An intelligent support system for automatic detection of cerebral vascular accidents from brain CT images

OBJECTIVE This paper presents a Radial Basis Functions Neural Network (RBFNN) based detection system, for automatic identification of Cerebral Vascular Accidents (CVA) through analysis of Computed Tomographic (CT) images. METHODS For the design of a neural network classifier, a Multi Objective Genetic Algorithm (MOGA) framework is used to determine the architecture of the classifier, its corresponding parameters and input features by maximizing the classification precision, while ensuring generalization. This approach considers a large number of input features, comprising first and second order pixel intensity statistics, as well as symmetry/asymmetry information with respect to the ideal mid-sagittal line. RESULTS Values of specificity of 98% and sensitivity of 98% were obtained, at pixel level, by an ensemble of non-dominated models generated by MOGA, in a set of 150 CT slices (1,867,602pixels), marked by a NeuroRadiologist. This approach also compares favorably at a lesion level with three other published solutions, in terms of specificity (86% compared with 84%), degree of coincidence of marked lesions (89% compared with 77%) and classification accuracy rate (96% compared with 88%).

[1]  R. Ganesan,et al.  Analysis of CT Brain Images using Radial Basis Function Neural Network , 2012 .

[2]  A. Aziz,et al.  Fast Talairach Transformation for Magnetic Resonance Neuroimages , 2006, Journal of computer assisted tomography.

[3]  António E. Ruano,et al.  Intelligent Control Systems using Computational Intelligence Techniques , 2005 .

[4]  Bernd Tomandl,et al.  Ischemic Stroke Segmentation on CT Images Using Joint Features , 2004, Informatica.

[5]  Domingues Teixeira.  Soft-computing techniques applied to artificial tissue temperature estimation , 2008 .

[6]  Hayit Greenspan,et al.  LESION DETECTION IN NOISY MR BRAIN IMAGES USING CONSTRAINED GMM AND ACTIVE CONTOURS , 2007, 2007 4th IEEE International Symposium on Biomedical Imaging: From Nano to Macro.

[7]  Kei-shing Douglas Ng.  Computer aided detection method for early detection of cerebrovascular accident , 2009 .

[8]  Xiaohong W. Gao,et al.  Classification of CT brain images based on deep learning networks , 2017, Comput. Methods Programs Biomed..

[9]  Elmira Hajimani,et al.  A software tool for intelligent CVA diagnosis by cerebral computerized tomography , 2013, 2013 IEEE 8th International Symposium on Intelligent Signal Processing.

[10]  M.G. Ruano,et al.  Neural networks assisted diagnosis of ischemic CVA's through CT scan , 2007, 2007 IEEE International Symposium on Intelligent Signal Processing.

[11]  António E. Ruano,et al.  A Randomized Approximation Convex Hull Algorithm for High Dimensions , 2015 .

[12]  Simon Haykin,et al.  Neural Networks: A Comprehensive Foundation , 1998 .

[13]  Yang Tang,et al.  Ideal Midline Detection Using Automated Processing of Brain CT Image , 2013 .

[14]  Mark D. Huffman,et al.  Heart disease and stroke statistics--2013 update: a report from the American Heart Association. , 2013, Circulation.

[15]  David A Clausi.  An analysis of co-occurrence texture statistics as a function of grey level quantization , 2002 .

[16]  Pedro M. Ferreira,et al.  A simple algorithm for convex hull determination in high dimensions , 2013, 2013 IEEE 8th International Symposium on Intelligent Signal Processing.

[17]  Kenneth Levenberg.  A METHOD FOR THE SOLUTION OF CERTAIN NON – LINEAR PROBLEMS IN LEAST SQUARES , 1944 .

[18]  Rebecca Smith,et al.  Automated ventricular systems segmentation in brain CT images by combining low-level segmentation and high-level template matching , 2009, BMC Medical Informatics Decis. Mak..

[19]  Xi-Zhao Wang,et al.  Feature Extraction and Classification for Human Brain CT Images , 2007, 2007 International Conference on Machine Learning and Cybernetics.

[20]  Lung Chan,et al.  The development of CAD system for hemorrhagic stroke in computed tomography images , 2014, 2014 IEEE International Symposium on Bioelectronics and Bioinformatics (IEEE ISBB 2014).

[21]  António E. Ruano,et al.  Evolutionary Multiobjective Neural Network Models Identification: Evolving Task-Optimised Models , 2011 .

[22]  B J Bedell,et al.  Automatic segmentation of gadolinium‐enhanced multiple sclerosis lesions , 1998, Magnetic resonance in medicine.

[23]  António E. Ruano,et al.  Exploiting the separability of linear and nonlinear parameters in radial basis function networks , 2000, Proceedings of the IEEE 2000 Adaptive Systems for Signal Processing, Communications, and Control Symposium (Cat. No.00EX373).

[24]  M. G. Ruano,et al.  MOGA design for neural networks based system for automatic diagnosis of Cerebral Vascular Accidents , 2015, 2015 IEEE 9th International Symposium on Intelligent Signal Processing (WISP) Proceedings.

[25]  Alex Rovira,et al.  Segmentation of multiple sclerosis lesions in brain MRI: A review of automated approaches , 2012, Inf. Sci..

[26]  Hayit Greenspan,et al.  Constrained Gaussian mixture model framework for automatic segmentation of MR brain images , 2006, IEEE Transactions on Medical Imaging.

[27]  Kesheng Wu,et al.  Fast connected-component labeling , 2009, Pattern Recognit..

[28]  Abdel-Ouahab Boudraa,et al.  Automated segmentation of multiple sclerosis lesions in multispectral MR imaging using fuzzy clustering , 2000, Comput. Biol. Medicine.

[29]  António E. Ruano,et al.  A convex hull-based data selection method for data driven models , 2016, Appl. Soft Comput..

[30]  Peter J. Fleming,et al.  Multiobjective optimization and multiple constraint handling with evolutionary algorithms. II. Application example , 1998, IEEE Trans. Syst. Man Cybern. Part A.

[31]  António E. Ruano,et al.  A Soft-Computing Methodology for Noninvasive Time-Spatial Temperature Estimation , 2008, IEEE Transactions on Biomedical Engineering.

[32]  A. Johnson,et al.  Automatic Segmentation of Ventricular Cerebrospinal Fluid from Ischemic Stroke CT Images , 2012, Neuroinformatics.

[33]  M. Gao,et al.  2100 POSTER Fully Automatic Segmentation of Brain Tumour in CT Images , 2011 .

[34]  D. Marquardt.  An Algorithm for Least-Squares Estimation of Nonlinear Parameters , 1963 .

[35]  Marek R. Ogiela,et al.  CAD system for automatic analysis of CT perfusion maps , 2011 .

[36]  Robert M. Haralick,et al.  Textural Features for Image Classification , 1973, IEEE Trans. Syst. Man Cybern..

[37]  N. Otsu.  A threshold selection method from gray level histograms , 1979 .

[38]  A. Padma Nanthagopal,et al.  Automatic classification of brain computed tomography images using wavelet-based statistical texture features , 2012, J. Vis..

[39]  Peter J. Fleming,et al.  Multiobjective genetic algorithms made easy: selection sharing and mating restriction , 1995 .

[40]  Corinna Cortes,et al.  Support-Vector Networks , 1995, Machine Learning.

[41]  Carlos M. Fonseca,et al.  Multiobjective genetic algorithms with application to control engineering problems. , 1995 .