# VoxelOpt: Voxel-Adaptive Message Passing for Discrete Optimization in Deformable Abdominal CT Registration

arXiv: https://arxiv.org/abs/2506.19975 · HTML: https://mlsanity.com/paper/2506.19975/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 35 references that are in the map.
- First posted on arXiv 24 Jun 2025.

## Builds on (most cited first, 17 of 17)

- [VoxelMorph: A Learning Framework for Deformable Medical Image Registration](https://mlsanity.com/paper/1809.05231/) (2018)
- [MoDL: Model Based Deep Learning Architecture for Inverse Problems](https://mlsanity.com/paper/1712.02862/) (2017)
- [CLIP-Driven Universal Model for Organ Segmentation and Tumor Detection](https://mlsanity.com/paper/2301.00785/) (2023)
- [Deep Learning in Medical Image Registration: A Survey](https://mlsanity.com/paper/1903.02026/) (2019)
- [Closing the Gap between Deep and Conventional Image Registration using Probabilistic Dense Displacement Networks](https://mlsanity.com/paper/1907.10931/) (2019)
- [Correlation-aware Coarse-to-fine MLPs for Deformable Medical Image Registration](https://mlsanity.com/paper/2406.00123/) (2024)
- [NODEO: A Neural Ordinary Differential Equation Based Optimization Framework for Deformable Image Registration](https://mlsanity.com/paper/2108.03443/) (2021)
- [Fourier-Net: Fast Image Registration with Band-limited Deformation](https://mlsanity.com/paper/2211.16342/) (2022)
- [Deep Learning in Medical Image Registration: Magic or Mirage?](https://mlsanity.com/paper/2408.05839/) (2024)
- [Spatially Covariant Image Registration with Text Prompts](https://mlsanity.com/paper/2311.15607/) (2023)
- [Robust deformable image registration using cycle-consistent implicit representations](https://mlsanity.com/paper/2310.01934/) (2023)
- [MemWarp: Discontinuity-Preserving Cardiac Registration with Memorized Anatomical Filters](https://mlsanity.com/paper/2407.08093/) (2024)
- [Spatially Covariant Lesion Segmentation](https://mlsanity.com/paper/2301.07895/) (2023)
- [A Plug-and-Play Image Registration Network](https://mlsanity.com/paper/2310.04297/) (2023)
- [LARO: Learned Acquisition and Reconstruction Optimization to accelerate Quantitative Susceptibility Mapping](https://mlsanity.com/paper/2211.00725/) (2022)
- [Slicer Networks](https://mlsanity.com/paper/2401.09833/) (2024)
- [Unsupervised Deformable Image Registration with Structural Nonparametric Smoothing](https://mlsanity.com/paper/2506.10813/) (2025)

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

- [Encoder-Only Image Registration](https://mlsanity.com/paper/2509.00451/) (2025)
- [Unsupervised MR-US Multimodal Image Registration with Multilevel Correlation Pyramidal Optimization](https://mlsanity.com/paper/2602.06288/) (2026)

## Abstract (arXiv)

Recent developments in neural networks have improved deformable image registration (DIR) by amortizing iterative optimization, enabling fast and accurate DIR results. However, learning-based methods often face challenges with limited training data, large deformations, and tend to underperform compared to iterative approaches when label supervision is unavailable. While iterative methods can achieve higher accuracy in such scenarios, they are considerably slower than learning-based methods. To address these limitations, we propose VoxelOpt, a discrete optimization-based DIR framework that combines the strengths of learning-based and iterative methods to achieve a better balance between registration accuracy and runtime. VoxelOpt uses displacement entropy from local cost volumes to measure displacement signal strength at each voxel, which differs from earlier approaches in three key aspects. First, it introduces voxel-wise adaptive message passing, where voxels with lower entropy receives less influence from their neighbors. Second, it employs a multi-level image pyramid with 27-neighbor cost volumes at each level, avoiding exponential complexity growth. Third, it replaces hand-crafted features or contrastive learning with a pretrained foundational segmentation model for feature extraction. In abdominal CT registration, these changes allow VoxelOpt to outperform leading iterative in both efficiency and accuracy, while matching state-of-the-art learning-based methods trained with label supervision. The source code will be available at https://github.com/tinymilky/VoxelOpt