# Semi-weakly-supervised neural network training for medical image registration

arXiv: https://arxiv.org/abs/2402.10728 · HTML: https://mlsanity.com/paper/2402.10728/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 44 references that are in the map.
- First posted on arXiv 16 Feb 2024.

## Builds on (most cited first, 21 of 21)

- [On the Opportunities and Risks of Foundation Models](https://mlsanity.com/paper/2108.07258/) (2021)
- [Semi-Supervised Semantic Segmentation with Cross Pseudo Supervision](https://mlsanity.com/paper/2106.01226/) (2021)
- [MONAI: An open-source framework for deep learning in healthcare](https://mlsanity.com/paper/2211.02701/) (2022)
- [PseudoSeg: Designing Pseudo Labels for Semantic Segmentation](https://mlsanity.com/paper/2010.09713/) (2020)
- [Adversarial Learning for Semi-Supervised Semantic Segmentation](https://mlsanity.com/paper/1802.07934/) (2018)
- [Deep Learning in Medical Image Registration: A Survey](https://mlsanity.com/paper/1903.02026/) (2019)
- [Guided Collaborative Training for Pixel-wise Semi-Supervised Learning](https://mlsanity.com/paper/2008.05258/) (2020)
- [Perturbed and Strict Mean Teachers for Semi-supervised Semantic Segmentation](https://mlsanity.com/paper/2111.12903/) (2021)
- [Deep Learning in Medical Image Registration: A Review](https://mlsanity.com/paper/1912.12318/) (2019)
- [Weakly-Supervised Convolutional Neural Networks for Multimodal Image Registration](https://mlsanity.com/paper/1807.03361/) (2018)
- [Foundational Models in Medical Imaging: A Comprehensive Survey and Future Vision](https://mlsanity.com/paper/2310.18689/) (2023)
- [End-to-End Unsupervised Deformable Image Registration with a Convolutional Neural Network](https://mlsanity.com/paper/1704.06065/) (2017)
- [DeepAtlas: Joint Semi-Supervised Learning of Image Registration and Segmentation](https://mlsanity.com/paper/1904.08465/) (2019)
- [Structured Consistency Loss for semi-supervised semantic segmentation](https://mlsanity.com/paper/2001.04647/) (2020)
- [Label-driven weakly-supervised learning for multimodal deformable image registration](https://mlsanity.com/paper/1711.01666/) (2017)
- [Non-rigid image registration using fully convolutional networks with deep self-supervision](https://mlsanity.com/paper/1709.00799/) (2017)
- [Linear and Deformable Image Registration with 3D Convolutional Neural Networks](https://mlsanity.com/paper/1809.06226/) (2018)
- [Enhancing Label-Driven Deep Deformable Image Registration with Local Distance Metrics for State-of-the-Art Cardiac Motion Tracking](https://mlsanity.com/paper/1812.01859/) (2018)
- [NeurReg: Neural Registration and Its Application to Image Segmentation](https://mlsanity.com/paper/1910.01763/) (2019)
- [Longitudinal Image Registration with Temporal-order and Subject-specificity Discrimination](https://mlsanity.com/paper/2008.13002/) (2020)
- [Deep Deformable Registration: Enhancing Accuracy by Fully Convolutional Neural Net](https://mlsanity.com/paper/1611.08796/) (2016)

## Built on by (most cited first, 2 of 2)

- [GuidedMorph: Two-Stage Deformable Registration for Breast MRI](https://mlsanity.com/paper/2505.13414/) (2025)
- [Segmentation Regularized Training for Multi-Domain Deep Learning Registration applied to MR-Guided Prostate Cancer Radiotherapy](https://mlsanity.com/paper/2507.06966/) (2025)

## Abstract (arXiv)

For training registration networks, weak supervision from segmented corresponding regions-of-interest (ROIs) have been proven effective for (a) supplementing unsupervised methods, and (b) being used independently in registration tasks in which unsupervised losses are unavailable or ineffective. This correspondence-informing supervision entails cost in annotation that requires significant specialised effort. This paper describes a semi-weakly-supervised registration pipeline that improves the model performance, when only a small corresponding-ROI-labelled dataset is available, by exploiting unlabelled image pairs. We examine two types of augmentation methods by perturbation on network weights and image resampling, such that consistency-based unsupervised losses can be applied on unlabelled data. The novel WarpDDF and RegCut approaches are proposed to allow commutative perturbation between an image pair and the predicted spatial transformation (i.e. respective input and output of registration networks), distinct from existing perturbation methods for classification or segmentation. Experiments using 589 male pelvic MR images, labelled with eight anatomical ROIs, show the improvement in registration performance and the ablated contributions from the individual strategies. Furthermore, this study attempts to construct one of the first computational atlases for pelvic structures, enabled by registering inter-subject MRs, and quantifies the significant differences due to the proposed semi-weak supervision with a discussion on the potential clinical use of example atlas-derived statistics.