Abstract #3515

Automated segmentation of midbrain structures using convolutional neural network

Weiwei Zhao¹, Fangfang Zhou¹, Yida Wang¹, Yang Song¹, Gaiying Li¹, Xu Yan², Yi Wang³, Guang Yang¹, and Jianqi Li¹

¹Shanghai Key Laboratory of Magnetic Resonance, School of Physics and Electronic Science, East China Normal University, Shanghai, China, ²MR Collaboration NE Asia, Siemens Healthcare, Shanghai, China, Shanghai, China, ³Department of Radiology, Weill Medical College of Cornell University, New York, NY, United States

Accurate and automated segmentation of substantia nigra (SN), the subthalamic nucleus (STN), and the red nucleus (RN) in quantitative susceptibility mapping (QSM) images has great significance in many neuroimaging studies. In the present study, we present a novel segmentation method by using convolution neural networks (CNN) to produce automated segmentations of the SN, STN, and RN. The model was validated on manual segmentations from 21 healthy subjects. Average Dice scores were 0.82±0.02 for the SN, 0.70±0.07 for the STN and 0.85±0.04 for the RN.

This abstract and the presentation materials are available to members only; a login is required.

Join Here