Precision Medicine for Apical Lesions and Peri-Endo Combined Lesions Based on Transfer Learning Using Periapical Radiographs

• Main Authors: Wu, Pei Yi, Mao, Yi Cheng, Lin, Yuan Jin, Li, Xin Hua, Ku, Li Tzu, Li, Kuo Chen, Chen, Chiung An, Chen, Tsung Yi, Chen, Shih Lun, Tu, Wei Chen, Abu, Patricia Angela R
• Format: text
• Published: Archīum Ateneo 2024
• Subjects: apical lesion; CNN; image segmentation; peri-endo combined lesion; YOLOv8-OBB; Analytical, Diagnostic and Therapeutic Techniques and Equipment; Biomedical; Biomedical Engineering and Bioengineering; Computer Engineering; Electrical and Computer Engineering; Engineering; Medicine and Health Sciences
• Online Access: https://archium.ateneo.edu/intelligent-visual-env/1; https://archium.ateneo.edu/context/intelligent-visual-env/article/1000/viewcontent/bioengineering_11_00877.pdf
• Institution: Ateneo De Manila University

An apical lesion is caused by bacteria invading the tooth apex through caries. Periodontal disease is caused by plaque accumulation. Peri-endo combined lesions include both diseases and significantly affect dental prognosis. The lack of clear symptoms in the early stages of onset makes diagnosis challenging, and delayed treatment can lead to the spread of symptoms. Early infection detection is crucial for preventing complications. PAs used as the database were provided by Chang Gung Memorial Medical Center, Taoyuan, Taiwan, with permission from the Institutional Review Board (IRB): 02002030B0. The tooth apex image enhancement method is a new technology in PA detection. This image enhancement method is used with convolutional neural networks (CNN) to classify apical lesions, peri-endo combined lesions, and asymptomatic cases, and to compare with You Only Look Once-v8-Oriented Bounding Box (YOLOv8-OBB) disease detection results. The contributions lie in the utilization of database augmentation and adaptive histogram equalization on individual tooth images, achieving the highest comprehensive validation accuracy of 95.23% with the ConvNextv2 model. Furthermore, the CNN outperformed YOLOv8 in identifying apical lesions, achieving an F1-Score of 92.45%. For the classification of peri-endo combined lesions, CNN attained the highest F1-Score of 96.49%, whereas YOLOv8 scored 88.49%.