Building a Deep Learning Model to Detect Osteoporosis from Dental Panoramic X-Ray Image  

作　　者：Farah Hassan Brangakgi Yasser Khadra Farah Hassan Brangakgi;Yasser Khadra(Department of Physiology, Faculty of Medicine, Damascus University, Damascus, Syria;Bioinformatics, Syrian Virtual University, Damascus, Syria;Medical Digital Image Processing and Pattern Recognition, University of Lyon, Lyon, France)

机构地区：[1]Department of Physiology, Faculty of Medicine, Damascus University, Damascus, Syria [2]Bioinformatics, Syrian Virtual University, Damascus, Syria [3]Medical Digital Image Processing and Pattern Recognition, University of Lyon, Lyon, France

出　　处：《Open Journal of Applied Sciences》2024年第12期3480-3489,共10页应用科学(英文)

摘　　要：The project discusses the development of a deep learning model to detect osteoporosis from dental panoramic X-Ray images. It provides an in-depth understanding of human bone structure, osteoporosis, its symptoms, causes, prevalence, and risk factors. The project also explains bone density measurement using dual-energy X-ray absorptiometry (DEXA) and the application of artificial intelligence (AI) and machine learning (ML) in medical imaging. The study uses panoramic dental X-rays to evaluate AI technology in dental imaging and classification of mandible inferior cortical based on Klemetti and Kolmakow criteria. The model architecture consists of convolutional, pooling, fully connected, ReLU, and Softmax layers. Dropout and early stopping are added to the model. The training process uses the train-test approach with 100 epochs and a batch size of 32, and performance evaluation measures such as accuracy, sensitivity, specificity, and F1-score are used to assess the classifier’s performance. The findings and methodology provide a comprehensive understanding of the application of deep learning in the detection of osteoporosis from dental panoramic X-Ray images, and the study demonstrates a robust approach to implementing AI in medical imaging for osteoporosis detection.The project discusses the development of a deep learning model to detect osteoporosis from dental panoramic X-Ray images. It provides an in-depth understanding of human bone structure, osteoporosis, its symptoms, causes, prevalence, and risk factors. The project also explains bone density measurement using dual-energy X-ray absorptiometry (DEXA) and the application of artificial intelligence (AI) and machine learning (ML) in medical imaging. The study uses panoramic dental X-rays to evaluate AI technology in dental imaging and classification of mandible inferior cortical based on Klemetti and Kolmakow criteria. The model architecture consists of convolutional, pooling, fully connected, ReLU, and Softmax layers. Dropout and early stopping are added to the model. The training process uses the train-test approach with 100 epochs and a batch size of 32, and performance evaluation measures such as accuracy, sensitivity, specificity, and F1-score are used to assess the classifier’s performance. The findings and methodology provide a comprehensive understanding of the application of deep learning in the detection of osteoporosis from dental panoramic X-Ray images, and the study demonstrates a robust approach to implementing AI in medical imaging for osteoporosis detection.

关 键 词：Deep Learning CNN Convolutional Neural Network PYTHON OSTEOPOROSIS Dental Panoramic X-Ray 

分 类 号：R58[医药卫生—内分泌]