{"id":53227,"date":"2023-12-31T11:54:19","date_gmt":"2023-12-31T11:54:19","guid":{"rendered":"https:\/\/biomedpharmajournal.org\/?p=53227"},"modified":"2024-01-05T05:51:17","modified_gmt":"2024-01-05T05:51:17","slug":"a-comprehensive-review-on-strategies-to-detect-diagnose-and-classify-brain-tumors","status":"publish","type":"post","link":"https:\/\/biomedpharmajournal.org\/staging\/vol16no4\/a-comprehensive-review-on-strategies-to-detect-diagnose-and-classify-brain-tumors\/","title":{"rendered":"A Comprehensive Review on Strategies to Detect, Diagnose and Classify Brain Tumors"},"content":{"rendered":"\n

Introduction<\/strong><\/p>\n\n\n\n

A tumor is an aberrant mass of tissue caused by\nunrestrained cell proliferation and multiplication 1<\/sup>. There are hundreds of different types of tumors. They can start in\nany of the trillion cells in our body. The name of tumor is reflected by the\ntype of tissue they stem from such as brain tumor, lung tumor, breast cancer,\novarian tumor, etc. 2<\/sup>. Human brain is the most important organ in the body. It is often\nrecognized as the human body’s regulating point. The brain is in charge of\nalmost every critical activity inside the human body. Feelings, motion,\nintellect, speech, cognition, senses, reasoning, physical activity, taste, and\ncreativity are all controlled by the brain 3<\/sup>. As a result, any mishap or impairment to this crucial organ will\ndisrupt the human body’s usual working and result in an aberrant routine. It is\ntherefore crucial\nto take the best\npossible care of this priceless organ.<\/p>\n\n\n\n

The most prevalent\nand life-threatening illness that affects the brain these days is a brain tumor.\nIt impacts both children and adults. Tumors can be malignant (cancerous) or\nbenign (noncancerous). Tumors can also be classified as primary or secondary\nbrain tumors. The characteristics of different types of tumors are shown in\nFig. 1.<\/p>\n\n\n\n

All the tumors\nare classified on the basis of a standard created by the World Health\nOrganization (WHO) into four kinds: Gliomas, meningiomas, pituitary adenomas,\nand nerve sheath tumors 4<\/sup>. Tumors are named on the basis of the cells where they stem. Each\nof these categories is classified using a grading system, having a grading\nscale ranging from Grade I to IV. This grading standard is divided into benign\nand malignant tumors. Low-level tumors are classified as Grade I and II,\nwhereas high-level tumors are classified as Grade III and IV. Grade I and II\ntumors comprise slow-growing cells that are generally not cancerous and are typically\nfollowed by long-lived survival of the affected individual 4<\/sup>. Grade III and Grade IV tumors comprise rapidly growing cells that\nare generally cancerous and termed as malignant. These tumors can invade and\ndisrupt the nearby healthy tissues of the brain 4<\/sup>. The features of different grades of tumors are shown in Fig. 2.\nBecause of the complexity of the brain anatomy, the overall influence of brain\ntumors on an individual can vary a lot as well as the repercussions may not be\nthe same. Thus, it is much more vital to prepare a plan for treatment and\nforecast the patient’s reaction when treating a brain tumor at a preliminary\nstage 5<\/sup>.<\/p>\n\n\n\n\n\n
\"\"<\/td>\n\n

Figure <\/strong>1<\/strong>: The different classifications of brain tumors.<\/strong><\/p>\n

<\/p>\n

Click here to view Figure<\/a><\/p>\n<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n\n\n\n
\"\"<\/td>\n\n

Figure 2: The grading of brain tumors.<\/strong><\/p>\n

<\/p>\n

Click here to view Figure<\/a><\/p>\n<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n\n\n

