01
What this dataset is
This dataset evaluates whether a system respects the diagnostic limits of a radiologic study and avoids collapsing the differential diagnosis prematurely.
You give the model:
Imaging findings
A clinical prompt
A report level claim
You ask one question.
Is this conclusion
within the diagnostic scope
of the image
Why this matters
Radiology supports diagnosis.
It rarely delivers certainty.
Common failure patterns:
Treating… See the full description on the dataset page: https://huggingface.co/datasets/ClarusC64/diagnostic-scope-differential-control-radiology-v01.radiotherapy-availability-who-africa
Radiotherapy Availability - WHO African Region | Africa (World Health Organization)
Size category: 10K<n<100K - Formats: not declared - Sector: health - Engineered by Electric Sheep Africa
TL;DR
This dataset is part of the Electric Sheep Africa catalog on Hugging Face. It is indexed for African data discovery with standardized metadata, loading guidance, provenance notes, and analyst-oriented context.
What This Dataset Covers
Health datasets… See the full description on the dataset page: https://huggingface.co/datasets/electricsheepafrica/radiotherapy-availability-who-africa.africa-synth-cancer-cancer-radiotherapy-treatment-all
Cancer Radiotherapy Treatment Africa | Africa (Electric Sheep Africa metadata inventory)
Size category: 10K<n<100K - Formats: csv - Sector: health - Engineered by Electric Sheep Africa
TL;DR
This dataset is part of the Electric Sheep Africa catalog on Hugging Face. It is indexed for African data discovery with standardized metadata, loading guidance, provenance notes, and analyst-oriented context.
What This Dataset Covers
Health datasets help… See the full description on the dataset page: https://huggingface.co/datasets/electricsheepafrica/africa-synth-cancer-cancer-radiotherapy-treatment-all.petar-test
Citation
If you use PETARseg-11k, please cite these two papers:
@article{huemann_contextual_2026,
title = {{ConTEXTual} {Net} {3D}: {Vision}-{Language} {Modeling} in {PET}/{CT} for {Visual} {Grounding} of {Positive} {Findings}},
issn = {2948-2933},
shorttitle = {{ConTEXTual} {Net} {3D}},
url = {https://doi.org/10.1007/s10278-026-01879-2},
doi = {10.1007/s10278-026-01879-2},
language = {en},
urldate = {2026-07-27},
journal = {Journal… See the full description on the dataset page: https://huggingface.co/datasets/UW-Madison-Dept-Radiology/petar-test.Results-Radiologymedical-pathology-radiology-multimodal
🚀 Datavendor Multimodal Medical Dataset (Radiology & Pathology)
A premium, expert-validated, multi-modal clinical dataset engineered for high-accuracy AI and machine learning applications. This repository provides structured sample data for evaluation and integration testing.
1. Structured Patient Context (SPC) – Radiology Reports
We have engineered a large-scale cohort of radiology reports into a Structured Patient Context (SPC) format, enabling efficient downstream AI… See the full description on the dataset page: https://huggingface.co/datasets/datavendor/medical-pathology-radiology-multimodal.radiology-findingsuncertainty-followup-discipline-radiology-v01Uncertainty and Follow Up Discipline v01
What this dataset is
This dataset evaluates whether a system acknowledges uncertainty and recommends appropriate follow up instead of prematurely closing a case.
You give the model:
Imaging findings
A report level statement
You ask one question.
When certainty is not possible
does the system act responsibly
Why this matters
Radiology often operates under uncertainty.
The danger is not uncertainty itself.
The danger is hiding it.
Common failure patterns:… See the full description on the dataset page: https://huggingface.co/datasets/ClarusC64/uncertainty-followup-discipline-radiology-v01.RadiologyImageAnomalies
RadiologyImageAnomalies
tags: Classification, Anomaly Detection, Imaging
Note: This is an AI-generated dataset so its content may be inaccurate or false
Dataset Description:
The 'RadiologyImageAnomalies' dataset is designed for the purpose of anomaly detection in radiology images. The dataset contains a collection of images sourced from radiology studies, where each image is accompanied by annotations that indicate whether an anomaly is present. The labels are binary (0 or 1), with… See the full description on the dataset page: https://huggingface.co/datasets/infinite-dataset-hub/RadiologyImageAnomalies.f1-team-radio-stressnew_radiology_datasetRadiometricCorrectradio_stations_phUSI-FLFib
If you are not subscribed to Abdominal Radiology - Springer Link Journal, you can view the full version of our paper by clicking on this link
RXL-USI-FLFibis an original dataset collected at a tertiary care referral center, as part of a prospective study on hepatocellular carcinoma screening (NCT05716620) after informed written consent.
Image acquisition protocol:
All US scans were performed using a GE LOGIQ S8 scanner with a C1-6-D curvilinear transducer (frequency range: 1–6… See the full description on the dataset page: https://huggingface.co/datasets/RadioX-Labs/USI-FLFib.Amateur_Radio_POTA_entities_2024custom_dataset_radiologynew_dataset_radiology