EUVIMEDEUVIMED entdecken
Crossref

A Deep Learning‐Based Fully Automated Cardiac MRI Segmentation Approach for Tetralogy of Fallot Patients

Wen-Yen Chai iD, Gigin Lin iD, Chao-Jan Wang, Hsin-Ju Chiang, Shu-Hang Ng, Yi-Shan Kuo, Yu-Chun Lin iD

Journal of Magnetic Resonance Imaging · 2026

DOI: 10.1002/jmri.70113 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Magnetic Resonance Imaging, 2026. Verfasst von Wen-Yen Chai und 6 weiteren Autor:innen. Beteiligte Einrichtung: Department of Medical Imaging and Intervention, Chang Gung Memorial Hospital at Linkou, Taoyuan City, Taiwan. Hauptthemen laut MEDLINE: Tetralogy of Fallot, Deep Learning, Magnetic Resonance Imaging, Cine, Image Processing, Computer-Assisted. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 31 Literaturangaben. Gefördert von: National Science and Technology Council, Chang Gung Medical Foundation.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Automated cardiac MR segmentation enables accurate and reproducible ventricular function assessment in Tetralogy of Fallot (ToF), whereas manual segmentation remains time‐consuming and variable.

Purpose

To evaluate the deep learning (DL)‐based models for automatic left ventricle (LV), right ventricle (RV), and LV myocardium segmentation in ToF, compared with manual reference standard annotations. Study Type Retrospective. Population 427 patients with diverse cardiac conditions (305 non‐ToF, 122 ToF), with 395 for training/validation, 32 ToF for internal testing, and 12 external ToF for generalizability assessment. Field Strength/Sequence Steady‐state free precession cine sequence at 1.5/3 T. Assessment U‐Net, Deep U‐Net, and MultiResUNet were trained under three regimes (non‐ToF, ToF‐only, mixed), using manual segmentations from one radiologist and one researcher (20 and 10 years of experience, respectively) as reference, with consensus for discrepancies. Performance for LV, RV, and LV myocardium was evaluated using Dice Similarity Coefficient (DSC), Intersection over Union (IoU), and F 1‐score, alongside regional (basal, middle, apical) and global ventricular function comparisons to manual results. Statistical Tests Friedman tests were applied for architecture and regime comparisons, paired Wilcoxon tests for ED–ES differences, and Pearson's r for assessing agreement in global function.

Results

MultiResUNet model trained on a mixed dataset (TOF and non‐TOF cases) achieved the best segmentation performance, with DSCs of 96.1% for LV and 93.5% for RV. In the internal test set, DSCs for LV, RV, and LV myocardium were 97.3%, 94.7%, and 90.7% at end‐diastole, and 93.6%, 92.1%, and 87.8% at end‐systole, with ventricular measurement correlations ranging from 0.84 to 0.99. Regional analysis showed LV DSCs of 96.3% (basal), 96.4% (middle), and 94.1% (apical), and RV DSCs of 92.8%, 94.2%, and 89.6%. External validation ( n = 12) showed correlations ranging from 0.81 to 0.98.

Conclusion

The MultiResUNet model enabled accurate automated cardiac MRI segmentation in ToF with the potential to streamline workflows and improve disease monitoring. Evidence Level 3. Technical Efficacy Stage 2.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Tetralogy of FallotDeep LearningMagnetic Resonance Imaging, CineImage Processing, Computer-AssistedImage Interpretation, Computer-AssistedMagnetic Resonance ImagingHeartHumansRetrospective StudiesMaleFemaleHeart VentriclesReproducibility of ResultsChildAdolescentAdultYoung AdultMiddle AgedChild, PreschoolInfant

Stichwörter der Autor:innen

Tetralogy of Fallotdeep learningsegmentation

Autor:innen und Institutionen

  • Department of Medical Imaging and Intervention, Chang Gung Memorial Hospital at Linkou, Taoyuan City, Taiwan.
  • Department of Medical Imaging and Radiological Sciences, College of Medicine, Chang Gung University, Taoyuan City, Taiwan.
  • Clinical Metabolomics Core Laboratory, Chang Gung Memorial Hospital at Linkou, Taoyuan City, Taiwan.

ORCID-Profile: Wen-Yen Chai, Gigin Lin, Yu-Chun Lin

Förderung

  • National Science and Technology Council
  • Chang Gung Medical Foundation

Zitieren

APA

Chai, W. Y., Lin, G., Wang, C. J., Chiang, H. J., Ng, S. H., Kuo, Y. S., & Lin, Y. C. (2026). A Deep Learning‐Based Fully Automated Cardiac MRI Segmentation Approach for Tetralogy of Fallot Patients. Journal of Magnetic Resonance Imaging. https://doi.org/10.1002/jmri.70113

Vancouver

Chai WY, Lin G, Wang CJ, Chiang HJ, Ng SH, Kuo YS, et al. A Deep Learning‐Based Fully Automated Cardiac MRI Segmentation Approach for Tetralogy of Fallot Patients. Journal of Magnetic Resonance Imaging. 2026. doi:10.1002/jmri.70113

BibTeX
@article{Chai2026,
  author = {Chai, Wen-Yen and Lin, Gigin and Wang, Chao-Jan and Chiang, Hsin-Ju and Ng, Shu-Hang and Kuo, Yi-Shan and Lin, Yu-Chun},
  title = {A Deep Learning‐Based Fully Automated Cardiac MRI Segmentation Approach for Tetralogy of Fallot Patients},
  journal = {Journal of Magnetic Resonance Imaging},
  year = {2026},
  doi = {10.1002/jmri.70113}
}
Kostenlos starten →