Towards a deep learning approach to brain parcellation
Noah Lee, Andrew F. Laine, Arno Klein · 2011
Establishing correspondences across structural and functional brain images via labeling, or parcellation, is an important and challenging task for clinical neuroscience and cognitive psychology. A limitation with existing approaches is that they i) possess shallow architectures, ii) are based on heuristic manual feature engineering, and iii) assume the validity of the designed feature model. In contrast, we advocate a deep learning approach to automate brain parcellation. We present a novel application of convolutional networks to build discriminative features for brain parcellation, which are automatically learned from labels provided by human experts. Initial validation experiments show promising results for automatic brain parcellation, suggesting that the proposed approach has potential to be an alternative to template or atlas-based parcellation approaches.