RibFrac dataset is a benchmark for developping algorithms on rib fracture detection, segmentation and classification. We hope this large-scale dataset could facilitate both clinical research for automatic rib fracture detection and diagnoses, and engineering research for 3D detection, segmentation and classification.

Due to size limit of zenodo.org, we split the whole RibFrac Training Set into 2 parts; This is the Training Set Part 1 of RibFrac dataset, including 300 CTs and the corresponding annotations. Files include:

1. ribfrac-train-images-1.zip: 300 chest-abdomen CTs in NII format (nii.gz).
2. ribfrac-train-labels-1.zip: 300 annotations in NII format (nii.gz).
3. ribfrac-train-info-1.csv: labels in the annotation NIIs.
   • public_id: anonymous patient ID to match images and annotations.
   • label_id: discrete label value in the NII annotations.
   • label_code: 0, 1, 2, 3, 4, -1
     • 0: it is background
     • 1: it is a displaced rib fracture
     • 2: it is a non-displaced rib fracture
     • 3: it is a buckle rib fracture
     • 4: it is a segmental rib fracture
     • -1: it is a rib fracture, but we could not define its type due to ambiguity, diagnosis difficulty, etc. Ignore it in the classification task.

If you find this work useful in your research, please acknowledge the RibFrac project teams in the paper and cite this project as:

Liang Jin, Jiancheng Yang, Kaiming Kuang, Bingbing Ni, Yiyi Gao, Yingli Sun, Pan Gao, Weiling Ma, Mingyu Tan, Hui Kang, Jiajun Chen, Ming Li. Deep-Learning-Assisted Detection and Segmentation of Rib Fractures from CT Scans: Development and Validation of FracNet. EBioMedicine (2020). (DOI)

or using bibtex

@article{ribfrac2020,
title={Deep-Learning-Assisted Detection and Segmentation of Rib Fractures from CT Scans: Development and Validation of FracNet},
author={Jin, Liang and Yang, Jiancheng and Kuang, Kaiming and Ni, Bingbing and Gao, Yiyi and Sun, Yingli and Gao, Pan and Ma, Weiling and Tan, Mingyu and Kang, Hui and Chen, Jiajun and Li, Ming},
journal={EBioMedicine},
year={2020},
publisher={Elsevier}
}

The RibFrac dataset is a research effort of thousands of hours by experienced radiologists, computer scientists and engineers. We kindly ask you to respect our effort by appropriate citation and keeping data license.

This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.

RibFrac dataset is a benchmark for developping algorithms on rib fracture detection, segmentation and classification. We hope this large-scale dataset could facilitate both clinical research for automatic rib fracture detection and diagnoses, and engineering research for 3D detection, segmentation and classification.

This is the Tuning Set (a.k.a. Validation Set in machine learning terminology) of RibFrac dataset, including 80 CTs and the corresponding annotations. Files include:

1. ribfrac-val-images.zip: 80 chest-abdomen CTs in NII format (nii.gz).
2. ribfrac-val-labels.zip: 80 annotations in NII format (nii.gz).
3. ribfrac-val-info.csv: labels in the annotation NIIs.
   • public_id: anonymous patient ID to match images and annotations.
   • label_id: discrete label value in the NII annotations.
   • label_code: 0, 1, 2, 3, 4, -1
     • 0: it is background
     • 1: it is a displaced rib fracture
     • 2: it is a non-displaced rib fracture
     • 3: it is a buckle rib fracture
     • 4: it is a segmental rib fracture
     • -1: it is a rib fracture, but we could not define its type due to ambiguity, diagnosis difficulty, etc. Ignore it in the classification task.

If you find this work useful in your research, please acknowledge the RibFrac project teams in the paper and cite this project as:

Liang Jin, Jiancheng Yang, Kaiming Kuang, Bingbing Ni, Yiyi Gao, Yingli Sun, Pan Gao, Weiling Ma, Mingyu Tan, Hui Kang, Jiajun Chen, Ming Li. Deep-Learning-Assisted Detection and Segmentation of Rib Fractures from CT Scans: Development and Validation of FracNet. EBioMedicine (2020). (DOI)

or using bibtex

@article{ribfrac2020,
title={Deep-Learning-Assisted Detection and Segmentation of Rib Fractures from CT Scans: Development and Validation of FracNet},
author={Jin, Liang and Yang, Jiancheng and Kuang, Kaiming and Ni, Bingbing and Gao, Yiyi and Sun, Yingli and Gao, Pan and Ma, Weiling and Tan, Mingyu and Kang, Hui and Chen, Jiajun and Li, Ming},
journal={EBioMedicine},
year={2020},
publisher={Elsevier}
}

The RibFrac dataset is a research effort of thousands of hours by experienced radiologists, computer scientists and engineers. We kindly ask you to respect our effort by appropriate citation and keeping data license.

