标题：S3egANet: 3D Spinal Structures Segmentation via Adversarial Nets
作者：Li T.; Wei B.; Cong J.; Li X.; Li S.
作者机构：[Li, T] College of Science and Technology, Shandong University of Traditional Chinese Medicine, Jinan, 250355, China, Center for Medical Artificial In 更多
通讯作者地址：[Wei, B] Center for Medical Artificial Intelligence, Shandong University of Traditional Chinese MedicineChina;
关键词：Adversarial nets; computer-aided detection and diagnosis; magnetic resonance imaging; multi-modality; multi-stage; segmentation; spine
摘要：3D spinal structures segmentation is crucial to reduce the time-consumption issue and provide quantitative parameters for disease treatment and surgical operation. However, the most related studies of spinal structures segmentation are based on 2D or 3D single structure segmentation. Due to the high complexity of spinal structures, the segmentation of 3D multiple spinal structures with consistently reliable and high accuracy is still a significant challenge. We developed and validated a relatively complete solution for the simultaneous 3D semantic segmentation of multiple spinal structures at the voxel level named as the S3egANet. Firstly, S3egANet explicitly solved the high variety and variability of complex 3D spinal structures through a multi-modality autoencoder module that was capable of extracting fine-grained structural information. Secondly, S3egANet adopted a cross-modality voxel fusion module to incorporate comprehensive spatial information from multi-modality MRI images. Thirdly, we presented a multi-stage adversarial learning strategy to achieve high accuracy and reliability segmentation of multiple spinal structures simultaneously. Extensive experiments on MRI images of 90 patients demonstrated that S3egANet achieved mean Dice coefficient of 88.3% and mean Sensitivity of 91.45%, which revealed its effectiveness and potential as a clinical tool. © 2013 IEEE.