A Cascaded Deep Convolutional Neural Network for Joint Segmentation and Genotype Prediction of Brainstem Gliomas.
Journal:
IEEE transactions on bio-medical engineering
PMID:
29993462
Abstract
GOAL: Automatic segmentation of brainstem gliomas and prediction of genotype (H3 K27M) mutation status based on magnetic resonance (MR) images are crucial but challenging tasks for computer-aided diagnosis in neurosurgery. In this paper, we present a novel cascaded deep convolutional neural network (CNN) to address these two challenging tasks simultaneously.