Fine-Grain Segmentation of the Intervertebral Discs from MR Spine Images Using Deep Convolutional Neural Networks: BSU-Net

Applied Sciences

Koichi Masuda¹  Christine B. Chung²  Won C. Bae²  Dosik Hwang³  Sewon Kim³ 

[1] Department of Orthopedic Surgery, University of California-San Diego, La Jolla, CA 92037, USA;Department of Radiology, VA San Diego Healthcare System, San Diego, CA 92161-0114, USA;School of Electrical and Electronic Engineering, Yonsei University, Seoul 03722, Korea;

关键词: intervertebral disc;    segmentation;    convolutional neural network;    fine grain segmentation;    U-net;    deep learning;    magnetic resonance image;    lumbar spine;   

DOI  :  10.3390/app8091656

来源: DOAJ

【 摘 要 】

We propose a new deep learning network capable of successfully segmenting intervertebral discs and their complex boundaries from magnetic resonance (MR) spine images. The existing U-network (U-net) is known to perform well in various segmentation tasks in medical images; however, its performance with respect to details of segmentation such as boundaries is limited by the structural limitations of a max-pooling layer that plays a key role in feature extraction process in the U-net. We designed a modified convolutional and pooling layer scheme and applied a cascaded learning method to overcome these structural limitations of the max-pooling layer of a conventional U-net. The proposed network achieved 3% higher Dice similarity coefficient (DSC) than conventional U-net for intervertebral disc segmentation (89.44% vs. 86.44%, respectively; p < 0.001). For intervertebral disc boundary segmentation, the proposed network achieved 10.46% higher DSC than conventional U-net (54.62% vs. 44.16%, respectively; p < 0.001).

【 授权许可】

Unknown