TY  - JOUR
AU  - Ross, Tobias
AU  - Zimmerer, David
AU  - Vemuri, Anant
AU  - Isensee, Fabian
AU  - Wiesenfarth, Manuel
AU  - Bodenstedt, Sebastian
AU  - Both, Fabian
AU  - Kessler, Philip
AU  - Wagner, Martin
AU  - Müller, Beat
AU  - Kenngott, Hannes
AU  - Speidel, Stefanie
AU  - Kopp-Schneider, Annette
AU  - Maier-Hein, Klaus
AU  - Maier-Hein, Lena
TI  - Exploiting the potential of unlabeled endoscopic video data with self-supervised learning.
JO  - International journal of computer assisted radiology and surgery
VL  - 13
IS  - 6
SN  - 1861-6429
CY  - Berlin
PB  - Springer
M1  - DKFZ-2018-00682
SP  - 925 - 933
PY  - 2018
N1  - E132 entspricht E230
AB  - Surgical data science is a new research field that aims to observe all aspects of the patient treatment process in order to provide the right assistance at the right time. Due to the breakthrough successes of deep learning-based solutions for automatic image annotation, the availability of reference annotations for algorithm training is becoming a major bottleneck in the field. The purpose of this paper was to investigate the concept of self-supervised learning to address this issue.Our approach is guided by the hypothesis that unlabeled video data can be used to learn a representation of the target domain that boosts the performance of state-of-the-art machine learning algorithms when used for pre-training. Core of the method is an auxiliary task based on raw endoscopic video data of the target domain that is used to initialize the convolutional neural network (CNN) for the target task. In this paper, we propose the re-colorization of medical images with a conditional generative adversarial network (cGAN)-based architecture as auxiliary task. A variant of the method involves a second pre-training step based on labeled data for the target task from a related domain. We validate both variants using medical instrument segmentation as target task.The proposed approach can be used to radically reduce the manual annotation effort involved in training CNNs. Compared to the baseline approach of generating annotated data from scratch, our method decreases exploratively the number of labeled images by up to 75
LB  - PUB:(DE-HGF)16
C6  - pmid:29704196
DO  - DOI:10.1007/s11548-018-1772-0
UR  - https://inrepo02.dkfz.de/record/134894
ER  -