School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University, Shanghai, China.
Shanghai Ninth People's Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai, China.
Int J Comput Assist Radiol Surg. 2021 Mar;16(3):415-422. doi: 10.1007/s11548-021-02309-0. Epub 2021 Feb 6.
The differentiation of the ameloblastoma and odontogenic keratocyst directly affects the formulation of surgical plans, while the results of differential diagnosis by imaging alone are not satisfactory. This paper aimed to propose an algorithm based on convolutional neural networks (CNN) structure to significantly improve the classification accuracy of these two tumors.
A total of 420 digital panoramic radiographs provided by 401 patients were acquired from the Shanghai Ninth People's Hospital. Each of them was cropped to a patch as a region of interest by radiologists. Furthermore, inverse logarithm transformation and histogram equalization were employed to increase the contrast of the region of interest (ROI). To alleviate overfitting, random rotation and flip transform as data augmentation algorithms were adopted to the training dataset. We provided a CNN structure based on a transfer learning algorithm, which consists of two branches in parallel. The output of the network is a two-dimensional vector representing the predicted scores of ameloblastoma and odontogenic keratocyst, respectively.
The proposed network achieved an accuracy of 90.36% (AUC = 0.946), while sensitivity and specificity were 92.88% and 87.80%, respectively. Two other networks named VGG-19 and ResNet-50 and a network trained from scratch were also used in the experiment, which achieved accuracy of 80.72%, 78.31%, and 69.88%, respectively.
We proposed an algorithm that significantly improves the differential diagnosis accuracy of ameloblastoma and odontogenic keratocyst and has the utility to provide a reliable recommendation to the oral maxillofacial specialists before surgery.
成釉细胞瘤和牙源性角化囊性瘤的鉴别直接影响手术方案的制定，而仅凭影像学的鉴别诊断结果并不令人满意。本研究旨在提出一种基于卷积神经网络（CNN）结构的算法，以显著提高这两种肿瘤的分类准确性。
从上海第九人民医院获得了 401 名患者的 420 张数字化全景片。由放射科医生将每张图像裁剪成感兴趣区域（ROI）的小图。此外，采用对数反转变换和直方图均衡化来增加 ROI 的对比度。为了缓解过拟合，采用随机旋转和翻转变换作为数据增强算法应用于训练数据集。我们提供了一种基于迁移学习算法的 CNN 结构，该结构由两个并行分支组成。网络的输出是一个二维向量，分别代表成釉细胞瘤和牙源性角化囊性瘤的预测得分。
所提出的网络的准确率为 90.36%（AUC=0.946），而敏感性和特异性分别为 92.88%和 87.80%。实验还使用了另外两个名为 VGG-19 和 ResNet-50 的网络以及一个从头开始训练的网络，它们的准确率分别为 80.72%、78.31%和 69.88%。
我们提出的算法显著提高了成釉细胞瘤和牙源性角化囊性瘤的鉴别诊断准确性，有望为口腔颌面外科专家在手术前提供可靠的建议。
