Why the study?
Intra-pancreatic fat deposition is closely linked to type 2 diabetes mellitus onset and progression, but accurate and automated methods for assessing it on multi-echo Dixon MRI were needed.
Does a deep learning radiomics model improve the accuracy of distinguishing T2DM from non-diabetes and pre-diabetes compared to radiologist assessment of intra-pancreatic fat deposition on MRI?
Does a deep learning radiomics model improve the accuracy of distinguishing T2DM from non-diabetes and pre-diabetes compared to radiologist assessment of intra-pancreatic fat deposition on MRI?
A deep learning radiomics model using Dixon MRI provides a more accurate and stable method for monitoring intra-pancreatic fat deposition and predicting T2DM risk compared to radiologist assessment.
No takes yet. Share an insight, caveat, or question.
Offers a scalable tool for quantifying pancreatic fat in metabolic risk assessment; leaves open whether automated MRI screening improves.
Pan et al. (2025) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: