Using deep learning to perform automatic quantitative measurement of masseter and tongue muscles in persons with dementia (Preprint)

Abstract

BACKGROUND Sarcopenia (loss of muscle mass and strength) increases adverse outcomes risk and contributes to cognitive decline in older adults. Accurate methods to quantify muscle mass and predict adverse outcomes, particularly in older persons with dementia, are still lacking. OBJECTIVE Here, we aimed to evaluate the role of a deep learning model in quantifying muscle volumes in head MRI in patients with neurocognitive disorders METHODS In a cross-sectional analysis of 65 participants, we used deep neural networks (Unet-type) to segment five different tissues in head MRI images, using the Dice similarity coefficient (DSC) and average symmetric surface distance to compare results. We also analyzed the relationship between body mass index (BMI) and muscle and fat volumes. RESULTS Our framework accurately quantified masseter and subcutaneous fat on the left and right sides of the head and tongue muscle (Avg DSC 92.4%). A significant correlation exists between the area and volume of tongue muscle, left masseter muscle, and BMI. CONCLUSIONS Our study demonstrates the successful application of a deep learning model to quantify muscle volumes in head MRI in patients with neurocognitive disorders. This is a promising first step towards clinically applicable artificial intelligence and machine learning methods for estimating masseter and tongue muscle and predicting adverse outcomes in this population.