Chest CT Radiomics is Feasible in Evaluating Muscle Change in Diabetes Patients

Area of Science:

• Radiology
• Medical Imaging
• Biomedical Engineering

Background:

• Non-invasive imaging methods for assessing muscle alterations in diabetes are currently limited.
• Diabetes mellitus can lead to significant changes in skeletal muscle structure and function.
• Early detection and monitoring of these muscle changes are crucial for managing diabetic complications.

Purpose of the Study:

• To evaluate the feasibility of using computed tomography (CT) radiomics for assessing muscle changes in individuals with diabetes.
• To determine if radiomics features extracted from muscle CT images can differentiate between diabetic patients and healthy controls.
• To develop a predictive model for diabetes based on muscle radiomics signatures.

Main Methods:

• A cohort of 60 diabetic patients and 60 healthy controls (HC) underwent muscle CT imaging.
• Radiomics features were extracted from CT images of the pectoralis major muscle (PMM) using 3D Slicer software.
• The least absolute shrinkage and selection operator (LASSO) regression was employed to build a prediction model, with performance assessed by receiver operating characteristic (ROC) curve analysis.

Main Results:

• Significant differences in 19 radiomics features were observed between diabetic patients and HC (P<0.05).
• A parsimonious model comprising 6 selected radiomics features was developed using LASSO regression.
• The prediction model demonstrated high diagnostic performance, with an area under the curve (AUC) of 0.92 for the training cohort and 0.90 for the validation cohort.

Conclusions:

• Muscle CT radiomics is a feasible and effective method for evaluating muscle changes associated with diabetes.
• This non-invasive imaging approach shows potential for differentiating diabetic individuals from healthy controls.
• Radiomics analysis of muscle CT scans may offer a valuable tool for the diagnosis and monitoring of diabetic myopathy.