% IMPORTANT: The following is UTF-8 encoded. This means that in the presence
% of non-ASCII characters, it will not work with BibTeX 0.99 or older.
% Instead, you should use an up-to-date BibTeX implementation like “bibtex8” or
% “biber”.
@ARTICLE{Ross:134894,
author = {T. Ross$^*$ and D. Zimmerer$^*$ and A. Vemuri$^*$ and F.
Isensee$^*$ and M. Wiesenfarth$^*$ and S. Bodenstedt and F.
Both and P. Kessler and M. Wagner and B. Müller and H.
Kenngott and S. Speidel and A. Kopp-Schneider$^*$ and K.
Maier-Hein$^*$ and L. Maier-Hein$^*$},
title = {{E}xploiting the potential of unlabeled endoscopic video
data with self-supervised learning.},
journal = {International journal of computer assisted radiology and
surgery},
volume = {13},
number = {6},
issn = {1861-6429},
address = {Berlin},
publisher = {Springer},
reportid = {DKFZ-2018-00682},
pages = {925 - 933},
year = {2018},
note = {E132 entspricht E230},
abstract = {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 $75\%$ without sacrificing
performance. Our method also outperforms alternative methods
for CNN pre-training, such as pre-training on publicly
available non-medical (COCO) or medical data (MICCAI
EndoVis2017 challenge) using the target task (in this
instance: segmentation).As it makes efficient use of
available (non-)public and (un-)labeled data, the approach
has the potential to become a valuable tool for CNN
(pre-)training.},
cin = {E130 / E132 / E230 / C060},
ddc = {610},
cid = {I:(DE-He78)E130-20160331 / I:(DE-He78)E132-20160331 /
I:(DE-He78)E230-20160331 / I:(DE-He78)C060-20160331},
pnm = {315 - Imaging and radiooncology (POF3-315)},
pid = {G:(DE-HGF)POF3-315},
typ = {PUB:(DE-HGF)16},
pubmed = {pmid:29704196},
doi = {10.1007/s11548-018-1772-0},
url = {https://inrepo02.dkfz.de/record/134894},
}