arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2402.09372eess.IVcs.AIcs.CV
收藏

基于RibFrac挑战赛的CT肋骨骨折深度实例分割与分类

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

Shanghai Jiao Tong University（上海交通大学）；Huadong Hospital affiliated to Fudan University（复旦大学附属华东医院）；Huashan Hospital affiliated to Fudan University（复旦大学附属华山医院）；Academy of Forensic Science, Ministry of Justice, China（中国司法部司法鉴定科学研究院）；Dianei Technology（点内科技）；Boston College（波士顿学院）；Harvard University（哈佛大学）；Huiying Medical Technology (Beijing) Co., Ltd.（北京惠每医疗科技有限公司）；ImsightMed（推想医疗）；Hong Kong University of Science and Technology（香港科技大学）；Zhejiang University（浙江大学）
Jiancheng Yang, Rui Shi, Liang Jin, Xiaoyang Huang, Kaiming Kuang, Donglai Wei, Shixuan Gu, Jianying Liu, Pengfei Liu, Zhizhong Chai, Yongjie Xiao, Hao Chen, Li… 展开作者

Jiancheng Yang, Rui Shi, Liang Jin, Xiaoyang Huang, Kaiming Kuang, Donglai Wei, Shixuan Gu, Jianying Liu, Pengfei Liu, Zhizhong Chai, Yongjie Xiao, Hao Chen, Liming Xu, Bang Du, Xiangyi Yan, Hao Tang, Adam Alessio, Gregory Holste, Jiapeng Zhang, Xiaoming Wang, Jianye He, Lixuan Che, Hanspeter Pfister, Ming Li, Bingbing Ni

备注：
Challenge paper for MICCAI RibFrac Challenge (https://ribfrac.grand-challenge.org/)
阅读 PDF
arXiv 页面 ↗HTML 原文 ↗

AI总结：

本文介绍了RibFrac Challenge基准数据集，用于肋骨骨折的检测与分类，并展示了顶级深度学习方案在检测上达到专家水平，同时提出FracNet+基线以促进AI辅助诊断研究。

摘要：

肋骨骨折是一种常见且可能严重的损伤，在CT扫描中检测起来具有挑战性且耗费人力。尽管已有针对该领域的研究，但缺乏大规模标注数据集和评估基准阻碍了深度学习算法的开发与验证。为解决此问题，引入了RibFrac Challenge，提供了一个包含来自660次CT扫描的5000多个肋骨骨折的基准数据集，并带有体素级实例掩码标注和四个临床类别（青枝骨折、无移位骨折、移位骨折或节段性骨折）的诊断标签。该挑战赛包括两个赛道：一个通过FROC风格指标评估的检测（实例分割）赛道，以及一个通过F1风格指标评估的分类赛道。在MICCAI 2020挑战赛期间，共评估了243项结果，并邀请了七支团队参与挑战赛总结。分析表明，几种顶级的肋骨骨折检测方案取得了与人类专家相当甚至更好的性能。然而，目前的肋骨骨折分类方案几乎无法应用于临床，这可能是未来一个有趣的研究领域。作为活跃的基准和研究资源，RibFrac Challenge的数据和在线评估可在挑战赛网站上获取。作为一项独立贡献，我们还通过结合大规模预训练网络和基于点的肋骨分割技术的最新进展，扩展了之前的内部基线。由此产生的FracNet+在肋骨骨折检测中展现出具有竞争力的性能，为AI辅助肋骨骨折检测和诊断的进一步研究与开发奠定了基础。

英文摘要：

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.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

↑