# FAIM -- A ConvNet Method for Unsupervised 3D Medical Image Registration

arXiv: https://arxiv.org/abs/1811.09243 · HTML: https://mlsanity.com/paper/1811.09243/

## Key facts

- Cited by 19 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 22 Nov 2018.

## Built on by (most cited first, 19 of 19)

- [A survey on deep learning in medical image registration: new technologies, uncertainty, evaluation metrics, and beyond](https://mlsanity.com/paper/2307.15615/) (2023)
- [Correlation-aware Coarse-to-fine MLPs for Deformable Medical Image Registration](https://mlsanity.com/paper/2406.00123/) (2024)
- [Non-iterative Coarse-to-fine Transformer Networks for Joint Affine and Deformable Image Registration](https://mlsanity.com/paper/2307.03421/) (2023)
- [Non-iterative Coarse-to-fine Registration based on Single-pass Deep Cumulative Learning](https://mlsanity.com/paper/2206.12596/) (2022)
- [Enhancing Medical Image Registration via Appearance Adjustment Networks](https://mlsanity.com/paper/2103.05213/) (2021)
- [Light-weight Deformable Registration using Adversarial Learning with Distilling Knowledge](https://mlsanity.com/paper/2110.01293/) (2021)
- [Brain Tumor Sequence Registration with Non-iterative Coarse-to-fine Networks and Dual Deep Supervision](https://mlsanity.com/paper/2211.07876/) (2022)
- [Deformer: Towards Displacement Field Learning for Unsupervised Medical Image Registration](https://mlsanity.com/paper/2207.03180/) (2022)
- [AutoFuse: Automatic Fusion Networks for Deformable Medical Image Registration](https://mlsanity.com/paper/2309.05271/) (2023)
- [Decoder-Only Image Registration](https://mlsanity.com/paper/2402.03585/) (2024)
- [Cascaded Feature Warping Network for Unsupervised Medical Image Registration](https://mlsanity.com/paper/2103.08213/) (2021)
- [MICS : Multi-steps, Inverse Consistency and Symmetric deep learning registration network](https://mlsanity.com/paper/2111.12123/) (2021)
- [Segmentation by Test-Time Optimization (TTO) for CBCT-based Adaptive Radiation Therapy](https://mlsanity.com/paper/2202.03978/) (2022)
- [Towards Positive Jacobian: Learn to Postprocess Diffeomorphic Image Registration with Matrix Exponential](https://mlsanity.com/paper/2202.00749/) (2022)
- [Exploring Deep Registration Latent Spaces](https://mlsanity.com/paper/2107.11238/) (2021)
- [Region Specific Optimization (RSO)-based Deep Interactive Registration](https://mlsanity.com/paper/2203.04295/) (2022)
- [Deep Learning based Direct Segmentation Assisted by Deformable Image Registration for Cone-Beam CT based Auto-Segmentation for Adaptive Radiotherapy](https://mlsanity.com/paper/2206.03413/) (2022)
- [Impact of Initialization on Intra-subject Pediatric Brain MR Image Registration: A Comparative Analysis between SyN ANTs and Deep Learning-Based Approaches](https://mlsanity.com/paper/2406.19943/) (2024)
- [Tetrahedron-Net for Medical Image Registration](https://mlsanity.com/paper/2505.04380/) (2025)

## Abstract (arXiv)

We present a new unsupervised learning algorithm, "FAIM", for 3D medical image registration. With a different architecture than the popular "U-net", the network takes a pair of full image volumes and predicts the displacement fields needed to register source to target. Compared with "U-net" based registration networks such as VoxelMorph, FAIM has fewer trainable parameters but can achieve higher registration accuracy as judged by Dice score on region labels in the Mindboggle-101 dataset. Moreover, with the proposed penalty loss on negative Jacobian determinants, FAIM produces deformations with many fewer "foldings", i.e. regions of non-invertibility where the surface folds over itself. In our experiment, we varied the strength of this penalty and investigated changes in registration accuracy and non-invertibility in terms of number of "folding" locations. We found that FAIM is able to maintain both the advantages of higher accuracy and fewer "folding" locations over VoxelMorph, over a range of hyper-parameters (with the same values used for both networks). Further, when trading off registration accuracy for better invertibility, FAIM required less sacrifice of registration accuracy. Codes for this paper will be released upon publication.