Constrained-CNN Losses for Weakly Supervised Segmentation

In the recent years, deep convolutional neural networks (CNNs) have been dominating semantic segmentation problems, both in computer vision and medical imaging, achieving ground-breaking performances when full-supervision is available (Long et  al., 2015; Dolz et al., 2018; Litjens et al., 2017). In semantic segmentation, full supervision requires laborious pixel/voxel annotations, which may not be available in a breadth of applications, more so when dealing with volumetric data. Furthermore, pixel/voxel level annotations become a seri ous impediment for scaling deep segmentation networks to new object categories or target domains.

Source: Medical Image Analysis - February 12, 2019 Category: Radiology Authors: Hoel Kervadec, Jose Dolz, Meng Tang, Eric Granger, Yuri Boykov, Ismail Ben Ayed Source Type: research