datasets
Training and evaluation data, with the modality, task and licence stated up front. Listed live from the Hugging Face Hub.
AbdomenAtlas2.0MiniAbdomenAtlas3.0MiniRadGPT & AbdomenAtlas 3.0
Subscribe us: https://groups.google.com/u/2/g/bodymaps
AbdomenAtlas 3.0 is the first public dataset with high quality abdominal CTs and paired radiology reports. The database includes more than 9,000 CT scans with radiology reports and per-voxel annotations of liver, kidney and pancreatic tumors.
Overall, AbdomenAtlas 3.0 presents per-voxel segmentation masks for:
tumors in the kidney, pancreas, and liver
blood vessels, including the aorta… See the full description on the dataset page: https://huggingface.co/datasets/AbdomenAtlas/AbdomenAtlas3.0Mini.AbdomenSmallsaramis_abdomenAbdomenAtlas1.0Mini
Dataset Summary
One of the largest, fully-annotated CT dataset to date, including 5,195 annotated CT volumes (with spleen, liver, kidneys, stomach,
gallbladder, pancreas, aorta, and IVC annotations).
Submit your Checkpoint for External Evaluation and Join the Touchstone Benchmarking Project!
The Benchmarking Project aims to compare diverse semantic segmentation algorithms.
We, the CCVL research group at Johns Hopkins University, invite you to contribute to this… See the full description on the dataset page: https://huggingface.co/datasets/AbdomenAtlas/AbdomenAtlas1.0Mini.TR_ABDOMEN_RAD
TR_ABDOMEN_RAD
Part of the TEKNOFEST Health AI (SYZ) Challenge Datasets (Stroke, Abdomen, Mammography) collection.
Medical radiology benchmark datasets for TEKNOFEST Sağlıkta Yapay Zeka (SYZ) competitions covering Brain Stroke (İskemi), Abdomen CT Radiology, and Mammography (MammosighTR) in collaboration with the Turkish Ministry of Health and Turkish Society of Radiology.
Original Source & License
Official Source / Project: TEKNOFEST Health AI (SYZ) Challenge… See the full description on the dataset page: https://huggingface.co/datasets/huseyincavus/TR_ABDOMEN_RAD.MerlinPlus
Merlin Plus
This repository provides Merlin Plus, with longitudinal metadata (patient IDs and scan dates) and per-voxel annotations for organs and 9 tumor types in the Merlin dataset (Stanford, 25,494 CT scans).
Merlin Plus is part of a collaboration between the Merlin Project at Stanford and the R-Super Project at Johns Hopkins University.
[!NOTE]
We also release AI models trained on Merlin Plus for detecting and segmenting tumors in 9 organs!… See the full description on the dataset page: https://huggingface.co/datasets/AbdomenAtlas/MerlinPlus.mood_abdomenAbdomenAtlas1.0Mini
Dataset Summary
The largest, fully-annotated abdominal CT dataset to date, including 9,262 CT volumes with annotations for 25 different anatomical structures.
Join the Touchstone Benchmarking Project
The Touchstone Project aims to compare diverse semantic segmentation and pre-training algorithms.
We, the CCVL research group at Johns Hopkins University, invite creators of these algorithms to contribute to the initiative.
With our support, contributors… See the full description on the dataset page: https://huggingface.co/datasets/BodyMaps/AbdomenAtlas1.0Mini.abdomen-mri
Abdomen Mri
This dataset is part of the Roboflow 100 benchmark, a diverse collection of 100 object detection datasets spanning 7 imagery domains.
Dataset Statistics
Split
Images
Train
1,887
Validation
479
Test
238
Total
2,604
Classes (1)
0
Usage
With LibreYOLO
from libreyolo import LIBREYOLO
# Load a model
model = LIBREYOLO(model_path="libreyoloXnano.pt")
# Train on this dataset… See the full description on the dataset page: https://huggingface.co/datasets/LibreYOLO/abdomen-mri.abdomen-mri
Dataset Card for abdomen-mri
** The original COCO dataset is stored at dataset.tar.gz**
Dataset Summary
abdomen-mri
Supported Tasks and Leaderboards
object-detection: The dataset can be used to train a model for Object Detection.
Languages
English
Dataset Structure
Data Instances
A data point comprises an image and its object annotations.
{
'image_id': 15,
'image': <PIL.JpegImagePlugin.JpegImageFile image mode=RGB… See the full description on the dataset page: https://huggingface.co/datasets/Francesco/abdomen-mri._AbdomenAtlas1.1Mini
Dataset Summary
The largest, fully-annotated abdominal CT dataset to date, including 9,262 CT volumes with annotations for 25 different anatomical structures.
Join the Touchstone Benchmarking Project
The Touchstone Project aims to compare diverse semantic segmentation and pre-training algorithms.
