# Multi-Class Disease Classification in Brain MRIs Using a Computer-Aided Diagnostic System

^{1}

^{2}

^{3}

^{4}

^{5}

^{*}

## Abstract

**:**

## 1. Introduction

## 2. Materials and Methods

#### 2.1. Dataset Collection

^{3}), Rect. FOV: 256/256, TR: 9.7 (ms), TE: 4.0 (ms), TI: 20.0 (ms), and flip angle: ${10}^{\circ}$. The dimensions of the image are $256\times 256$ in a plane-resolution. Three hundred and ten patients’ (men and women) brain MRI scans were involved to formulate this database.

#### 2.2. Master Feature Extraction

#### 2.3. Preparation of the Principal Feature Vector

#### 2.3.1. Feature Subset Sizes

#### 2.4. Classifier Models

#### 2.4.1. J48 Classifier (J48)

#### 2.4.2. K-Nearest Neighbor (kNN)

#### 2.4.3. Random Forest (RF)

#### 2.4.4. Least Squares-Support Vector Machine (LS-SVM)

#### 2.5. Performance Measures

- TP (True Positive): Number of images correctly diagnosed under any specific class;
- TN (True Negative): Number of images correctly rejected by the classifier;
- FP (False Positive): Number of images incorrectly identified by the classifier;
- FN (False Negative): Number of images incorrectly discarded by the classifier.

**Recall**is the average of the each class recall (i.e., the probability of the test finding the positive cases among all the positive cases of the respective class):_{M}$$Recal{l}_{M}\text{}=\frac{{\displaystyle \sum _{i\text{}=\text{}1}^{C}\text{}\frac{T{P}_{i}}{T{P}_{i}+F{N}_{i}}}}{C}$$**Precision**is the average of the each class precision (i.e., the probability of the test correctly diagnosed as positive cases given that the number of cases labelled by the system as positive):_{M}$$Precisio{n}_{M}=\frac{{\displaystyle \sum _{i\text{}=\text{}1}^{C}\text{}\frac{T{P}_{i}}{T{P}_{i}+F{P}_{i}}}}{C}$$**F-Measure**(macro-averaged F-measure) is a weighted combination of the $Recal{l}_{M}$ and $Precisio{n}_{M}$. Mathematically, it is defined as:_{M}$${\mathit{\text{F-Measure}}}_{M}=\frac{\left({\beta}^{2}+1\right)\text{}Recal{l}_{M}\times \text{}Precisio{n}_{M}}{{\beta}^{2}\text{}Precisio{n}_{M}+Recal{l}_{M}}$$**Average Accuracy**is the fraction of test results predicted as correct among all the classes:$$Accurac{y}_{Avg}=\frac{{\displaystyle \sum _{i\text{}=\text{}1}^{C}\text{}\frac{T{P}_{i}+T{N}_{i}}{T{P}_{i}+F{N}_{i}+T{N}_{i}+F{P}_{i}}}}{C}$$**Area under the ROC curve (AUC)**is the area occupied by the receiver operating characteristic curve of each class. It is used to analyse how good any classification model predicts the specific class versus all other classes:$$AUC\text{}=\frac{1}{2}\left(\frac{TP}{TP+FN}+\frac{TN}{TN+FP}\right)$$

#### 2.6. Experimental Setup

## 3. Results and Discussion

#### 3.1. Feature Reduction

#### 3.2. Performance Evaluation

_{M}values greater than 81% for any number of principal components were used. To observe the effect of the feature subset sizes, the results indicate that the LS-SVM (RBF) classifier model produced fixed 86% recall

_{M}without dependence on feature subset sizes. However, RF and J48 models increase recall

_{M}values as the number of principal feature subset sizes increase and the attained macro-averaged recall values increase to 96% and 87%, respectively, whereas the remaining classifier models (kNN and LS-SVM (Poly)) were not able to increase their performance in terms of recall

_{M}.

_{M}greater than 90% for all five classifier models. However, the RF model outperformed and achieved precision

_{M}values up to 96% using a feature subset size of 20. The lowest precision

_{M}was observed in LS-SVM (Poly) for any number of given principal features.

