Deep learning for semantic segmentation of organs and tissues in laparoscopic surgery
Author:
Scheikl Paul Maria1, Laschewski Stefan1, Kisilenko Anna2, Davitashvili Tornike2, Müller Benjamin2, Capek Manuela2, Müller-Stich Beat P.2, Wagner Martin2, Mathis-Ullrich Franziska1
Affiliation:
1. Institute for Anthropomatics and Robotics, Karlsruhe Institute of Technology , Karlsruhe , Germany 2. Department for General, Visceral and Transplantation Surgery, Heidelberg University Hospital , Heidelberg , Germany
Abstract
Abstract
Semantic segmentation of organs and tissue types is an important sub-problem in image based scene understanding for laparoscopic surgery and is a prerequisite for context-aware assistance and cognitive robotics. Deep Learning (DL) approaches are prominently applied to segmentation and tracking of laparoscopic instruments. This work compares different combinations of neural networks, loss functions, and training strategies in their application to semantic segmentation of different organs and tissue types in human laparoscopic images in order to investigate their applicability as components in cognitive systems. TernausNet-11 trained on Soft-Jaccard loss with a pretrained, trainable encoder performs best in regard to segmentation quality (78.31% mean Intersection over Union [IoU]) and inference time (28.07 ms) on a single GTX 1070 GPU.
Publisher
Walter de Gruyter GmbH
Subject
Biomedical Engineering
Reference20 articles.
1. Teatini, A, Pelanis, E, Aghayan, DL, Kumar, RP, Palomar, R, Fretland, ÅA, et al. The effect of intraoperative imaging on surgical navigation for laparoscopic liver resection surgery. Sci Rep 2019;9:1–11. https://doi.org/10.1038/s41598-019-54915-3. 2. Hashizume, M, Yasunaga, T, Tanoue, K, Ieiri, S, Konishi, K, Kishi, K, et al. New real-time mr image-guided surgical robotic system for minimally invasive precision surgery. Int J Comput Assist Radiol Surg 2008;2:317–25. https://doi.org/10.1007/s11548-007-0146-9. 3. Zadeh, SM, Francois, T, Calvet, L, Chauvet, P, Canis, M, Bartoli, A, et al. Surgai: deep learning for computerized laparoscopic image understanding in gynaecology. Surg Endosc 2020:1–7. https://doi.org/10.1007/s00464-019-07330-8. 4. Long, J, Shelhamer, E, Darrell, T. Fully convolutional networks for semantic segmentation. In: IEEE CVPR; 2015:3431–40 pp. 5. Isensee, F. Petersen, J, Kohl, SAA, Jäger, PF, Maier-Hein, KH. nnu-net: breaking the spell on successful medical image segmentation. ArXiv 2019;abs/1904.08128.
Cited by
22 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献
|
|