We, the CCVL research group at Johns Hopkins University, invite creators of these algorithms to contribute to the initiative.
With our support, contributors will train their… See the full description on the dataset page: https://huggingface.co/datasets/AbdomenAtlas/_AbdomenAtlas1.1Mini._AbdomenAtlas1.0Mini
Dataset Summary
One of the largest, fully-annotated CT dataset to date, including 5,195 annotated CT volumes (with spleen, liver, kidneys, stomach,
gallbladder, pancreas, aorta, and IVC annotations).
Join the AbdomenAtlas Benchmarking Project (Touchstone)
The Benchmarking Project aims to compare diverse semantic segmentation and pre-training algorithms.
We, the CCVL research group at Johns Hopkins University, invite creators of these algorithms to contribute to the… See the full description on the dataset page: https://huggingface.co/datasets/AbdomenAtlas/_AbdomenAtlas1.0Mini.abdomen-prepared
abdomen-prepared
Part of the TEKNOFEST Health AI (SYZ) Challenge Datasets (Stroke, Abdomen, Mammography) collection.
Medical radiology benchmark datasets for TEKNOFEST Sağlıkta Yapay Zeka (SYZ) competitions covering Brain Stroke (İskemi), Abdomen CT Radiology, and Mammography (MammosighTR) in collaboration with the Turkish Ministry of Health and Turkish Society of Radiology.
Original Source & License
Official Source / Project: TEKNOFEST Health AI (SYZ) Challenge… See the full description on the dataset page: https://huggingface.co/datasets/huseyincavus/abdomen-prepared.abdomen-18aug
abdomen-18aug
Part of the TEKNOFEST Health AI (SYZ) Challenge Datasets (Stroke, Abdomen, Mammography) collection.
Medical radiology benchmark datasets for TEKNOFEST Sağlıkta Yapay Zeka (SYZ) competitions covering Brain Stroke (İskemi), Abdomen CT Radiology, and Mammography (MammosighTR) in collaboration with the Turkish Ministry of Health and Turkish Society of Radiology.
Original Source & License
Official Source / Project: TEKNOFEST Health AI (SYZ) Challenge… See the full description on the dataset page: https://huggingface.co/datasets/huseyincavus/abdomen-18aug.ct_abdomenct_abdomen_seg_AbdomenAtlas1.1Mini
Dataset Summary
The largest, fully-annotated abdominal CT dataset to date, including 9,262 CT volumes with annotations for 25 different anatomical structures.
Join the Touchstone Benchmarking Project
The Touchstone Project aims to compare diverse semantic segmentation and pre-training algorithms.
We, the CCVL research group at Johns Hopkins University, invite creators of these algorithms to contribute to the initiative.
With our support, contributors… See the full description on the dataset page: https://huggingface.co/datasets/BodyMaps/_AbdomenAtlas1.1Mini.AbdomenAtlas2_labelAbdomenAtlas1.1MiniMask
Dataset Summary
Per-voxel annotations for AbdomenAtlas 1.1 Mini (cropped), the largest, fully-annotated abdominal CT dataset to date, including 9,262 CT volumes.
Downloading Instructions
1- Install the Hugging Face library:
pip install huggingface_hub[hf_transfer]==0.24.0
HF_HUB_ENABLE_HF_TRANSFER=1
[Optional] Alternative without HF Trasnsfer (slower)
pip install huggingface_hub==0.24.0
2- Download the dataset:… See the full description on the dataset page: https://huggingface.co/datasets/BodyMaps/AbdomenAtlas1.1MiniMask.AbdomenAtlas1.0MiniBeta
Dataset Summary
One of the largest, fully-annotated CT dataset to date, including 5,195 annotated CT volumes (with spleen, liver, kidneys, stomach,
gallbladder, pancreas, aorta, and IVC annotations). A version with improved annotation quality for the aorta and kidney classes is available
at AbdomenAtlas1.0Mini.
Join the AbdomenAtlas Benchmarking Project (Touchstone)
The Benchmarking Project aims to compare diverse semantic segmentation and pre-training algorithms.… See the full description on the dataset page: https://huggingface.co/datasets/AbdomenAtlas/AbdomenAtlas1.0MiniBeta.AbdomenAtlasDataMini
Dataset Summary
CT scans (cropped background) for AbdomenAtlas, the largest, fully-annotated abdominal CT dataset to date, including and liver, pancreas and kidney tumor annotations and 9,262 CT volumes.
Downloading Instructions
1- Install the Hugging Face library:
pip install huggingface_hub[hf_transfer]==0.24.0
HF_HUB_ENABLE_HF_TRANSFER=1
[Optional] Alternative without HF Trasnsfer (slower)
pip install huggingface_hub==0.24.0
2- Download… See the full description on the dataset page: https://huggingface.co/datasets/AbdomenAtlasProMax/AbdomenAtlasDataMini.