DocumentCode :
21889
Title :
A Statistical Modeling Approach to Computer-Aided Quantification of Dental Biofilm
Author :
Mansoor, Awais ; Patsekin, Valery ; Scherl, Dale ; Robinson, J. Paul ; Rajwa, Bartlomiej
Author_Institution :
Dept. of Electr. & Comput. Eng., Purdue Univ., West Lafayette, IN, USA
Volume :
19
Issue :
1
fYear :
2015
fDate :
Jan. 2015
Firstpage :
358
Lastpage :
366
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 semiautomated approach to quantification with significant input from a human grader that comes with the grader´s bias of what is 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 2-D 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 postprocess 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.
Keywords :
Gaussian processes; Markov processes; biological tissues; biomedical optical imaging; cellular biophysics; dentistry; feature extraction; fluorescence; image classification; image segmentation; image texture; learning (artificial intelligence); medical disorders; medical image processing; microorganisms; parameter estimation; random processes; statistical analysis; thin films; GMRF parameter estimation; QLF image partitioning; QLF image segment; automatic plaque quantification; automatic quantification postprocessing; background bias; background class assignment; biofilm bias; biofilm boundary marking; biofilm class assignment; biofilm coverage quantification level; canine teeth image; commercial scale; computer-aided quantification; data training; dental biofilm coverage quantification; foreground bias; grader bias; grader perceptual bias independence; human assessment index; human grader input; human input; interactive biofilm quantification method; microbial biofilm formation; microbial material; misclassification handling; misclassified superpixel flipping; pathology; practical application; quantification consistency; quantification precision; quantification scale resolution limitation; quantitative light-induced fluorescence image; semiautomated quantification; single 2D Gaussian Markov random field; superpixel class assignment; superpixel statistical modeling; tooth bias; tooth boundary marking; tooth substrata; tooth substratum class assignment; uniform QLF image intensity; uniform QLF image texture; usability; Biomedical imaging; Calibration; Dentistry; Estimation; Image segmentation; Manuals; Teeth; Biofilm; Gaussian Markov random field (GMRF); dental plaque; quantitative fluorescence; superpixelization;
fLanguage :
English
Journal_Title :
Biomedical and Health Informatics, IEEE Journal of
Publisher :
ieee
ISSN :
2168-2194
Type :
jour
DOI :
10.1109/JBHI.2014.2310204
Filename :
6758338
Link To Document :
بازگشت