Unilateral sensorineural hearing loss identification based on double-density dual-tree complex wavelet transform and multinomial logistic regression

Article type: Research Article

Authors: Wang, Shui-Hua^{a; b; h} | Zhang, Yu-Dong^{a; c; *} | Yang, Ming^{d; 1} | Liu, Bin^e | Ramirez, Javier^{f; 1} | Gorriz, Juan Manuel^{g; 1}

Affiliations: [a] School of Computer Science and Technology, Henan Polytechnic University, Jiaozuo, Henan 454000, China | [b] Department of Rheumatology and Immunology Nanjing Drum Tower Hospital, The Affiliated Hospital of Nanjing University Medical School, Nanjing, Jiangsu 210008, China | [c] Department of Informatics, University of Leicester, Leicester, UK | [d] Department of Radiology, Children’s Hospital of Nanjing Medical University, Nanjing 210008, China | [e] Department of Radiology, Zhong-Da Hospital of Southeast University, Nanjing 210009, China | [f] Department of Signal Theory, Networking and Communications, University of Granada, Spain | [g] Department of Psychiatry, Robinson Way, University of Cambridge, UK | [h] Department of Math, University of Leicester, UK

Correspondence: [*] Corresponding author: Yu-Dong Zhang, School of Computer Science and Technology, Henan Polytechnic University, Jiaozuo, Henan 454000, China and Department of Informatics, University of Leicester, Leicester, UK. E-mail: [email protected].

Note: [1] Those authors contribute equally.

Abstract: AIM: Unilateral sensorineural hearing loss is a brain disease, which causes slight morphology changes within brain structure. Traditional manual method may ignore this change. METHOD: In this work, we developed a novel method, based on the double-density dual-tree complex (DDDTCWT), and radial basis function kernel principal component analysis (RKPCA) and multinomial logistic regression (MLR) for the magnetic resonance imaging scanning. We first used DDDTCWT to extract features. Afterwards, we used RKPCA to reduce feature dimensionalities. Finally, MLR was employed to be the classifier. RESULT: The 10 times of 10-fold stratified cross validation showed our method achieved an overall accuracy of 96.44 ± 0.88%. The sensitivities of detecting left-sided sensorineural hearing loss, right-sided sensorineural hearing loss, and healthy controls were 96.67 ± 2.72%, 96.67 ± 3.51%, and 96.00 ± 4.10%, respectively. CONCLUSION: Our method performed better than both raw and improved AlexNet, and eight state-of-the-art methods via a stringent statistical 10 × 10-fold stratified cross validation. The MLR gives better classification performance than decision tree, support vector machine, and back-propagation neural network.

Keywords: Unilateral sensorineural hearing loss, dual-tree complex wavelet transform, kernel principal component analysis, multinomial logistic regression, double-density dual-tree complex wavelet transform, magnetic resonance imaging, alexNet

DOI: 10.3233/ICA-190605

Journal: Integrated Computer-Aided Engineering, vol. 26, no. 4, pp. 411-426, 2019