In this paper, an Automated Brain Image Analysis (ABIA) system that classifies the Magnetic Resonance Imaging (MRI) of human brain is presented. The classification of MRI images into normal or low grade or high grade plays a vital role for the early diagnosis. The Non-Subsampled Shearlet Transform (NSST) that captures more visual information than conventional wavelet transforms is employed for feature extraction. As the feature space of NSST is very high, a statistical t-test is applied to select the dominant directional sub-bands at each level of NSST decomposition based on sub-band energies. A combination of features that includes Gray Level Co-occurrence Matrix (GLCM) based features, Histograms of Positive Shearlet Coefficients (HPSC), and Histograms of Negative Shearlet Coefficients (HNSC) are estimated. The combined feature set is utilized in the classification phase where a hybrid approach is designed with three classifiers; k-Nearest Neighbor (kNN), Naive Bayes (NB) and Support Vector Machine (SVM) classifiers. The output of individual trained classifiers for a testing input is hybridized to take a final decision. The quantitative results of ABIA system on Repository of Molecular Brain Neoplasia Data (REMBRANDT) database show the overall improved performance in comparison with a single classifier model with accuracy of 99% for normal/abnormal classification and 98% for low and high risk classification.
The brain is the primary organ of the human body. As the cause of brain cancer is still unknown, an early diagnosis is required to decrease the mortality rate. Image classification is one of the diagnostic approaches used in the medical field which does not require segmentation [
A regularized extreme learning machine is discussed in Gumaei et al. [
Though deep learning approaches provide better results, it is very difficult to understand their architectures and also time complexity is very high. To achieve highest accuracy with reduced complexity, a hybrid approach is developed in this study using three different classifiers; kNN, NB and SVM. It is well known that the hybrid approach combines the qualities of each technique and thus provides better performance than single approach.
An approach to classify brain MRI images is described in Madheswaran et al. [
The energy features of different wavelet families are discussed in Mohankumar [
In this paper, an efficient ABIA system for brain MRI image classification is presented by the use of NSST with a hybrid classification approach. Though the use of certain type of frequency domain analysis and the extraction of features for a particular classification system is not new, the salient feature of ABIA system is the extraction of combination of features (GLCM + HPSC + HNSC) from the selected NSST sub-bands at each level rather than selecting the features extracted from all NSST sub-bands. In many transformation based systems in the literature, features are extracted directly from the sub-bands [
The organization of the paper about ABIA system is as follows; the methods and materials used to develop the ABIA system for brain MRI image classification are discussed in Section 2. The next section conveys the quantitative results and the performances of ABIA system and the last section presents the conclusion of ABIA system.
The non-invasive diagnostic support system for brain cancer is considered as a two-class image classification system with two stages. At first, the given brain image is classified as Normal or Abnormal (NA Stage) and then the abnormal severity is classified as Low grade or High grade (LH Stage). Shearlet transform is analyzed well in various image processing based applications such as de-noising [
A directional representation system is employed by ABIA system due to its superior approximation performance over wavelets [
where
Let
where
The horizontal truncated cone regions (
Based on the horizontal and vertical cone regions, the Shearlet system in
where the index d is horizontal and vertical cone regions. NSST is employed in ABIA system in order to overcome lack of translation invariance of the Shearlet transform. The feature extraction stage of ABIA system is shown in
At first, the given MRI brain image is represented by NSST at various scale of decomposition. It produces various directional sub-bands and each sub-band carries significant information about the given image.
As the feature space of NSST coefficients is very high, a statistical t-test is applied to select the directional sub-bands based on their energies. For the features of two classes A and B, it is defined by
where
NSST Level | NSST Directions | ||||
---|---|---|---|---|---|
2 | 4 | 8 | 16 | 32 | |
1 | 3 | 5 | 9 | 17 | 33 |
2 | 5 | 9 | 17 | 33 | 65 |
3 | 7 | 13 | 25 | 49 | 97 |
4 | 9 | 17 | 33 | 65 | 129 |
The selected directional sub-bands are utilized for extracting features such as GLCM [
Extracted Features | Formula | Interpretation |
---|---|---|
GLCM-Homogeneity | It measures the uniformity of textures in the brain MRI images | |
GLCM-Contrast | It measures the local variance in the brain MRI images | |
GLCM-Energy | It measures the texture energy in the brain MRI images | |
GLCM-Correlation | It gives the relation between the textures in the brain MRI images | |
HNSC | Histogram of –ve Shearlet coefficients in the selected sub-band | It represents the distribution of edge information in the brain MRI images |
HPSC | Histogram of +ve Shearlet coefficients in the selected sub-band | |
The selection of good classification algorithm is also an important step to achieve higher accuracy. In the ABIA system, a hybrid classification is employed with three different classifiers; kNN, NB and SVM classifiers. The output of individual classifiers for a testing input is hybridized to take a final decision for the classification of brain cancer.
kNN [
Euclidean distance
There is no training phase in kNN. Hence, it is classified as a lazy classifier. As the computation of Euclidean distance requires all of the training objects each time, kNN requires more storage space and more calculation at the time of classification.
