Longitudinal Image Registration with Temporal-order and Subject-specificity Discrimination

TL;DR

This paper introduces a learning-based image registration method for longitudinal prostate MRI analysis, improving accuracy in tracking disease progression by combining intensity similarity, gland segmentation, and novel regularization techniques.

Contribution

It presents a new registration algorithm that leverages weak supervision and a maximum mean discrepancy regularization to enhance longitudinal image alignment accuracy.

Findings

Significantly reduced registration errors compared to baseline methods.

Effective use of gland segmentation as weak supervision.

Statistically significant improvements with proposed sampling strategies.

Abstract

Morphological analysis of longitudinal MR images plays a key role in monitoring disease progression for prostate cancer patients, who are placed under an active surveillance program. In this paper, we describe a learning-based image registration algorithm to quantify changes on regions of interest between a pair of images from the same patient, acquired at two different time points. Combining intensity-based similarity and gland segmentation as weak supervision, the population-data-trained registration networks significantly lowered the target registration errors (TREs) on holdout patient data, compared with those before registration and those from an iterative registration algorithm. Furthermore, this work provides a quantitative analysis on several longitudinal-data-sampling strategies and, in turn, we propose a novel regularisation method based on maximum mean discrepancy, between differently-sampled training image pairs. Based on 216 3D MR images from 86 patients, we report a mean TRE of 5.6 mm and show statistically significant differences between the different training data sampling strategies.