Back to all papers

Domain-specific adaptation for MR image synthesis with text-guided diffusion.

June 3, 2026pubmed logopapers

Authors

Wen Y,Healy J,Song Y,Fu X,Song S,Curran KM

Affiliations (5)

  • School of Electrical and Electronic Eng, University College Dublin, Belfield, Dublin 4, Dublin, D04V1W8, Ireland.
  • School of Electrical and Electronic Engineering, University College Dublin, Engineering and Material Science, Belfield, Dublin 4, Dublin, 4, Ireland.
  • Department of Radiological Imaging, Haibin People's Hospital, Xingfu Road, Binhai New Area, Tianjin, 300280, China.
  • Department of Radiological Imaging, Haibin People's Hospital, Xingfu Road, Binhai New Area, Tianjin, Tianjin, 300280, China.
  • School of Medicine, University College Dublin, Health Science Centre, Belfield, Dublin 4, Dublin, D04 C7X2, Ireland.

Abstract

Deep learning in medical imaging is severely constrained by data scarcity. Data synthesis offers a promising solution, but existing generative models have difficulty in restoring pathological texture features when trained on small-scale datasets. To address this, we propose a domain-specific, partition-based parallel text-guided Latent Diffusion Model (LDM) for medical image synthesis. Each LDM operates on a defined image domain and is fine-tuned to reproduce texture characteristics specific. Diseased regions are identified from segmentation masks, while healthy regions are further subdivided using Voronoi-grayscale adaptation, enabling localized texture preservation. The fine-tuned LDMs independently synthesize corresponding image partitions, which are subsequently merged and denoised to form complete synthetic images with paired segmentation masks.

We evaluated the approach on glioma MRI data, achieving a FID of 13.65, demonstrating high perceptual realism. Texture fidelity was further supported by SSIM of 0.9674 and radiomic feature distribution analyses, both confirming close alignment between real and synthetic images. In a blinded visual Turing test, three radiologists achieved an average sensitivity of only 25.5% when identifying synthetic MRI slices, resulting in a 74.5% deception rate, and 41% of the synthetic samples were universally misclassified as real by all experts. In downstream experiments, U-Net trained on the synthetic-augmented dataset improved DSC by 14% on average. These results demonstrate that the proposed domain-specific adaptation framework can generate perceptually plausible, structure-preserving synthetic MRI slices in data-constrained environments, while improving downstream segmentation performance. The method therefore shows potential as an augmentation-oriented tool for AI model development, clinical teaching, assisted diagnosis, and rare-disease research.

Topics

Journal Article

Ready to Sharpen Your Edge?

Subscribe to join 11k+ peers who rely on RadAI Slice. Get the essential weekly briefing that empowers you to navigate the future of radiology.

We respect your privacy. Unsubscribe at any time.