Learning unbiased group-wise registration (LUGR) and joint segmentation: evaluation on longitudinal diffusion MRI

TL;DR

This paper introduces an unbiased group-wise registration framework for longitudinal diffusion MRI analysis, improving segmentation consistency and reducing bias compared to traditional pairwise methods, with broad applicability in longitudinal imaging studies.

Contribution

The paper presents a novel analytical framework for unbiased group-wise registration that jointly optimizes registration and segmentation, overcoming limitations of fixed-reference approaches.

Findings

Significantly lower processing bias than pairwise fixed-reference methods

Reproducibility confirmed on test-retest data

Implicit reference image is an average of input images

Abstract

Analysis of longitudinal changes in imaging studies often involves both segmentation of structures of interest and registration of multiple timeframes. The accuracy of such analysis could benefit from a tailored framework that jointly optimizes both tasks to fully exploit the information available in the longitudinal data. Most learning-based registration algorithms, including joint optimization approaches, currently suffer from bias due to selection of a fixed reference frame and only support pairwise transformations. We here propose an analytical framework based on an unbiased learning strategy for group-wise registration that simultaneously registers images to the mean space of a group to obtain consistent segmentations. We evaluate the proposed method on longitudinal analysis of a white matter tract in a brain MRI dataset with 2-3 time-points for 3249 individuals, i.e., 8045 images in total. The reproducibility of the method is evaluated on test-retest data from 97 individuals. The results confirm that the implicit reference image is an average of the input image. In addition, the proposed framework leads to consistent segmentations and significantly lower processing bias than that of a pair-wise fixed-reference approach. This processing bias is even smaller than those obtained when translating segmentations by only one voxel, which can be attributed to subtle numerical instabilities and interpolation. Therefore, we postulate that the proposed mean-space learning strategy could be widely applied to learning-based registration tasks. In addition, this group-wise framework introduces a novel way for learning-based longitudinal studies by direct construction of an unbiased within-subject template and allowing reliable and efficient analysis of spatio-temporal imaging biomarkers.