A new take on measuring relative nutritional density: The feasibility of using a deep neural network to assess commercially-prepared puréed food concentrations

Dysphagia affects 590 million people worldwide and increases risk for malnutrition. Puréed food may reduce choking, however preparation differences impact nutrient density making quality assurance necessary. This paper is the first study to investigate the feasibility of computational puréed food nutritional density analysis using an imaging system. Motivated by a theoretical optical dilution model, a novel deep neural network (DNN) was evaluated using 390 samples from thirteen types of commercially prepared purées at five dilutions. The DNN predicted relative concentration of the purée sample (20%, 40%, 60%, 80%, 100% initial concentration). Data were captured using same-side reflectance of multispectral imaging data at different polarizations at three exposures. Experimental results yielded an average top-1 prediction accuracy of 92.2% ± 0.41% with sensitivity and specificity of 83.0% ± 15.0% and 95.0% ± 4.8%, respectively. This DNN imaging system for nutrient density analysis of puréed food shows promise as a novel tool for nutrient quality assurance.