Academic Journal
View in EDS
Linked Full Text

Impact of Synthetic Lesional MR Images in Automated Focal Cortical Dysplasia Detection in Low-Data Scenarios.

Bibliographic Details
Title: Impact of Synthetic Lesional MR Images in Automated Focal Cortical Dysplasia Detection in Low-Data Scenarios.
Authors: Kaur P; Computational Radiology Laboratory, Boston Children's Hospital, Harvard Medical School, Boston, Massachusetts, USA., Ouaalam H; Computational Radiology Laboratory, Boston Children's Hospital, Harvard Medical School, Boston, Massachusetts, USA., Kandemirli S; Computational Radiology Laboratory, Boston Children's Hospital, Harvard Medical School, Boston, Massachusetts, USA.; Department of Radiology, Boston Children's Hospital, Boston, Massachusetts, USA., Prabhu SP; 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., Warfield SK; Computational Radiology Laboratory, Boston Children's Hospital, Harvard Medical School, Boston, Massachusetts, USA.
Source: Journal of neuroimaging : official journal of the American Society of Neuroimaging [J Neuroimaging] 2026 May-Jun; Vol. 36 (3), pp. e70137.
Publication Type: Journal Article
Language: English
Journal Info: Publisher: Wiley Country of Publication: United States NLM ID: 9102705 Publication Model: Print Cited Medium: Internet ISSN: 1552-6569 (Electronic) Linking ISSN: 10512284 NLM ISO Abbreviation: J Neuroimaging Subsets: MEDLINE
Imprint Name(s): Publication: 2009- : Hoboken, NJ : Wiley
Original Publication: Boston, Mass. : Little, Brown and Co., c1991-
MeSH Terms: Focal Cortical Dysplasia*/diagnostic imaging , Focal Cortical Dysplasia*/pathology , Image Interpretation, Computer-Assisted*/methods , Magnetic Resonance Imaging*/methods , Detection Algorithms* , Generative Artificial Intelligence*, Pattern Recognition, Automated/methods ; Adolescent ; Adult ; Child ; Humans ; Reproducibility of Results ; Retrospective Studies ; Sensitivity and Specificity ; Infant ; Child, Preschool ; Young Adult ; Middle Aged ; Aged
Abstract: 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.
(© 2026 American Society of Neuroimaging.)
References: L. Kalilani, X. Sun, B. Pelgrims, M. Noack‐Rink, and V. Villanueva, “The Epidemiology of Drug‐Resistant Epilepsy: A Systematic Review and Meta‐Analysis, ” Epilepsia 59, no. 12 (2018): 2179–2193.
B. Sultana, M. A. Panzini, A. Veilleux Carpentier, et al., “Incidence and Prevalence of Drug‐Resistant Epilepsy: A Systematic Review and Meta‐Analysis, ” Neurology 96, no. 17 (2021): 805–817.
J. S. Hauptman and G. W. Mathern, “Surgical Treatment of Epilepsy Associated With Cortical Dysplasia: 2012 Update, ” Epilepsia 53, no. S4 (2012): 98–104.
L. Walger, S. Adler, K. Wagstyl, et al., “Artificial Intelligence for the Detection of Focal Cortical Dysplasia: Challenges in Translating Algorithms Into Clinical Practice, ” Epilepsia 64, no. 5 (2023): 1093–1112.
B. David, J. Kröll‐Seger, F. Schuch, et al., “External Validation of Automated Focal Cortical Dysplasia Detection Using Morphometric Analysis, ” Epilepsia 62, no. 4 (2021): 1005–1021.
R. S. Gill, H. M. Lee, B. Caldairou, et al., “Multicenter Validation of a Deep Learning Detection Algorithm for Focal Cortical Dysplasia, ” Neurology 97, no. 16 (2021): e1571–e1582.
H. Spitzer, M. Ripart, K. Whitaker, et al., “Interpretable Surface‐Based Detection of Focal Cortical Dysplasias: A Multi‐Centre Epilepsy Lesion Detection Study, ” Brain 145, no. 11 (2022): 3859–3871.
J. Wagner, B. Weber, H. Urbach, C. E. Elger, and H. J. Huppertz, “Morphometric MRI Analysis Improves Detection of Focal Cortical Dysplasia Type II, ” Brain 134, no. 10 (2011): 2844–2854.
M. Ripart, M. consortium, S. Adler, and K. Wagstyl, Multi‐Pathology MRI Lesion Segmentation in a Multi‐Centre Cohort of Patients With Focal Epilepsy: A MELD Study (AES Publication, 2024).
E. Thomas, S. J. Pawan, S. Kumar, et al., “Multi‐Res‐Attention UNet: A CNN Model for the Segmentation of Focal Cortical Dysplasia Lesions From Magnetic Resonance Images, ” IEEE Journal of Biomedical and Health Informatics 25, no. 5 (2021): 1724–1734.
D. Jiménez‐Murillo, A. E. Castro‐Ospina, L. Duque‐Muñoz, et al., “Automatic Detection of Focal Cortical Dysplasia Using MRI: A Systematic Review, ” Sensors (Basel) 23, no. 16 (2023): 7072.
P. E. Adjei, Z. M. Lonseko, W. Du, H. Zhang, and N. Rao, “Examining the Effect of Synthetic Data Augmentation in Polyp Detection and Segmentation, ” International Journal of Computer Assisted Radiology and Surgery 17, no. 7 (2022): 1289–1302.
Z. Yang, F. Zhan, K. Liu, M. Xu, and S. Lu, “AI‐Generated Images as Data Source: The Dawn of Synthetic Era, ” preprint, arXiv, October 3, 2023, https://arxiv.org/abs/2310.01830.
