College of Dentistry, King Saud bin Abdulaziz University for Health Sciences, Riyadh, Saudi Arabia.
King Abdullah International Medical Research Centre, Riyadh, Saudi Arabia.
BMC Oral Health. 2022 Sep 13;22(1):399. doi: 10.1186/s12903-022-02436-3.
The purpose of this investigation was to develop a computer-assisted detection system based on a deep convolutional neural network (CNN) algorithm and to evaluate the accuracy and usefulness of this system for the detection of alveolar bone loss in periapical radiographs in the anterior region of the dental arches. We also aimed to evaluate the usefulness of the system in categorizing the severity of bone loss due to periodontal disease.
A data set of 1724 intraoral periapical images of upper and lower anterior teeth in 1610 adult patients were retrieved from the ROMEXIS software management system at King Saud bin Abdulaziz University for Health Sciences. Using a combination of pre-trained deep CNN architecture and a self-trained network, the radiographic images were used to determine the optimal CNN algorithm. The diagnostic and predictive accuracy, precision, confusion matrix, recall, F1-score, Matthews Correlation Coefficient (MCC), Cohen Kappa, were calculated using the deep CNN algorithm in Python.
The periapical radiograph dataset was divided randomly into 70% training, 20% validation, and 10% testing datasets. With the deep learning algorithm, the diagnostic accuracy for classifying normal versus disease was 73.0%, and 59% for the classification of the levels of severity of the bone loss. The Model showed a significant difference in the confusion matrix, accuracy, precision, recall, f1-score, MCC and Matthews Correlation Coefficient (MCC), Cohen Kappa, and receiver operating characteristic (ROC), between both the binary and multi-classification models.
This study revealed that the deep CNN algorithm (VGG-16) was useful to detect alveolar bone loss in periapical radiographs, and has a satisfactory ability to detect the severity of bone loss in teeth. The results suggest that machines can perform better based on the level classification and the captured characteristics of the image diagnosis. With additional optimization of the periodontal dataset, it is expected that a computer-aided detection system can become an effective and efficient procedure for aiding in the detection and staging of periodontal disease.
本研究旨在开发一种基于深度卷积神经网络（CNN）算法的计算机辅助检测系统，并评估该系统在检测前牙弓牙槽骨骨丧失的根尖放射片中的准确性和实用性。我们还旨在评估该系统在分类因牙周病导致的骨丧失严重程度方面的实用性。
从沙特阿拉伯阿卜杜勒阿齐兹国王健康科学大学的 ROMEXIS 软件管理系统中检索了 1610 名成年患者的 1724 张上颌和下颌前牙的口腔根尖图像。使用预训练的深度 CNN 架构和自训练网络的组合，确定了最佳的 CNN 算法。使用 Python 中的深度 CNN 算法计算了诊断和预测准确性、精度、混淆矩阵、召回率、F1 评分、马修斯相关系数（MCC）、科恩kappa、 Cohen Kappa。
根尖放射数据集随机分为 70%的训练集、20%的验证集和 10%的测试集。使用深度学习算法，对正常与疾病分类的诊断准确率为 73.0%，对骨丧失严重程度分类的准确率为 59%。模型在混淆矩阵、准确性、精度、召回率、F1 评分、马修斯相关系数（MCC）、科恩 kappa 和接收器操作特征（ROC）之间存在显著差异，二进制和多分类模型之间存在显著差异。
本研究表明，深度 CNN 算法（VGG-16）可用于检测根尖放射片中的牙槽骨骨丧失，并且具有令人满意的检测牙齿骨丧失严重程度的能力。结果表明，机器可以根据等级分类和图像诊断的特征更好地执行任务。通过对牙周数据集进行进一步优化，预计计算机辅助检测系统将成为一种有效且高效的辅助检测和分期牙周病的方法。
