TU Darmstadt / ULB / TUbiblio

Endo-Sim2Real: Consistency Learning-Based Domain Adaptation for Instrument Segmentation

Sahu, Manish ; Strömsdörfer, Ronja ; Mukhopadhyay, Anirban ; Zachow, Stefan (2020):
Endo-Sim2Real: Consistency Learning-Based Domain Adaptation for Instrument Segmentation.
In: Medical Image Computing and Computer Assisted Intervention – MICCAI 2020, pp. 784-794,
Springer, 23rd International Conference on Medical Image Computing and Computer Assisted Intervention, virtual Conference, 04.-08.10., ISSN 03029743, ISBN 9783030597153,
DOI: 10.1007/978-3-030-59716-0_75,
[Conference or Workshop Item]

Abstract

Surgical tool segmentation in endoscopic videos is an important component of computer assisted interventions systems. Recent success of image-based solutions using fully-supervised deep learning approaches can be attributed to the collection of big labeled datasets. However, the annotation of a big dataset of real videos can be prohibitively expensive and time consuming. Computer simulations could alleviate the manual labeling problem, however, models trained on simulated data do not generalize to real data. This work proposes a consistency-based framework for joint learning of simulated and real (unlabeled) endoscopic data to bridge this performance generalization issue. Empirical results on two data sets (15 videos of the Cholec80 and EndoVis’15 dataset) highlight the effectiveness of the proposed Endo-Sim2Real method for instrument segmentation. We compare the segmentation of the proposed approach with state-of-the-art solutions and show that our method improves segmentation both in terms of quality and quantity.

Item Type: Conference or Workshop Item
Erschienen: 2020
Creators: Sahu, Manish ; Strömsdörfer, Ronja ; Mukhopadhyay, Anirban ; Zachow, Stefan
Title: Endo-Sim2Real: Consistency Learning-Based Domain Adaptation for Instrument Segmentation
Language: English
Abstract:

Surgical tool segmentation in endoscopic videos is an important component of computer assisted interventions systems. Recent success of image-based solutions using fully-supervised deep learning approaches can be attributed to the collection of big labeled datasets. However, the annotation of a big dataset of real videos can be prohibitively expensive and time consuming. Computer simulations could alleviate the manual labeling problem, however, models trained on simulated data do not generalize to real data. This work proposes a consistency-based framework for joint learning of simulated and real (unlabeled) endoscopic data to bridge this performance generalization issue. Empirical results on two data sets (15 videos of the Cholec80 and EndoVis’15 dataset) highlight the effectiveness of the proposed Endo-Sim2Real method for instrument segmentation. We compare the segmentation of the proposed approach with state-of-the-art solutions and show that our method improves segmentation both in terms of quality and quantity.

Title of Book: Medical Image Computing and Computer Assisted Intervention – MICCAI 2020
Publisher: Springer
ISBN: 9783030597153
Divisions: 20 Department of Computer Science
20 Department of Computer Science > Interactive Graphics Systems
Event Title: 23rd International Conference on Medical Image Computing and Computer Assisted Intervention
Event Location: virtual Conference
Event Dates: 04.-08.10.
Date Deposited: 16 Dec 2020 08:14
DOI: 10.1007/978-3-030-59716-0_75
Additional Information:

Part of the Lecture Notes in Computer Science book series (LNCS, volume 12263), Proceedings Part III

Export:
Suche nach Titel in: TUfind oder in Google
Send an inquiry Send an inquiry

Options (only for editors)
Show editorial Details Show editorial Details