# Learning Multi-Modal Volumetric Prostate Registration with Weak Inter-Subject Spatial Correspondence

arXiv: https://arxiv.org/abs/2102.04938 · HTML: https://mlsanity.com/paper/2102.04938/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 6 of its 13 references that are in the map.
- First posted on arXiv 9 Feb 2021.

## Builds on (most cited first, 6 of 6)

- [3D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotation](https://mlsanity.com/paper/1606.06650/) (2016)
- [Weakly-Supervised Convolutional Neural Networks for Multimodal Image Registration](https://mlsanity.com/paper/1807.03361/) (2018)
- [NiftyNet: a deep-learning platform for medical imaging](https://mlsanity.com/paper/1709.03485/) (2017)
- [Label-driven weakly-supervised learning for multimodal deformable image registration](https://mlsanity.com/paper/1711.01666/) (2017)
- [Learning Deep Similarity Metric for 3D MR-TRUS Registration](https://mlsanity.com/paper/1806.04548/) (2018)
- [Deep Attentive Features for Prostate Segmentation in 3D Transrectal Ultrasound](https://mlsanity.com/paper/1907.01743/) (2019)

## Built on by (most cited first, 4 of 4)

- [Cross-modal Attention for MRI and Ultrasound Volume Registration](https://mlsanity.com/paper/2107.04548/) (2021)
- [A Narrative Review of Image Processing Techniques Related to Prostate Ultrasound](https://mlsanity.com/paper/2407.00678/) (2024)
- [Deep learning in medical image registration: introduction and survey](https://mlsanity.com/paper/2309.00727/) (2023)
- [The use of deep learning in interventional radiotherapy (brachytherapy): a review with a focus on open source and open data](https://mlsanity.com/paper/2205.07516/) (2022)

## Abstract (arXiv)

Recent studies demonstrated the eligibility of convolutional neural networks (CNNs) for solving the image registration problem. CNNs enable faster transformation estimation and greater generalization capability needed for better support during medical interventions. Conventional fully-supervised training requires a lot of high-quality ground truth data such as voxel-to-voxel transformations, which typically are attained in a too tedious and error-prone manner. In our work, we use weakly-supervised learning, which optimizes the model indirectly only via segmentation masks that are a more accessible ground truth than the deformation fields. Concerning the weak supervision, we investigate two segmentation similarity measures: multiscale Dice similarity coefficient (mDSC) and the similarity between segmentation-derived signed distance maps (SDMs). We show that the combination of mDSC and SDM similarity measures results in a more accurate and natural transformation pattern together with a stronger gradient coverage. Furthermore, we introduce an auxiliary input to the neural network for the prior information about the prostate location in the MR sequence, which mostly is available preoperatively. This approach significantly outperforms the standard two-input models. With weakly labelled MR-TRUS prostate data, we showed registration quality comparable to the state-of-the-art deep learning-based method.