Latifoğlu Fatma, Kodaz Halife, Kara Sadik, Güneş Salih
Department of Electronics Engineering, Erciyes University, 38039 Kayseri, Turkey.
Comput Biol Med. 2007 Aug;37(8):1092-9. doi: 10.1016/j.compbiomed.2006.09.009. Epub 2006 Dec 6.
This study was conducted to distinguish between atherosclerosis and healthy subjects. Hence, we have employed the maximum envelope of the carotid artery Doppler sonograms derived from Fast Fourier Transformation-Welch method and Artificial Immune Recognition System (AIRS). The fuzzy appearance of the carotid artery Doppler signals makes physicians suspicious about the existence of diseases and sometimes causes false diagnosis. Our technique gets around this problem using AIRS to decide and assist the physician to make the final judgment in confidence. AIRS has reached 99.29% classification accuracy using 10-fold cross validation. Results show that the proposed method classified Doppler signals successfully.
本研究旨在区分动脉粥样硬化患者与健康受试者。因此,我们采用了基于快速傅里叶变换-韦尔奇方法和人工免疫识别系统(AIRS)得出的颈动脉多普勒超声图的最大包络线。颈动脉多普勒信号的模糊外观使医生怀疑疾病的存在,有时会导致误诊。我们的技术通过使用AIRS来解决这个问题,以协助医生做出最终的可靠判断。使用10折交叉验证时,AIRS的分类准确率达到了99.29%。结果表明,所提出的方法成功地对多普勒信号进行了分类。