Ultrasound Image Classification of Thyroid Nodules Using Machine Learning Techniques

• Main Authors: Vijay Vyas Vadhiraj, Andrew Simpkin, James O’Connell, Naykky Singh Ospina, Spyridoula Maraka, Derek T. O’Keeffe
• Format: Article
• Language: English
• Published: MDPI AG 2021-05-01
• Series: Medicina
• Subjects: computer aided diagnostics; CAD; artificial intelligence; AI; digital health; TI-RADS
• Online Access: https://www.mdpi.com/1648-9144/57/6/527

<i>Background and Objectives</i>: 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. <i>Materials and Methods</i>: 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. <i>Results</i>: 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. <i>Conclusions</i>: 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.