Abstract
Background: Brain tumor is the leading cause of death worldwide. It is obvious that the chances of survival can be increased if the tumor is identified and properly classified at an initial stage. MRI (Magnetic Resonance Imaging) is one source of brain tumors detection tool and is extensively used in the diagnosis of brain to detect blood clots. In the past, many researchers developed Computer-Aided Diagnosis (CAD) systems that help the radiologist to detect the abnormalities in an efficient manner.
Objective: The aim of this research is to improve the brain tumor detection performance by proposing a multimodal feature extracting strategy and employing machine learning techniques.
Methods: In this study, we extracted multimodal features such as texture, morphological, entropybased, Scale Invariant Feature Transform (SIFT), and Elliptic Fourier Descriptors (EFDs) from brain tumor imaging database. The tumor was detected using robust machine learning techniques such as Support Vector Machine (SVM) with kernels: polynomial, Radial Base Function (RBF), Gaussian; Decision Tree (DT), and Naïve Bayes. Most commonly used Jack-knife 10-fold Cross- Validation (CV) was used for testing and validation of dataset.
Results: The performance was evaluated in terms of specificity, sensitivity, Positive Predictive Value (PPV), Negative Predictive Value (NPV), False Positive Rate (FPR), Total Accuracy (TA), Area under the receiver operating Curve (AUC), and P-value. The highest performance of 100% in terms of Specificity, Sensitivity, PPV, NPV, TA, AUC using Naïve Bayes classifiers based on entropy, morphological, SIFT and texture features followed by Decision Tree classifier with texture features (TA=97.81%, AUC=1.0) and SVM polynomial kernel with texture features (TA=94.63%). The highest significant p-value was obtained using SVM polynomial with texture features (P-value 2.65e-104) followed by SVM RB with texture features (P-value 1.96e-98).
Conclusion: The results reveal that Naïve Bayes followed by Decision Tree gives highest detection accuracy based on entropy, morphological, SIFT and texture features.
Keywords: Brain tumor, MRI, CAD, Support Vector Machine (SVM), decision tree, naïve bayes, morphological, entropy, Scale Invariant Feature Transform (SIFT), texture, Elliptic Fourier Descriptors (EFDs).
Graphical Abstract
[1]
Gaikwad SB, Joshi MS. Brain tumor classification using principal component analysis and probabilistic neural network. Int J Comput Appl 2015; 120: 5-9.
[2]
Rathi VPGP, Palani S. Brain tumor MRI image classification with feature selection and extration using linear discriminant analysis. Int J Comput Inf Sci Eng 2012; 2: 131-46.
[3]
Naik J, Patel S. Tumor detection and classification using decision tree in brain MRI. IJCSNS Int J Comput Sci Netw Secur 2014; 14: 87.
[5]
Prabin A, Veerappan J. Robust classification of primary brain tumor in MRI images based on multi model textures features and kernel based SVM. Biomed Pharmacol J 2015; 8: 611-8.
[6]
Li Y, Dou Q, Yu J, Jia F, Qin J, Heng P. Automatic brain tumor segmentation from MR images via a multimodal sparse coding based probabilistic model. In: International Workshop on Pattern Recognition in NeuroImaging June 2015; Stanford, CA, USA. 41-4.
[7]
Cheng J, Huang W, Cao S, et al. Enhanced performance of brain tumor classification via tumor region augmentation and partition. PLoS One 2015; 10: 1-13.
[9]
Subash N, Rajeesh J. Brain tumor classification using machine learning. Int J Circuit Theory Appl 2015; 8: 2335-41.
[10]
Jiang J, Wu Y, Huang M, Yang W, Chen W, Feng Q. 3D brain tumor segmentation in multimodal MR images based on learning population- and patient-specific feature sets. Comput Med Imaging Graph 2013; 37: 512-21.
[11]
Damodharan S, Raghavan D. Combining tissue segmentation and neural network for brain tumor detection. Int Arab J Inf 2015; 12: 42-52.
[12]
Singh A, Bajpai S, Karanam S, Choubey A, Raviteja T. Malignant brain tumor detection. Int J Comput Theory Eng 2012; 4: 1002-6.
[13]
Roopali R. Laddha DSAL. Brain tumor detection using morphological and watershed operators. Int J Appl Innov Eng Manag 2014; 3: 383-7.
[14]
Javed U, Riaz MM, Ghafoor A, Cheema TA. MRI brain classification using texture features, fuzzy weighting and support vector machine. Prog Electromagn Res B 2013; 53: 73-88.
