Back to Search
Start Over
Deformable registration of magnetic resonance images using unsupervised deep learning in neuro-/radiation oncology.
- Source :
-
Radiation oncology (London, England) [Radiat Oncol] 2024 May 21; Vol. 19 (1), pp. 61. Date of Electronic Publication: 2024 May 21. - Publication Year :
- 2024
-
Abstract
- Purpose: Accurate deformable registration of magnetic resonance imaging (MRI) scans containing pathologies is challenging due to changes in tissue appearance. In this paper, we developed a novel automated three-dimensional (3D) convolutional U-Net based deformable image registration (ConvUNet-DIR) method using unsupervised learning to establish correspondence between baseline pre-operative and follow-up MRI scans of patients with brain glioma.<br />Methods: This study involved multi-parametric brain MRI scans (T1, T1-contrast enhanced, T2, FLAIR) acquired at pre-operative and follow-up time for 160 patients diagnosed with glioma, representing the BraTS-Reg 2022 challenge dataset. ConvUNet-DIR, a deep learning-based deformable registration workflow using 3D U-Net style architecture as a core, was developed to establish correspondence between the MRI scans. The workflow consists of three components: (1) the U-Net learns features from pairs of MRI scans and estimates a mapping between them, (2) the grid generator computes the sampling grid based on the derived transformation parameters, and (3) the spatial transformation layer generates a warped image by applying the sampling operation using interpolation. A similarity measure was used as a loss function for the network with a regularization parameter limiting the deformation. The model was trained via unsupervised learning using pairs of MRI scans on a training data set (n = 102) and validated on a validation data set (n = 26) to assess its generalizability. Its performance was evaluated on a test set (n = 32) by computing the Dice score and structural similarity index (SSIM) quantitative metrics. The model's performance also was compared with the baseline state-of-the-art VoxelMorph (VM1 and VM2) learning-based algorithms.<br />Results: The ConvUNet-DIR model showed promising competency in performing accurate 3D deformable registration. It achieved a mean Dice score of 0.975 ± 0.003 and SSIM of 0.908 ± 0.011 on the test set (n = 32). Experimental results also demonstrated that ConvUNet-DIR outperformed the VoxelMorph algorithms concerning Dice (VM1: 0.969 ± 0.006 and VM2: 0.957 ± 0.008) and SSIM (VM1: 0.893 ± 0.012 and VM2: 0.857 ± 0.017) metrics. The time required to perform a registration for a pair of MRI scans is about 1 s on the CPU.<br />Conclusions: The developed deep learning-based model can perform an end-to-end deformable registration of a pair of 3D MRI scans for glioma patients without human intervention. The model could provide accurate, efficient, and robust deformable registration without needing pre-alignment and labeling. It outperformed the state-of-the-art VoxelMorph learning-based deformable registration algorithms and other supervised/unsupervised deep learning-based methods reported in the literature.<br /> (© 2024. The Author(s).)
- Subjects :
- Humans
Radiation Oncology methods
Image Processing, Computer-Assisted methods
Imaging, Three-Dimensional methods
Deep Learning
Magnetic Resonance Imaging methods
Brain Neoplasms diagnostic imaging
Brain Neoplasms radiotherapy
Unsupervised Machine Learning
Glioma diagnostic imaging
Glioma radiotherapy
Glioma pathology
Subjects
Details
- Language :
- English
- ISSN :
- 1748-717X
- Volume :
- 19
- Issue :
- 1
- Database :
- MEDLINE
- Journal :
- Radiation oncology (London, England)
- Publication Type :
- Academic Journal
- Accession number :
- 38773620
- Full Text :
- https://doi.org/10.1186/s13014-024-02452-3