mlsanityData to 14 Oct 2026

GAN-based synthetic FDG PET images from T1 brain MRI can serve to improve performance of deep unsupervised anomaly detection models

arXiv 2505.07364 ↗First posted 12 May 2025eess.IV cs.AIcited by 1

Not on the map. Why?

Abstract (arXiv)

Background and Objective. Research in the cross-modal medical image translation domain has been very productive over the past few years in tackling the scarce availability of large curated multimodality datasets with the promising performance of GAN-based architectures. However, only a few of these studies assessed task-based related performance of these synthetic data, especially for the training of deep models. Method. We design and compare different GAN-based frameworks for generating synthetic brain [18F]fluorodeoxyglucose (FDG) PET images from T1 weighted MRI data. We first perform standard qualitative and quantitative visual quality evaluation. Then, we explore further impact of using these fake PET data in the training of a deep unsupervised anomaly detection (UAD) model designed to detect subtle epilepsy lesions in T1 MRI and FDG PET images. We introduce novel diagnostic task-oriented quality metrics of the synthetic FDG PET data tailored to our unsupervised detection task, then use these fake data to train a use case UAD model combining a deep representation learning based on siamese autoencoders with a OC-SVM density support estimation model. This model is trained on normal subjects only and allows the detection of any variation from the pattern of the normal population. We compare the detection performance of models trained on 35 paired real MR T1 of normal subjects paired either on 35 true PET images or on 35 synthetic PET images generated from the best performing generative models. Performance analysis is conducted on 17 exams of epilepsy patients undergoing surgery. Results. The best performing GAN-based models allow generating realistic fake PET images of control subject with SSIM and PSNR values around 0.9 and 23.8, respectively and in distribution (ID) with regard to the true control dataset. The best UAD model trained on these synthetic normative PET data allows reaching 74% sensitivity. Conclusion. Our results confirm that GAN-based models are the best suited for MR T1 to FDG PET translation, outperforming transformer or diffusion models. We also demonstrate the diagnostic value of these synthetic data for the training of UAD models and evaluation on clinical exams of epilepsy patients. Our code and the normative image dataset are available.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 13 of its 39 references that are in the map. First posted on arXiv 12 May 2025.

Builds on

13 of 39 references.

References · 13

  1. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,177
  2. 2016Least Squares Generative Adversarial Networkscited by 1,001
  3. 2019Embracing Imperfect Datasets: A Review of Deep Learning Solutions for Medical Image Segmentationcited by 260
  4. 2021ResViT: Residual vision transformers for multi-modal medical image synthesiscited by 177
  5. 2020Autoencoders for Unsupervised Anomaly Segmentation in Brain MR Images: A Comparative Studycited by 147
  6. 2019Unsupervised Medical Image Translation Using Cycle-MedGANcited by 44
  7. 2022One Model to Synthesize Them All: Multi-contrast Multi-scale Transformer for Missing Data Imputationcited by 40
  8. 2018Tiling and Stitching Segmentation Output for Remote Sensing: Basic Challenges and Recommendationscited by 24
  9. 2021MRI to PET Cross-Modality Translation using Globally and Locally Aware GAN (GLA-GAN) for Multi-Modal Diagnosis of Alzheimer's Diseasecited by 16
  10. 2023Synthesizing PET images from High-field and Ultra-high-field MR images Using Joint Diffusion Attention Modelcited by 14
  11. 2018MRI to FDG-PET: Cross-Modal Synthesis Using 3D U-Net For Multi-Modal Alzheimer's Classificationcited by 9
  12. 2021Patch vs. Global Image-Based Unsupervised Anomaly Detection in MR Brain Scans of Early Parkinsonian Patientscited by 5
1 more
  1. 2023Brain subtle anomaly detection based on auto-encoders latent space analysis : application to de novo parkinson patientscited by 4

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026Translating MRI to PET through Conditional Diffusion Models with Enhanced Pathology Awarenesscited by 1

Similar, not cited

Close in wording, no citation either way

  1. 2025Score-based Generative Diffusion Models to Synthesize Full-dose FDG Brain PET from MRI in Epilepsy Patients
  2. 2025Unsupervised anomaly detection using Bayesian flow networks: application to brain FDG PET in the context of Alzheimer's disease
  3. 2024IgCONDA-PET: Weakly-Supervised PET Anomaly Detection using Implicitly-Guided Attention-Conditional Counterfactual Diffusion Modeling -- a Multi-Center, Multi-Cancer, and Multi-Tracer Study
  4. 2025Benchmarking GANs, Diffusion Models, and Flow Matching for T1w-to-T2w MRI Translation
  5. 2024Non-Reference Quality Assessment for Medical Imaging: Application to Synthetic Brain MRIs
  6. 2023Patched Diffusion Models for Unsupervised Anomaly Detection in Brain MRI
  7. 2023Brain tumor segmentation using synthetic MR images -- A comparison of GANs and diffusion models
  8. 2025MCR-VQGAN: A Scalable and Cost-Effective Tau PET Synthesis Approach for Alzheimer's Disease Imaging