GAN-Based Cross-Modality Brain MRI Synthesis: Paired Versus Unpaired Training and Comparison with Diffusion and Transformer Models
Biomimetics · 02.03.2026 · 11 (3) · 175
DOI: 10.3390/biomimetics11030175 ↗Kurz gefasst
Fachartikel in der Zeitschrift Biomimetics, online erschienen am 02.03.2026. Verfasst von Behnam Kiani Kalejahi und 2 weiteren Autor:innen. Beteiligte Einrichtung: Department of Computer Science, School of Engineering, Central Asian University, Tashkent 111211, Uzbekistan. Die Arbeit wurde bisher 9-mal zitiert (Crossref) und nennt 45 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Incomplete or faulty MRI sequences are common in clinical practice and can impair AI-based analyses that rely on complete multi-contrast data. The relative effectiveness of classical generative adversarial networks (GANs) versus modern diffusion and transformer-based models for clinically usable MRI synthesis remains unclear. This study evaluates cross-modality MRI synthesis using the BraTS 2019 brain tumour dataset, focusing on T1-to-T2 translation. We assess paired and unpaired CycleGAN models and compare them with two stronger but computationally intensive baselines, a conditional denoising diffusion probabilistic model (DDPM) and a transformer-enhanced GAN, using identical data splits and preprocessing pipelines. Inter-modality correlation was evaluated to estimate the achievable similarity between modalities. Conceptually, modality synthesis may be viewed as a representation-learning approach that compensates for missing imaging information by reconstructing clinically relevant features from available contrasts. Paired CycleGAN achieved correlations of r≈0.92–0.93 and SSIM ≈0.90–0.92, approaching natural T1–T2 correlation (r≈0.95) while maintaining very fast inference (
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Computer Science, School of Engineering, Central Asian University, Tashkent 111211, Uzbekistan.
- Faculty of Data Science and Information Technology, INTI International University, Persiaran Perdana BBN Putra Nilai, Nilai 71800, Malaysia.
- Department of Electronic and Computer Engineering, Brunel University, Uxbridge UB83PH, UK.
ORCID-Profile: Behnam Kiani Kalejahi, Sebelan Danishvar
Zitieren
APA
Kiani Kalejahi, B., Danishvar, S., & Rajabi, M. J. (2026). GAN-Based Cross-Modality Brain MRI Synthesis: Paired Versus Unpaired Training and Comparison with Diffusion and Transformer Models. Biomimetics, 11(3), 175. https://doi.org/10.3390/biomimetics11030175
Vancouver
Kiani Kalejahi B, Danishvar S, Rajabi MJ. GAN-Based Cross-Modality Brain MRI Synthesis: Paired Versus Unpaired Training and Comparison with Diffusion and Transformer Models. Biomimetics. 2026;11(3):175. doi:10.3390/biomimetics11030175
BibTeX
@article{KianiKalejahi2026,
author = {Kiani Kalejahi, Behnam and Danishvar, Sebelan and Rajabi, Mohammad Javad},
title = {GAN-Based Cross-Modality Brain MRI Synthesis: Paired Versus Unpaired Training and Comparison with Diffusion and Transformer Models},
journal = {Biomimetics},
year = {2026},
volume = {11},
number = {3},
pages = {175},
doi = {10.3390/biomimetics11030175}
}
EUVIMED