Optimization methods for deep neural networks classifying OCT images to detect dental caries

Optimization methods for deep neural networks classifying OCT images to detect dental caries
复制标题

深度神经网络 OCT 图像分类检测龋齿的优化方法

DOI:
10.1117/12.2545421
复制
发表时间:
2020
期刊:
Lasers in Dentistry XXVI
影响因子:
--
通讯作者:
Mahdian, Mina
Mahdian, Mina
中科院分区:
--
文献类型:
--
作者:
Salehi, Hassan S.;Barchini, Majd;Mahdian, Mina

文献摘要

参考文献

被引文献

相似文献

龋齿是一种常见的慢性口腔传染病,影响着全世界大多数青少年和成年人。光学相干断层扫描(OCT)已被广泛研究用于早期龋损的检测。深度学习技术是生物医学研究的一个新兴领域,在口腔放射学领域的诊断和预测方面取得了令人印象深刻的成果。深度学习模型,特别是深度卷积神经网络(CNN),可以与OCT成像系统一起使用沿着,以更准确地识别早期龋齿。在这项工作中,在OCT数据采集后,进行数据增强以获得大量的训练数据,以便有效地学习,其中这种训练数据的收集通常是昂贵和费力的。对于反向传播过程,使用七种优化方法,即Adadelta,AdaGrad,Adam,AdaMax,Nadam,RMSProp和随机梯度下降(SGD)来提高CNN分类器诊断龋齿的准确性。在这项研究中,75%的数据用于训练,25%用于测试。计算诊断准确性、灵敏度、特异性、阳性预测值、阴性预测值和受试者工作特征(ROC)曲线,以用于深度CNN算法的检测和诊断性能。这项研究强调了使用OCT图像检测龋齿的深度CNN模型的各种优化方法的性能。
Dental caries are common chronic infectious oral diseases affecting most teenagers and adults worldwide. Optical coherence tomography (OCT) has been studied extensively for the detection of early carious lesions. Deep learning techniques are a rapidly emerging new area of biomedical research and have yielded impressive results in diagnosis and prediction in the field of oral radiology. Deep learning models particularly deep convolutional neural networks (CNN) can be employed along with OCT imaging system to more accurately identify early dental caries. In this work, after OCT data acquisition, data augmentation was performed to obtain a large amount of training data in order to effectively learn, where collection of such training data is often expensive and laborious. For the backpropagation process, seven optimization methods, namely Adadelta, AdaGrad, Adam, AdaMax, Nadam, RMSProp, and Stochastic Gradient Descent (SGD) were utilized to improve the accuracy of a CNN classifier for diagnosing dental caries. In this study, 75% of the data were utilized for training and 25% for testing. The diagnostic accuracy, sensitivity, specificity, positive predictive value, negative predictive value, and receiver operating characteristic (ROC) curve were calculated for detection and diagnostic performance of the deep CNN algorithm. This study highlighted the performance of various optimization methods for deep CNN models with OCT images to detect dental caries.
基于光学相干断层扫描图像定量分析的人体口腔组织表征
DOI: 10.1117/12.2253362
发表时间: 2017
影响因子: 3.5
作者:
H. Salehi;A. Kósa;M. Mahdian;S. Moslehpour;H. Alnajjar;Aditya Tadinada
通讯作者: Aditya Tadinada
开发 Adaptive Boost 方法并使用该方法分析铁中的碳扩散 [MD 奖获得者]
DOI: --
发表时间: 2011
期刊:
影响因子: --
作者:
石井明男;尾方成信;君塚肇
通讯作者: 君塚肇
DOI: 10.1002/jbio.201200210
发表时间: 2014-07-01
影响因子: 2.8
作者:
Shimada, Yasushi;Nakagawa, Hisaichi;Sumi, Yasunori
通讯作者: Sumi, Yasunori
DOI: 10.1155/2010/270729
发表时间: 2010
影响因子: 2.1
作者:
Karlsson L
通讯作者: Karlsson L
DOI: 10.1109/tmi.2016.2528129
发表时间: 2016-05-01
影响因子: 10.6
作者:
Dou, Qi;Chen, Hao;Heng, Pheng-Ann
通讯作者: Heng, Pheng-Ann