Related Experiment Video
Updated: Jan 7, 2026
Author Spotlight: Bridging Gaps in Anatomy and Establishing a Foundation for Algorithmic Studies
Published on: December 15, 2023
Automated synthetic contrast-enhanced MRI improves choroid plexus segmentation in Parkinsonian syndromes
Dagnachew Tessema Ambaye1,2, Sungyang Jo3, Huseyin Enes Candan4
1Department of Biomedical Engineering, Ulsan National Institute of Science and Technology, Ulsan, 44919, Republic of Korea.
Background:
Choroid plexus (ChP) has gained attention as a potential biomarker in neurodegenerative diseases, yet its segmentation remains challenging. Gadolinium-based contrast-enhanced MRI (CE-MRI) is the reference standard, as non-contrast MRI images lack sufficient contrast. However, gadolinium deposition, risk of nephrogenic system fibrosis in renally impaired patients, and patient discomfort limit its repeated administration.
Purpose:
To develop deep learning-based synthetic-contrast-enhanced MRI (SynCE-MRI) using T1-weighted images to improve ChP visualization and evaluate its ability to detect morphological changes in Parkinsonian syndromes.
Materials And Methods:
This retrospective study included 265 (mean age = 65.7 ± 7.00 years, males/females: 120/145) consecutive patients in the internal cohort (174 with Parkinson's disease [PD], 46 with essential tremor, and 45 with atypical Parkinsonian disorder [APD]) who underwent T1W and CE-MRI at 3T from Asan Medical Center (June 2021-December 2023), and an external cohort of 58 (mean age = 60.7 ± 7.8 years, males/females: 40/18) patients (29/29 PD/APD) from Pusan National University, Yangsan Hospital (April 2011-December 2014). Nested-UNet was used for SynCE-MRI synthesis from T1W images. The 3D-UNet ChP segmentation model was trained by CE-MRI and tested using SynCE-MRI. Kruskal-Wallis and Bonferroni-corrected Mann-Whitney U tests assessed image synthesis, segmentation, and ChP morphometry (P < .05).
Results:
SynCE-MRI achieved high-fidelity images with peak signal-to-noise ratio (PSNR) 35.37 ± 1.32 and structural similarity index measure (SSIM) 0.970 ±0.0054. Segmentation accuracy for SynCE-MRI (dice score = 0.803 ± 0.029, 95% CI: 0.797-0.810) significantly outperformed manual (dice score = 0.59 ± 0.057, 95% CI: 0.578-0.603; P < .001) and automated (dice score = 0.489 ± 0.049, 95% CI: 0.479-0.500; P < .001) T1W-based segmentations. SynCE-MRI-based ChP volumes closely matched CE-MRI (mean absolute-volume difference [MAVD] = 6.7%; ICC = 0.88, 95% CI: 0.82-0.92). SynCE-MRI revealed significantly larger ChP volumes in APD versus PD using internal cohort (APD: 2.69 ± 0.39 mL, 95% CI: 2.54-2.84 vs PD: 2.43 ± 0.47 mL, 95% CI: 2.25-2.52; P = .04) and external cohort (APD: 2.81 ± 0.48 mL, 95% CI: 2.60-3.02 vs PD: 2.52 ± 0.45 mL, 95% CI: 2.36-2.69; P = .03).
Conclusion:
SynCE-MRI accurately replicates CE-MRI for ChP imaging and morphometry, outperforms T1W imaging in segmentation, and detects ChP enlargement in APD versus PD across internal and external cohorts, consistent with CE-MRI findings.
Insights
Synthetic contrast-enhanced MRI (SynCE-MRI) accurately visualizes the choroid plexus (ChP) and detects morphological changes in Parkinsonian syndromes. This deep learning approach offers a promising alternative to traditional contrast-enhanced MRI for ChP analysis.
Area of Science:
- Neuroimaging
- Artificial Intelligence in Medicine
- Biomarker Discovery
Background:
- Choroid plexus (ChP) is a potential neurodegenerative disease biomarker, but its segmentation is challenging with standard MRI.
- Gadolinium-based contrast-enhanced MRI (CE-MRI) is effective but limited by gadolinium deposition risks and patient discomfort.
Purpose of the Study:
- To develop deep learning-based synthetic-contrast-enhanced MRI (SynCE-MRI) from T1-weighted images for improved ChP visualization.
- To evaluate SynCE-MRI's capability in detecting morphological changes in Parkinsonian syndromes.
Main Methods:
- A retrospective study utilized T1W and CE-MRI data from two cohorts (n=265 and n=58) including patients with Parkinson's disease (PD) and atypical Parkinsonian disorder (APD).
- Nested-UNet model was employed for SynCE-MRI synthesis, and a 3D-UNet model was trained for ChP segmentation using CE-MRI, subsequently tested on SynCE-MRI.
- Statistical analyses (Kruskal-Wallis, Mann-Whitney U tests) were performed to assess image synthesis, segmentation accuracy, and ChP morphometry.
Main Results:
- SynCE-MRI generated high-fidelity images (PSNR 35.37±1.32, SSIM 0.970±0.0054).
- SynCE-MRI segmentation (Dice score 0.803±0.029) significantly outperformed manual (0.59±0.057) and automated T1W-based methods (0.489±0.049).
- SynCE-MRI-based ChP volumes closely matched CE-MRI (MAVD 6.7%, ICC 0.88). Significantly larger ChP volumes were observed in APD compared to PD in both cohorts (P < .05).
Conclusions:
- SynCE-MRI accurately replicates CE-MRI for ChP imaging and morphometry.
- SynCE-MRI segmentation surpasses standard T1W imaging and detects significant ChP enlargement in APD versus PD.
- This deep learning method offers a viable, contrast-free alternative for ChP analysis in neurodegenerative diseases.
