Encoding matching criteria for cross‐domain deformable image registration
Authors:
- 17 December 2024
- journal article
- research article
- Published by Wiley in Medical Physics
- Vol. 52 (4) , 2305-2315
Abstract
Background: Most existing deep learning‐based registration methods are trained on single‐type images to address same‐domain tasks, resulting in performance degradation when applied to new scenarios. Retraining a model for new scenarios requires extra time and data. Therefore, efficient and accurate solutions for cross‐domain deformable registration are in demand.Purpose: We argue that the tailor‐made matching criteria in traditional registration methods is one of the main reason they are applicable in different domains. Motivated by this, we devise a registration‐oriented encoder to model the matching criteria of image features and structural features, which is beneficial to boost registration accuracy and adaptability.Methods: Specifically, a general feature encoder (Encoder‐G) is proposed to capture comprehensive medical image features, while a structural feature encoder (Encoder‐S) is designed to encode the structural self‐similarity into the global representation. Moreover, by updating Encoder‐S using one‐shot learning, our method can effectively adapt to different domains. The efficacy of our method is evaluated using MRI images from three different domains, including brain images (training/testing: 870/90 pairs), abdomen images (training/testing: 1406/90 pairs), and cardiac images (training/testing: 64770/870 pairs). The comparison methods include traditional method (SyN) and cutting‐edge deep networks. The evaluation metrics contain dice similarity coefficient (DSC) and average symmetric surface distance (ASSD).Results: In the single‐domain task, our method attains an average DSC of 68.9%/65.2%/72.8%, and ASSD of 9.75/3.82/1.30 mm on abdomen/cardiac/brain images, outperforming the second‐best comparison methods by large margins. In the cross‐domain task, without one‐shot optimization, our method outperforms other deep networks in five out of six cross‐domain scenarios and even surpasses symmetric image normalization method (SyN) in two scenarios. By conducting the one‐shot optimization, our method successfully surpasses SyN in all six cross‐domain scenarios.Conclusions: Our method yields favorable results in the single‐domain task while ensuring improved generalization and adaptation performance in the cross‐domain task, showing its feasibility for the challenging cross‐domain registration applications. The code is publicly available at https://github.com/JuliusWang‐7/EncoderReg.Keywords
All Related Versions
Funding Information
- National Natural Science Foundation of China (62471306, 62071305, 82071951)
This publication has 26 references indexed in Scilit:
- DGM-DR: Domain Generalization with Mutual Information Regularized Diabetic Retinopathy Classification2023
- ModeT: Learning Deformable Image Registration via Motion Decomposition Transformer2023
- PIViT: Large Deformation Image Registration with Pyramid-Iterative Vision Transformer2023
- Coordinate Translator for Learning Deformable Medical Image Registration2022
- TransMorph: Transformer for unsupervised medical image registrationMedical Image Analysis, 2022
- Dual-stream pyramid registration networkMedical Image Analysis, 2022
- Joint affine and deformable three‐dimensional networks for brain MRI registrationMedical Physics, 2020
- On the Adaptability of Unsupervised CNN-Based Deformable Image Registration to Unseen Image Domains2018
- Symmetric diffeomorphic image registration with cross-correlation: Evaluating automated labeling of elderly and neurodegenerative brainMedical Image Analysis, 2008
- Principal components analysis (PCA)Computers & Geosciences, 1993