Sciatic Nerve Segmentation in MRI Volumes of the Upper Leg via 3D Convolutional Neural Networks

In Charcot-Marie-Tooth disease (CMT) diseases, sciatic nerve (SN) hypertrophy may be a viable biomarker of patient impairment. Estimating nerve diameters currently requires labor-intensive manual segmentations. Our goal was to use 3D convolutional neural networks (CNN), which have been applied successfully in other biomedical imaging applications, to segment the SN. Using a 3D U-Net architecture developed in Keras 2.0 and Python 2.7, we trained CNNs on data partitioned from 38 control and 34 CMT patients with manually defined region-of-interests (ROI). We found that batch-normalizing 3D CNNs achieved the highest performance, demonstrating CNN’s ability to automatically produce high-quality segmentations of the SN.