A Statistical Modeling Approach to Computer-Aided Quantification of Dental Biofilm

TL;DR

This paper introduces an interactive, statistically-based method for quantifying dental biofilm in QLF images that reduces human bias and allows easy correction of misclassifications, improving accuracy and usability.

Contribution

It presents a novel superpixel-based GMRF modeling approach for biofilm quantification that incorporates user interaction for correction, enhancing current semi-automated techniques.

Findings

High consistency and precision in biofilm quantification

User interaction improves correction of misclassifications

Method outperforms existing semi-automated approaches

Abstract

Biofilm is a formation of microbial material on tooth substrata. Several methods to quantify dental biofilm coverage have recently been reported in the literature, but at best they provide a semi-automated approach to quantification with significant input from a human grader that comes with the graders bias of what are foreground, background, biofilm, and tooth. Additionally, human assessment indices limit the resolution of the quantification scale; most commercial scales use five levels of quantification for biofilm coverage (0%, 25%, 50%, 75%, and 100%). On the other hand, current state-of-the-art techniques in automatic plaque quantification fail to make their way into practical applications owing to their inability to incorporate human input to handle misclassifications. This paper proposes a new interactive method for biofilm quantification in Quantitative light-induced fluorescence (QLF) images of canine teeth that is independent of the perceptual bias of the grader. The method partitions a QLF image into segments of uniform texture and intensity called superpixels; every superpixel is statistically modeled as a realization of a single 2D Gaussian Markov random field (GMRF) whose parameters are estimated; the superpixel is then assigned to one of three classes (background, biofilm, tooth substratum) based on the training set of data. The quantification results show a high degree of consistency and precision. At the same time, the proposed method gives pathologists full control to post-process the automatic quantification by flipping misclassified superpixels to a different state (background, tooth, biofilm) with a single click, providing greater usability than simply marking the boundaries of biofilm and tooth as done by current state-of-the-art methods.