# Inverse-Consistent Deep Networks for Unsupervised Deformable Image Registration

arXiv: https://arxiv.org/abs/1809.03443 · HTML: https://mlsanity.com/paper/1809.03443/

## Key facts

- Cited by 32 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 10 Sep 2018.

## Built on by (most cited first, 30 of 32)

- [A survey on deep learning in medical image registration: new technologies, uncertainty, evaluation metrics, and beyond](https://mlsanity.com/paper/2307.15615/) (2023)
- [U-Net vs Transformer: Is U-Net Outdated in Medical Image Registration?](https://mlsanity.com/paper/2208.04939/) (2022)
- [ICON: Learning Regular Maps Through Inverse Consistency](https://mlsanity.com/paper/2105.04459/) (2021)
- [Learning a Model-Driven Variational Network for Deformable Image Registration](https://mlsanity.com/paper/2105.12227/) (2021)
- [Fourier-Net: Fast Image Registration with Band-limited Deformation](https://mlsanity.com/paper/2211.16342/) (2022)
- [Inverse Consistency by Construction for Multistep Deep Registration](https://mlsanity.com/paper/2305.00087/) (2023)
- [Unsupervised Landmark Detection Based Spatiotemporal Motion Estimation for 4D Dynamic Medical Images](https://mlsanity.com/paper/2109.14805/) (2021)
- [SITReg: Multi-resolution architecture for symmetric, inverse consistent, and topology preserving image registration](https://mlsanity.com/paper/2303.10211/) (2023)
- [Medical image registration using unsupervised deep neural network: A scoping literature review](https://mlsanity.com/paper/2208.01825/) (2022)
- [CartiMorph: a framework for automated knee articular cartilage morphometrics](https://mlsanity.com/paper/2308.01981/) (2023)
- [Decoder-Only Image Registration](https://mlsanity.com/paper/2402.03585/) (2024)
- [MICS : Multi-steps, Inverse Consistency and Symmetric deep learning registration network](https://mlsanity.com/paper/2111.12123/) (2021)
- [MICDIR: Multi-scale Inverse-consistent Deformable Image Registration using UNetMSS with Self-Constructing Graph Latent](https://mlsanity.com/paper/2203.04317/) (2022)
- [Fourier-Net+: Leveraging Band-Limited Representation for Efficient 3D Medical Image Registration](https://mlsanity.com/paper/2307.02997/) (2023)
- [WiNet: Wavelet-based Incremental Learning for Efficient Medical Image Registration](https://mlsanity.com/paper/2407.13426/) (2024)
- [Towards Saner Deep Image Registration](https://mlsanity.com/paper/2307.09696/) (2023)
- [EfficientMorph: Parameter-Efficient Transformer-Based Architecture for 3D Image Registration](https://mlsanity.com/paper/2403.11026/) (2024)
- [Employing similarity to highlight differences: On the impact of anatomical assumptions in chest X-ray registration methods](https://mlsanity.com/paper/2301.09338/) (2023)
- [Structure-aware registration network for liver DCE-CT images](https://mlsanity.com/paper/2303.04595/) (2023)
- [Tumor aware recurrent inter-patient deformable image registration of computed tomography scans with lung cancer](https://mlsanity.com/paper/2409.11910/) (2024)
- [SACB-Net: Spatial-awareness Convolutions for Medical Image Registration](https://mlsanity.com/paper/2503.19592/) (2025)
- [Multi-class motion-based semantic segmentation for ureteroscopy and laser lithotripsy](https://mlsanity.com/paper/2104.01268/) (2021)
- [TransMorph: Transformer for unsupervised medical image registration](https://mlsanity.com/paper/2111.10480/) (2021)
- [Unsupervised Image Registration Towards Enhancing Performance and Explainability in Cardiac And Brain Image Analysis](https://mlsanity.com/paper/2203.03638/) (2022)
- [Impact of PCA-based preprocessing and different CNN structures on deformable registration of sonograms](https://mlsanity.com/paper/2301.08802/) (2023)
- [RS-MOCO: A deep learning-based topology-preserving image registration method for cardiac T1 mapping](https://mlsanity.com/paper/2410.11651/) (2024)
- [Dual-Flow Transformation Network for Deformable Image Registration with Region Consistency Constraint](https://mlsanity.com/paper/2112.02249/) (2021)
- [Deformable Image Registration using Unsupervised Deep Learning for CBCT-guided Abdominal Radiotherapy](https://mlsanity.com/paper/2208.13686/) (2022)
- [Morph-SSL: Self-Supervision with Longitudinal Morphing to Predict AMD Progression from OCT](https://mlsanity.com/paper/2304.08439/) (2023)
- [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)

## Abstract (arXiv)

Deformable image registration is a fundamental task in medical image analysis, aiming to establish a dense and non-linear correspondence between a pair of images. Previous deep-learning studies usually employ supervised neural networks to directly learn the spatial transformation from one image to another, requiring task-specific ground-truth registration for model training. Due to the difficulty in collecting precise ground-truth registration, implementation of these supervised methods is practically challenging. Although several unsupervised networks have been recently developed, these methods usually ignore the inherent inverse-consistent property (essential for diffeomorphic mapping) of transformations between a pair of images. Also, existing approaches usually encourage the to-be-estimated transformation to be locally smooth via a smoothness constraint only, which could not completely avoid folding in the resulting transformation. To this end, we propose an Inverse-Consistent deep Network (ICNet) for unsupervised deformable image registration. Specifically, we develop an inverse-consistent constraint to encourage that a pair of images are symmetrically deformed toward one another, until both warped images are matched. Besides using the conventional smoothness constraint, we also propose an anti-folding constraint to further avoid folding in the transformation. The proposed method does not require any supervision information, while encouraging the diffeomoprhic property of the transformation via the proposed inverse-consistent and anti-folding constraints. We evaluate our method on T1-weighted brain magnetic resonance imaging (MRI) scans for tissue segmentation and anatomical landmark detection, with results demonstrating the superior performance of our ICNet over several state-of-the-art approaches for deformable image registration. Our code will be made publicly available.