[15]
Rajeshwari S, Sharmila TS. Efficient quality analysis of MRI image using preprocessing techniques. IEEE Conference on Information and Communication Technologies. Thuckalay, Tamil Nadu, India. 2013; pp. 391-6.
[16]
Sawakare S, Chaudhari D. Classification of brain tumor using discrete wavelet transform, principal component analysis and probabilistic neural network. Int J Res Emerg Sci Technol 2014; 1(6): 13-9.
[17]
Cheng J, Yang W, Huang M, et al. Retrieval of brain tumors by adaptive spatial pooling and fisher vector representation. PLoS One 2016; 11: 1-15.
[18]
Rathore S, Hussain M, Khan A. Automated colon cancer detection using hybrid of novel geometric features and some traditional features. Comput Biol Med 2015; 65: 279-96.
[19]
Rathore S, Hussain M, Ali A, Khan A. A recent survey on colon cancer detection techniques. IEEE/ACM Trans Comput Biol Bioinform 2013; 10: 545-63.
[20]
Rathore S, Iftikhar A, Ali A, Hussain M, Jalil A. Capture largest included circles: An approach for counting red blood cells. Commun Comput Inf Sci 2012; 281: 373-84.
[21]
Rathore S, Hussain M, Aksam IM, Jalil A. Ensemble classification of colon biopsy images based on information rich hybrid features. Comput Biol Med 2014; 47: 76-92.
[22]
Hussain L, Ahmed A, Saeed S, Rathore S, Ahmed I. Prostate cancer detection using machine learning techniques by employing combination of features extracting strategies. Cancer Biomarkers 2018; 21: 393-413.
[23]
Hussain L. Detecting epileptic seizure with different feature extracting strategies using robust machine learning classification techniques by applying advance parameter optimization approach. Cogn Neurodyn 2018; 12: 271-94.
[24]
Hussain L, Aziz W, Nadeem SA, Abbasi AQ. Classification of normal and pathological heart signal variability using machine learning techniques classification of normal and pathological heart signal variability using machine learning techniques. Int J Darshan Inst Eng Res Emerg Technol 2015; 3: 13-9.
[25]
Hussain L, Aziz W, Kazmi SZH, Awan IA. Classification of human faces and non faces using machine learning techniques. Int J Electron Electr Eng 2014; 2: 116-23.
[26]
Hussain L, Aziz W, Saeed S, et al. Complexity analysis of EEG motor movement with eye open and close subjects using Multiscale Permutation Entropy (MPE) technique. Biomed Res 2017; 28: 7104-11.
[27]
Hussain L, Aziz W, Alowibdi JS, et al. Symbolic time series analysis of Electroencephalographic (EEG) epileptic seizure and brain dynamics with eye-open and eye-closed subjects during resting states. J Physiol Anthropol 2017; 36: 21.
[28]
Hussain L, Aziz W. Time-frequency spatial wavelet phase coherence analysis of EEG in EC and EO during resting state. Procedia Comput Sci 2016; 95: 297-302.
[29]
Hussain L, Aziz W, Saeed S. Coupling functions between brain waves : Significance of opened / closed eyes. In: Proceedings of The 21st World Multi-Conference on Systemics, Cybernetics and Informatics (WMSCI 2017). Orlando, Florida, USA 2017; pp. 275-80.
[30]
Hussain L, Aziz W, Saeed S, et al. Complexity analysis of EEG motor movement with eye open and close subjects using multiscale permutation entropy (MPE) technique. Biomed Res 2017; 28: 7104-11.
[31]
Stankovski T, Ticcinelli V, McClintock PVE, Stefanovska A. Neural cross-frequency coupling functions. Front Syst Neurosci 2017; 11
[http://dx.doi.org/10.3389/fnsys.2017.00033]
[http://dx.doi.org/10.3389/fnsys.2017.00033]
[32]
Asim Y, Raza B, Kamran A, Saima M. A multi-modal, multi-atlas-based approach for Alzheimer detection via machine learning. Int J Imaging Syst Technol 2018; 1-11.
[33]
Zeng J, Qiao W. Support vector machine-based short-term wind power forecasting. In: IEEE/PES Power Systems Conference and Exposition; 20-23 March 2011; Phoenix, AZ; USA: 1-8.
[34]
Hussain L, Shafi I, Saeed S, et al. A radial base neural network approach for emotion recognition in human speech. Int J Comput Sci Netw Secur 2017; 17: 52-62.
[35]
Masseroli M, Bollea A, Forloni G. Quantitative morphology and shape classification of neurons by computerized image analysis. Comput Methods Programs Biomed 1993; 41: 89-99.
