Impact of Synthetic Lesional MR Images in Automated Focal Cortical Dysplasia Detection in Low‐Data Scenarios
Journal of Neuroimaging · 2026
DOI: 10.1111/jon.70137 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Neuroimaging, 2026. Verfasst von Prabhjot Kaur und 4 weiteren Autor:innen. Beteiligte Einrichtung: Computational Radiology Laboratory, Boston Children's Hospital, Harvard Medical School, Boston, Massachusetts, USA. Hauptthemen laut MEDLINE: Detection Algorithms, Focal Cortical Dysplasia, Generative Artificial Intelligence, Image Interpretation, Computer-Assisted. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 34 Literaturangaben. Gefördert von: NIH HHS, Thrasher Research Fund, National Institutes of Health.
Abstract (Originalsprache)
Background and Purpose Automated detection of focal cortical dysplasia (FCD) requires large volumes of voxelwise‐lesion‐delineated MRI data, which are difficult to acquire. This study aims to generate synthetic MRI data exhibiting FCD, assess its realism, and evaluate its impact on automated FCD detection—particularly in reducing the need for manual annotations.
Methods
T1‐weighted (T1w) and T2‐weighted‐fluid‐attenuated inversion recovery (FLAIR) MRI scans from 131 FCD patients and 90 healthy controls from multiple (3) sites were retrospectively studied. Synthetic MRIs were generated by conditioning a generative network on binary FCD mask. Two neuroradiologists identified real images from a random set of 14 real and 14 synthetic scans. Three nnU‐Net models were trained to detect FCD using (i) real‐only (35‐FCD/35‐controls), (ii) real (35‐FCD/35‐controls) + synthetic augmentation, and (iii) expanded real data (70‐FCD/70 controls).
Results
Experts showed limited ability to distinguish real from synthetic images, with classification accuracy of 60% for T1w and 70% for FLAIR (inter‐rater agreement κ = 0.86). Augmenting automated FCD detection with synthetic data increased sensitivity by 8.14% ( p = 0.12) and improved model confidence at true lesion sites (0.83 ± 0.11 to 0.89 ± 0.12; p = 0.02). The expanded real‐data model further improved sensitivity to 73.8% ( p < 0.001) and confidence to 0.90 ± 0.14 ( p = 0.01).
Conclusion
Conditional generative networks can generate realistic synthetic FCD‐MRIs, reducing labeled data needs by ∼20% while maintaining equivalent sensitivity. Equivalent amounts of real data, when available, remain more effective than synthetic augmentation.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Computational Radiology Laboratory, Boston Children's Hospital, Harvard Medical School, Boston, Massachusetts, USA.
- Department of Radiology, Boston Children's Hospital, Boston, Massachusetts, USA.
- Department of Radiology, Harvard Medical School, Boston, Massachusetts, USA.
ORCID-Profile: Prabhjot Kaur
Förderung
- NIH HHS
- Thrasher Research Fund
- National Institutes of Health
Zitieren
APA
Kaur, P., Ouaalam, H., Kandemirli, S., Prabhu, S. P., & Warfield, S. K. (2026). Impact of Synthetic Lesional MR Images in Automated Focal Cortical Dysplasia Detection in Low‐Data Scenarios. Journal of Neuroimaging. https://doi.org/10.1111/jon.70137
Vancouver
Kaur P, Ouaalam H, Kandemirli S, Prabhu SP, Warfield SK. Impact of Synthetic Lesional MR Images in Automated Focal Cortical Dysplasia Detection in Low‐Data Scenarios. Journal of Neuroimaging. 2026. doi:10.1111/jon.70137
BibTeX
@article{Kaur2026,
author = {Kaur, Prabhjot and Ouaalam, Hakim and Kandemirli, Sedat and Prabhu, Sanjay P and Warfield, Simon K},
title = {Impact of Synthetic Lesional MR Images in Automated Focal Cortical Dysplasia Detection in Low‐Data Scenarios},
journal = {Journal of Neuroimaging},
year = {2026},
doi = {10.1111/jon.70137}
}
EUVIMED