Deep learning object detection of maxillary cyst-like lesions on panoramic radiographs: preliminary study
- PDF / 941,203 Bytes
- 7 Pages / 595.276 x 790.866 pts Page_size
- 30 Downloads / 191 Views
ORIGINAL ARTICLE
Deep learning object detection of maxillary cyst‑like lesions on panoramic radiographs: preliminary study Hirofumi Watanabe1 · Yoshiko Ariji1 · Motoki Fukuda1 · Chiaki Kuwada1 · Yoshitaka Kise1 · Michihito Nozawa1 · Yoshihiko Sugita2 · Eiichiro Ariji1 Received: 17 June 2020 / Accepted: 5 September 2020 © Japanese Society for Oral and Maxillofacial Radiology and Springer Nature Singapore Pte Ltd. 2020
Abstract Objectives This study aimed to examine the performance of deep learning object detection technology for detecting and identifying maxillary cyst-like lesions on panoramic radiography. Methods Altogether, 412 patients with maxillary cyst-like lesions (including several benign tumors) were enrolled. All panoramic radiographs were arbitrarily assigned to the training, testing 1, and testing 2 datasets of the study. The deep learning process of the training images and labels was performed for 1000 epochs using the DetectNet neural network. The testing 1 and testing 2 images were applied to the created learning model, and the detection performance was evaluated. For lesions that could be detected, the classification performance (sensitivity) for identifying radicular cysts or other lesions were examined. Results The recall, precision, and F-1 score for detecting maxillary cysts were 74.6%/77.1%, 89.8%/90.0%, and 81.5%/83.1% for the testing 1/testing 2 datasets, respectively. The recall was higher in the anterior regions and for radicular cysts. The sensitivity was higher for identifying radicular cysts than for other lesions. Conclusions Using deep learning object detection technology, maxillary cyst-like lesions could be detected in approximately 75–77%. Keywords Deep learning · Object detection · Maxillary cysts · Radicular cysts · Panoramic radiography
Introduction Application of artificial intelligence with deep learning system in the field of medical imaging has been increasing [1–5], prompting the appearance of various studies on the computer-assisted detection (CAD) system to diagnose pathology in the dental field [6–12].Unlike the CAD systems created based on traditional methodology [13], deep learning system, which does not require manual input of imaging characteristics of lesions, has enabled the creation of a learning model by simply importing imaging datasets into the system. Among several functions of deep learning, the object detection, which can automatically detect specific * Yoshiko Ariji [email protected] 1
Department of Oral and Maxillofacial Radiology, AichiGakuin University School of Dentistry, 2‑11 Suemori‑dori, Chikusa‑ku, Nagoya 464‑8651, Japan
Department of Oral Pathology, Aichi-Gakuin University School of Dentistry, Nagoya, Japan
2
lesions and conditions, has been applied to panoramic radiographs [9–12]. A recent study verified a high performance for automatic detection of mandibular radiolucent lesions (cysts and benign tumors) on panoramic radiographs [9]. This would be partially attributed to relatively high contrast between the radiolucent lesi
Data Loading...
