Brain tumor detection using statistical and machine learning method
Introduction
The brain is a complex human body organ and works through billions of cells. Brain tumors are caused due to the uncontrolled growth of cells. These cells might affect normal brain activities and also destroy normal cells [1], [2]. Gliomas are a primary type of brain tumors. It contains IV grades (I, II: High Grade (HG) and III, IV: Low Grade (LG)) [3]. Despite major developments in the medical field like surgical procedure, chemotherapy and radiotherapy, still malignant brain tumor cases are untreatable. According to reports, brain tumor is the 5th primary reason for the death of women from twenty to thirty nine years [4].
MRI is particularly helpful to validate gliomas because it gives detailed structure about the human brain [5]. For the brain analysis, T1c, Tl, Flair and T2 are the most commonly used MRI sequences. These sequences provide different information related to the brain tumor. MRI test is based on radio frequency (RF) in which time of repetition (TR) and time of echo (TE) is calculated. T1c and T1 MRI are produced through short TR and TE time and cerebrospinal fluid (CSF) is dark in these sequences. CSF is colorless found in brain/ spinal cord. T2 MRI is produced by larger TR and TE time; therefore, CSF is bright in this modality. Flair is produced through very large TR and TE time; hence abnormal region remains bright and CSF is dark [6]. T2 is more sensitive to water content and more suitable for the abnormal region where water accumulates inside tissues of the brain. Flair provides more clear differentiation between the abnormal region and CSF as compared to other modalities (Fig. 1).
For brain tumor detection, accurate segmentation is a crucial process. The manual segmentation is time consuming for the radiologist [7] and hence, automated/ semi-automated techniques are required for precise tumor detection [8], [9]. Nowadays fully automated methods [10] for classification between the tumor and non-tumor MRI [11] are common for clinical and research studies. These methods can provide more help to analyze the tumor region [12] and are developed rapidly in the last ten years [13]. Therefore, radiologists assume that computerized methods can improve their diagnosis abilities on the basis of automated machine learning methods [14], [15], [16], [17]. Despite more efforts and promising outcomes in medical images analysis, still reproducible and correct segmentation along with abnormalities characterization is a challenging task of brain tumor detection because of its variability in location, shape and size [18], [19]. Presenting an automated method to increase tumor detection performance is a motivation of this work. The contributions are as follows:
- 1.
Lesion enhancement: Weiner Filter in wavelet domain is employed for noise removal and to enhance lesion region.
- 2.
Lesion segmentation: PF clustering method is applied to find out the subset of tumor pixels. Moreover, the global threshold method is used for lesion segmentation. Finally, mathematical morphology is applied for refining the tumor segmentation results.
- 3.
Feature extraction: In this phase, GWT and LBP features are obtained through every segmented image and then both texture features are fused to improve discrimination results.
The paper is organized into different sections. Existing work for brain lesions is discussed in Section 2. The presented approach for tumor detection is presented in Section 3 and 4 shows the achieved outcomes. The conclusion of the presented work is defined in Section 5.
Section snippets
Related work
In the past, many approaches are proposed for the detection of tumor using MRI. Abbasi and Tajeripour [20] suggested a method in which preprocessing is performed using histogram matching and bias field correction. Various machine learning techniques are also used for tumor detection using MRI [21], [22] including k-means, Fuzzy C-Means (FCM), thresholding, kernel extreme learning machine (KELM) and level set methods. Yamamoto et al. [23] proposed rule based and level set methods for tumor
Proposed methodology
The presented method for tumor detection is shown in Fig. 2. Weiner filter with different wavelet bands is used for noise reduction and to enhance the region of interest (ROI), PF clustering is applied for segmentation purpose. In addition, an optimal gray level thresholding method is also used. Different texture features are obtained from each segmented slice. Furthermore, multiple classifiers are utilized for separation of MR slices.
