Keywords: Assessor inter-variability modeling, Hypersphere auto-encoder, segmentation, localization
TL;DR: In this paper, assessor inter-variability is modeled in a novel deep learning architecture to improve performance on several data sets using the proposed hypersphere auto-encoder.
Abstract: In medical imaging, a proper gold-standard ground truth as e.g. annotated segmentations by assessors or experts is lacking or only scarcely available and suffers from large inter- variability in those segmentations. Most state-of-the-art segmentation models do not take inter-observer variability into account and are fully deterministic in nature. In this work, we propose hypersphere auto-encoders in combination with dynamic leaky ReLUs, as a new method to explicitly incorporate inter-observer variability into a segmentation model. With this model we can then generate multiple proposals based on the inter-observer agreement. As a result, the output segmentations of the proposed model can be tuned to typical margins inherent to the ambiguity in the data. For experimental validation, we show improved segmentation results on a medical data set. The proposed method has several advantages over current state-of-the-art segmentation models such as interpretability in the uncertainty of segmentation borders.
Code Of Conduct: I have read and accept the code of conduct.
Remove If Rejected: Remove submission from public view if paper is rejected.