Deep learning-based apical lesion segmentation from panoramic radiographs
송일석, 강주희, 김조은, 이원진, 이삼선, 허민석, 신학균, 허경호,
소속 상세정보
송일석 ( Song Il-seok ) - Seoul National University Department of Oral and Maxillofacial Radiology and Dental Research Institute
강주희 ( Kang Ju-Hee ) - Seoul National University Dental Hospital Department of Oral and Maxillofacial Radiology
김조은 ( Kim Jo-Eun ) - Seoul National University Dental Hospital Department of Oral and Maxillofacial Radiology
이원진 ( Lee Won-Jin ) - Sogang University Department of Chemical and Biomolecular Engineering
이삼선 ( Lee Sam-Sun ) - Seoul National University School of Dentistry Department of Oral and Maxillofacial Radiology
허민석 ( Heo Min-Suk ) - Seoul National University School of Dentistry Department of Oral and Maxillofacial Radiology
신학균 ( Shin Hak-Kyun ) - Seoul National University Department of Oral and Maxillofacial Radiology and Dental Research Institute
허경호 ( Hun Kying-Hoe ) - Seoul National University Department of Oral and Maxillofacial Radiology and Dental Research Institute
Abstract
Purpose : Convolutional neural networks (CNNs) have rapidly emerged as one of the most promising artificial intelligence methods in the field of medical and dental research. CNNs can provide an effective diagnostic methodology allowing for the detection of early-staged diseases. Therefore, this study aimed to evaluate the performance of a deep CNN algorithm for apical lesion segmentation from panoramic radiographs.
Materials and Methods : A total of 1000 panoramic images showing apical lesions were separated into training (n=800, 80%), validation (n=100, 10%), and test (n=100, 10%) datasets. The performance of identifying apical lesions was evaluated by calculating the precision, recall, and F1-score.
Results : In the test group of 180 apical lesions, 147 lesions were segmented from panoramic radiographs with an intersection over union (IoU) threshold of 0.3. The F1-score values, as a measure of performance, were 0.828, 0.815, and 0.742, respectively, with IoU thresholds of 0.3, 0.4, and 0.5.
Conclusion : This study showed the potential utility of a deep learning-guided approach for the segmentation of apical lesions. The deep CNN algorithm using U-Net demonstrated considerably high performance in detecting apical lesions.
키워드
Artificial Intelligence; Deep Learning; Periapical Periodontitis; Radiography, Panoramic
원문 및 링크아웃 정보
등재저널 정보