Find in Library

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.