Five-category classification of pathological brain images based on deep stacked sparse autoencoder

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.

[1]  Farhan Khan,et al.  Message Concealment Techniques using Image based Steganography , 2007 .

[2]  Yudong Zhang,et al.  Pathological Brain Detection via Wavelet Packet Tsallis Entropy and Real-Coded Biogeography-based Optimization , 2017, Fundam. Informaticae.

[3]  Basem Y. Alkazemi,et al.  LIGHT-WEIGHT CRYPTOGRAPHY TO SECURE MEDICAL DATA IN IOT , 2017 .

[4]  Levi J. Hargrove,et al.  User intent prediction with a scaled conjugate gradient trained artificial neural network for lower limb amputees using a powered prosthesis , 2016, 2016 38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC).

[5]  Ming Yang,et al.  A pathological brain detection system based on kernel based ELM , 2016, Multimedia Tools and Applications.

[6]  Liang Liu,et al.  Enhance the Quality of Crowdsensing for Fine-Grained Urban Environment Monitoring via Data Correlation , 2017, Sensors.

[7]  Hiroshi Ohno,et al.  Linear guided autoencoder: Representation learning with linearity , 2017, Appl. Soft Comput..

[8]  A. Rahimdel,et al.  Comparison of Diffuse Weighted Imaging and Fluid Attenuation Inversion Recovery Sequences of MRI in Brain Multiple Sclerosis Plaques Detection , 2017, Iranian journal of child neurology.

[9]  Adnan Abdul-Aziz Gutub,et al.  Pixel Indicator Technique for RGB Image Steganography , 2010 .

[10]  Nithya Ramakrishnan,et al.  Analysis of healthy and tumour DNA methylation distributions in kidney-renal-clear-cell-carcinoma using Kullback-Leibler and Jensen-Shannon distance measures. , 2017, IET systems biology.

[11]  Wah June Leong,et al.  A scaled three-term conjugate gradient method for unconstrained optimization , 2016, Journal of Inequalities and Applications.

[12]  Richa Singh,et al.  Group sparse autoencoder , 2017, Image Vis. Comput..

[13]  Michael G. Rabbat,et al.  Efficient Distributed Online Prediction and Stochastic Optimization With Approximate Distributed Averaging , 2014, IEEE Transactions on Signal and Information Processing over Networks.

[14]  Saudi Arabia,et al.  Flexible Stego-System for Hiding Text in Images of Personal Computers Based on User Security Priority , 2014 .

[15]  A. Gutub,et al.  Vibrant Color Image Steganography using Channel Differences and Secret Data Distribution , 2010 .

[16]  Mauridhi Hery Purnomo,et al.  Study on Electronic-Nose-Based Quality Monitoring System for Coffee Under Roasting , 2016, J. Circuits Syst. Comput..

[17]  Yi Chen,et al.  A Feature-Free 30-Disease Pathological Brain Detection System by Linear Regression Classifier. , 2017, CNS & neurological disorders drug targets.

[18]  Nemshan Alharthi,et al.  Data Visualization to Explore Improving Decision-Making within Hajj Services , 2017 .

[19]  Neculai Andrei,et al.  Eigenvalues versus singular values study in conjugate gradient algorithms for large-scale unconstrained optimization , 2017, Optim. Methods Softw..

[20]  Leon O. Chua,et al.  A Circuit-Based Neural Network with Hybrid Learning of Backpropagation and Random Weight Change Algorithms , 2016, Sensors.

[21]  Huanxin Zou,et al.  Synthetic Aperture Radar Target Recognition with Feature Fusion Based on a Stacked Autoencoder , 2017, Sensors.

[22]  Yudong Zhang,et al.  Detection of abnormal MR brains based on wavelet entropy and feature selection , 2016 .

[23]  Misko Subotic,et al.  Whispered speech recognition using deep denoising autoencoder , 2017, Eng. Appl. Artif. Intell..

[24]  Yudong Zhang,et al.  A Pathological Brain Detection System Based on Radial Basis Function Neural Network , 2016 .

[25]  Nouf A. Al-Otaibi,et al.  2-Leyer Security System for Hiding Sensitive Text Data on Personal Computers , 2014 .

[26]  Maan El Badaoui El Najjar,et al.  Multi-sensor fusion approach with fault detection and exclusion based on the KullbackLeibler Divergence , 2017 .

[27]  Maan El Badaoui El Najjar,et al.  Multi-sensor fusion approach with fault detection and exclusion based on the Kullback-Leibler Divergence: Application on collaborative multi-robot system , 2017, Inf. Fusion.

[28]  Xiaojie Wang,et al.  Offline Urdu Nastaleeq optical character recognition based on stacked denoising autoencoder , 2017, China Communications.

[29]  Hong Chen,et al.  Seven-layer deep neural network based on sparse autoencoder for voxelwise detection of cerebral microbleed , 2017, Multimedia Tools and Applications.

[30]  Takayuki Takahashi,et al.  Autoencoder-based holographic image restoration , 2016, Applied optics.