作者: Stavros Tsantis , Dionisis Cavouras , Ioannis Kalatzis , Nikos Piliouras , Nikos Dimitropoulos
DOI: 10.1016/J.ULTRASMEDBIO.2005.07.009
关键词:
摘要: Abstract An SVM-based image analysis system was developed for assessing the malignancy risk of thyroid nodules. Ultrasound images 120 cytology confirmed nodules (78 low-risk and 42 high-risk malignancy) were manually segmented by a physician using custom software in C++. From each nodule, 40 textural features automatically calculated used with SVM algorithm design system. Highest classification accuracy 96.7%, misdiagnosing two The proposed may be value to physicians as second opinion tool avoiding unnecessary invasive procedures. (E-mail: tsantis@med.upatras.gr )