M. Foroozandeh and A. Eklund, “Synthesizing Brain Tumor Images and Annotations by Combining Progressive Growing GAN and SPADE, ” preprint, arXiv, September 13, 2020, https://doi.org/10.48550/arXiv.2009.02044.
V. Fernandez, W. H. L. Pinaya, P. Borges, et al., “Generating Multi‐Pathological and Multi‐Modal Images and Labels for Brain MRI, ” Medical Image Analysis 97 (2024): 103278.
H. C. Shin, N. A. Tenenholtz, J. K. Rogers, et al., “Medical Image Synthesis for Data Augmentation and Anonymization Using Generative Adversarial Networks, ” in Simulation and Synthesis in Medical Imaging: Third International Workshop, SASHIMI 2018, Held in Conjunction With MICCAI 2018 (Springer International Publishing, September 2018).
T. Islam, M. S. Hafiz, J. R. Jim, M. M. Kabir, and M. F. Mridha, “A Systematic Review of Deep Learning Data Augmentation in Medical Imaging: Recent Advances and Future Research Directions, ” Healthcare Analytics 5 (2024): 100340.
P. Alimisis, I. Mademlis, P. Radoglou‐Grammatikis, P. Sarigiannidis, and G. T. Papadopoulos, “Advances in Diffusion Models for Image Data Augmentation: A Review of Methods, Models, Evaluation Metrics and Future Research Directions, ” Artificial Intelligence Review 58 (2025): 112.
S. Chen, E. Dobriban, and J. H. Lee, “A Group‐Theoretic Framework for Data Augmentation, ” Journal of Machine Learning Research 21, no. 1 (2020): 2985–3055.
M. Hoffmann, “Domain‐Randomized Deep Learning for Neuroimage Analysis: Selecting Training Strategies, Navigating Challenges, and Maximizing Benefits, ” IEEE Signal Processing Magazine 42, no. 4 (2025): 78–90.
F. Schuch, L. Walger, M. Schmitz, et al., “An Open Presurgery MRI Dataset of People With Epilepsy and Focal Cortical Dysplasia Type II, ” Scientific Data 10, no. 1 (2023): 475.
P. N. Taylor, Y. Wang, C. Simpson, et al., “The Imaging Database for Epilepsy and Surgery (IDEAS), ” Epilepsia 66, no. 2 (2025): 471–481.
B. Fischl, “FreeSurfer, ” Neuroimage 62, no. 2 (2012): 774–781.
A. Carré, G. Klausner, M. Edjlali, et al., “Standardization of Brain MR Images Across Machines and Protocols: Bridging the Gap for MRI‐Based Radiomics, ” Scientific Reports 10, no. 1 (2020): 12340.
M. J. Cardoso, R. Wolz, M. Modat, N. C. Fox, D. Rueckert, and S. Ourselin, “Geodesic Information Flows, ” in International Conference on Medical Image Computing and Computer‐Assisted Intervention (Heidelberg: Springer Berlin Heidelberg, 2012).
F. Isensee, T. Wald, and C. Ulrich, “nnU‐Net Revisited: A Call for Rigorous Validation in 3d Medical Image Segmentation, ” in International Conference on Medical Image Computing and Computer‐Assisted Intervention (Cham: Springer Nature Switzerland, 2024).
S. Zhang, Y. Zhuang, Y. Luo, F. Zhu, W. Zhao, and H. Zeng, “Deep Learning‐Based Automated Lesion Segmentation on Pediatric Focal Cortical Dysplasia II Preoperative MRI: A Reliable Approach, ” Insights Into Imaging 15, no. 1 (2024): 71.
IBM Corp., IBM SPSS Statistics for Windows, Version 18.0 (IBM Corp, 2009).
L. D. Brown, T. T. Cai, and A. DasGupta, “Interval Estimation for a Binomial Proportion, ” Statistical Science 16, no. 2 (2001): 101–133.
K. L. Hom, V. S. P. Illapani, H. Xie, et al., “Application of Preoperative MRI Lesion Identification Algorithm in Pediatric and Young Adult Focal Cortical Dysplasia‐Related Epilepsy, ” Seizure: The Journal of the British Epilepsy Association 122 (2024): 64–70.
A. Goel, S. Seri, S. Agrawal, et al., “The Utility of Multicentre Epilepsy Lesion Detection (MELD) Algorithm in Identifying Epileptic Activity and Predicting Seizure Freedom in MRI Lesion‐Negative Pediatric Patients, ” Epilepsy Research 206 (2024): 107429.
Z. Dorjsembe, H. K. Pao, S. Odonchimed, and F. Xiao, “Conditional Diffusion Models for Semantic 3D Brain MRI Synthesis, ” IEEE Journal of Biomedical and Health Informatics 28, no. 7 (2024): 4084–4093.
B. Billot, D. N. Greve, O. Puonti, et al., “SynthSeg: Segmentation of Heterogeneous MRI Scans of any Contrast or Resolution Without Retraining, ” Medical Image Analysis 87 (2023): 102789.
L. Zhang, B. Jindal, A. Alaa, et al., “Generative AI Enables Medical Image Segmentation in Ultra Low‐Data Regimes, ” Nature Communications 16, no. 1 (2025): 6486.
Grant Information: S10 OD025111 United States GF NIH HHS; R01 LM013608 United States GF NIH HHS; R01 EB019483 United States GF NIH HHS; R01 NS124212 United States GF NIH HHS; Thrasher Research Fund
Contributed Indexing: Keywords: epilepsy; focal cortical dysplasia; generative AI; lesion detection; synthetic MRI
Entry Date(s): Date Created: 20260604 Date Completed: 20260607 Latest Revision: 20260610
Update Code: 20260611
DOI: 10.1111/jon.70137
PMID: 42240056
Database: MEDLINE
Description
ISSN:1552-6569
DOI:10.1111/jon.70137