Ultrasound Image Classification of Thyroid Nodules Using Machine Learning Techniques.
Ultrasound Image Classification of Thyroid Nodules Using Machine Learning Techniques.
复制标题
DOI：
10.3390/medicina57060527
复制
发表时间：
2021-05-24
期刊：
影响因子：
--
通讯作者：
O'Keeffe DT
中科院分区：
文献类型：
--
作者：
Vadhiraj VV;Simpkin A;O'Connell J;Singh Ospina N;Maraka S;O'Keeffe DT
背景和目标：甲状腺结节是甲状腺内形成的固体或充满液体的肿瘤，可以是恶性或良性。我们的目的是测试所描述的甲状腺成像报告和数据系统（TI-RADS）的功能是否可以提高放射科医生的决策时，集成到一个计算机系统。在这项研究中，我们开发了一个计算机辅助诊断系统集成到多实例学习（MIL），将重点放在良恶性分类。数据来自哥伦比亚国立大学。材料与方法：99例（良性33例，恶性66例）。本文采用中值滤波和图像二值化的方法对图像进行预处理和分割。利用灰度共生矩阵（GLCM）提取7个超声图像特征。这些数据被分为87%的训练集和13%的验证集。我们比较了支持向量机（SVM）和人工神经网络（ANN）分类算法的准确性得分，灵敏度和特异性的基础上。结果测量是甲状腺结节是良性还是恶性。我们还开发了一个图形用户界面（GUI），以显示图像的功能，这将有助于放射科医生的决策。结果：人工神经网络和支持向量机的准确率分别达到75%和96%。SVM在所有性能指标上都优于所有其他模型，实现了更高的准确性，灵敏度和特异性得分。结论：我们的研究表明，MIL在甲状腺癌检测中有希望的结果。在我们的分类模型可以在实践中使用之前，需要进一步测试外部数据。
Background and Objectives: Thyroid nodules are lumps of solid or liquid-filled tumors that form inside the thyroid gland, which can be malignant or benign. Our aim was to test whether the described features of the Thyroid Imaging Reporting and Data System (TI-RADS) could improve radiologists’ decision making when integrated into a computer system. In this study, we developed a computer-aided diagnosis system integrated into multiple-instance learning (MIL) that would focus on benign–malignant classification. Data were available from the Universidad Nacional de Colombia. Materials and Methods: There were 99 cases (33 Benign and 66 malignant). In this study, the median filter and image binarization were used for image pre-processing and segmentation. The grey level co-occurrence matrix (GLCM) was used to extract seven ultrasound image features. These data were divided into 87% training and 13% validation sets. We compared the support vector machine (SVM) and artificial neural network (ANN) classification algorithms based on their accuracy score, sensitivity, and specificity. The outcome measure was whether the thyroid nodule was benign or malignant. We also developed a graphic user interface (GUI) to display the image features that would help radiologists with decision making. Results: ANN and SVM achieved an accuracy of 75% and 96% respectively. SVM outperformed all the other models on all performance metrics, achieving higher accuracy, sensitivity, and specificity score. Conclusions: Our study suggests promising results from MIL in thyroid cancer detection. Further testing with external data is required before our classification model can be employed in practice.
登录
查看更多内容
DOI：
10.1111/j.1365-2362.2009.02162.x
发表时间：
2009-08-01
影响因子：
5.5
作者：
Guth, S.;Theune, U.;Bamberger, C. M.
通讯作者：
Bamberger, C. M.
DOI：
10.1016/j.bjoms.2016.11.321
发表时间：
2017-04-01
影响因子：
1.8
作者：
Cappelli, C.;Pirola, I.;Castellano, M.
通讯作者：
Castellano, M.
影响因子：
3.9
作者：
Dat Tien Nguyen;Kang, Jin Kyu;Park, Kang Ryoung
通讯作者：
Park, Kang Ryoung
影响因子：
158.5
作者：
Burman, Kenneth D.;Wartofsky, Leonard
通讯作者：
Wartofsky, Leonard
超声图像中的甲状腺结节分类通过微调深卷积神经网络。
影响因子：
4.4
作者：
Chi J;Walia E;Babyn P;Wang J;Groot G;Eramian M
通讯作者：
Eramian M