A new deep-learning approach for early detection of shape variations in autism using structural mr

Abstract

This paper introduces a novel shape-based computer-aided diagnosis (CAD) system using magnetic resonance (MR) brain images for autism diagnosis at different life stages. To improve the classification robustness, the system fuses the shape features extracted from the cerebral cortex (Cx) and cerebral white matter (CWM). Fusion is conducted based on the findings suggesting that Cx changes in autism are related to CWM abnormalities. The CAD system starts with segmenting Cx and CWM using a 3D joint model that combines intensity, shape, and spatial information. Then, Spherical Harmonic (SPHARM) is applied to the re-constructed meshes of Cx to derive 4 metrics for each mesh point; normal curvature, mean curvature, gaussian curvature, and Cx surface reconstruction error. To analyze the CWM shape, distance maps of its gyri are computed and three more shape features are extracted for these gyri. Finally, all the extracted shape features are fed to a multi-level deep network for feature fusion and diagnosis. The CAD system has been evaluated using subjects from the ABIDE database (8-12.8 years), achieving an accuracy of 93%, and from NDAR/Pitt database (16-51 years), achieving an accuracy of 97%. Also in order to show the capability of the system for early diagnosis, it has been tested on NDAR/IBIS database for infants, resulting in an accuracy of 85%. These initial results on the 3 databases hold the promise of efficient autism diagnosis.