Ontology highlight
ABSTRACT:
SUBMITTER: Kim D
PROVIDER: S-EPMC6682685 | biostudies-literature | 2019
REPOSITORIES: biostudies-literature
Kim Donnie D Wang Nicholas N Ravikumar Viswesh V Raghuram D R DR Li Jinju J Patel Ankit A Wendt Richard E RE Rao Ganesh G Rao Arvind A
Frontiers in computational neuroscience 20190730
This study compared the predictive power and robustness of texture, topological, and convolutional neural network (CNN) based image features for measuring tumors in MRI. These features were used to predict 1p/19q codeletion in the MICCAI BRATS 2017 challenge dataset. Topological data analysis (TDA) based on persistent homology had predictive performance as good as or better than texture-based features and was also less susceptible to image-based perturbations. Features from a pre-trained convolu ...[more]