Exploring a smart pathological brain detection method on pseudo Zernike moment

Yudong Zhang, Yongyan Jiang, Weiguo Zhu, Siyuan Lu, Guihu Zhao

Abstract: Pathological brain detection by computer vision is now attracting intense attentions from academic fields. Nevertheless, most of recent methods suffer from low-accuracy. This study combined two successful techniques: pseudo Zernike moment and kernel support vector machine. Three open datasets were downloaded and used. The 10 times of K-fold stratified cross validation showed our method using 19-order pseudo Zernike moments achieved perfect classification on the first dataset. It achieved a sensitivity of 99.93 ± 0.23%, a specificity of 98.50 ± 2.42%, and an accuracy of 99.75 ± 0.32% on the second dataset. It achieved a sensitivity of 99.64 ± 0.42%, a specificity of 98.29 ± 2.76%, and an accuracy of 99.45 ± 0.38% on the third dataset. This approach performs better than eleven state-of-the-art smart pathological brain detection methods.

External IDs:dblp:journals/mta/ZhangJZLZ18