End-to-end susceptibility-induced distortion correction for diffusion MRI with unsupervised deep learning.
Saved in:
| Title: | End-to-end susceptibility-induced distortion correction for diffusion MRI with unsupervised deep learning. |
|---|---|
| Authors: | Feng, Jianhui1 (AUTHOR) 23210850006@m.fudan.edu.cn, Shi, Yonggang2 (AUTHOR) Yonggang.Shi@loni.usc.edu, Qiao, Yuchuan1 (AUTHOR) yuchuanqiao@fudan.edu.cn |
| Source: | Pattern Recognition. May2026, Vol. 173, pN.PAG-N.PAG. 1p. |
| Subjects: | Diffusion magnetic resonance imaging, Deep learning, Machine learning, Decoding algorithms, Artificial neural networks |
| Abstract: | • To improve the accuracy and efficiency of susceptibility-induced distortion correction in diffusion MRI, we develop a novel coarse-to-fine unsupervised deep learning-based framework in an end-to-end manner. • We propose DiscoNet, a pyramid-based distortion correction network that effectively learns a distortion field from FOD images in two opposite PEs. Specifically, we design a dual-branch encoder that aggregates the advantages of CNNs and Swin Transformer to separately extract the rich information from FOD images. A multi-resolution decoder is then used to learn the deformation field from coarse to fine. • Extensive experiments across three datasets-HCP, HCP-Aging, and HCLV-with over 1400 cases, demonstrate the superior and efficient correction performance of our method for dMRI data. • We confirm the robust out-of-domain generalizability of our method by training DiscoNet on HCP-Aging data and subsequently testing its efficacy on HCLV data sourced from various sites. This process effectively showcases the capacity of our method to accurately correct the distortions in previously unseen diffusion MRI datasets. High-resolution, multi-shell diffusion MRI (dMRI) data provides exceptional advantages for studying human brain pathways. However, significant residual distortions remain in certain brain regions, such as the brainstem, even after processing with existing distortion correction methods. In this paper, we propose a novel unsupervised learning-based framework to correct the susceptibility-induced distortion in dMRI. This end-to-end coarse-to-fine network named Distortion Correction Network (DiscoNet), consists of a dual-branch encoder and a multi-resolution decoder. Instead of using the b0 (b = 0) image in most methods, fiber orientation distribution (FOD) images computed from dMRI data are utilized to provide more reliable information. A dual-branch encoder integrating the advantages of Convolutional Neural Networks and Swin Transformer is designed to capture the latent information of FOD images from opposite phase encoding (PE) separately; while a subsequent multi-resolution decoder decomposes the distortion fields into rigid and non-rigid components. We then evaluated our method on large-scale datasets with over 1400 cases, including data in AP-PA PE direction and RL-LR PE direction. Comprehensive experiments had shown that our method achieves over 42 % improvement in the Mean Square Difference (MSD) metric for distortion correction compared to the SOTA methods in the pons of the brainstem region. [ABSTRACT FROM AUTHOR] |
| Copyright of Pattern Recognition is the property of Pergamon Press - An Imprint of Elsevier Science and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.) | |
| Database: | Engineering Source |
Be the first to leave a comment!
