Automatic detection and classification of radiolucent lesions in the mandible on panoramic radiographs using a deep learning object detection technique Publication date: Available online 6 June 2019 Source: Oral Surgery, Oral Medicine, Oral Pathology and Oral Radiology Author(s): Yoshiko Ariji, Yudai Yanashita, Syota Kutsuna, Chisako Muramatsu, Motoki Fukuda, Yoshitaka Kise, Michihito Nozawa, Chiaki Kuwada, Hiroshi Fujita, Akitoshi Katsumata, Eiichiro Ariji Abstract Objective To investigate whether a deep learning object detection technique can automatically detect and classify radiolucent lesions in the mandible on panoramic radiographs. Study Design Panoramic radiographs of patients with mandibular radiolucent lesions of 10 mm or more, including ameloblastomas, odontogenic keratocysts, dentigerous cysts, radicular cysts, and simple bone cysts, were included. Lesion labels including region of interest coordinates were created in text format. In total, 210 training images and labels were imported into the ‘DIGITS’ deep learning training system. A learning model was created using the deep neural network ‘DetectNet’. Two testing datasets (testing 1 and 2) were applied to the learning model. Similarities and differences between the prediction and ground-truth images were evaluated using Intersection over Union (IoU). Sensitivity and false positive rate per image were calculated using an IoU threshold of 0.6. The detection performance for each disease was assessed using multi-class learning. Results Sensitivity was 0.88 for both testing 1 and 2. False positive rate per image was 0.00 for testing 1 and 0.04 for testing 2. The best combination of detection and classification sensitivity occurred with dentigerous cysts. Conclusion Radiolucent lesions of the mandible can be detected with high sensitivity using deep learning.