Longitudinal Image Registration with Temporal-order and Subject-specificity Discrimination
This work addresses monitoring disease progression in prostate cancer patients under active surveillance, representing an incremental improvement with domain-specific impact.
The paper tackled the problem of quantifying changes in longitudinal MR images for prostate cancer patients by developing a learning-based image registration algorithm, which reduced target registration errors to a mean of 5.6 mm on holdout data compared to baseline methods.
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.