Abstract
Magnetic resonance imaging (MRI) is employed in medical treatment broadly, due to the quick development of computer technology. It is beneficial to classify the pathological brain images into healthy or other different categories automatically and accurately. This work aims to generate a pathological brain detecting system to classify the pathological brain images into five different categories of healthy; cerebrovascular disease; neoplastic disease; degenerative disease; and inflammatory disease. Our proposed method can be composed of the following several steps: First, we used data augmentation technology to deal with unbalanced distribution of the dataset. Then, we used deep stacked sparse autoencoder with minibatch scaled conjugate gradient to train the network, and the softmax layer is used as the classifier. As a result, the accuracy of our deep stacked sparse autoencoder over the test set is 98.6%. The prediction time of each image in test stage is only 0.070 s. Our experiment will be a powerful proof of the effectiveness of our proposed method that based on deep stacked sparse autoencoder.
Similar content being viewed by others
References
Ahmad I et al (2017) Offline Urdu Nastaleeq Optical Character Recognition Based on Stacked Denoising Autoencoder. Chin Commun 14(1):146–157
Al Hage J, El Najjar ME, Pomorski D (2017) Multi-sensor fusion approach with fault detection and exclusion based on the Kullback-Leibler Divergence: Application on collaborative multi-robot system. Inform Fusion 37:61–76
Alassaf N, Alkazemi B, Gutub A (2017) Applicable light-weight cryptography to secure medical data in IoT systems. J Res Eng Appl Sci (JREAS) 2(2):50–58
Alharthi N, Gutub A (2017) Data visualization to explore improving decision-making within Hajj services. Sci Modell Res 2(1):9–18
Al-Otaibi NA, Gutub AA (2014a) 2-Leyer Security System for Hiding Sensitive Text Data on Personal Computers. Lecture Notes on Information Theory
Al-Otaibi NA, Gutub AA (2014b) Flexible stego-system for hiding text in images of personal computers based on user security priority. Adv Eng Technol. Dubai UAE. p. 250–256
Andrei N (2017) Eigenvalues versus singular values study in conjugate gradient algorithms for large-scale unconstrained optimization. Optim Methods Softw 32(3):534–551
Arzuka, I., M.R. Abu Bakar, and W.J. Leong, (2016) A scaled three-term conjugate gradient method for unconstrained optimization. J Inequal Appl, 16
Chen H (2017b) Seven-layer deep neural network based on sparse autoencoder for voxelwise detection of cerebral microbleed. Multimed Tools Appl. https://doi.org/10.1007/s11042-017-4554-8
Chen P, Du S (2017) Pathological brain detection via wavelet packet tsallis entropy and real-coded biogeography-based optimization. Fundamenta Informaticae 151(1–4):275–291
Chen Y (2017a) A feature-free 30-disease pathological brain detection system by linear regression classifier. CNS Neurol Disord Drug Targets 16(1):5–10
Grozdic DT, Jovicic ST, Subotic M (2017) Whispered speech recognition using deep denoising autoencoder. Eng Appl Artif Intell 59:15–22
Gutub A (2015) Exploratory data visualization for smart system. in smart cities 2015 - 3rd annual digital grids and smart cities workshop. Burj Rafal Hotel Kempinski, Riyadh, Saudi Arabia
Gutub AA.-A (2010) Pixel indicator technique for RGB image steganography. J Emerg Technol Web Intell 2(1)
Gutub, A.A.-A. and N. Alharthi (2016) Improving Hajj and Umrah Services Utilizing Exploratory Data Visualization Techniques, in Hajj Forum 2016 - the 16th Scientific Hajj Research Forum, Organized by the Custodian of the Two Holy Mosques Institute for Hajj Research, Umm AI-Qura University - King Abdulaziz Historical Hall
Kang M et al (2017) Synthetic aperture radar target recognition with feature fusion based on a stacked autoencoder. Sensors 17(1):16
Khan F, Gutub AA.-A (2007) Message concealment techniques using image based steganography. 4th IEEE GCC Conf Exhibit. Bhrain. p. 11–14
Lu S, Lu Z (2016) A pathological brain detection system based on kernel based ELM. Multimed Tools Appl. https://doi.org/10.1007/s11042-016-3559-z
Lu Z (2016) A pathological brain detection system based on radial basis function neural network. J Med Imag Health Inform 6(5):1218–1222
Nafisi-Moghadam R et al (2017) comparison of diffuse weighted imaging and fluid attenuation inversion recovery sequences of MRI in brain multiple sclerosis plaques detection. Iran J Child Neurol 11(1):13–20
Ohno H (2017) Linear guided autoencoder: representation learning with linearity. Appl Soft Comput 55:566–575
Parvez MT, Gutub AA-A (2011) Vibrant color image steganography using channel differences and secret data distribution. Kuwait J Ofence Eng 38:127–142
Radi MR, Purnomo MH (2016) Study on electronic-nose-based quality monitoring system for coffee under roasting. J Circ Syst Comput 25(10):19
Ramakrishnan N, Bose R (2017) Analysis of healthy and tumour DNA methylation distributions in kidney-renal-clear-cell-carcinoma using Kullback-Leibler and Jensen-Shannon distance measures. IET Syst Biol 11(3):99–104
Sankaran A et al (2017) Group sparse autoencoder. Image Vis Comput 60:64–74
Shimobaba T et al (2017) Autoencoder-based holographic image restoration. Appl Opt 56(13):F27–F30
Tsianos KI, Rabbat MG (2016) Efficient distributed online prediction and stochastic optimization with approximate distributed averaging. IEEE Trans Sign Inform Process Over Netw 2(4):489–506
Woodward RB, Spanias JA, Hargrove LJ (2016) User intent prediction with a scaled conjugate gradient trained artificial neural network for lower limb amputees using a powered prosthesis. IEEE Eng Med Biol Soc: Ann Conf 2016:6405–6408
Zhou XX, Zhang GS (2016) Detection of abnormal MR brains based on wavelet entropy and feature selection. IEEJ Trans Electr Electron Eng 11(3):364–373
Acknowledgements
This paper is supported by Natural Science Foundation of China (61602250) and Natural Science Foundation of Jiangsu Province (BK20150983).
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Jia, W., Muhammad, K., Wang, SH. et al. Five-category classification of pathological brain images based on deep stacked sparse autoencoder. Multimed Tools Appl 78, 4045–4064 (2019). https://doi.org/10.1007/s11042-017-5174-z
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11042-017-5174-z