# Warm-Started Reinforcement Learning for Iterative 3D/2D Liver Registration

arXiv: https://arxiv.org/abs/2604.10245 · HTML: https://mlsanity.com/paper/2604.10245/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in RL for clinical treatment and surgery, one of 15 directions in Deep reinforcement learning methods.
- Builds on 4 of its 22 references that are in the map.
- First posted on arXiv 11 Apr 2026.

## Placed in

- Deep reinforcement learning methods / [RL for clinical treatment and surgery](https://mlsanity.com/deeprl/rl-for-clinical-treatment-and-surgery/)

## Builds on (most cited first, 4 of 4)

- [An objective comparison of methods for augmented reality in laparoscopic liver resection by preoperative-to-intraoperative image fusion](https://mlsanity.com/paper/2401.15753/) (2024)
- [Learning Feature Descriptors for Pre- and Intra-operative Point Cloud Matching for Laparoscopic Liver Registration](https://mlsanity.com/paper/2211.03688/) (2022)
- [SE(3)-Equivariant Robot Learning and Control: A Tutorial Survey](https://mlsanity.com/paper/2503.09829/) (2025)
- [Depth Augmented and FE Free 3D/2D Liver Registration for Laparoscopic Liver AR](https://mlsanity.com/paper/2602.17517/) (2026)

## Abstract (arXiv)

Registration between preoperative CT and intraoperative laparoscopic video plays a crucial role in augmented reality (AR) guidance for minimally invasive surgery. Learning-based methods have recently achieved registration errors comparable to optimization-based approaches while offering faster inference. However, many supervised methods produce coarse alignments that rely on additional optimization-based refinement, thereby increasing inference time. We present a discrete-action reinforcement learning (RL) framework that formulates CT-to-video registration as a sequential decision-making process. A shared feature encoder, warm-started from a supervised pose estimation network to provide stable geometric features and faster convergence, extracts representations from CT renderings and laparoscopic frames, while an RL policy head learns to choose rigid transformations along six degrees of freedom and to decide when to stop the iteration. Experiments on a public laparoscopic dataset demonstrated that our method achieved an average target registration error (TRE) of 15.70 mm, comparable to supervised approaches with optimization, while achieving faster convergence. The proposed RL-based formulation enables automated, efficient iterative registration without manually tuned step sizes or stopping criteria. This discrete framework provides a practical foundation for future continuous-action and deformable registration models in surgical AR applications.