Key result
Deep learning model estimates adipose tissue metabolic activity from non-contrast CT with strong PET agreement.
Why the study?
Detection of brown adipose tissue typically relies on 18F-FDG PET, which is costly, radiation-intensive, and impractical for large-scale screening.
Does a deep learning model accurately estimate regional metabolic activity in adipose tissue from non-contrast CT compared to 18F-FDG PET?
Does a deep learning model accurately estimate regional metabolic activity in adipose tissue from non-contrast CT compared to 18F-FDG PET?
A deep learning model can estimate brown adipose tissue metabolic activity from standard non-contrast CT scans, potentially enabling large-scale cardiometabolic screening without the radiation and cost of PET scans.
Answers are grounded in this paper and cite their sources.
May enable radiation-free adipose metabolic assessment; leaves open validation for cardiometabolic risk stratification.
Brown adipose tissue (BAT) plays a key role in energy metabolism and cardiometabolic health. Its detection typically relies on 18F-FDG PET, which is costly, radiation-intensive, and impractical for large-scale screening. We propose a deep learning model to estimate regional metabolic activity in adipose tissue from standard non-contrast CT, enabling PET-like insights without radiotracers. Using paired PET/CT data from two independent cohorts, we trained a conditional Generative Adversarial Network (cGAN) to predict standardized uptake values (SUV) within adipose regions identified on CT. The network included a fat-focused loss function to enhance metabolic signal estimation. Predicted activations showed strong agreement with PET-derived values and were reproducible across anatomical regions and datasets. This method provides a radiation-sparing alternative for assessing adipose metabolic activity in clinical and research settings and it could support population-based studies of BAT, metabolic health, and disease progression using routine chest CT scans without additional imaging burden.
No takes yet. Share an insight, caveat, or question.
Cano-Espinosa et al. (2026) studied Brown adipose tissue metabolic activity (n=424). Conditional Generative Adversarial Network (cGAN) prediction from non-contrast CT vs. Reference 18F-FDG PET/CT (measured SUV) was evaluated on Voxel-wise Mean Absolute Error (MAE) and correlation of mean activation (SUV) between predicted and reference PET. A deep learning model successfully estimated regional metabolic activity in adipose tissue from non-contrast CT scans, demonstrating strong agreement with PET-derived standardized uptake values.
Synapse has enriched 10 related papers. Consider them for comparative context: