Selection of Filtering and Image Texture Analysis in the Radiographic Images Processing of Horses’ Incisor Teeth Affected by the EOTRH Syndrome

• Main Authors: Bereznowski, A. (Author), Borowska, M. (Author), Domino, M. (Author), Górski, K. (Author), Polkowska, I. (Author), Stefanik, E. (Author), Turek, B. (Author)
• Format: Article
• Language: English
• Published: MDPI 2022
• Subjects: dental care; Dental care; Diagnosis; digital image processing; equine odontoclastic tooth resorption and hypercementosis; Equine odontoclastic tooth resorption and hypercementosis; filtering; Gray level run length; Gray-level co-occurrence matrix; Grey-level co-occurrence matrixes; Image analysis; Image texture; Image texture analysis; Images processing; matrix; Median filters; Processing; Radiographic images; texture analysis; Texture analysis; Textures
• Online Access: View Fulltext in Publisher

 Equine odontoclastic tooth resorption and hypercementosis (EOTRH) is one of the horses’ dental diseases, mainly affecting the incisor teeth. An increase in the incidence of aged horses and a painful progressive course of the disease create the need for improved early diagnosis. Besides clinical findings, EOTRH recognition is based on the typical radiographic findings, including levels of dental resorption and hypercementosis. This study aimed to introduce digital processing methods to equine dental radiographic images and identify texture features changing with disease progression. The radiographs of maxillary incisor teeth from 80 horses were obtained. Each incisor was annotated by separate masks and clinically classified as 0, 1, 2, or 3 EOTRH degrees. Images were filtered by Mean, Median, Normalize, Bilateral, Binomial, CurvatureFlow, LaplacianSharpening, DiscreteGaussian, and SmoothingRecursiveGaussian filters independently, and 93 features of image texture were extracted using First Order Statistics (FOS), Gray Level Co-occurrence Matrix (GLCM), Neighbouring Gray Tone Difference Matrix (NGTDM), Gray Level Dependence Matrix (GLDM), Gray Level Run Length Matrix (GLRLM), and Gray Level Size Zone Matrix (GLSZM) approaches. The most informative processing was selected. GLCM and GLRLM return the most favorable features for the quantitative evaluation of radiographic signs of the EOTRH syndrome, which may be supported by filtering by filters improving the edge delimitation. © 2022 by the authors. Licensee MDPI, Basel, Switzerland.