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.
@article{arxiv.2008.13002,
title = {Longitudinal Image Registration with Temporal-order and Subject-specificity Discrimination},
author = {Qianye Yang and Yunguan Fu and Francesco Giganti and Nooshin Ghavami and Qingchao Chen and J. Alison Noble and Tom Vercauteren and Dean Barratt and Yipeng Hu},
journal= {arXiv preprint arXiv:2008.13002},
year = {2020}
}