3D Deep Neural Network to Automatically Identify TSC Structural Brain Pathology based on MRI

During childhood, neurological involvement in tuberous sclerosis complex (TSC) is a leading cause of death. Neurological involvement, including epilepsy, can cause significant long-term sequelae in children. Recent research demonstrates a correlation between tuber load and outcome. Although this relationship is complex, tubers are associated with epilepsy, affecting more than 90% of patients with TSC and may become intractable. Brain involvement in TSC can be detected by magnetic resonance imaging (MRI). Still, neuroimaging analysis is time- and labor-intensive, begging the need for automated approaches to these tasks to improve speed, accuracy, and availability. In this light, we explored the general feasibility of using three-dimensional convolutional neural networks (CNNs) to automatically enhance image diagnosis quality and consistency to identify anatomical abnormalities in TSC children. We trained the 3D CNN on axial T1-weighted, axial T2-weighted FLAIR, and 3D T1-FSPGR weighted images from 296 TSC and 245 Normal cases from birth to 8 years of age acquired at Le Bonheur Children’s Hospital. In the best performing approach, we achieved an accuracy of 0.86 [95% CI:0.76-0.97] with 0.95% AUC. The code can be found in https://github.com/shabanian2018/TSC3DCNN