Automatic Site-Specific Multiple Level Gum Disease Detection Based on Deep Neural Network

Abstract

The Gum diseases (gingivitis and periodontitis) is one of the most prevalent dental diseases which are initiated by dental plaque (bacterial biofilm). It has been strongly linked to the systemic diseases including cardiovascular (atherosclerosis, hypertension, stroke), respiratory (aspiration pneumonia), adverse pregnancy outcomes and even cancer via systemic routes with significant health implications. As the inflammation of gum is manifested as increased in redness (colour), increase in volume (oedema), and loss of surface characteristics (stippling; gum fibre attachment). These diseased sites are site- specific (i.e. subject can have healthy and disease sites in a mouth) can be identified by visual examination of dentists. Moreover, these inflammatory changes of gum can also be recognized by intraoral photography which has been clinical practice of regular dental check-up. The aim of this study is to train the computer to identify the inflamed disease sites in pixel level by deep learning approach. We collected 337 and 110 images for training and validation respectively from 110 patients' standard intraoral photographs and randomly. They are labeled into four health status levels (healthy, questionable healthy, questionable diseased and diseased) and verified by a dental specialist with more than 15 years clinical experience. The proposed semantic segmentation architecture is based on the DeepLabv3+ network with Xception and MobileNetV2 as the backbone. Experimental results show the effectiveness of the proposed system, which shows possible application on dental self check-up using mobile app particularly during the disease pandemic where visit to dentists are difficult or even impossible.