New AI Method Improves CT-PET Medical Image Synthesis Using Dual-Domain Learning
Researchers have developed a Dual-Domain Equivariant Generative Adversarial Network (DDE-GAN) that synthesizes CT and PET medical images by jointly learning from spatial and frequency domains. Unlike traditional GAN-based approaches that work only in the spatial domain, DDE-GAN incorporates rotational equivariance and hierarchical multi-stage training to improve geometric and structural consistency. The method could enable practical applications in PET image completion and medical data augmentation, addressing a key bottleneck in clinical imaging workflows.
A team of researchers has proposed DDE-GAN, a novel generative adversarial network architecture designed for multimodal CT-PET image synthesis. The model addresses a known limitation of conventional GAN approaches—operating exclusively in the spatial domain—by simultaneously learning from both spatial and Fourier frequency domains, thereby capturing complementary anatomical and spectral features. A key innovation is the integration of rotational equivariance, a property grounded in the physics of CT and PET acquisition, into the loss functions of both the generator and discriminator, ensuring that synthesized images remain consistent under rotational transformations. A hierarchical dual-domain training strategy further enforces consistency within and across domains through multi-stage loss functions. The model was evaluated on the publicly available HECKTOR 2022 CT-PET dataset and demonstrated superior synthesis quality compared to baseline models. The authors suggest the approach has practical utility for PET completion—generating PET images when only CT data is available—and for augmenting limited medical imaging datasets. The paper is accepted for presentation at the 2026 IEEE International Symposium on Biomedical Imaging (ISBI).
What's missing
The abstract does not report specific quantitative metrics (e.g., SSIM, PSNR, FID scores) by which 'superior synthesis quality' is claimed, making independent assessment of the magnitude of improvement difficult. The study is limited to a single dataset (HECKTOR 2022), so generalizability to other anatomical regions or imaging protocols is unestablished. Computational cost and inference time relative to baseline models are not discussed, which are relevant for clinical deployment.
What different sources said
- arXiv cs.AICenter
Dual-Domain Equivariant Generative Adversarial Network for Multimodal CT-PET Synthesis
Related
Gut Bacteria Enzyme Found to Break Down Heat-Processed Food Compounds, Producing Novel Biogenic Amines
Researchers have discovered that an enzyme in common gut bacteria can degrade N-epsilon-carboxymethyllysine (CML), a compound formed during thermal food processing, producing previously unknown biogenic amines. The enzyme, ornithine decarboxylase SpeC from enterobacteria, acts on CML and related modified lysine derivatives through a low-level 'underground' catalytic activity. This finding suggests a previously unrecognized communication axis between thermally processed dietary compounds and gut microbial physiology, with potential implications for host health.
Full-Length Gene Sequencing Reveals Two Distinct Bacterial Communities in Black-Legged Ticks Expanding Into Canada
Researchers used Oxford Nanopore full-length 16S rRNA gene sequencing to characterize the microbiome of Ixodes scapularis black-legged ticks collected in Nova Scotia, Canada, distinguishing between tick-adapted bacteria and environmentally acquired bacteria. The study comes as I. scapularis — the primary vector of Lyme disease — is rapidly expanding northward into Canada due to climate change. The findings suggest that environmentally derived bacteria in tick microbiomes are not mere contamination, which has implications for how tick microbiome data is collected and interpreted across surveillance studies.
Study Identifies Metabolic Link Between Cell Envelope Stress and Biofilm Formation in Bacteria
Researchers have discovered that the metabolite acetyl-CoA directly inhibits enzymes that degrade the bacterial signaling molecule c-di-GMP, connecting cell envelope biosynthesis stress to biofilm formation in Pseudomonas aeruginosa. The study found that sub-inhibitory concentrations of antibiotics targeting early peptidoglycan biosynthesis — but not other antibiotic classes — elevate c-di-GMP levels by reducing phosphodiesterase activity, with acetyl-CoA competing for the enzyme active site. Because the relevant enzyme domain is broadly conserved across bacterial species, this checkpoint mechanism may be widespread and could have implications for understanding antibiotic-induced biofilm responses.