Mortaheb Parinaz, Rezaeian Mehdi
Department of Electrical and Computer Engineering, Yazd University, Yazd, Iran.
J Med Signals Sens. 2016 Jan-Mar;6(1):1-11.
Segmentation and three-dimensional (3D) visualization of teeth in dental computerized tomography (CT) images are of dentists' requirements for both abnormalities diagnosis and the treatments such as dental implant and orthodontic planning. On the other hand, dental CT image segmentation is a difficult process because of the specific characteristics of the tooth's structure. This paper presents a method for automatic segmentation of dental CT images. We present a multi-step method, which starts with a preprocessing phase to reduce the metal artifact using the least square support vector machine. Integral intensity profile is then applied to detect each tooth's region candidates. Finally, the mean shift algorithm is used to partition the region of each tooth, and all these segmented slices are then applied for 3D visualization of teeth. Examining the performance of our proposed approach, a set of reliable assessment metrics is utilized. We applied the segmentation method on 14 cone-beam CT datasets. Functionality analysis of the proposed method demonstrated precise segmentation results on different sample slices. Accuracy analysis of the proposed method indicates that we can increase the sensitivity, specificity, precision, and accuracy of the segmentation results by 83.24%, 98.35%, 72.77%, and 97.62% and decrease the error rate by 2.34%. The experimental results show that the proposed approach performs well on different types of CT images and has better performance than all existing approaches. Moreover, segmentation results can be more accurate by using the proposed algorithm of metal artifact reduction in the preprocessing phase.
牙科计算机断层扫描（CT）图像中牙齿的分割和三维（3D）可视化是牙医进行异常诊断以及诸如牙种植和正畸治疗规划等治疗的需求。另一方面，由于牙齿结构的特定特征，牙科CT图像分割是一个困难的过程。本文提出了一种牙科CT图像自动分割方法。我们提出了一种多步骤方法，该方法首先是预处理阶段，使用最小二乘支持向量机减少金属伪影。然后应用积分强度轮廓来检测每个牙齿的候选区域。最后，使用均值漂移算法对每个牙齿的区域进行划分，然后将所有这些分割后的切片用于牙齿的3D可视化。为检验我们提出的方法的性能，使用了一组可靠的评估指标。我们将分割方法应用于14个锥形束CT数据集。所提方法的功能分析表明在不同样本切片上有精确的分割结果。所提方法的准确性分析表明，我们可以将分割结果的灵敏度、特异性、精度和准确性分别提高83.24%、98.35%、72.77%和97.62%，并将错误率降低2.34%。实验结果表明，所提方法在不同类型的CT图像上表现良好，并且比所有现有方法具有更好的性能。此外，通过在预处理阶段使用所提的减少金属伪影算法，分割结果可以更准确。
