Many recent machine learning approaches used in medical imaging are highly reliant on large amounts of image and ground truth data. In the context of object segmentation, pixel-wise annotations are extremely expensive to collect, especially in video and 3D volumes. To reduce this annotation burden, we propose a novel framework to allow annotators to simply observe the object to segment and record where they have looked at with a $200 eye gaze tracker. Our method then estimates pixel-wise probabilities for the presence of the object throughout the sequence from which we train a classifier in semi-supervised setting using a novel Expected Exponential loss function. We show that our framework provides superior performances on a wide range of medical image settings compared to existing strategies and that our method can be combined with current crowd-sourcing paradigms as well.
@article{arxiv.1707.04905,
title = {Expected exponential loss for gaze-based video and volume ground truth annotation},
author = {Laurent Lejeune and Mario Christoudias and Raphael Sznitman},
journal= {arXiv preprint arXiv:1707.04905},
year = {2017}
}