当前位置:
X-MOL 学术
›
arXiv.cs.CV
›
论文详情
Our official English website, www.x-mol.net, welcomes your
feedback! (Note: you will need to create a separate account there.)
CHAOS Challenge -- Combined (CT-MR) Healthy Abdominal Organ Segmentation
arXiv - CS - Computer Vision and Pattern Recognition Pub Date : 2020-01-17 , DOI: arxiv-2001.06535 A. Emre Kavur, N. Sinem Gezer, Mustafa Bar{\i}\c{s}, Sinem Aslan, Pierre-Henri Conze, Vladimir Groza, Duc Duy Pham, Soumick Chatterjee, Philipp Ernst, Sava\c{s} \"Ozkan, Bora Baydar, Dmitry Lachinov, Shuo Han, Josef Pauli, Fabian Isensee, Matthias Perkonigg, Rachana Sathish, Ronnie Rajan, Debdoot Sheet, Gurbandurdy Dovletov, Oliver Speck, Andreas N\"urnberger, Klaus H. Maier-Hein, G\"ozde Bozda\u{g}{\i} Akar, G\"ozde \"Unal, O\u{g}uz Dicle, M. Alper Selver
arXiv - CS - Computer Vision and Pattern Recognition Pub Date : 2020-01-17 , DOI: arxiv-2001.06535 A. Emre Kavur, N. Sinem Gezer, Mustafa Bar{\i}\c{s}, Sinem Aslan, Pierre-Henri Conze, Vladimir Groza, Duc Duy Pham, Soumick Chatterjee, Philipp Ernst, Sava\c{s} \"Ozkan, Bora Baydar, Dmitry Lachinov, Shuo Han, Josef Pauli, Fabian Isensee, Matthias Perkonigg, Rachana Sathish, Ronnie Rajan, Debdoot Sheet, Gurbandurdy Dovletov, Oliver Speck, Andreas N\"urnberger, Klaus H. Maier-Hein, G\"ozde Bozda\u{g}{\i} Akar, G\"ozde \"Unal, O\u{g}uz Dicle, M. Alper Selver
Segmentation of abdominal organs has been a comprehensive, yet unresolved,
research field for many years. In the last decade, intensive developments in
deep learning (DL) have introduced new state-of-the-art segmentation systems.
In order to expand the knowledge on these topics, the CHAOS - Combined (CT-MR)
Healthy Abdominal Organ Segmentation challenge has been organized in
conjunction with IEEE International Symposium on Biomedical Imaging (ISBI),
2019, in Venice, Italy. CHAOS provides both abdominal CT and MR data from
healthy subjects for single and multiple abdominal organ segmentation. Five
different but complementary tasks have been designed to analyze the
capabilities of current approaches from multiple perspectives. The results are
investigated thoroughly, compared with manual annotations and interactive
methods. The analysis shows that the performance of DL models for single
modality (CT / MR) can show reliable volumetric analysis performance (DICE:
0.98 $\pm$ 0.00 / 0.95 $\pm$ 0.01) but the best MSSD performance remain limited
(21.89 $\pm$ 13.94 / 20.85 $\pm$ 10.63 mm). The performances of participating
models decrease significantly for cross-modality tasks for the liver (DICE:
0.88 $\pm$ 0.15 MSSD: 36.33 $\pm$ 21.97 mm) and all organs (DICE: 0.85 $\pm$
0.21 MSSD: 33.17 $\pm$ 38.93 mm). Despite contrary examples on different
applications, multi-tasking DL models designed to segment all organs seem to
perform worse compared to organ-specific ones (performance drop around 5\%).
Besides, such directions of further research for cross-modality segmentation
would significantly support real-world clinical applications. Moreover, having
more than 1500 participants, another important contribution of the paper is the
analysis on shortcomings of challenge organizations such as the effects of
multiple submissions and peeking phenomena.
中文翻译:
CHAOS 挑战——联合 (CT-MR) 健康腹部器官分割
多年来,腹部器官的分割一直是一个综合但尚未解决的研究领域。在过去十年中,深度学习 (DL) 的深入发展引入了新的最先进的分割系统。为了扩展这些主题的知识,CHAOS - 联合 (CT-MR) 健康腹部器官分割挑战已与 IEEE 生物医学成像国际研讨会 (ISBI) 联合举办,2019 年在意大利威尼斯举行。CHAOS 提供来自健康受试者的腹部 CT 和 MR 数据,用于单个和多个腹部器官分割。设计了五个不同但互补的任务来从多个角度分析当前方法的能力。与手动注释和交互式方法相比,对结果进行了彻底调查。分析表明,DL 模型对单模态 (CT / MR) 的性能可以显示可靠的体积分析性能(DICE:0.98 $\pm$ 0.00 / 0.95 $\pm$ 0.01),但最佳 MSSD 性能仍然有限(21.89 $ \pm$ 13.94 / 20.85 $\pm$ 10.63 毫米)。对于肝脏(DICE:0.88 $\pm$ 0.15 MSSD:36.33 $\pm$ 21.97 mm)和所有器官(DICE:0.85 $\pm$ 0.21 MSSD:33.17 $),参与模型的性能显着下降\pm$ 38.93 毫米)。尽管在不同的应用中有相反的例子,但与器官特异性模型相比,旨在分割所有器官的多任务 DL 模型的性能似乎更差(性能下降约 5%)。此外,跨模态分割的进一步研究方向将极大地支持现实世界的临床应用。而且,
更新日期:2020-05-12
中文翻译:
CHAOS 挑战——联合 (CT-MR) 健康腹部器官分割
多年来,腹部器官的分割一直是一个综合但尚未解决的研究领域。在过去十年中,深度学习 (DL) 的深入发展引入了新的最先进的分割系统。为了扩展这些主题的知识,CHAOS - 联合 (CT-MR) 健康腹部器官分割挑战已与 IEEE 生物医学成像国际研讨会 (ISBI) 联合举办,2019 年在意大利威尼斯举行。CHAOS 提供来自健康受试者的腹部 CT 和 MR 数据,用于单个和多个腹部器官分割。设计了五个不同但互补的任务来从多个角度分析当前方法的能力。与手动注释和交互式方法相比,对结果进行了彻底调查。分析表明,DL 模型对单模态 (CT / MR) 的性能可以显示可靠的体积分析性能(DICE:0.98 $\pm$ 0.00 / 0.95 $\pm$ 0.01),但最佳 MSSD 性能仍然有限(21.89 $ \pm$ 13.94 / 20.85 $\pm$ 10.63 毫米)。对于肝脏(DICE:0.88 $\pm$ 0.15 MSSD:36.33 $\pm$ 21.97 mm)和所有器官(DICE:0.85 $\pm$ 0.21 MSSD:33.17 $),参与模型的性能显着下降\pm$ 38.93 毫米)。尽管在不同的应用中有相反的例子,但与器官特异性模型相比,旨在分割所有器官的多任务 DL 模型的性能似乎更差(性能下降约 5%)。此外,跨模态分割的进一步研究方向将极大地支持现实世界的临床应用。而且,