Automatic diagnosis and detection of dental caries in bitewing radiographs using pervasive deep gradient based LeNet classifier model

Abstract

In the field of dental radiography, dental caries prevails to be an extremely common issues which affects major part of population. Radiographic images more specifically, the bitewing images are commonly used one in such cases. An incorrect or inaccurate interpretation will impact the process of diagnosis. So as to aid dentists in the caries assessment, an effective and new technique which integrates image processing and neural network approaches are presented for the exact and precise identification of dental caries in bitewing radiography by classifying them as per the severity of lesions. A deep learning based fully automatic model is proposed in this work for the effective classification of dental images. Initially, the input images are taken and are preprocessed by means of filtering, gray scaling and thresholding process so as to remove noise and to enhance the input images. The enhanced image if then segmented by means of region of interest (ROI) scheme thereby performing blob detection. From the segmented image, the features are extracted by means of Kernel Non-linear Fisher Discriminant Analysis (FDA) which is then followed by selection of suitable features through dimensionality reduction technique. The extracted and selected features are classified using Deep Gradient based LeNet classifier model (DG-LeNet) to diagnose the dental caries by classifying normal and abnormal images and by detecting the decayed region of teeth image. Finally, the dental caries are detected in bitewing radiographs successfully by this method of implementation. A performance of suggested method is estimated in terms of accuracy, sensitivity, specificity, PPV (positive predicted value), NPV (negative predicted value), and error rates. The outcomes attained are compared with existing methods to exemplify the efficacy of suggested model. Thus, the proposed model is effective in detecting the dental caries in bitewing radiographs with the use of pervasive deep gradient based LeNet classifier model.