DDSurfer: A Weakly‐Supervised Dual‐Stream Deep Learning Framework for Cortical Surface Reconstruction From Diffusion MRI
Open Access
- 23 July 2026
- journal article
- Published by Wiley in Advanced Science
- Vol. 13 (56)
Abstract
Cortical surface reconstruction of white matter and pial surfaces from diffusion MRI (dMRI) is critical for neuroimaging analyses, including tractography, connectomics, and multimodal data integration. However, obtaining these surfaces from dMRI data is inherently challenged by its low spatial resolution and poor tissue contrast. Currently, this relies on T1‐weighted images, from which the surfaces are reconstructed and then registered to the dMRI space—a process affected by inaccurate inter‐modality registration. This study introduces DDSurfer , an end‐to‐end deep learning framework that directly generates high‐fidelity cortical surfaces from dMRI data. DDSurfer leverages a novel dual‐stream architecture that processes and synergistically fuses complementary microstructural features from dMRI, learning a diffeomorphic transformation for subject‐specific surface reconstruction. The model is trained using a robust weakly‐supervised strategy with automatically generated pseudo‐ground‐truth surfaces. Extensive evaluations on diverse datasets demonstrate that DDSurfer surpasses traditional methods in geometric accuracy, morphological consistency, and generalization. By providing a computationally efficient and robust T1‐weighted‐independent solution, DDSurfer overcomes a major bottleneck in dMRI, delivering a practical tool to advance accurate dMRI‐centric connectomics and surface‐based investigations. Source code and implementation as an interactive 3D Slicer module are publicly available at: https://github.com/ChengjinLii/DDSurfer .Keywords
Funding Information
- National Natural Science Foundation of China (62371107)
- National Key Research and Development Program of China (2023YFE0118600)
- Science and Technology Department of Sichuan Province (2026YFHZ0045)
This publication has 54 references indexed in Scilit:
- Polymorph segmentation representation for medical image computingComputer Methods and Programs in Biomedicine, 2019
- Test–retest reproducibility of white matter parcellation using diffusion MRI tractography fiber clusteringHuman Brain Mapping, 2019
- Automated pixel‐wise brain tissue segmentation of diffusion‐weighted images via machine learningNMR in Biomedicine, 2018
- Building connectomes using diffusion MRI: why, how and butNMR in Biomedicine, 2017
- Test–retest reliability of freesurfer measurements within and between sites: Effects of visual approval processHuman Brain Mapping, 2015
- Registration of FA and T1-Weighted MRI Data of Healthy Human Brain Based on Template Matching and Normalized Cross-CorrelationJournal of Digital Imaging, 2013
- Surface reconstruction techniques: a reviewArtificial Intelligence Review, 2012
- Twenty‐five pitfalls in the analysis of diffusion MRI dataNMR in Biomedicine, 2010
- Topology correction of segmented medical images using a fast marching algorithmComputer Methods and Programs in Biomedicine, 2007
- Toward a quantitative assessment of diffusion anisotropyMagnetic Resonance in Medicine, 1996