The Transverse Ultrasonogram of Thyroid Papillary Carcinoma Has a Better Prediction Accuracy Than the Longitudinal One

• Published in: IEEE access Vol. 7; pp. 100763 - 100770
• Main Authors: Yu, Bingxin, Wang, Zhongyu, Zhu, Renxiang, Feng, Xin, Qi, Mingran, Li, Jialiang, Zhao, Ruixue, Huang, Lan, Xin, Ruihao, Li, Fan, Zhou, Fengfeng
• Format: Journal Article
• Language: English
• Published: Piscataway IEEE 2019; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Biochemistry; Biomedical data; Cancer; Feature extraction; Hormones; Image coding; Imaging; local binary pattern (LBP); longitudinal ultrasonogram; support vector machine (SVM); Support vector machines; Thyroid cancer; Thyroid pappilary carcinoma (TPC); transverse ultrasonogram; Ultrasonic imaging; Ultrasound
• ISSN: 2169-3536; 2169-3536
• DOI: 10.1109/ACCESS.2019.2926377

Thyroid produces multiple essential hormones for vital life processes. Thyroid cancer has no symptoms and may be detected by ultrasound imaging incidentally for other medical conditions. An accurate computational detection model may help the precise diagnose of thyroid papillary cancer (TPC). A standard protocol captures at least the transverse and longitudinal ultrasonograms of the thyroid. This study investigated the detection problem of thyroid cancer using the ultrasound images. Our data suggested that the original local binary pattern (LBP) features extracted from the ultrasonograms were very sparse and the compressed LBP features outperformed the original version. And the best model (Acc = 0.9829) was achieved by the fivefold cross validation of the classifier support vector machine (SVM). Other sources of biomedical data may be integrated to further improve the TPC detection model in future studies.