Detection of diabetes from whole-body MRI using deep learning

Deep learning for the prediction of type 2 diabetes mellitus from neck-to-knee Dixon MRI in the UK biobank

Rationale and objectives

We evaluate the automatic identification of type 2 diabetes from neck-to-knee, two-point Dixon MRI scans with 3D convolutional neural networks on a large, population-based dataset. To this end, we assess the best combination of MRI contrasts and stations for diabetes prediction, and the benefit of integrating risk factors.

Materials and methods

Subjects with type 2 diabetes mellitus have been identified in the prospective UK Biobank Imaging study, and a matched control sample has been created to avoid confounding bias. Five-fold cross-validation is used for the evaluation. All scans from the two-point Dixon neck-to-knee sequence have been standardized. A neural network that considers multi-channel MRI input was developed and integrates clinical information in tabular format. An ensemble strategy is used to combine multi-station MRI predictions. A subset with quantitative fat measurements is identified for comparison to prior approaches.

Results

MRI scans from 3406 subjects (mean age, 66.2 years ± 7.1 [standard deviation]; 1128 women) were analyzed with 1703 diabetics. A balanced accuracy of 78.7 %, AUC ROC of 0.872, and an average precision of 0.878 was obtained for the classification of diabetes. The ensemble over multiple Dixon MRI stations yields better performance than selecting the individually best station. Moreover, combining fat and water scans as multi-channel inputs to the networks improves upon just using single contrasts as input. Integrating clinical information about known risk factors of diabetes in the network boosts the performance across all stations and the ensemble. The neural network achieved superior results compared to the prediction based on quantitative MRI measurements.

Conclusions

The developed deep learning model accurately predicted type 2 diabetes from neck-to-knee two-point Dixon MRI scans.

Opportunistic detection of type 2 diabetes using deep learning from frontal chest radiographs

Deep learning (DL) models can harness electronic health records (EHRs) to predict diseases and extract radiologic findings for diagnosis. With ambulatory chest radiographs (CXRs) frequently ordered, we investigated detecting type 2 diabetes (T2D) by combining radiographic and EHR data using a DL model. Our model, developed from 271,065 CXRs and 160,244 patients, was tested on a prospective dataset of 9,943 CXRs. Here we show the model effectively detected T2D with a ROC AUC of 0.84 and a 16% prevalence. The algorithm flagged 1,381 cases (14%) as suspicious for T2D. External validation at a distinct institution yielded a ROC AUC of 0.77, with 5% of patients subsequently diagnosed with T2D. Explainable AI techniques revealed correlations between specific adiposity measures and high predictivity, suggesting CXRs' potential for enhanced T2D screening.

Gender-specific data-driven adiposity subtypes using deep-learning-based abdominal CT segmentation

OBJECTIVE

The aim of this study was to quantify abdominal adiposity and generate data-driven adiposity subtypes with different diabetes risks.

METHODS

A total of 3817 participants from the Pinggu Metabolic Disease Study were recruited. A deep-learning-based recognition model on abdominal computed tomography (CT) images (A-CT model) was developed and validated in 100 randomly selected cases. The volumes and proportions of subcutaneous fat, visceral fat, liver fat, and muscle fat were automatically recognized in all cases. K-means clustering was used to identify subgroups using the proportions of the four fat components.

RESULTS

The Dice indices among the measurements assessed by the A-CT model and manual evaluation to detect liver fat, muscle fat, and subcutaneous fat areas were 0.96, 0.95, and 0.92, respectively. Three subtypes were generated separately in men and women: visceral fat dominant type (VFD); subcutaneous fat dominant type (SFD); and intermuscular fat dominant type (MFD). Compared with the SFD group, the MFD group had similar diabetes risk, and the VFD group had a 60% higher diabetes risk when age and BMI were adjusted for in men. The adjusted odds ratio for diabetes was 1.92 (95% CI: 1.32-2.78) in the MFD group and 6.14 (95% CI: 4.18-9.03) in the VFD group in women.

CONCLUSIONS

This study identified gender-specific abdominal adiposity subgroups, which may help clinicians to distinguish diabetes risk quickly and automatically.

