Deep Learning based Diagnosis of Jaw Cyst using Hematoxylin and Eosin -Stained Incisional Biopsies Microscopic Images

Clinicians and pathologists may find it difficult to distinguish between a radicular cyst, dentigerous cyst, and odontogenic keratocyst due to their complex microscopic diagnostic distinction. The development of computer-aided diagnostics for cyst identification leads to more accurate and timely diagnosis while reducing false positives and negatives. This research aimed to develop a deep learning based automated jaw cyst diagnosis system that recognizes Odontogenic Keratocyst (OKC), Dentigerous Cyst (DC) and Radicular Cyst (RC) based on Hematoxylin and Eosin-Stained images. Here 54 Odontogenic Keratocyst (OKC), 23 Dentigerous Cysts (DC), and 20 Radicular Cysts (RC) patient’s data were examined using a 40× magnification microscope. In this case, two stains were isolated, and convolutional layers were used to extract attributes from each stain image. These attributes were concatenated and relevant ones were selected by Relief F. Dense layer was used for classification. Obtained an accuracy of 95% on test dataset.