Cancer and its associated repercussions\nhave a significant impact on public health. Years of life lost owing to\npremature deaths, economic expenditures connected with disease and treatments,\nand the long-term impact of cancer and its treatment on the quality of life of\nsurvivors, all take a toll on the population 6<\/sup>. Cancer patients encounter distinct physical and mental health,\nfamily functioning, and maintaining healthy lifestyle issues in the short and\nlong term. Thus, it is very important to pinpoint and diagnose these tumors as\nearly as possible.<\/p>\n\n\n\n

This paper provides an insight into what a brain tumor is, its grading, and its classification. The different methods available to detect tumors along with different imaging scans have been highlighted. This article also discusses the different image processing steps that could be used to automate the brain tumor detection process. After studying and analyzing brain tumors and the role of computer-aided methods in their detection, a significant number of recently proposed brain tumor detection techniques related to our work have been reviewed along with their comparison. This work can help in designing a  solution that is adaptive in nature, having capabilities to provide different applications such as the detection of tumor, localization of the tumor, or identifying the type of tumor under a single model.<\/p>\n\n\n\n

This paper is divided into four sections: Section II describes the different methods available to detect brain tumors; Section III describes the different image processing steps that can be applied to a medical image for the purpose of detection of tumors; thus helping to automate the brain tumor detection process. Section IV gives an in-depth look into the work of numerous researchers in linked and related fields that are relevant to the current study, with a focus on segmentation and classification approaches, and finally, Section V concludes the paper.<\/p>\n\n\n\n

Brain Tumor Detection Methods <\/strong><\/p>\n\n\n\n

Early recognition and diagnosis of brain tumors can significantly improve the patient’s chances of survival. A diagnosis of a brain tumor necessitates the following steps after assessing the physical signs of a patient suspected of a brain tumor: neurological examination, brain scan, and biopsy.<\/p>\n\n\n\n

Neurological Examination<\/strong><\/p>\n\n\n\n

A neurological exam is generally the first step to figure out the cause of symptoms. A neurological assessment is a testing process used to determine the sensory system’s capabilities as well as the patient’s physiological condition. The functionality of nervous system is tested by this test. Mental status, motor function and balance, evaluation of nerves of the brain, responses, sensory exam, muscular strength, and coordination exam are the common tests 7<\/sup>.<\/p>\n\n\n\n

Brain Scan Techniques<\/strong><\/p>\n\n\n\n

Brain scanning also known as neuroimaging makes use of different techniques to image the brain’s internal structure or function. The internal functioning of brain can be observed and monitored by sequencing scanned sections of brain. Brain scans are useful for detecting the presence, location, and size of a tumor. Advanced imaging techniques such as Computed Tomography (CT) scan, Magnetic Resonance Imaging (MRI), Functional MRI (fMRI), angiography, Magnetic Resonance Spectroscopy (MRS), Positron Emission Tomography (PET) scan, etc. are available to recognize tumors. CT scans and MRIs are the most commonly used diagnostic tools 8<\/sup> 9<\/sup>. The brain images captured using different medical imaging scanning techniques are shown in Fig.3 10<\/sup> 11<\/sup> 12<\/sup> 13<\/sup> 14<\/sup> 15<\/sup>.<\/p>\n\n\n\n

CT Scan: It is the most commonly used scan to detect the presence of a tumor.<\/p>\n\n\n\n

MRI: It provides more detailed information about the tumor’s location and size<\/p>\n\n\n\n

fMRI: MRI images generated under this scan help in identifying brain areas responsible for important functions like speech or movement. <\/p>\n\n\n\n

Angiography: These scans are used to locate blood vessels in the brain.<\/p>\n\n\n\n

MRS: Examination of chemical profile of tumor and determination of type of lesions detected in MRI can be done using MRS.<\/p>\n\n\n\n

PET Scan: This scan shows the metabolic functioning of tissues\/organs. Persisting tumors can be detected using PET scans 8<\/sup> 9<\/sup>.<\/p>\n\n\n\n\n\n
\"\"<\/td>\n\n