_{M}generally exceeded 90% for RF and J48 when feature subset size used 10 or more. However, LS-SVM (RBF) achieved 90% F-measure

_{M}values for any combination of feature subsets. Furthermore, kNN and LS-SVM (Poly) could not able to improve the efficiency significantly in terms of F-measure

_{M}even the number of features was increased.

_{M}, recall

_{M}, F-measure

_{M}, and AUC. On the other hand, the overall comparison also reveals that LS-SVM (RBF) achieved significant performance regardless of the feature set size. LS-SVM (RBF) achieved a constant performance trend for any number of principal features used, which leads to a decrease in the computational time and complexity of the multi-class classifier.

#### 3.3. Comparison with Existing State-of-the-Art Classification Schemes

## 4. Conclusions

## Acknowledgments

## Author Contributions

## Conflicts of Interest

## References

- McKhann, G.; Drachman, D.; Folstein, M.; Katzman, R.; Price, D.; Stadlan, E.M. Clinical diagnosis of Alzheimer’s disease report of the nincds-adrda work group* under the auspices of department of health and human services task force on Alzheimer’s disease. Neurology
**1984**, 34, 939. [Google Scholar] [CrossRef] [PubMed] - Sahu, O.; Anand, V.; Kanhangad, V.; Pachori, R.B. Classification of magnetic resonance brain images using bi-dimensional empirical mode decomposition and autoregressive model. Biomed. Eng. Lett.
**2015**, 5, 311–320. [Google Scholar] [CrossRef] - Prasad, P.V. Magnetic Resonance Imaging: Methods and Biologic Applications; Springer Science & Business Media: New York, NY, USA, 2006; Volume 124. [Google Scholar]
- Maji, P.; Chanda, B.; Kundu, M.K.; Dasgupta, S. Deformation correction in brain MRI using mutual information and genetic algorithm. In Proceedings of the International Conference on Computing: Theory and Applications, Kolkata, India, 5–7 March 2007; pp. 372–376.
- Scapaticci, R.; Di Donato, L.; Catapano, I.; Crocco, L. A feasibility study on microwave imaging for brain stroke monitoring. Prog. Electromagn. Res. B Pier B
**2012**, 40, 305–324. [Google Scholar] [CrossRef] - Siddiqui, M.F.; Reza, A.W.; Kanesan, J. An automated and intelligent medical decision support system for brain MRI scans classification. PLoS ONE
**2015**, 10, e0135875. [Google Scholar] - Mujtaba, G.; Shuib, L.; Raj, R.G.; Rajandram, R.; Shaikh, K. Automatic text classification of ICD-10 related CoD from complex and free text forensic autopsy reports. In Proceedings of the 5th IEEE International Conference on Machine Learning and Applications (ICMLA), Anaheim, CA, USA, 18–20 December 2016; pp. 1055–1058.
- Mujtaba, G.; Shuib, L.; Raj, R.G.; Rajandram, R.; Shaikh, K.; Al-Garadi, M.A. Automatic ICD-10 multi-class classification of cause of death from plaintext autopsy reports through expert-driven feature selection. PLoS ONE
**2017**, 12, e0170242. [Google Scholar] [CrossRef] [PubMed] - Jin, Y.; Wee, C.Y.; Shi, F.; Thung, K.H.; Ni, D.; Yap, P.T.; Shen, D. Identification of infants at high-risk for autism spectrum disorder using multiparameter multiscale white matter connectivity networks. Hum. Brain Mapp.
**2015**, 36, 4880–4896. [Google Scholar] [CrossRef] - Huang, L.; Jin, Y.; Gao, Y.; Thung, K.-H.; Shen, D.; Initiative, A.S.D.N. Longitudinal clinical score prediction in Alzheimer’s disease with soft-split sparse regression based random forest. Neurobiol. Aging
**2016**, 46, 180–191. [Google Scholar] [CrossRef] [PubMed] - Mwangi, B.; Ebmeier, K.P.; Matthews, K.; Steele, J.D. Multi-centre diagnostic classification of individual structural neuroimaging scans from patients with major depressive disorder. Brain
**2012**, 135, 1508–1521. [Google Scholar] [CrossRef] [PubMed] - Klöppel, S.; Stonnington, C.M.; Barnes, J.; Chen, F.; Chu, C.; Good, C.D.; Mader, I.; Mitchell, L.A.; Patel, A.C.; Roberts, C.C. Accuracy of dementia diagnosis—A direct comparison between radiologists and a computerized method. Brain
**2008**, 131, 2969–2974. [Google Scholar] [CrossRef] [PubMed] - Faisal, A.; Parveen, S.; Badsha, S.; Sarwar, H.; Reza, A.W. Computer assisted diagnostic system in tumor radiography. J. Med. Syst.
