Texture Analysis Method Based on Fractional Fourier Entropy and Fitness-scaling Adaptive Genetic Algorithm for Detecting Left-sided and Right-sided Sensorineural Hearing Loss

Issue title: Theory and Applications of Fractional Fourier Transform and its Variants

Guest editors: Yudong Zhang, Xiao-Jun Yang, Carlo Cattani, Zhengchao Dong, Ti-Fei Yuan and Liang-Xiu Han

Article type: Research Article

Authors: Wang, Shuihua^{a; *} | Yang, Ming^{b; †} | Li, Jianwu^c | Wu, Xueyan^{a; ‡} | Wang, Hainan^{a; §} | Liu, Bin^d | Dong, Zhengchao^e | Zhang, Yudong^{f; C; ¶}

Affiliations: [a] School of Computer Science and Technology, Nanjing Normal University, Nanjing, Jiangsu 210023, China | [b] Department of Radiology, Nanjing Childrens Hospital, Nanjing Medical University, Nanjing 210008, China | [c] School of Computer Science and Technology, Beijing Institute of Technology, Beijing 100081, China | [d] Department of Radiology, Zhong-Da Hospital of Southeast University, Nanjing 210009, China | [e] Translational Imaging Division & MRI Unit, Columbia University and New York, State Psychiatric Institute, New York, NY 10032, USA | [f] School of Computer Science and Technology, Nanjing Normal University, Nanjing, Jiangsu 210023, China. zhangyudong@njnu.edu.cn

Correspondence: [C] Address for correspondence: School of Computer Science and Technology, Nanjing Normal University, Nanjing, Jiangsu 210023, China.

Note: [*] Also affiliated at: First Affiliated Hospital of Nanjing Medical University, Nanjing 210029, China

Note: [†] Also affiliated at: State Key Lab of CAD & CG, Zhejiang University, Hangzhou, Zhejiang 310027, China

Note: [‡] Also affiliated at: Jilin University, Changchun, Jilin 130012, China

Note: [§] Also affiliated at: Manchester Metropolitan University, Manchester, M156BH, UK

Note: [¶] Also affiliated at: State Statistics Bureau, Chengdu, Sichuan 610225, China

Abstract: To detect the sensorineural hearing loss (SNHL) from healthy people accurately, we used magnetic resonance imaging (MRI) to obtain the imaging data, and then proposed a new computer-aided diagnosis (CAD) system, on the basis of texture analysis method. In the first, we extracted 12-element feature from each brain image via fractional Fourier entropy (FRFE). Afterwards, multilayer perceptron (MLP) was employed as the classifier, which was trained by a novel fitness-scaling adaptive genetic algorithm (FSAGA). The statistical analysis over 49 subjects showed the overall accuracy of our method yielded 95.51%. Experimental results performed better than four state-of-the-art weight optimization methods, and this CAD system give significantly better performance than manual interpretation.

Keywords: texture analysis, fractional Fourier entropy, power-rank fitness scaling, sensorineural hearing loss, genetic algorithm

DOI: 10.3233/FI-2017-1507

Journal: Fundamenta Informaticae, vol. 151, no. 1-4, pp. 505-521, 2017