[36]
Li YM, Zeng XP. A new strategy for urinary sediment segmentation based on wavelet, morphology and combination method. Comput Methods Programs Biomed 2006; 84: 162-73.
[37]
Ramteke RJ. Y KM. Automatic medical image classification and abnormality detection using k- nearest neighbour. Int J Adv Comput Res 2012; 2: 190-6.
[38]
Murthy TSD, Sadashivappa G. Brain tumor segmentation using thresholding, morphological operations and extraction of features of tumor. In: International Conference on Advances in Electronics Computers and Communications 10-11 Oct 2014. Bangalore, India 2014; pp. 1-6.
[39]
Naranjo V, Lloréns R, Alca M, López-mir F. Metal artifact reduction in dental CT images using polar mathematical morphology. Comput Methods Programs Biomed 2011; 102(1): 64-74.
[40]
Trier OD, Jain AK, Taxt T. Feature extraction methods for character recognition - A survey. Patt Recog 1996; 29: 641-62.
[41]
Guru DS, Sharath YH, Manjunath S. Texture features and KNN in classification of flower images. Int J Comput Appl 2010; 2010: 21-9.
[42]
Keypoints S, Lowe DG. Distinctive image features from scale-invariant keypoints. Int J Comput Vis 2004; 60: 91-110.
[43]
Kisku DR, Rattani A, Grosso E, Tistarelli M. Face identification by SIFT-based complete graph topology.IEEE Workshop on Automatic Identification Advanced Technologies. Alghero, Italy 7-8 June 2007; pp. 63-8.
[44]
Neeru N, Kaur L. Modified SIFT descriptors for face recognition under different emotions. J Eng (United States) 2016; 2016
[http://dx.doi.org/10.1155/2016/9387545]
[http://dx.doi.org/10.1155/2016/9387545]
[45]
Luo J, Ma Y, Takikawa E, Lao S, Kawade M, Lu BL. Person-specific SIFT features for face recognition. In: IEEE International Conference on Acoustics,Speech and Signal Processing - ICASSP '07; 15-20 April 2007; Honolulu, HI; USA:. 593-6.
[46]
Brown M, Lowe DG. Automatic panoramic image stitching using invariant features. Int J Comput Vis 2007; 74: 59-73.
[47]
Cheung W, Hannarneh G. N -SIFT : N -dimensional scale invariant feature transform for matching medical images. In: 4th IEEE International Symposium on Biomedical Imaging: From Nano to Macro. 12-15 April 2007. AArlington, VA; USA: pp. 720-23
[48]
Nicoli LP, Anagnostopoulos GC. Shape-based recognition of targets in synthetic aperture radar images using elliptical fourier descriptors.Proc SPIE-Int Soc Opt Eng. 2008; 6967: pp. 1-12.
[49]
Hussain L, Aziz W. Time-frequency spatial wavelet phase coherence analysis of EEG in EC and EO during resting state. Procedia Comput Sci 2016; 95: 297-302.
[50]
Hussain L, Aziz W, Saeed S, et al. Quantifying the dynamics of electroencephalographic (EEG) signals to distinguish alcoholic and non-alcoholic subjects using an MSE based K-d tree algorithm. Biomed Eng. Biomed Tech 2018; 63(4): 481-90.
[51]
Hussain L, Aziz W, Saeed S, et al. Complexity analysis of EEG motor movement with eye open and close subjects using Multiscale Permutation Entropy (MPE) technique. Biomed Res 2017; 28: 1-8.
[52]
Rosso O a, Blanco S, Yordanova J, etal.. Wavelet entropy: A new tool for analysis of short duration brain electrical signals. J Neurosci Methods 2001; 105: 65-75.
[53]
Wang D, Miao D, Xie C. Best basis-based wavelet packet entropy feature extraction and hierarchical EEG classification for epileptic detection. Expert Syst Appl 2011; 38: 14314-20.
[54]
Bhattacharyya A, Pachori RB, Upadhyay A, Acharya UR. Tunable-Q wavelet transform based multiscale entropy measure for automated classification of epileptic EEG signals. Appl Sci 2017; 7: 1-18.
[55]
Mendes A, Hoeberechts M, Albu AB. Evolutionary computational methods for optimizing the classification of sea stars in underwater images. In: IEEE Winter Applications and Computer Vision Workshops; 6-9 Jan 2015; Waikoloa, HI; USA:. 44-50.
