A Novel Color-Based Segmentation Method for the Objective Measurement of Human Masticatory Performance

The aims of this study were to propose an automatic color-based segmentation method to separate mixed and unmixed colors of images that were derived from the application of the two-color chewing-gum mixing test and to determine the validity of this method in the assessment of masticatory performance (MP). Fifty young adults (mean age: 24.3 ± 2.7 years) were enrolled in the study. Each participant chewed a double-colored chewing gum for 5, 10, 20, 30, and 50 masticatory cycles. Boluses were collected and flattened. Both sides of each bolus were photographed, and images were processed using a novel k-means clustering method. The specimens corresponding to 20 masticatory cycles were re-analyzed by the same investigator in order to evaluate the intra-rater reliability and by a second investigator to assess the inter-rater reliability. To assess the test–retest reliability, 25% of the participants performed a second test with 20 chewing cycles. Each bolus was subjectively scored as either poorly, moderately, or highly mixed by an investigator to assess the construct validity. The percentage of mixed colors in the samples increased with an increase in the number of strokes. Significative differences were detected when varying from 5 to 10 strokes, from 10 to 20 strokes, and from 30 to 50 strokes (p < 0.05). The Pearson correlation coefficient explained these relations (r = 0.78, p < 0.05). The interclass correlation coefficient (ICC) showed a good correlation concerning both the intra- and inter-rater reliability (r = 0.85 and r = 0.77, respectively) and an excellent test–retest correlation (r = 0.93). The subjective assessment was coherent with the digital one. The proposed digital method was proved to be able to automatically quantify the percentage of the mixed color area by providing quantitative data with minimal human interaction.