**2013**, 37. [Google Scholar] [CrossRef] [PubMed] - Zhang, Y.; Wu, L.; Wang, S. Magnetic resonance brain image classification by an improved artificial bee colony algorithm. Prog. Electromagn. Res. Pier
**2011**, 116, 65–79. [Google Scholar] [CrossRef] - Zhang, Y.; Dong, Z.; Wu, L.; Wang, S. A hybrid method for MRI brain image classification. Expert Syst. Appl.
**2011**, 38, 10049–10053. [Google Scholar] [CrossRef] - Zhang, Y.; Wu, L. An MR brain images classifier via principal component analysis and kernel support vector machine. Prog. Electromagn. Res. Pier
**2012**, 130, 369–388. [Google Scholar] [CrossRef] - Zhang, Y.; Wang, S.; Ji, G.; Dong, Z. An MR brain images classifier system via particle swarm optimization and kernel support vector machine. Sci. World J.
**2013**, 2013. [Google Scholar] [CrossRef] [PubMed] - El-Dahshan, E.-S.A.; Hosny, T.; Salem, A.-B.M. Hybrid intelligent techniques for MRI brain images classification. Digit. Signal Process.
**2010**, 20, 433–441. [Google Scholar] [CrossRef] - El-Dahshan, E.-S.A.; Mohsen, H.M.; Revett, K.; Salem, A.-B.M. Computer-aided diagnosis of human brain tumor through MRI: A survey and a new algorithm. Expert Syst. Appl.
**2014**, 41, 5526–5545. [Google Scholar] [CrossRef] - Das, S.; Chowdhury, M.; Kundu, M.K. Brain MR image classification using multiscale geometric analysis of Ripplet. Prog. Electromagn. Res. Pier
**2013**, 137, 1–17. [Google Scholar] [CrossRef] - Zhang, Y.; Dong, Z.; Wang, S.; Ji, G.; Yang, J. Preclinical diagnosis of magnetic resonance (MR) brain images via discrete wavelet packet transform with Tsallis entropy and generalized eigenvalue proximal support vector machine (GEPSVM). Entropy
**2015**, 17, 1795–1813. [Google Scholar] [CrossRef] - Zhou, X.; Wang, S.; Xu, W.; Ji, G.; Phillips, P.; Sun, P.; Zhang, Y. Detection of pathological brain in MRI scanning based on wavelet-entropy and naive Bayes classifier. In Proceedings of the Bioinformatics and Biomedical Engineering, Granada, Spain, 15–17 April 2015; pp. 201–209.
- Wang, S.; Lu, S.; Dong, Z.; Yang, J.; Yang, M.; Zhang, Y. Dual-tree complex wavelet transform and twin support vector machine for pathological brain detection. Appl. Sci.
**2016**, 6, 169. [Google Scholar] [CrossRef] - Zacharaki, E.I.; Wang, S.; Chawla, S.; Soo Yoo, D.; Wolf, R.; Melhem, E.R.; Davatzikos, C. Classification of brain tumor type and grade using MRI texture and shape in a machine learning scheme. Magn. Reson. Med.
**2009**, 62, 1609–1618. [Google Scholar] [CrossRef] [PubMed] - Chaplot, S.; Patnaik, L.; Jagannathan, N. Classification of magnetic resonance brain images using wavelets as input to support vector machine and neural network. Biomed. Signal Process. Control
**2006**, 1, 86–92. [Google Scholar] [CrossRef] - Zhang, Y.; Wang, S.; Wu, L. A novel method for magnetic resonance brain image classification based on adaptive chaotic pso. Prog. Electromagn. Res. Pier
**2010**, 109, 325–343. [Google Scholar] [CrossRef] - Maitra, M.; Chatterjee, A. A slantlet transform based intelligent system for magnetic resonance brain image classification. Biomed. Signal Process. Control
**2006**, 1, 299–306. [Google Scholar] [CrossRef] - Lustig, M.; Donoho, D.L.; Santos, J.M.; Pauly, J.M. Compressed sensing MRI. IEEE Signal Process. Mag.
