A convolutional autoencoder approach to learn volumetric shape representations for brain structures.

A CONVOLUTIONAL AUTOENCODER APPROACH TO LEARN VOLUMETRIC SHAPE REPRESENTATIONS FOR BRAIN STRUCTURES. Proc IEEE Int Symp Biomed Imaging. 2019 Apr;2019:1559-1562 Authors: Yu EM, Sabuncu MR Abstract We propose a novel machine learning strategy for studying neuroanatomical shape variation. Our model works with volumetric binary segmentation images, and requires no preprocessing such as the extraction of surface points or a mesh. The learned shape descriptor is invariant to affine transformations, including shifts, rotations and scaling. Thanks to the adopted autoencoder framework, inter-subject differences are automatically enhanced in the learned representation, while intra-subject variances are minimized. Our experimental results on a shape retrieval task showed that the proposed representation outperforms a state-of-the-art benchmark for brain structures extracted from MRI scans. PMID: 32774763 [PubMed]
Source: Proceedings - International Symposium on Biomedical Imaging - Category: Radiology Tags: Proc IEEE Int Symp Biomed Imaging Source Type: research