Machine Learning as a Support for the Diagnosis of Type 2 Diabetes

Diabetes is a chronic, metabolic disease characterized by high blood sugar levels. Among the main types of diabetes, type 2 is the most common. Early diagnosis and treatment can prevent or delay the onset of complications. Previous studies examined the application of machine learning techniques for prediction of the pathology, and here an artificial neural network shows very promising results as a possible valuable aid in the management and prevention of diabetes. Additionally, its superior ability for long-term predictions makes it an ideal choice for this field of study. We utilized machine learning methods to uncover previously undiscovered associations between an individual’s health status and the development of type 2 diabetes, with the goal of accurately predicting its onset or determining the individual’s risk level. Our study employed a binary classifier, trained on scratch, to identify potential nonlinear relationships between the onset of type 2 diabetes and a set of parameters obtained from patient measurements. Three datasets were utilized, i.e., the National Center for Health Statistics’ (NHANES) biennial survey, MIMIC-III and MIMIC-IV. These datasets were then combined to create a single dataset with the same number of individuals with and without type 2 diabetes. Since the dataset was balanced, the primary evaluation metric for the model was accuracy. The outcomes of this study were encouraging, with the model achieving accuracy levels of up to 86% and a ROC AUC value of 0.934. Further investigation is needed to improve the reliability of the model by considering multiple measurements from the same patient over time.

Recent applications of machine learning and deep learning models in the prediction, diagnosis, and management of diabetes: a comprehensive review

Diabetes as a metabolic illness can be characterized by increased amounts of blood glucose. This abnormal increase can lead to critical detriment to the other organs such as the kidneys, eyes, heart, nerves, and blood vessels. Therefore, its prediction, prognosis, and management are essential to prevent harmful effects and also recommend more useful treatments. For these goals, machine learning algorithms have found considerable attention and have been developed successfully. This review surveys the recently proposed machine learning (ML) and deep learning (DL) models for the objectives mentioned earlier. The reported results disclose that the ML and DL algorithms are promising approaches for controlling blood glucose and diabetes. However, they should be improved and employed in large datasets to affirm their applicability.

Interscapular fat is associated with impaired glucose tolerance and insulin resistance independent of visceral fat mass

OBJECTIVE

Dysregulated body fat distribution is a major determinant of various diseases. In particular, increased visceral fat mass and ectopic lipids in the liver are linked to metabolic disorders such as insulin resistance and type 2 diabetes. Furthermore, interscapular fat is considered to be a metabolically active fat compartment.

METHODS

This study measured interscapular fat mass and investigated its relationship with glucose metabolism in 822 individuals with a wide range of BMI values and different glucose tolerance statuses. Magnetic resonance imaging was used to quantify body fat depots, and an oral glucose tolerance test was performed to determine glucose metabolism.

RESULTS

Elevated interscapular fat mass was positively associated with age, BMI, and total body, visceral, and subcutaneous adipose tissue mass. High interscapular fat mass associated with elevated fasting glucose levels, glucose levels at 2 hours during the oral glucose tolerance test, glycated hemoglobin, and insulin resistance, independent of sex, age, and total body and visceral fat mass.

CONCLUSIONS

In conclusion, interscapular fat might be a highly specific fat compartment with a potential impact on glucose metabolism and the pathogenesis of diabetes mellitus.

Cardiovascular Disease Risk Reduction and Body Mass Index

PURPOSE OF REVIEW

Anti-hypertensive and lipid lowering therapy addresses only half of the cardiovascular disease risk in patients with body mass index > 30 kg/m², i.e., obesity. We examine newer aspects of obesity pathobiology that underlie the partial effectiveness of anti-hypertensive lipid lowering therapy for the reduction of cardiovascular disease risk in obesity.

RECENT FINDINGS

Obesity-related insulin resistance, vascular endothelium dysfunction, increased sympathetic nervous system/renin-angiotensin-aldosterone system activity, and glomerulopathy lead to type 2 diabetes, coronary atherosclerosis, and chronic disease kidney disease that besides hypertension and dyslipidemia increase cardiovascular disease risk. Obesity increases cardiovascular disease risk through multiple pathways. Optimal reduction of cardiovascular disease risk in patients with obesity is likely to require therapy targeted at both obesity and obesity-associated conditions.