EUVIMEDEUVIMED entdecken
Crossref

Improved BG ‐ PVS Quantification in Infant Brain MRI Using Anatomy‐Informed Pseudo‐Labels for Joint BG and PVS Segmentation

Junghwa Kang, Dayeon Bak, Na-Young Shin, Hyun Gi Kim, Yoonho Nam

Journal of Magnetic Resonance Imaging · 2026

DOI: 10.1002/jmri.70298 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Magnetic Resonance Imaging, 2026. Verfasst von Junghwa Kang und 4 weiteren Autor:innen. Beteiligte Einrichtung: Department of Biomedical Engineering, Hankuk University of Foreign Studies, Yongin-si, Republic of Korea. Hauptthemen laut MEDLINE: Magnetic Resonance Imaging, Basal Ganglia, Image Processing, Computer-Assisted, Glymphatic System. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 34 Literaturangaben. Gefördert von: National Research Foundation of Korea, NIH Blueprint for Neuroscience Research, European Research Council.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

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.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Magnetic Resonance ImagingBasal GangliaImage Processing, Computer-AssistedGlymphatic SystemBrainHumansFemaleInfantMaleInfant, NewbornReproducibility of ResultsRetrospective StudiesDeep LearningConnectomeAlgorithmsGestational AgeImage Interpretation, Computer-Assisted

Stichwörter der Autor:innen

basal gangliaglymphatic systeminfantperivascular spacesegmentation

Autor:innen und Institutionen

  • Department of Biomedical Engineering, Hankuk University of Foreign Studies, Yongin-si, Republic of Korea.
  • Department of Radiology and Research Institute of Radiological Science and Center for Clinical Imaging Data Science, Yonsei University College of Medicine, Seoul, Republic of Korea.
  • Institute for Innovation in Digital Healthcare, Yonsei University, Seoul, Republic of Korea.
  • Department of Radiology and Research Institute of Radiology, Asan Medical Center, University of Ulsan College of Medicine, Seoul, Republic of Korea.
  • Department of Radiology, Eunpyeong St. Mary's Hospital, College of Medicine, The Catholic University of Korea, Seoul, Republic of Korea.

Förderung

  • National Research Foundation of Korea
  • NIH Blueprint for Neuroscience Research
  • European Research Council

Zitieren

APA

Kang, J., Bak, D., Shin, N. Y., Kim, H. G., & Nam, Y. (2026). Improved BG ‐ PVS Quantification in Infant Brain MRI Using Anatomy‐Informed Pseudo‐Labels for Joint BG and PVS Segmentation. Journal of Magnetic Resonance Imaging. https://doi.org/10.1002/jmri.70298

Vancouver

Kang J, Bak D, Shin NY, Kim HG, Nam Y. Improved BG ‐ PVS Quantification in Infant Brain MRI Using Anatomy‐Informed Pseudo‐Labels for Joint BG and PVS Segmentation. Journal of Magnetic Resonance Imaging. 2026. doi:10.1002/jmri.70298

BibTeX
@article{Kang2026,
  author = {Kang, Junghwa and Bak, Dayeon and Shin, Na-Young and Kim, Hyun Gi and Nam, Yoonho},
  title = {Improved BG ‐ PVS Quantification in Infant Brain MRI Using Anatomy‐Informed Pseudo‐Labels for Joint BG and PVS Segmentation},
  journal = {Journal of Magnetic Resonance Imaging},
  year = {2026},
  doi = {10.1002/jmri.70298}
}
Kostenlos starten →