NB classifier [
The posterior probability defined by Bayes theory is the probability that the object belongs to
where,
In many machine learning applications, SVM classifier [
where the bias(b) and weight(w) are computed using T. The hyperplane defined in (12) separates the features in T optimally [
where the trade-off parameter (C) controls the trade-off between complexity and empirical risk.
where the support vectors are
where
The final decision of ABIA system is made from the classification results of each classifier to obtain a better decision. It combines the robustness of each classification algorithm and eliminates their drawbacks. Let
where k is the number of classifiers used. The weight of each classifier is assigned to their accuracy when using different training samples.
The performance of ABIA system to classify brain MRI images is evaluated by using the standard set of brain tumor images available in the REMBRANDT database [
The ability of ABIA system to classify all brain MRI images is measured by classification accuracy (
Performance measures | Formula | Interpretation |
---|---|---|
It measures the ability of ABIA system to classify abnormal (NA Stage)/high grade (LH Stage) brain MRI images. | ||
It measures the ability of ABIA system to classify normal (NA Stage)/low grade (LH Stage) brain MRI images. | ||
It measures the ability of ABIA system to classify total brain MRI images. | ||
NSST Level | Classifier | NSST Directions | ||||
---|---|---|---|---|---|---|
D2 | D4 | D8 | D16 | D32 | ||
L1 | 75.19 | 73.68 | 75.19 | 68.42 | 80.45 | |
NB | 74.63 | 80.60 | 82.84 | 78.36 | 76.87 | |
SVM | 84.21 | 85.71 | 89.47 | 86.47 | 85.71 | |
Hybrid | 86.50 | 88.50 | 91.00 | 88.00 | 88.00 | |
L2 | 79.70 | 80.45 | 76.69 | 75.94 | 80.45 | |
NB | 82.84 | 86.57 | 88.81 | 85.82 | 84.33 | |
SVM | 87.97 | 88.72 | 91.73 | 89.47 | 88.72 | |
Hybrid | 89.50 | 90.00 | 93.50 | 90.50 | 90.00 | |
L3 | 85.71 | 85.71 | 85.71 | 76.69 | 84.96 | |
NB | 87.31 | 90.30 | 94.78 | 93.28 | 90.30 | |
SVM | 91.73 | 93.23 | 97.74 | 94.74 | 92.48 | |
Hybrid | ||||||
L4 | 78.95 | 83.46 | 79.70 | 84.96 | 88.72 | |
NB | 85.82 | 88.81 | 93.28 | 91.79 | 88.81 | |
SVM | 90.23 | 91.73 | 96.24 | 93.99 | 90.98 | |
Hybrid | 92.00 | 93.00 | 97.00 | 94.00 | 93.00 |
It is observed that the hybrid approach gives much higher performance in L3-D8 than other combinations. Also the
NSST Level | Classifier | NSST Directions | ||||
---|---|---|---|---|---|---|
D2 | D4 | D8 | D16 | D32 | ||
L1 | 50.75 | 55.22 | 53.73 | 53.73 | 56.72 | |
NB | 70.15 | 73.13 | 76.12 | 74.63 | 73.13 | |
SVM | 78.79 | 80.30 | 83.33 | 81.82 | 80.30 | |
Hybrid | 81.00 | 85.00 | 89.00 | 87.00 | 87.00 | |
L2 | 46.27 | 49.25 | 50.75 | 55.22 | 52.24 | |
NB | 74.63 | 76.12 | 79.10 | 79.10 | 76.12 | |
SVM | 80.30 | 83.33 | 84.85 | 83.33 | 83.33 | |
Hybrid | 85.00 | 89.00 | 92.00 | 89.00 | 85.00 | |
L3 | 53.73 | 53.73 | 58.21 | 55.22 | 50.75 | |
NB | 80.60 | 82.09 | 85.07 | 80.60 | 79.10 | |
SVM | 83.33 | 84.85 | 86.36 | 84.85 | 84.85 | |
Hybrid | ||||||
L4 | 47.76 | 56.72 | 52.24 | 55.22 | 58.21 | |
NB | 76.12 | 79.10 | 82.09 | 80.60 | 76.12 | |
SVM | 80.30 | 81.82 | 83.33 | 81.82 | 80.30 | |
Hybrid | 87.00 | 90.00 | 93.00 | 89.00 | 87.00 |
It is observed from
It is observed from the performance comparisons in
Author | #Images used | Features used | Classifier used | |||
---|---|---|---|---|---|---|
Mohankumar [ |
100 | DWT | SVM | 93.5 | 95 | 92 |
Babu et al [ |
200 | Tetrolet Transform | SVM | 98 | 96 | 100 |
Ayalapogu et al [ |
200 | DTMBWT | SVM | 97.5 | 95 | 100 |
ABIA system | 200 | NSST | Hybrid |
99 | 99 | 99 |
From
In this paper, an ABIA system to classify brain MRI images is discussed. The most correlated NSST sub-band at each NSST level is selected by t-test on training data set. The ABIA system uses the combination of features that includes GLCM, HPSC, and HNSC as indicators for the characterization of brain MRI images. Then, the extracted features are trained by a hybrid classification approach that includes kNN, NB and SVM. A two two-class classification system (NA stage and LH stage) is designed to classify brain MRI images. Results show that the clinical applicability of ABIA system for brain MRI image classification with an accuracy of 99% for NA stage and 98% for LH stage using the hybrid approach.