Longitudinal diffusion MRI analysis using Segis-Net: a single-step deep-learning framework for simultaneous segmentation and registration

Abstract

This work presents a single-step deep-learning framework for longitudinal image analysis, coined Segis-Net. To optimally exploit information available in longitudinal data, this method concurrently learns a multi-class segmentation and nonlinear registration. Segmentation and registration are modeled using a convolutional neural network and optimized simultaneously for their mutual benefit. An objective function that optimizes spatial correspondence for the segmented structures across time-points is proposed. We applied Segis-Net to the analysis of white matter tracts from N=8045 longitudinal brain MRI datasets of 3249 elderly individuals. Segis-Net approach showed a significant increase in registration accuracy, spatio-temporal segmentation consistency, and reproducibility comparing with two multistage pipelines. This also led to a significant reduction in the sample-size that would be required to achieve the same statistical power in analyzing tract-specific measures. Thus, we expect that Segis-Net can serve as a new reliable tool to support longitudinal imaging studies to investigate macro- and microstructural brain changes over time.

To appear in NeuroImage

References in corpus (10)

• Adam: A Method for Stochastic Optimization
• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• VoxelMorph: A Learning Framework for Deformable Medical Image Registration
• TractSeg - Fast and accurate white matter tract segmentation
• Semi-Supervised Medical Image Segmentation via Learning Consistency under Transformations
• Label-driven weakly-supervised learning for multimodal deformable image registration
• DeepAtlas: Joint Semi-Supervised Learning of Image Registration and Segmentation
• Deep Segmentation and Registration in X-Ray Angiography Video
• A hybrid deep learning framework for integrated segmentation and registration: evaluation on longitudinal white matter tract changes
• Learning unbiased group-wise registration (LUGR) and joint segmentation: evaluation on longitudinal diffusion MRI

Cited by in corpus (2)

• Local Spatiotemporal Representation Learning for Longitudinally-consistent Neuroimage Analysis
• FetDTIAlign: A Deep Learning Framework for Affine and Deformable Registration of Fetal Brain dMRI