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

arXiv: https://arxiv.org/abs/2008.13002 · HTML: https://mlsanity.com/paper/2008.13002/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 29 Aug 2020.

## Built on by (most cited first, 5 of 5)

- [Cross-Modality Image Registration using a Training-Time Privileged Third Modality](https://mlsanity.com/paper/2207.12901/) (2022)
- [Capturing Longitudinal Changes in Brain Morphology Using Temporally Parameterized Neural Displacement Fields](https://mlsanity.com/paper/2504.09514/) (2025)
- [Morphological Change Forecasting for Prostate Glands using Feature-based Registration and Kernel Density Extrapolation](https://mlsanity.com/paper/2101.06425/) (2021)
- [Semi-weakly-supervised neural network training for medical image registration](https://mlsanity.com/paper/2402.10728/) (2024)
- [Collaborative Quantization Embeddings for Intra-Subject Prostate MR Image Registration](https://mlsanity.com/paper/2207.06189/) (2022)

## Abstract (arXiv)

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.