uniGradICON: A Foundation Model for Medical Image Registration

• URL: http://arxiv.org/abs/2403.05780v1
• Date: Sat, 9 Mar 2024 03:26:35 GMT
• Title: uniGradICON: A Foundation Model for Medical Image Registration
• Authors: Lin Tian, Hastings Greer, Roland Kwitt, Francois-Xavier Vialard, Raul San Jose Estepar, Sylvain Bouix, Richard Rushmore, Marc Niethammer
• Abstract summary: We propose uniGradICON, a first step toward a foundation model for registration. We extensively trained and evaluated uniGradICON on twelve different public datasets.
• Score: 17.23463407622614
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Conventional medical image registration approaches directly optimize over the parameters of a transformation model. These approaches have been highly successful and are used generically for registrations of different anatomical regions. Recent deep registration networks are incredibly fast and accurate but are only trained for specific tasks. Hence, they are no longer generic registration approaches. We therefore propose uniGradICON, a first step toward a foundation model for registration providing 1) great performance \emph{across} multiple datasets which is not feasible for current learning-based registration methods, 2) zero-shot capabilities for new registration tasks suitable for different acquisitions, anatomical regions, and modalities compared to the training dataset, and 3) a strong initialization for finetuning on out-of-distribution registration tasks. UniGradICON unifies the speed and accuracy benefits of learning-based registration algorithms with the generic applicability of conventional non-deep-learning approaches. We extensively trained and evaluated uniGradICON on twelve different public datasets. Our code and the uniGradICON model are available at https://github.com/uncbiag/uniGradICON.

Related papers

• multiGradICON: A Foundation Model for Multimodal Medical Image Registration [15.174094859157288]
  We develop multiGradICON as a first step towards universal *multimodal* medical image registration. We show that 1) we can train a DL registration model that is suitable for monomodal *and* multimodal registration; 2) loss function randomization can increase multimodal registration accuracy; and 3) training a model with multimodal data helps multimodal generalization.
  arXiv  Detail & Related papers  (2024-08-01T01:23:02Z)
• ConKeD++ -- Improving descriptor learning for retinal image registration: A comprehensive study of contrastive losses [6.618504904743609]
  We propose to test and improve a state-of-the-art framework for color fundus image registration, ConKeD. Using the ConKeD framework we test multiple loss functions, adapting them to the framework and the application domain. Our work demonstrates state-of-the-art performance across all datasets and metrics.
  arXiv  Detail & Related papers  (2024-04-25T17:24:35Z)
• DISA: DIfferentiable Similarity Approximation for Universal Multimodal Registration [39.44133108254786]
  We propose a generic framework for creating expressive cross-modal descriptors. We achieve this by approximating existing metrics with a dot-product in the feature space of a small convolutional neural network. Our method is several orders of magnitude faster than local patch-based metrics and can be directly applied in clinical settings.
  arXiv  Detail & Related papers  (2023-07-19T12:12:17Z)
• Non-iterative Coarse-to-fine Transformer Networks for Joint Affine and Deformable Image Registration [10.994223928445589]
  We propose a Non-Iterative Coarse-to-finE Transformer network (NICE-Trans) for image registration. Our NICE-Trans is the first deep registration method that performs joint affine and deformable coarse-to-fine registration within a single network.
  arXiv  Detail & Related papers  (2023-07-07T07:07:42Z)
• Unsupervised 3D registration through optimization-guided cyclical self-training [71.75057371518093]
  State-of-the-art deep learning-based registration methods employ three different learning strategies. We propose a novel self-supervised learning paradigm for unsupervised registration, relying on self-training. We evaluate the method for abdomen and lung registration, consistently surpassing metric-based supervision and outperforming diverse state-of-the-art competitors.
  arXiv  Detail & Related papers  (2023-06-29T14:54:10Z)
• GSMorph: Gradient Surgery for cine-MRI Cardiac Deformable Registration [62.41725951450803]
  Learning-based deformable registration relies on weighted objective functions trading off registration accuracy and smoothness of the field. We construct a registration model based on the gradient surgery mechanism, named GSMorph, to achieve a hyper parameter-free balance on multiple losses. Our method is model-agnostic and can be merged into any deep registration network without introducing extra parameters or slowing down inference.
  arXiv  Detail & Related papers  (2023-06-26T13:32:09Z)
• Adapting the Mean Teacher for keypoint-based lung registration under geometric domain shifts [75.51482952586773]
  deep neural networks generally require plenty of labeled training data and are vulnerable to domain shifts between training and test data. We present a novel approach to geometric domain adaptation for image registration, adapting a model from a labeled source to an unlabeled target domain. Our method consistently improves on the baseline model by 50%/47% while even matching the accuracy of models trained on target data.
  arXiv  Detail & Related papers  (2022-07-01T12:16:42Z)
• DAFormer: Improving Network Architectures and Training Strategies for Domain-Adaptive Semantic Segmentation [99.88539409432916]
  We study the unsupervised domain adaptation (UDA) process. We propose a novel UDA method, DAFormer, based on the benchmark results. DAFormer significantly improves the state-of-the-art performance by 10.8 mIoU for GTA->Cityscapes and 5.4 mIoU for Synthia->Cityscapes.
  arXiv  Detail & Related papers  (2021-11-29T19:00:46Z)
• A Meta-Learning Approach for Medical Image Registration [6.518615946009265]
  We propose a novel unsupervised registration model which is integrated with a gradient-based meta learning framework. In our experiments, the proposed model obtained significantly improved performance in terms of accuracy and training time.
  arXiv  Detail & Related papers  (2021-04-21T10:27:05Z)
• Few-Shot Named Entity Recognition: A Comprehensive Study [92.40991050806544]
  We investigate three schemes to improve the model generalization ability for few-shot settings. We perform empirical comparisons on 10 public NER datasets with various proportions of labeled data. We create new state-of-the-art results on both few-shot and training-free settings.
  arXiv  Detail & Related papers  (2020-12-29T23:43:16Z)
• Deep learning based registration using spatial gradients and noisy segmentation labels [52.78503776563559]
  deep learning based approaches became quite popular, providing fast and performing registration strategies. Our work relies on (i) a symmetric formulation, predicting the transformations from source to target and from target to source simultaneously, enforcing the trained representations to be similar. Our method reports a mean dice of $0.64$ for task 3 and $0.85$ for task 4 on the test sets, taking third place on the challenge.
  arXiv  Detail & Related papers  (2020-10-21T11:08:45Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.