Diagnosis and prediction of periodontally compromised teeth using a deep learning-based convolutional neural network algorithm.
Diagnosis and prediction of periodontally compromised teeth using a deep learning-based convolutional neural network algorithm.
复制标题
DOI：
10.5051/jpis.2018.48.2.114
复制
发表时间：
2018-04
影响因子：
1.9
通讯作者：
Choi SH
中科院分区：
文献类型：
--
作者：
Lee JH;Kim DH;Jeong SN;Choi SH
本研究的目的是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，并评估该系统用于诊断和预测牙周受损牙齿（PCT）的潜在有用性和准确性。结合预训练的深度CNN架构和自我训练的网络，根尖周放射图像用于确定最佳CNN算法和权重。诊断和预测准确性，灵敏度，特异性，阳性预测值，阴性预测值，受试者工作特征（ROC）曲线，ROC曲线下面积，混淆矩阵和95%置信区间（CI）使用我们的深度CNN算法计算，基于Python中的Keras框架。根尖周影像学数据集分为训练（n= 1，044）、验证（n=348）和测试（n=348）数据集。使用深度学习算法，PCT的诊断准确率为前磨牙81.0%，磨牙76.7%。使用临床诊断为重度PCT的64颗前磨牙和64颗磨牙，预测拔除的准确性为82.8%（95%CI，70.1%-91.2%），前磨牙为73.4%（95%CI，59.9%-84.0%）。我们证明了深度CNN算法对于评估PCT的诊断和可预测性是有用的。因此，随着PCT数据集的进一步优化和算法的改进，计算机辅助检测系统有望成为诊断和预测PCT的有效和高效的方法。
The aim of the current study was to develop a computer-assisted detection system based on a deep convolutional neural network (CNN) algorithm and to evaluate the potential usefulness and accuracy of this system for the diagnosis and prediction of periodontally compromised teeth (PCT). Combining pretrained deep CNN architecture and a self-trained network, periapical radiographic images were used to determine the optimal CNN algorithm and weights. The diagnostic and predictive accuracy, sensitivity, specificity, positive predictive value, negative predictive value, receiver operating characteristic (ROC) curve, area under the ROC curve, confusion matrix, and 95% confidence intervals (CIs) were calculated using our deep CNN algorithm, based on a Keras framework in Python. The periapical radiographic dataset was split into training (n=1,044), validation (n=348), and test (n=348) datasets. With the deep learning algorithm, the diagnostic accuracy for PCT was 81.0% for premolars and 76.7% for molars. Using 64 premolars and 64 molars that were clinically diagnosed as severe PCT, the accuracy of predicting extraction was 82.8% (95% CI, 70.1%–91.2%) for premolars and 73.4% (95% CI, 59.9%–84.0%) for molars. We demonstrated that the deep CNN algorithm was useful for assessing the diagnosis and predictability of PCT. Therefore, with further optimization of the PCT dataset and improvements in the algorithm, a computer-aided detection system can be expected to become an effective and efficient method of diagnosing and predicting PCT.
登录
查看更多内容
影响因子：
19.7
作者：
Lakhani, Paras;Sundaram, Baskaran
通讯作者：
Sundaram, Baskaran
影响因子：
4.3
作者：
Kim, Ti-Sun;Obst, Christian;Geenen, Claudia
通讯作者：
Geenen, Claudia
影响因子：
1.6
作者：
Lee JH;Oh JY;Youk TM;Jeong SN;Kim YT;Choi SH
通讯作者：
Choi SH
影响因子：
64.8
作者：
Esteva A;Kuprel B;Novoa RA;Ko J;Swetter SM;Blau HM;Thrun S
通讯作者：
Thrun S
深度学习（一种机器学习技术）的准确性，使用超宽眼底眼镜检查来检测Rhegmatogen opental视网膜脱离。
影响因子：
4.6
作者：
Ohsugi H;Tabuchi H;Enno H;Ishitobi N
通讯作者：
Ishitobi N