Learning Normalized Inputs for Iterative Estimation in Medical Image Segmentation

Segmentation is an active area of research in medical image analysis. With the introduction of Convolutional Neural Networks (CNNs), significant improvements in performance have been achieved in many standard datasets. For example, for the EM ISBI 2012 dataset  (Arganda-Carreras et al., 2015), PROMISE12 challenge or MS lesions (Styner et al., 2008), the top entries are built on CNNs (Ronneberger et al., 2015; Chen et al., 2016b; Havaei et al., 2017; Yu et al., 2017).

Source: Medical Image Analysis - November 14, 2017 Category: Radiology Authors: Michal Drozdzal, Gabriel Chartrand, Eugene Vorontsov, Mahsa Shakeri, Lisa Di Jorio, An Tang, Adriana Romero, Yoshua Bengio, Chris Pal, Samuel Kadoury Source Type: research