Department of Electronics and Computer Engineering, Ngee Ann Polytechnic, 535 Clementi Road, Singapore 599489, Singapore.
Ultrasonics. 2012 Apr;52(4):508-20. doi: 10.1016/j.ultras.2011.11.003. Epub 2011 Nov 25.
Ultrasound-based thyroid nodule characterization into benign and malignant types is limited by subjective interpretations. This paper presents a Computer Aided Diagnostic (CAD) technique that would present more objective and accurate classification and further would offer the physician a valuable second opinion. In this paradigm, we first extracted the features that quantify the local changes in the texture characteristics of the ultrasound off-line training images from both benign and malignant nodules. These features include: Fractal Dimension (FD), Local Binary Pattern (LBP), Fourier Spectrum Descriptor (FS), and Laws Texture Energy (LTE). The resulting feature vectors were used to build seven different classifiers: Support Vector Machine (SVM), Decision Tree (DT), Sugeno Fuzzy, Gaussian Mixture Model (GMM), K-Nearest Neighbor (KNN), Radial Basis Probabilistic Neural Network (RBPNN), and Naive Bayes Classifier (NBC). Subsequently, the feature vector-classifier combination that results in the maximum classification accuracy was used to predict the class of a new on-line test thyroid ultrasound image. Two data sets with 3D Contrast-Enhanced Ultrasound (CEUS) and 3D High Resolution Ultrasound (HRUS) images of 20 nodules (10 benign and 10 malignant) were used. Fine needle aspiration biopsy and histology results were used to confirm malignancy. Our results show that a combination of texture features coupled with SVM or Fuzzy classifiers resulted in 100% accuracy for the HRUS dataset, while GMM classifier resulted in 98.1% accuracy for the CEUS dataset. Finally, for each dataset, we have proposed a novel integrated index called Thyroid Malignancy Index (TMI) using the combination of FD, LBP, LTE texture features, to diagnose benign or malignant nodules. This index can help clinicians to make a more objective differentiation of benign/malignant thyroid lesions. We have compared and benchmarked the system with existing methods.
基于超声的甲状腺结节良恶性特征分类受到主观解释的限制。本文提出了一种计算机辅助诊断（CAD）技术，该技术将提供更客观、更准确的分类，并为医生提供有价值的第二意见。在这种模式下，我们首先从良性和恶性结节的离线训练图像中提取量化超声纹理特征局部变化的特征。这些特征包括：分形维数（FD）、局部二值模式（LBP）、傅里叶频谱描述符（FS）和 Laws 纹理能量（LTE）。得到的特征向量用于构建七种不同的分类器：支持向量机（SVM）、决策树（DT）、Sugeno 模糊、高斯混合模型（GMM）、K-最近邻（KNN）、径向基概率神经网络（RBPNN）和朴素贝叶斯分类器（NBC）。随后，使用产生最大分类准确性的特征向量-分类器组合来预测新的在线甲状腺超声图像的类别。使用 20 个结节（10 个良性和 10 个恶性）的 3D 对比增强超声（CEUS）和 3D 高分辨率超声（HRUS）数据集进行了两项研究。细针抽吸活检和组织学结果用于确认恶性肿瘤。我们的结果表明，纹理特征与 SVM 或模糊分类器的组合对 HRUS 数据集的准确率达到 100%，而 GMM 分类器对 CEUS 数据集的准确率达到 98.1%。最后，对于每个数据集，我们使用 FD、LBP、LTE 纹理特征的组合提出了一个新的综合指数，称为甲状腺恶性指数（TMI），用于诊断良性或恶性甲状腺结节。该指数可以帮助临床医生更客观地区分良性/恶性甲状腺病变。我们已经将该系统与现有的方法进行了比较和基准测试。
