Improved BG-PVS Quantification in Infant Brain MRI Using Anatomy-Informed Pseudo-Labels for Joint BG and PVS
Junghwa Kang1, Dayeon Bak1, Na-Young Shin2,3
1Department of Biomedical Engineering, Hankuk University of Foreign Studies, Yongin-si, Republic of Korea.
Background:
Reliable quantification of perivascular spaces (PVS) in the basal ganglia (BG) is of growing interest for understanding the glymphatic system but remains challenging in infants.
Purpose:
To develop an automated deep learning method for BG and BG-PVS segmentation in infant brain MRI using an anatomy-informed pseudo-labeling approach.
Study Type:
Retrospective, multi-cohort technical development, and validation study.
Population:
Three cohorts: 150 neonates from the Developing Human Connectome Project (dHCP, 37-44 weeks of gestational age (GA); 76 males, 74 females), 133 infants from the Baby Connectome Project (BCP; ≤ 24 months; 70 males, 63 females) and 70 infants from an in-house dataset (30-41 weeks of GA; 36 males, 34 females). Manual ground-truth labels were generated by a trained researcher (dHCP, n = 150; BCP, n = 8; in-house, n = 10) and validated by a radiologist with 15 years of experience.
Field Strength/Sequence:
Data included 3 T MRI with T1- and T2-weighted sequences: dHCP (inversion recovery turbo spin-echo [IR-TSE] and turbo spin-echo [TSE]), BCP (magnetization-prepared rapid gradient-echo [MPRAGE] and TSE), and in-house (MPRAGE and variable-flip-angle TSE).
Assessment:
The proposed approach was compared with alternative automated approaches trained with different labeling strategies. Training/validation/test splits were 100/25/25 (dHCP), 100/25/8 (BCP), and 50/10/10 (in-house).
Statistical Tests:
Dice similarity coefficient (DSC), recall, positive predictive value, and Hausdorff distance were calculated for BG and BG-PVS quantification. Statistical significance was assessed using Wilcoxon signed-rank tests (p < 0.05), and quantification agreement was evaluated using Pearson's correlation, intraclass correlation coefficient (ICC), and mean absolute error (MAE).
Results:
The proposed method improved accuracy (dHCP: BG DSC = 0.91 ± 0.03 and BG-PVS DSC = 0.78 ± 0.09; external datasets with fine-tuning: BG DSC = 0.86-0.89) and high agreement in PVS quantification with reference measurements (r = 0.90-0.99, ICC ≥ 0.96, MAE = 0.10).
Data Conclusion:
The proposed method seems to enable robust and annotation-efficient BG and BG-PVS segmentation in infants.
Evidence Level:
3.
Technical Efficacy:
1.
