Automatic diagnosis for cysts and tumors of both jaws on panoramic radiographs using a deep convolution neural network.

Researchers

Journal

Modalities

Models

Abstract

The purpose of this study was to automatically diagnose odontogenic cysts and tumors of both jaws on panoramic radiographs using deep learning. We proposed a novel framework of deep convolution neural network (CNN)with data augmentationfor detection and classification of the multiple diseases.
We developed a deep CNN modified from YOLOv3 for detecting and classifying odontogenic cysts and tumorsof both jaws. Our dataset of 1,282 panoramic radiographs comprised350 dentigerous cysts (DCs), 302 periapical cysts (PCs), 300 odontogenic keratocysts (OKCs), 230 ameloblastomas (ABs), and 100 normal jaws with no disease. In addition, the number of radiographs was augmented12-foldby flip, rotation, and intensity changes. We evaluated the classification performance of the developed CNN by calculating sensitivity, specificity, accuracy, and AUC for diseasesof both jaws.
The overall classification performance for the diseases improved from 78.2% sensitivity, 93.9% specificity,91.3% accuracy, and 0.86 AUCusing the CNN with unaugmented datasetto 88.9% sensitivity, 97.2% specificity, 95.6% accuracy, and 0.94 AUCusing the CNNwith augmented dataset. CNN using augmented dataset had the following sensitivities, specificities, accuracies, and AUCs: 91.4%, 99.2%, 97.8%, and 0.96for DCs, 82.8%, 99.2%, 96.2%, and 0.92for PCs, 98.4%,92.3%,94.0%, and 0.97for OKCs, 71.7%, 100%, 94.3%, and 0.86for ABs, and 100.0%, 95.1%, 96.0%, and 0.94for normal jaws, respectively.
The CNN method we developed for automatically diagnosing odontogenic cysts and tumors of both jaws on panoramic radiographs using data augmentation showed high sensitivity, specificity, accuracy, and AUC despite the limited number of panoramic images involved.