Otitis Media Detection using Tympanic Membrane Images with Automated Image Segmentation Techniques

Abstract

Otitis media (OM) is the infection and inflammation of the mucous membrane covering the Eustachian with the airy cavities of the middle ear and temporal bone. OM is also one of the most common ailments. In clinical practice, the diagnosis of OM is carried out by visual inspection however this inclined process is subjective and error-prone. Medical images are frequently affected by noise due to errors occurred in noisy sensor, the process of translating signals from analog-to-digital as well as occurred during the communication process. This corrupted pixel certainly modifies intensity values of remaining noiseless pixels in an input image. In order to eliminate noise and enhance the image quality, this paper develop the Histogram Equalization (HE) based Adaptive Center Weighted Median (ACWM) filter and computer-aided model is used for segment/detect the OMin Tympanic membranes images using various segmentation method. All experiments were performed on an open access tympanic membrane dataset that consists of two classes. The goal of segmentation is to simplify and change the representation of an image into something that is more meaningful and easier to analyze. Image segmentation is typically used to locate objects and boundaries in input images.