**2008**, 25, 72–82. [Google Scholar] [CrossRef] - Blum, A.L.; Langley, P. Selection of relevant features and examples in machine learning. Artif. Intell.
**1997**, 97, 245–271. [Google Scholar] [CrossRef] - Kohavi, R.; John, G.H. Wrappers for feature subset selection. Artif. Intell.
**1997**, 97, 273–324. [Google Scholar] [CrossRef] - Wettschereck, D.; Aha, D.W.; Mohri, T. A review and empirical evaluation of feature weighting methods for a class of lazy learning algorithms. Artif. Intell. Rev.
**1997**, 11, 273–314. [Google Scholar] [CrossRef] - Sengur, A. An expert system based on principal component analysis, artificial immune system and fuzzy k-NN for diagnosis of valvular heart diseases. Comput. Biol. Med.
**2008**, 38, 329–338. [Google Scholar] [CrossRef] [PubMed] - Duda, R.O.; Hart, P.E.; Stork, D.G. Pattern Classification; John Wiley & Sons: New York, NY, USA, 2012. [Google Scholar]
- Zhao, Y.; Zhang, Y. Comparison of decision tree methods for finding active objects. Adv. Space Res.
**2008**, 41, 1955–1959. [Google Scholar] [CrossRef] - Bao, Y.; Ishii, N.; Du, X. Combining multiple k-nearest neighbor classifiers using different distance functions. In Proceedings of the International Conference on Intelligent Data Engineering and Automated Learning, Exeter, UK, 25–27 August 2004; pp. 634–641.
- Fukunaga, K. Introduction to Statistical Pattern Recognition; Academic Press: Salk Lake City, UT, USA, 2013. [Google Scholar]
- Breiman, L. Random forests. Mach. Learn.
**2001**, 45, 5–32. [Google Scholar] [CrossRef] - Liaw, A.; Wiener, M. Classification and regression by random forest. R News
**2002**, 2, 18–22. [Google Scholar] - Vapnik, V. The Nature of Statistical Learning Theory; Springer Science & Business Media: New York, NY, USA, 2013. [Google Scholar]
- Patil, N.; Shelokar, P.; Jayaraman, V.; Kulkarni, B. Regression models using pattern search assisted least square support vector machines. Chem. Eng. Res. Des.
**2005**, 83, 1030–1037. [Google Scholar] [CrossRef] - Wang, F.-F.; Zhang, Y.-R. The support vector machine for dielectric target detection through a wall. Prog. Electromagn. Res. Pier Lett.
**2011**, 23, 119–128. [Google Scholar] [CrossRef] - Chen, G.-C.; Juang, C.-F. Object detection using color entropies and a fuzzy classifier. IEEE Comput. Intell. Mag.
**2013**, 8, 33–45. [Google Scholar] [CrossRef] - Magalhães, F.; Sousa, R.; Araújo, F.M.; Correia, M.V. Compressive sensing based face detection without explicit image reconstruction using support vector machines. In Proceedings of the 10th International Conference on Image Analysis and Recognition, Berlin, Germany, 26–28 June 2013; pp. 758–765.
- Dasgupta, J.; Bhattacharya, K.; Chanda, B. A holistic approach for off-line handwritten cursive word recognition using directional feature based on arnold transform. Pattern Recogn. Lett.
**2016**, 79, 73–79. [Google Scholar] [CrossRef] - Komiyama, Y.; Banno, M.; Ueki, K.; Saad, G.; Shimizu, K. Automatic generation of bioinformatics tools for predicting protein–ligand binding sites. Bioinformatics
**2015**, 32, 901–907. [Google Scholar] [CrossRef] [PubMed] - Cristianini, N.; Shawe-Taylor, J. An introduction to SVM; Cambridge University Press: Cambridge, UK, 1999. [Google Scholar]
- Suykens, J.A.; Vandewalle, J. Least squares support vector machine classifiers. Neural Process. Lett.
**1999**, 9, 293–300. [Google Scholar] [CrossRef] - Van Gestel, T.; Suykens, J.A.; Baesens, B.; Viaene, S.; Vanthienen, J.; Dedene, G.; De Moor, B.; Vandewalle, J. Benchmarking least squares support vector machine classifiers. Mach. Learn.
**2004**, 54, 5–32. [Google Scholar] [CrossRef] - Sokolova, M.; Lapalme, G. A systematic analysis of performance measures for classification tasks. Inf. Process. Manag.
**2009**, 45, 427–437. [Google Scholar] [CrossRef]

