Automated caries detection with smartphone color photography using machine learning

Duc Long Duong, Malitha Humayun Kabir, Rong Fu Kuo

Research output: Contribution to journalArticlepeer-review

8 Citations (Scopus)

Abstract

Untreated caries is significant problem that affected billion people over the world. Therefore, the appropriate method and accuracy of caries detection in clinical decision-making in dental practices as well as in oral epidemiology or caries research, are required urgently. The aim of this study was to introduce a computational algorithm that can automate recognize carious lesions on tooth occlusal surfaces in smartphone images according to International Caries Detection and Assessment System (ICDAS). From a group of extracted teeth, 620 unrestored molars/premolars were photographed using smartphone. The obtained images were evaluated for caries diagnosis with the ICDAS II codes, and were labeled into three classes: “No Surface Change” (NSC); “Visually Non-Cavitated” (VNC); “Cavitated” (C). Then, a two steps detection scheme using Support Vector Machine (SVM) has been proposed: “C versus (VNC + NSC)” classification, and “VNC versus NSC” classification. The accuracy, sensitivity, and specificity of best model were 92.37%, 88.1%, and 96.6% for “C versus (VNC + NSC),” whereas they were 83.33%, 82.2%, and 66.7% for “VNC versus NSC.” Although the proposed SVM system required further improvement and verification, with the data only imaged from the smartphone, it performed an auspicious potential for clinical diagnostics with reasonable accuracy and minimal cost.

Original languageEnglish
JournalHealth Informatics Journal
Volume27
Issue number2
DOIs
Publication statusPublished - 2021

All Science Journal Classification (ASJC) codes

  • Health Informatics

Fingerprint

Dive into the research topics of 'Automated caries detection with smartphone color photography using machine learning'. Together they form a unique fingerprint.

Cite this