Deep Rib Fracture Instance Segmentation and Classification from CT on the RibFrac Challenge

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Yang, Jiancheng, Shi, Rui, Jin, Liang, Huang, Xiaoyang, Kuang, Kaiming, Wei, Donglai, Gu, Shixuan, Liu, Jianying, Liu, Pengfei, Chai, Zhizhong, Xiao, Yongjie, Chen, Hao, Xu, Liming, Du, Bang, Yan, Xiangyi, Tang, Hao, Alessio, Adam, Holste, Gregory, Zhang, Jiapeng, Wang, Xiaoming, He, Jianye, Che, Lixuan, Pfister, Hanspeter, Li, Ming, Ni, Bingbing
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866914679235805184
author Yang, Jiancheng
Shi, Rui
Jin, Liang
Huang, Xiaoyang
Kuang, Kaiming
Wei, Donglai
Gu, Shixuan
Liu, Jianying
Liu, Pengfei
Chai, Zhizhong
Xiao, Yongjie
Chen, Hao
Xu, Liming
Du, Bang
Yan, Xiangyi
Tang, Hao
Alessio, Adam
Holste, Gregory
Zhang, Jiapeng
Wang, Xiaoming
He, Jianye
Che, Lixuan
Pfister, Hanspeter
Li, Ming
Ni, Bingbing
author_facet Yang, Jiancheng
Shi, Rui
Jin, Liang
Huang, Xiaoyang
Kuang, Kaiming
Wei, Donglai
Gu, Shixuan
Liu, Jianying
Liu, Pengfei
Chai, Zhizhong
Xiao, Yongjie
Chen, Hao
Xu, Liming
Du, Bang
Yan, Xiangyi
Tang, Hao
Alessio, Adam
Holste, Gregory
Zhang, Jiapeng
Wang, Xiaoming
He, Jianye
Che, Lixuan
Pfister, Hanspeter
Li, Ming
Ni, Bingbing
contents Rib fractures are a common and potentially severe injury that can be challenging and labor-intensive to detect in CT scans. While there have been efforts to address this field, the lack of large-scale annotated datasets and evaluation benchmarks has hindered the development and validation of deep learning algorithms. To address this issue, the RibFrac Challenge was introduced, providing a benchmark dataset of over 5,000 rib fractures from 660 CT scans, with voxel-level instance mask annotations and diagnosis labels for four clinical categories (buckle, nondisplaced, displaced, or segmental). The challenge includes two tracks: a detection (instance segmentation) track evaluated by an FROC-style metric and a classification track evaluated by an F1-style metric. During the MICCAI 2020 challenge period, 243 results were evaluated, and seven teams were invited to participate in the challenge summary. The analysis revealed that several top rib fracture detection solutions achieved performance comparable or even better than human experts. Nevertheless, the current rib fracture classification solutions are hardly clinically applicable, which can be an interesting area in the future. As an active benchmark and research resource, the data and online evaluation of the RibFrac Challenge are available at the challenge website. As an independent contribution, we have also extended our previous internal baseline by incorporating recent advancements in large-scale pretrained networks and point-based rib segmentation techniques. The resulting FracNet+ demonstrates competitive performance in rib fracture detection, which lays a foundation for further research and development in AI-assisted rib fracture detection and diagnosis.
format Preprint
id arxiv_https___arxiv_org_abs_2402_09372
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Deep Rib Fracture Instance Segmentation and Classification from CT on the RibFrac Challenge
Yang, Jiancheng
Shi, Rui
Jin, Liang
Huang, Xiaoyang
Kuang, Kaiming
Wei, Donglai
Gu, Shixuan
Liu, Jianying
Liu, Pengfei
Chai, Zhizhong
Xiao, Yongjie
Chen, Hao
Xu, Liming
Du, Bang
Yan, Xiangyi
Tang, Hao
Alessio, Adam
Holste, Gregory
Zhang, Jiapeng
Wang, Xiaoming
He, Jianye
Che, Lixuan
Pfister, Hanspeter
Li, Ming
Ni, Bingbing
Image and Video Processing
Artificial Intelligence
Computer Vision and Pattern Recognition
Rib fractures are a common and potentially severe injury that can be challenging and labor-intensive to detect in CT scans. While there have been efforts to address this field, the lack of large-scale annotated datasets and evaluation benchmarks has hindered the development and validation of deep learning algorithms. To address this issue, the RibFrac Challenge was introduced, providing a benchmark dataset of over 5,000 rib fractures from 660 CT scans, with voxel-level instance mask annotations and diagnosis labels for four clinical categories (buckle, nondisplaced, displaced, or segmental). The challenge includes two tracks: a detection (instance segmentation) track evaluated by an FROC-style metric and a classification track evaluated by an F1-style metric. During the MICCAI 2020 challenge period, 243 results were evaluated, and seven teams were invited to participate in the challenge summary. The analysis revealed that several top rib fracture detection solutions achieved performance comparable or even better than human experts. Nevertheless, the current rib fracture classification solutions are hardly clinically applicable, which can be an interesting area in the future. As an active benchmark and research resource, the data and online evaluation of the RibFrac Challenge are available at the challenge website. As an independent contribution, we have also extended our previous internal baseline by incorporating recent advancements in large-scale pretrained networks and point-based rib segmentation techniques. The resulting FracNet+ demonstrates competitive performance in rib fracture detection, which lays a foundation for further research and development in AI-assisted rib fracture detection and diagnosis.
title Deep Rib Fracture Instance Segmentation and Classification from CT on the RibFrac Challenge
topic Image and Video Processing
Artificial Intelligence
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2402.09372