# MICDIR: Multi-scale Inverse-consistent Deformable Image Registration using UNetMSS with Self-Constructing Graph Latent

arXiv: https://arxiv.org/abs/2203.04317 · HTML: https://mlsanity.com/paper/2203.04317/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 49 references that are in the map.
- First posted on arXiv 8 Mar 2022.

## Builds on (most cited first, 19 of 19)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [3D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotation](https://mlsanity.com/paper/1606.06650/) (2016)
- [Spatial Transformer Networks](https://mlsanity.com/paper/1506.02025/) (2015)
- [Geometric deep learning: going beyond Euclidean data](https://mlsanity.com/paper/1611.08097/) (2016)
- [VoxelMorph: A Learning Framework for Deformable Medical Image Registration](https://mlsanity.com/paper/1809.05231/) (2018)
- [Generating Sequences With Recurrent Neural Networks](https://mlsanity.com/paper/1308.0850/) (2013)
- [A Deep Learning Framework for Unsupervised Affine and Deformable Image Registration](https://mlsanity.com/paper/1809.06130/) (2018)
- [Learning Dense Correspondence via 3D-guided Cycle Consistency](https://mlsanity.com/paper/1604.05383/) (2016)
- [ST-GAN: Spatial Transformer Generative Adversarial Networks for Image Compositing](https://mlsanity.com/paper/1803.01837/) (2018)
- [CycleMorph: Cycle Consistent Unsupervised Deformable Image Registration](https://mlsanity.com/paper/2008.05772/) (2020)
- [Inverse-Consistent Deep Networks for Unsupervised Deformable Image Registration](https://mlsanity.com/paper/1809.03443/) (2018)
- [Biomechanics-informed Neural Networks for Myocardial Motion Tracking in MRI](https://mlsanity.com/paper/2006.04725/) (2020)
- [Medical Image Registration Using Deep Neural Networks: A Comprehensive Review](https://mlsanity.com/paper/2002.03401/) (2020)
- [Information-based Disentangled Representation Learning for Unsupervised MR Harmonization](https://mlsanity.com/paper/2103.13283/) (2021)
- [FIRE: Unsupervised bi-directional inter-modality registration using deep networks](https://mlsanity.com/paper/1907.05062/) (2019)
- [Segmentation of Intracranial Arterial Calcification with Deeply Supervised Residual Dropout Networks](https://mlsanity.com/paper/1706.01148/) (2017)
- [Multi Scale Supervised 3D U-Net for Kidney and Tumor Segmentation](https://mlsanity.com/paper/1908.03204/) (2019)
- [Self-Constructing Graph Convolutional Networks for Semantic Labeling](https://mlsanity.com/paper/2003.06932/) (2020)

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

- [Liver Segmentation using Turbolift Learning for CT and Cone-beam C-arm Perfusion Imaging](https://mlsanity.com/paper/2207.10167/) (2022)
- [PatchMorph: A Stochastic Deep Learning Approach for Unsupervised 3D Brain Image Registration with Small Patches](https://mlsanity.com/paper/2312.06958/) (2023)
- [Towards Segmenting the Invisible: An End-to-End Registration and Segmentation Framework for Weakly Supervised Tumour Analysis](https://mlsanity.com/paper/2602.05453/) (2026)
- [Transcending the Annotation Bottleneck: AI-Powered Discovery in Biology and Medicine](https://mlsanity.com/paper/2602.20100/) (2026)

## Abstract (arXiv)

Image registration is the process of bringing different images into a common coordinate system - a technique widely used in various applications of computer vision, such as remote sensing, image retrieval, and, most commonly, medical imaging. Deep learning based techniques have been applied successfully to tackle various complex medical image processing problems, including medical image registration. Over the years, several image registration techniques have been proposed using deep learning. Deformable image registration techniques such as Voxelmorph have been successful in capturing finer changes and providing smoother deformations. However, Voxelmorph, as well as ICNet and FIRE, do not explicitly encode global dependencies (i.e. the overall anatomical view of the supplied image) and, therefore, cannot track large deformations. In order to tackle the aforementioned problems, this paper extends the Voxelmorph approach in three different ways. To improve the performance in case of small as well as large deformations, supervision of the model at different resolutions has been integrated using a multi-scale UNet. To support the network to learn and encode the minute structural co-relations of the given image-pairs, a self-constructing graph network (SCGNet) has been used as the latent of the multi-scale UNet - which can improve the learning process of the model and help the model to generalise better. And finally, to make the deformations inverse-consistent, cycle consistency loss has been employed. On the task of registration of brain MRIs, the proposed method achieved significant improvements over ANTs and VoxelMorph, obtaining a Dice score of 0.8013 ± 0.0243 for intramodal and 0.6211 ± 0.0309 for intermodal, while VoxelMorph achieved 0.7747 ± 0.0260 and 0.6071 ± 0.0510, respectively