Experiments and results
The presented technique is checked on two publicly accessible datasets and one locally collected dataset. The local dataset contains 86 images, where 49 tumor and 37 non-tumor images were collected from Nishtar Hospital Multan, Pakistan. BRATS 2013 challenge dataset consists of thirty cases with ground truth annotations in which 20 belong to HG and 10 to LG tumors. BRATS 2015 has 273 cases in which 54 LG and 220 HG gliomas are included. Two modalities (Flair and T2) of each case are utilized
Conclusion
Detection at an early stage of brain tumor is presented in this article. The major contribution of this research work is an in-depth focus on enhancement, segmentation and features fusion process. The proposed hybrid texture features from each segmented slice are supplied to multiple classifiers for the classification of tumor /non-tumor MR slices. On the basis of detailed performance evaluation, it is confirmed that features fusion and KNN outperform as compared to other classifiers. The
Conflict of interest
None.
References (44)
- et al.
Application of deep transfer learning for automated brain abnormality classification using MR images
Cognit. Syst. Res.
(2019) Computer-aided diagnosis: the emerging of three CAD systems induced by Japanese health care needs
Comput. Methods Programs Biomed.
(2008)- et al.
Big data analysis for brain tumor detection: deep convolutional neural networks
Future Gener. Comput. Syst.
(2018) - et al.
Segmentation of glioblastoma multiforme from MR images–A comprehensive review
Egypt. J. Radiol. Nuclear Med.
(2015) - et al.
Detection of brain tumor in 3D MRI images using local binary patterns and histogram orientation gradient
Neurocomputing
(2017) - et al.
Brain tumor segmentation based on a hybrid clustering technique
Egypt. Inform. J.
(2015) Computer-aided detection of multiple sclerosis lesions in brain magnetic resonance images: false positive reduction scheme consisted of rule-based, level set method, and support vector machine
Comput. Med. ImagingGraphics
(2010)- et al.
Application of multiresolution analysis for automated detection of brain abnormality using MR images: a comparative study
Future Gener. Comput. Syst.
(2019) - et al.
Hybrid intelligent techniques for MRI brain images classification
Digital Signal Process.
(2010) Computer aided diagnosis system for Alzheimer disease using brain diffusion tensor imaging features selected by Pearson's correlation
Neurosci. Lett.
(2011)
MRI segmentation fusion for brain tumor detection
Inf. Fusion
An automated hybrid approach using clustering and nature inspired optimization technique for improved tumor and tissue segmentation in magnetic resonance brain images
Appl. Soft Comput.
Local binary features for texture classification: taxonomy and experimental study
Pattern Recognit.
Brain tumors detection and segmentation in MR images: gabor wavelet vs. statistical features
Comput. Electr. Eng.
Detection and classification of citrus diseases in agriculture based on optimized weighted segmentation and feature selection
Comput. Electron. Agric.
Glioma detection on brain MRIs using texture and morphological features with ensemble learning
Biomed. Signal Process. Control
Hierarchical brain tumour segmentation using extremely randomized trees
Pattern Recognit.
Brain tumor segmentation with deep neural networks
Medical Image Anal.
Efficient multi-scale 3D CNN with fully connected CRF for accurate brain lesion segmentation
Med. image Anal.
A deep learning model integrating FCNNs and CRFs for brain tumor segmentation
Medical Image Anal.
Dual-force convolutional neural networks for accurate brain tumor segmentation
Pattern Recognit.
Brain tumor segmentation using genetic algorithm with SVM classifier
Int. J. Adv. Res. Electr. Electron. Instrum. Eng.
Cited by (179)
A review on brain tumor segmentation based on deep learning methods with federated learning techniques
2023, Computerized Medical Imaging and GraphicsFP-CNN: Fuzzy pooling-based convolutional neural network for lung ultrasound image classification with explainable AI
2023, Computers in Biology and MedicineHOG transformation based feature extraction framework in modified Resnet50 model for brain tumor detection
2023, Biomedical Signal Processing and ControlComparing of brain tumor diagnosis with developed local binary patterns methods
2024, Neural Computing and Applications