当前位置: X-MOL 学术Med. Image Anal. › 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.)
Comparative validation of multi-instance instrument segmentation in endoscopy: Results of the ROBUST-MIS 2019 challenge
Medical Image Analysis ( IF 10.9 ) Pub Date : 2020-11-28 , DOI: 10.1016/j.media.2020.101920
Tobias Roß 1 , Annika Reinke 1 , Peter M Full 2 , Martin Wagner 3 , Hannes Kenngott 3 , Martin Apitz 3 , Hellena Hempe 4 , Diana Mindroc-Filimon 4 , Patrick Scholz 5 , Thuy Nuong Tran 4 , Pierangela Bruno 6 , Pablo Arbeláez 7 , Gui-Bin Bian 8 , Sebastian Bodenstedt 9 , Jon Lindström Bolmgren 10 , Laura Bravo-Sánchez 7 , Hua-Bin Chen 8 , Cristina González 7 , Dong Guo 11 , Pål Halvorsen 12 , Pheng-Ann Heng 13 , Enes Hosgor 10 , Zeng-Guang Hou 8 , Fabian Isensee 2 , Debesh Jha 14 , Tingting Jiang 15 , Yueming Jin 13 , Kadir Kirtac 10 , Sabrina Kletz 16 , Stefan Leger 9 , Zhixuan Li 15 , Klaus H Maier-Hein 17 , Zhen-Liang Ni 8 , Michael A Riegler 18 , Klaus Schoeffmann 16 , Ruohua Shi 15 , Stefanie Speidel 9 , Michael Stenzel 10 , Isabell Twick 10 , Gutai Wang 11 , Jiacheng Wang 19 , Liansheng Wang 19 , Lu Wang 11 , Yujie Zhang 19 , Yan-Jie Zhou 8 , Lei Zhu 13 , Manuel Wiesenfarth 20 , Annette Kopp-Schneider 20 , Beat P Müller-Stich 3 , Lena Maier-Hein 4
Affiliation  

Intraoperative tracking of laparoscopic instruments is often a prerequisite for computer and robotic-assisted interventions. While numerous methods for detecting, segmenting and tracking of medical instruments based on endoscopic video images have been proposed in the literature, key limitations remain to be addressed: Firstly, robustness, that is, the reliable performance of state-of-the-art methods when run on challenging images (e.g. in the presence of blood, smoke or motion artifacts). Secondly, generalization; algorithms trained for a specific intervention in a specific hospital should generalize to other interventions or institutions.

In an effort to promote solutions for these limitations, we organized the Robust Medical Instrument Segmentation (ROBUST-MIS) challenge as an international benchmarking competition with a specific focus on the robustness and generalization capabilities of algorithms. For the first time in the field of endoscopic image processing, our challenge included a task on binary segmentation and also addressed multi-instance detection and segmentation. The challenge was based on a surgical data set comprising 10,040 annotated images acquired from a total of 30 surgical procedures from three different types of surgery. The validation of the competing methods for the three tasks (binary segmentation, multi-instance detection and multi-instance segmentation) was performed in three different stages with an increasing domain gap between the training and the test data. The results confirm the initial hypothesis, namely that algorithm performance degrades with an increasing domain gap. While the average detection and segmentation quality of the best-performing algorithms is high, future research should concentrate on detection and segmentation of small, crossing, moving and transparent instrument(s) (parts).



中文翻译:

内窥镜中多实例仪器细分的比较验证:ROBUST-MIS 2019挑战的结果

腹腔镜器械的术中跟踪通常是计算机和机器人辅助干预的先决条件。尽管在文献中提出了许多基于内窥镜视频图像的医疗器械检测,分割和跟踪方法,但仍存在一些关键的局限性:首先,鲁棒性,即最先进方法的可靠性能在具有挑战性的图像上运行时(例如在有血液,烟雾或运动伪影的情况下)。其次,泛化;在特定医院接受特定干预措施培训的算法应推广到其他干预措施或机构。

为了推广解决这些局限性的解决方案,我们组织了稳健的医疗器械细分(ROBUST-MIS)挑战作为一项国际基准测试竞赛,重点关注算法的鲁棒性和泛化能力。在内窥镜图像处理领域,我们的挑战首次包括二进制分割任务,并且还解决了多实例检测和分割问题。挑战基于外科手术数据集,该数据集包括从三种不同类型的手术中总共进行的30项手术程序中获得的10,040张带注释的图像。在三个不同阶段中对三个任务(二进制分割,多实例检测和多实例分割)的竞争方法进行了验证,并且训练和测试数据之间的域差距越来越大。结果证实了最初的假设,即算法性能随着域间隙的增加而降低。

更新日期:2020-11-28
down
wechat
bug