Behnam Askarian1, Fatemehsadat Tabei1, Grace Anne Tipton1, Jo Woon Chong
12:15 - 14:15 | Wed 20 Nov | Upper Foyer Balcony | A1P-D.1
In this paper, we propose a novel periodontal disease detection method using smartphones which are highlighted as promising tools for health monitoring and disease diagnosis since smartphones are widespread and have versatile sensors embedded in them nowadays. Periodontal disease is an inflammatory disease which is known to be the main cause of tooth loss in the U.S. Here we adopted a CIELAB color space for feature extraction and Support Vector Machine (SVM) classifier for distinguishing healthy gums from diseased ones. A novel gadget was designed to eliminate refraction effect and reduce ambient light. 30 volunteers were recruited for this study which 15 of them had periodontal disease and 15 had healthy gums. Our proposed method resulted in 94.3% accuracy, 92.6% sensitivity and 93% specificity in distinguishing healthy subjects from subjects with periodontal disease.