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

TL;DR

Segis-Net is a novel deep-learning framework that simultaneously performs segmentation and registration on longitudinal MRI data, improving accuracy and reproducibility for brain analysis over time.

Contribution

This work introduces Segis-Net, a single-step deep-learning method that jointly optimizes segmentation and registration for longitudinal MRI analysis, enhancing efficiency and reliability.

Findings

Significant improvement in registration accuracy.

Enhanced spatio-temporal segmentation consistency.

Reduced sample size needed for statistical power.

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.