Deep Learning Based Ear Disease Prediction a Novel Approach Using Modified Vgg-19 Architecture Enhanching Accuracy

Middle ear inflammatory diseases are a worldwide health concern that leads to severe effects like speech problems and hearing loss. Experts visually examine the tympanic membrane during a clinical examination. The five classes of Tympanic Membrane (TM) image inside the middle ear is predicted by using the proposed Deep Learning method called Modified VGG 19. Initially, data augmentation is applied to the TM image to eliminate the black margin and to resize, remove noise using bilateral filtering to get high quality input data. Next, the images are segmented using the Fuzzy C means clustering, allowing for partition of data. Features are then extracted from the segmented images using the Gray Level Co occurrence Matrix the TM image is textured for further analysis. Finally, a Modified VGG 19 framework is proposed to enhance the classification of TM images, in middle ear diagnosis. The assessment of proposed work using python software reveals that the proposed framework with Modified VGG 19 classifier ranks with improved accuracy of 92.09 % when compared to the other techniques.