Abstract
Obesity is one of the main drivers of type 2 diabetes, but it is not uniformly associated with the disease. The location of fat accumulation is critical for metabolic health. Specific patterns of body fat distribution, such as visceral fat, are closely related to insulin resistance. There might be further, hitherto unknown, features of body fat distribution that could additionally contribute to the disease. We used machine learning with dense convolutional neural networks to detect diabetes-related variables from 2371 T1-weighted whole-body MRI data sets. MRI was performed in participants undergoing metabolic screening with oral glucose tolerance tests. Models were trained for sex, age, BMI, insulin sensitivity, HbA1c, and prediabetes or incident diabetes. The results were compared with those of conventional models. The area under the receiver operating characteristic curve was 87% for the type 2 diabetes discrimination and 68% for prediabetes, both superior to conventional models. Mean absolute regression errors were comparable to those of conventional models. Heatmaps showed that lower visceral abdominal regions were critical in diabetes classification. Subphenotyping revealed a group with high future diabetes and microalbuminuria risk.Our results show that diabetes is detectable from whole-body MRI without additional data. Our technique of heatmap visualization identifies plausible anatomical regions and highlights the leading role of fat accumulation in the lower abdomen in diabetes pathogenesis.
Highlights
Around 500 million individuals worldwide have diabetes with a dramatically rising prevalence [1]
We used machine learning with dense convolutional neural networks (DCNN) to detect diabetes related variables from 2,371 T1-weighted whole-body magnetic resonance imaging (MRI) datasets
Interpretation Our results show that diabetes is detectable from whole-body MRI without additional data
Summary
Around 500 million individuals worldwide have diabetes with a dramatically rising prevalence [1]. There are individuals who remain metabolically healthy despite being obese [3], while others develop insulin resistance despite normal body weight [4] This is because the distribution of fat within the human body crucially determines its metabolic role. Subcutaneous abdominal and thigh fat seem to act as protective triglyceride dumps in the body which preserve insulin sensitivity by confining fat to metabolically inert body regions [6, 7] Specific fat compartments, such as fat depots near arteries, seem to play distinctive roles in the pathophysiology of insulin resistance, insulin secretion and probably the manifestation of metabolic complications [8]. It is notoriously challenging to derive human-readable information on key patterns of machine learning classifiers [17], we aimed to extract information on the anatomical regions decisive in establishing these associations
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