This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.

The RibFrac dataset, publicly available from the RibFrac Challenge: Rib Fracture Detection and Classification, organized by the International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI), was chosen for inclusion in this study.The data can be accessed at https://ribfrac.grand-challenge.org/dataset/.The dataset is composed of 3D rib CT images in the format of the Neuroimaging Informatics Technology Initiative (NIFTI), and annotated by multiple radiologists with varying years of experience in chest CT interpretation using the human-in-the-loop labeling program to ensure high-quality annotation.

Manual rib inspections in computed tomography (CT) scans are clinically critical but labor-intensive, as 24 ribs are typically elongated and oblique in 3D volumes. Automatic rib segmentation methods can speed up the process through rib measurement and visualization. However, prior arts mostly use in-house labeled datasets that are publicly unavailable and work on dense 3D volumes that are computationally inefficient. To address these issues, we develop a labeled rib segmentation benchmark, named RibSeg, including 490 CT scans (11,719 individual ribs) from a public dataset. For ground truth generation, we used existing morphology-based algorithms and manually refined its results. Then, considering the sparsity of ribs in 3D volumes, we thresholded and sampled sparse voxels from the input and designed a point cloud-based baseline method for rib segmentation. The proposed method achieves state-of-the-art segmentation performance (Dice\(\approx95\%\)) with significant efficiency (\(10\sim40\times\) faster than prior arts). The RibSeg dataset, code, and model in PyTorch are available at https://github.com/M3DV/RibSeg.

Note: This repository provides rib segmentation ("RibFrac31-rib-seg.nii.gz") and centerline ("RibFrac31-rib-cl.nii.gz") annotations for 490 cases in RibFrac dataset. Please download the corresponding CT images ("RibFrac31-image.nii.gz") at https://ribfrac.grand-challenge.org/ (1-click registration is needed via "Join").

This Upload contains the segmentations used in the paper titled "Automated Thoracolumbar Stump Rib Detection and Analysis in a Large CT Cohort".

Rib segmentation masks for:

• Public VerSe Dataset
• Public RibFrac Dataset

It contains the predictions of our segmentation model as well as manually corrected samples that were used for training/testing. The segmentation masks are binary and differentiate between rib (1) and background (0).

This upload also contains the nnUNet model weights for the rib segmentation model that was used to create them.

If you use any of the contents provided, cite our publication:

[1] H. Möller, H. Schön, B. C. Keinertand J. Kirschke, “Data from -- Automated Thoracolumbar Stump Rib Detection and Analysis in a Large CT Cohort”. Deep-Spine "iback-epic" Research Group, Feb. 11, 2025. doi: 10.5281/zenodo.14850929.

This data set is part of the public development data for the 2023 Automated Universal Classification Challenge (AUC23). The data set concerns the detection and classification of rib fractures on computed tomography (CT) scans and was previously introduced and described by Jin, L. et al (2020). The original dataset was modified to classify center-cropped rib fractures and no images or patient information were added. Data was restructured in compliance with the AUC23 challenge format.

Images are 3D tensors:

• 0: 3D center-cropped CT scan

Fracture classification labels:

• 0: Displaced
• 1: Non-displaced
• 2: Buckle
• 3: Segmental

Folder structure:

imagesTr (root folder with all patients and studies)
├── ribfrac_0001001_0000.mha (3D CT for fracture 0001001)
├── ribfrac_0001002_0000.mha (3D CT for fracture 0001002)
├── ...

Please cite the following article if you are using the Rib Fracture Detection and Classification dataset:

Liang Jin, Jiancheng Yang, Kaiming Kuang, Bingbing Ni, Yiyi Gao, Yingli Sun, Pan Gao, Weiling Ma, Mingyu Tan, Hui Kang, Jiajun Chen, Ming Li. Deep-Learning-Assisted Detection and Segmentation of Rib Fractures from CT Scans: Development and Validation of FracNet. EBioMedicine (2020).DOI: https://doi.org/10.1016/j.ebiom.2020.103106