Oral Diseases Recognition Based on Photographic Images and Dental Decay Diagnosis

In the realm of medical applications, the automation diagnosis process of dental lesions has gained a pivotal role and considered as a crucial advancement. This work provides a new dataset of photographic images for six different types of oral diseases. The dataset is gathered and labeled by professional medical operators in the dentistry field. We use the collected dataset to train a binary classifier to determine whether the region of interests (ROI) needs detection or not inside the input image. Then, we train a detector to detect and localize the required ROI. Finally, we use the detected regions to train a CNN network by adopting transfer learning technique to classify various kinds of teeth diseases. At the end, we obtained an almost 93.24% accuracy by modifying and re-training the pre-trained model VGG19.