[56]
Polat K, Güneş S. Classification of epileptiform EEG using a hybrid system based on decision tree classifier and fast Fourier transform. Appl Math Comput 2007; 187: 1017-26.
[57]
Krizhevsky A, Sutskever I, Hinton GE. ImageNet classification with deep convolutional neural networks. Adv Neural Inf Process Syst 2012; 25(2): 1-9.
[58]
Bosch A, Zisserman A, Munoz X. Image Classification using random forests and ferns.IEEE 11th International Conference on Computer Vision; 14-21 Oct 2007; Rio de Janeiro, Brazil. 1-8.
[59]
Coudray N, Ocampo PS, Sakellaropoulos T, et al. Classification and mutation prediction from non-small cell lung cancer histopathology images using deep learning. Nat Med 2018; 24(10): 1559-67.
[60]
Subasi A, Erçelebi E. Classification of EEG signals using neural network and logistic regression. Comput Methods Programs Biomed 2005; 78: 87-99.
[61]
Obermaier B, Guger C, Neuper C, Pfurtscheller G. Hidden Markov models for online classification of single trial EEG data. Patt Recognit Lett 2001; 22: 1299-309.
[62]
Sivakumaran N, Sathish E, Radhakrishnan R. Importance of classification algorithms in epileptic seizure detection. J Bioeng Biomed Sci 2016; 6(3): 1-2.
[63]
Hassan AR, Bashar SK, Imamul M, Bhuiyan H. Automatic classification of sleep stages from single-channel electroencephalogram automatic classification of sleep stages from single-channel electroencephalogram. Annual IEEE India Conference (INDICON). New Delhi, India. 2015; pp. 1-6.
[64]
Chen DR, Chang RF, Chen CJ, et al. Classification of breast ultrasound images using fractal feature. Clin Imaging 2005; 29: 235-45.
[65]
Roebuck A, Clifford GD. Comparison of standard and novel signal analysis approaches to obstructive sleep apnea classification. Front Bioeng Biotechnol 2015; 3: 114.
[66]
Mougiakakou SG, Valavanis I, Nikita KS, Nikita A, Kelekis D. Characterization of CT liver lesions based on texture features and a multiple neural network classification scheme. In: Proceedings of the 25th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (IEEE Cat No03CH37439); 17- 21 Sept 2003; Cancun; Mexico: . 1287-90.
[67]
Mishra S, Panda M. A Histogram-based classification of image database using scale invariant features. Int J Image Graph Signal Process 2017; 9: 55-64.
[68]
Chernbumroong S, Atkins AS, Yu H, Mai C. Activity classification using a single wrist-worn accelerometer. In: 5th International Conference on Software, Knowledge Information, Industrial Management and Applications (SKIMA) Proceedings; 8-11 Sept 2011; Benevento; Italy;. 1-6.1-6.
[69]
Li Y, Wee CY, Jie B, Peng Z, Shen D. Sparse multivariate autoregressive modeling for mild cognitive impairment classification. Neuroinformatics 2014; 12: 455-69.
[70]
AlZoubi O, Koprinska I, Calvo RA. Classification of brain-computer interface data. Conf Res Pract Inf Technol Ser 2008; 87: 123-31.
[71]
Chandaka S, Chatterjee A, Munshi S. Cross-correlation aided support vector machine classifier for classification of EEG signals. Expert Syst Appl 2009; 36: 1329-36.
[72]
Zacharaki EI, Wang S, Chawla S, et al. Classification of brain tumor type and grade using MRI texture and shape in a machine learning scheme. Magn Reson Med 2009; 62: 1609-18.
[73]
Mu T, Nandi AK, Rangayyan RM. Classification of breast masses using selected shape, edge-sharpness, and texture features with linear and kernel-based classifiers. J Digit Imaging 2008; 21: 153-69.
[74]
Subasi A. Classification of EMG signals using PSO optimized SVM for diagnosis of neuromuscular disorders. Comput Biol Med 2013; 43: 576-86.
[75]
Fabien Lotte, Marco Congedo, Anatole Lécuyer, Fabrice Lamarche, Bruno Arnaldi. A review of classification algorithms for EEG-based brain–computer interfaces. J Neur Eng 2007; 4: 24.
[76]
Karahaliou AN, Boniatis IS, Skiadopoulos SG, et al. Breast cancer diagnosis: Analyzing texture of tissue surrounding microcalcifications. IEEE Trans Inf Technol Biomed 2008; 12: 731-8.
[77]
Sahiner B, Chan HP, Petrick N, Helvie MA, Hadjiiski LM. Improvement of mammographic mass characterization using spiculation measures and morphological features. Med Phys 2001; 28: 1455-65.
