mlsanityData to 14 Oct 2026

Cyclic 2.5D Perceptual Loss for Cross-Modal 3D Medical Image Synthesis: T1w MRI to Tau PET

arXiv 2406.12632 ↗First posted 18 Jun 2024eess.IV cs.CVcited by 2

Not on the map. Why?

Abstract (arXiv)

Positron emission tomography (PET) provides molecular biomarkers for Alzheimer's disease and related dementias (ADRD) and is increasingly used for diagnosis, staging, and clinical trial enrichment. However, its use is limited by cost, regulatory restrictions, and the invasiveness of radiotracer injection. Although current frameworks emphasize multimodal biomarker assessment, including the amyloid/tau/neurodegeneration (A/T/N) scheme, these barriers constrain access to PET imaging. Cross-modal image synthesis may help address this gap by reconstructing unavailable modalities from routine scans. Because PET is clinically valuable for regional uptake patterns rather than exact voxel-wise intensities, perceptual losses that capture higher-level semantic features are well suited to PET synthesis. Existing 2D, 3D, and 2.5D perceptual losses for 3D synthesis each have limitations, including restricted volumetric context, scarcity of pretrained 3D models, and difficulty balancing optimization across anatomical planes. In this study, we synthesize tau PET from structural MRI by generating 3D pseudo-[18F]flortaucipir standardized uptake value ratio (SUVR) maps from 3D T1-weighted MR images. We propose a cyclic 2.5D perceptual loss that alternates optimization across axial, coronal, and sagittal planes during training to improve volumetric consistency. We also standardize PET SUVRs by scanner manufacturer, reducing inter-manufacturer variability and better preserving high-uptake regions. Using cohorts spanning the ADRD spectrum from the ADNI and the SCAN cohort, we show that the method generalizes across U-Net, UNETR, SwinUNETR, CycleGAN, and Pix2Pix, with strong performance. Notably, it improves agreement between synthesized SUVRs and measured PET in brain regions relevant to Alzheimer-type tau pathology. Code is publicly available at https://github.com/labhai/Cyclic-2.5D-Perceptual-Loss.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 34 of its 147 references that are in the map. First posted on arXiv 18 Jun 2024.

Builds on

34 of 147 references.

References · 34

  1. 2017Attention Is All You Needcited by 60,361
  2. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  3. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  4. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  5. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  6. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
  7. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,498
  8. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 7,005
  9. 2015Rethinking the Inception Architecture for Computer Visioncited by 5,475
  10. 2016SGDR: Stochastic Gradient Descent with Warm Restartscited by 5,045
  11. 2016Image-to-Image Translation with Conditional Adversarial Networkscited by 4,527
  12. 2016Perceptual Losses for Real-Time Style Transfer and Super-Resolutioncited by 2,694
22 more
  1. 20163D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotationcited by 1,476
  2. 2016Instance Normalization: The Missing Ingredient for Fast Stylizationcited by 1,198
  3. 2021UNETR: Transformers for 3D Medical Image Segmentationcited by 959
  4. 2022Swin UNETR: Swin Transformers for Semantic Segmentation of Brain Tumors in MRI Imagescited by 830
  5. 2015Cyclical Learning Rates for Training Neural Networkscited by 629
  6. 2022MONAI: An open-source framework for deep learning in healthcarecited by 448
  7. 2019Med3D: Transfer Learning for 3D Medical Image Analysiscited by 288
  8. 2018MedGAN: Medical Image Translation using GANscited by 152
  9. 2018Image Synthesis in Multi-Contrast MRI with Conditional Generative Adversarial Networkscited by 132
  10. 2022SynthStrip: Skull-Stripping for Any Brain Imagecited by 127
  11. 2019Unsupervised Medical Image Translation Using Cycle-MedGANcited by 44
  12. 2020Bidirectional Mapping Generative Adversarial Networks for Brain MR to PET Synthesiscited by 38
  13. 2018Unpaired Brain MR-to-CT Synthesis using a Structure-Constrained CycleGANcited by 31
  14. 2021SOUP-GAN: Super-Resolution MRI Using Generative Adversarial Networkscited by 18
  15. 2023Cycle-guided Denoising Diffusion Probability Model for 3D Cross-modality MRI Synthesiscited by 18
  16. 2023Synthesizing PET images from High-field and Ultra-high-field MR images Using Joint Diffusion Attention Modelcited by 14
  17. 2020GANDALF: Generative Adversarial Networks with Discriminator-Adaptive Loss Fine-tuning for Alzheimer's Disease Diagnosis from MRIcited by 13
  18. 2024PASTA: Pathology-Aware MRI to PET Cross-Modal Translation with Diffusion Modelscited by 10
  19. 2018MRI to FDG-PET: Cross-Modal Synthesis Using 3D U-Net For Multi-Modal Alzheimer's Classificationcited by 9
  20. 2021Generic Perceptual Loss for Modeling Structured Output Dependenciescited by 9
  21. 2023TauPETGen: Text-Conditional Tau PET Image Synthesis Based on Latent Diffusion Modelscited by 7
  22. 20243D Volumetric Super-Resolution in Radiology Using 3D RRDB-GANcited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 2.

2 papers.

  1. 2026SFL-Net: Source-Factorized Latent Representation Learning for Multi-Contrast MRI to Tau-PET Synthesiscited by 1
  2. 2026vSV-ViT: Variable-size SuperVertex Vision Transformer for Cortical Surface Learning in Alzheimer's Diseasecited by 0