Utilizing contrast enhancement algorithms (CEAs) in identification of dental abnormalities

Abstract

This study focuses on the identification of dental abnormalities in intra-oral dental radiographs. The abnormalities of interest are periapical radiolucency (PA), widen periodontal ligament space (widen PDLs) and Loss of Lamina Dura (Loss of LD). The intra-oral dental radiographs usually have poor image quality due to the acquisition processes as well as the low usage of x-ray dose. The poor image quality may lead to misdiagnosis. Image processing techniques such as Contrast enhancement algorithms (CEAs) are accepted in dentistry in enhancing digital dental radiographs and assisting the dentists during interpretation process. Thus this study compares the performance between original images and the images enhanced by CEAs. The algorithms are Adaptive Histogram Equalization (AHE), Contrast Limited Adaptive Histogram Equalization (CLAHE) and Sharp Contrast Limited Adaptive Histogram Equalization (SCLAHE). Questionnaires are used to evaluate the performance of the original against the CEAs images. The finding identifies the abnormalities in the intra-oral dental radiographs as well as the performance analysis among the CEAs. Hence, we expect this work could contribute in understanding the characteristic of the abnormalities in digital intra-oral dental radiographs.