[78]
Kupinski MA, Giger ML. Automated seeded lesion segmentation on digital mammograms. IEEE Trans Med Imaging 1998; 17: 510-7.
[79]
Zheng L, Chan AK. An artificial intelligent algorithm for tumor detection in screening mammogram. IEEE Trans Med Imaging 2001; 20: 559-67.
[80]
Rathore S, Hussain M, Khan A. Automated colon cancer detection using hybrid of novel geometric features and some traditional features. Comput Biol Med 2015; 65: 279-96.
[81]
Burges CJC. A tutorial on support vector machines for pattern recognition. Data Min Knowl Discov 1998; 2: 121-67.
[82]
Laura A, Rouslan A. Support Vector Machines (SVM) as a technique for solvency analysis, 2008. Available from: https://www.econstor.eu/dspace/handle/10419/27334
[83]
Vempati S, Vedaldi A, Zisserman A, Jawahar CV. Generalized RBF feature maps for Efficient Detection.Proc Br Mach Vis Conf 2010 2010. 2.1-2.11.
[84]
Huang FJ, LeCun Y. Large-scale learning with SVM and convolutional nets for generic object categorization. Proc IEEE Comput Soc Conf Comput Vis Pattern Recognit 2006; 1: 284-91.
[85]
Übeyli ED. Least squares support vector machine employing model-based methods coefficients for analysis of EEG signals. Expert Syst Appl 2010; 37: 233-9.
[86]
Bengio Y. LeCun Y, Lecun Y Scaling learning algorithms towards AI. Large Scale Kernel Mach 2007; pp. 321-60.
[87]
Erfani SM, Baktashmotlagh M, Rajasegarar S, Karunasekera S, Leckie C. R1SVM: A randomised nonlinear approach to large-scale anomaly detection.Proc Natl Conf Artif Intell 2015; 1. 432-8.
[88]
John P. Brain tumor classification using wavelet and texture based neural network. Int J Sci Eng Res 2012; 3: 1-7.
[89]
Science C, Studies M. Calculation using median filter. K-Means, SVM and Naïve 2014; pp. 285-90.
[90]
Rajendran P, Madheswaran M. Hybrid Medical Image Classification Using Association Rule Mining with Decision Tree Algorithm. J Comput 2010; 2: 2151-9617.
[91]
Deivamani M, Kannan A. A Multi Agent Approach for Texture Based Classification and Retrieval (MATBCR) using binary decision tree 2004; 2: 13-
2924 .
[92]
Varsha YVS, Shyry SP. A novel approach for identifying the stages of brain tumor 2014; 10: 92-6.
[94]
Dan L, Lihua L, Zhaoxin Z. Research of text categorization on Weka. roceedings of International Conference on Intelligent System Design and Engineering Applications; 2013; Hong Kong;1129-31.
[95]
Angel M, Jim A, Fernando D, Ad J, Fern P, Mara HG. A bayesian model for brain tumor classification using clinical-based 1. Int Conf Image Process 2014; 2014: 2779-83.
[96]
Figueiredo JJS de, Oliveira F, Esmi E, et al. Automatic detection and imaging of diffraction points using pattern recognition. Geophys Prospect 2013; 61: 368-79.
[97]
Fang X. Inference-based naïve bayes: Turning naïve bayes cost-sensitive. IEEE Trans Knowledg Data Eng 2013; 25: 2302-14.
[98]
Huang T, Weng RC, Lin C. Generalized bradley-terry models and multi-class probability estimates. J Mach Learn Res 2006; 7: 85-115.
[99]
Zhang J, Chen C, Xiang Y, Zhou W, Xiang Y. Internet Traffic Classification by Aggregating Correlated Naive Bayes Predictions. IEEE Trans Inf Forensics Secur 2013; 8: 5-15.
[100]
Zaidi NA, Du Y, Webb GI. On the effectiveness of discretizing quantitative attributes in linear classifiers. J Mach Learn Res 2017; 1: 1-28.
[101]
Chen C, Zhang G, Yang J, Milton JC, Alcántara AD. An explanatory analysis of driver injury severity in rear-end crashes using a decision table/Naïve Bayes (DTNB) hybrid classifier. Accid Anal Prev 2016; 90: 95-107.
[102]
Bermejo P, Gámez JA, Puerta JM. Knowledge-based systems speeding up incremental wrapper feature subset selection with Naive Bayes classifier. Knowledge-Based Syst 2014; 55: 140-7.
Article Metrics
40
5