Intelligent Decision Support System for Differential Diagnosis of Chronic Odontogenic Rhinosinusitis Based on U-Net Segmentation

The share of chronic odontogenic rhinosinusitis is 40% among all rhinosinusitis. Using automated information systems for differential diagnosis will improve the efficiency decision-making by doctors in diagnosing Therefore, this study aimed to develop an intelligent decision support system based on computer vision methods. A dataset was collected and processed, including 162 MSCT images. deep learning model image segmentation developed. 23 convolutional layer U-Net network architecture has been used multi-spiral computed tomography (MSCT) data with maxillary sinusitis. proposed implemented such a way that each pair repeated 3 × convolutions layers followed Exponential Linear Unit instead Rectified as activation function. showed accuracy 90.09%. To system, chatbot allows user conduct patient survey collect examination from several various profiles. made it possible combine processing interview data, improving physician Chronic Odontogenic Rhinosinusitis. solution first comprehensive area.