Application of Texture Features algorithm using Computer Aided Diagnosis of Papillary Thyroid Cancer in the Ultrasonography
초음파영상에서 갑상선 결절의 컴퓨터자동진단을 위한 Texture Features 알고리즘 응용

Seong-Jin Ko, Jin-Soo Lee, Soo-Young Ye, Changsoo Kim
2013 The Journal of the Korea Contents Association  
Thyroid nodular disease is the most frequently appeared in thyroid disease. Thyroid ultrasonography offers location of nodules, size, the number, information of internal echo characteristic. Thus, it makes possible to sort high-risk nodule containing high possibility about thyroid cancer and to induct precisely when take a Fine Needle Biopsy Aspiration. On thyroid nodule, the case which is diagnosed as malignant is less than 5% but screening test is very important on ultrasound and also must be
more » ... reduced unnecessary procedure. Therefore, in this study an approach for describing a region is to quantity its texture content. We applied TFA algorithm on case which has been pathologically diagnosed as papillary thyroid cancer. we obtained experiment image which set the ROI on ultrasound and cut the 50x50 pixel size, histogram equalization. Consequently, Disease recognition detection efficiency of GLavg, SKEW, UN, ENT parameter were high as 91∼100%. It is suggestion about possibility on CAD which distinguishes thyroid nodule. In addition, it will be helpful to differential diagnosis of thyroid nodule. If the study on additional parameter algorithm is continuously progressed from now on, it is able to arrange practical base on CAD and it is possible to apply various disease in the thyroid US. ■ keyword :|Thyroid US|Papillary thyroid CA|TFA|CAD| * 본 논문은 2012년도 부산가톨릭대학교 교내학술연구비 지원에 의하여 수행되었습니다.
doi:10.5392/jkca.2013.13.05.303 fatcat:wl5v3ql5wjc2veppev54aamz34