**Figure 2.**The sample images of healthy and abnormal magnetic resonance imaging (MRI) (

**a**) normal/healthy; (

**b**) Alzheimer’s disease; (

**c**) AIDS dementia; (

**d**) cerebral calcinosis; (

**e**) glioma; and (

**f**) metastatic dementia.

**Figure 3.**Performance measures of the proposed multi-class classifiers: (

**a**) macro-averaged recall; (

**b**) macro-averaged precision; (

**c**) macro-averaged f-measure; and (

**d**) average accuracy.

**Figure 4.**Area under the receiver operating characteristic (ROC) curve for each class: (

**a**) normal; (

**b**) Alzheimer; (

**c**) AIDS; (

**d**) cerebral calcinosis; (

**e**) glioma; and (

**f**) metastasis.

Class | Total No. of Images | Total No. of Training Images | Total No. of Testing Images | Distribution (%) |
---|---|---|---|---|

Normal | 70 | 49 | 21 | 22.58 |

Alzheimer | 70 | 49 | 21 | 22.58 |

Aids | 50 | 35 | 15 | 16.13 |

Cerebral Calcinosis | 40 | 28 | 12 | 12.90 |

Glioma | 40 | 28 | 12 | 12.90 |

Metastasis | 40 | 28 | 12 | 12.90 |

Kernel | Expression |
---|---|

Linear | $K(x,y)={x}^{T}y$ |

Polynomial | $K(x,y)={\left(1+\frac{{x}^{T}y}{{\sigma}^{2}}\right)}^{d}$ |

RBF | $K(x,y)=\mathrm{exp}\text{}\left\{-\frac{{\Vert x-y\Vert}^{2}}{{\sigma}^{2}}\right\}$ |

© 2017 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license ( http://creativecommons.org/licenses/by/4.0/).

## Share and Cite

**MDPI and ACS Style**

Siddiqui, M.F.; Mujtaba, G.; Reza, A.W.; Shuib, L.
Multi-Class Disease Classification in Brain MRIs Using a Computer-Aided Diagnostic System. *Symmetry* **2017**, *9*, 37.
https://doi.org/10.3390/sym9030037

**AMA Style**

Siddiqui MF, Mujtaba G, Reza AW, Shuib L.
Multi-Class Disease Classification in Brain MRIs Using a Computer-Aided Diagnostic System. *Symmetry*. 2017; 9(3):37.
https://doi.org/10.3390/sym9030037

**Chicago/Turabian Style**

Siddiqui, Muhammad Faisal, Ghulam Mujtaba, Ahmed Wasif Reza, and Liyana Shuib.
2017. "Multi-Class Disease Classification in Brain MRIs Using a Computer-Aided Diagnostic System" *Symmetry* 9, no. 3: 37.
https://doi.org/10.3390/sym9030037