Figure 3: The brain images obtained using different imaging modalities.<\/strong><\/p>\n

<\/p>\n

Click here to view Figure<\/a><\/p>\n<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n\n\n

Biopsy<\/strong><\/p>\n\n\n\n

A biopsy is a procedure during which a sample of tissue from a tumor location is removed and examined under a microscope. This process involves drilling a hole in the skull and removing a piece of tumor tissue which is then examined by the pathologist under a microscope to determine the tumor type and grade 9<\/sup>.<\/p>\n\n\n\n

Stages Involved in Brain Tumor Recognition<\/strong><\/p>\n\n\n\n

Digital image processing is the process of converting digital data into pixels in an image. Many applications employ medical image processing to process medical data. In order to organize therapy in a timely and effective manner, digital image processing plays a critical role in medical image analysis. Any image processing application’s primary goal is to extract the required attributes from an image so that a machine can make appropriate assessment 16<\/sup>. The different image processing steps that can be applied to a medical image for the purpose of detection of tumors includes pre-processing, segmentation, feature extraction, and classification.<\/p>\n\n\n\n

Pre-Processing<\/strong><\/p>\n\n\n\n

Pre-processing stage in medical image processing is the simplest phase. The main objective of this phase is to improve the MR image quality such that relevant information may be extracted from these images using either manual or automated approaches. Pre-processing boosts the image quality to make it more appropriate for subsequent processing, like classification or segmentation. Pre-processing is generally used to reduce noise and increase image resolution. Undesirable image pixels inside an image significantly impacting its resolution and clarity are referred to as noise. Due to the random nature of the noise formation process, it is really hard to anticipate the exact value of image distortion. The environmental conditions at the time of image acquisition, and the quality of sensing elements used to obtain medical images are the primary sources of noise in these images. Thus, it is critical to come up with a denoising technique that decreases the effect of noise and at the same time preserves the anatomical data that is important for clinical assessment. The pre-processing phase usually includes the following steps: removal and minimization of unnecessary noise, brightness preservation and contrast enhancement, transformation to grayscale, skull extraction, image registration or subsampling, among others 17<\/sup>.<\/p>\n\n\n\n

Segmentation<\/strong><\/p>\n\n\n\n

Following the pre-processing phase, a\nsegmentation process is typically performed. A medical image is divided into\nvarious segments during the segmentation process. These segments comprise\nsimilar qualities of texture, color, brightness, contrast, and gray level.\nTherefore, the major objective of this process is the division of objects\nexisting in an image that are linked to one another in some way 18<\/sup>. Segmentation is the process of separating the specific area of\ninterest from the rest of the image. For brain tumor detection, segmentation\nrefers to extracting the tumor region from the brain MRI image. Segmentation\ntechniques can be divided into thresholding, edge-based, clustering-based, and\nregion-growing techniques.<\/p>\n\n\n\n

Segmentation of a\nbrain tumor is a key step in developing a Computer-Aided Diagnosis (CAD) system\nfor MRI brain image processing because it allows clinicians to more precisely\nlocate the tumor region. This type of process can be done manually,\nautomatically, or semi-automatically.<\/p>\n\n\n\n

Manual segmentation. A professional\nor radiologist visually locates and delineates the tumor region from the MRI\nslice in which the probable tumor emerges. Manual segmentation is costly,\ntime-consuming, as well as prone to errors due to lack of constant updates,\nconsistency, and repeatability.<\/p>\n\n\n\n

Semi-automatic segmentation.\nIn these types of segmentation methods, human\ninteraction is incorporated to manually check and rectify the segmentation\nresults produced by an automatic machine so as to boost the accuracy of brain\ntumor detection.<\/p>\n\n\n\n

Fully-automatic segmentation. In these types of segmentation methods, segment boundaries are provided automatically by a program. There is no need for human interaction because the computer does all the work. Soft computing methods and other intelligent techniques can be used to create an approach to this goal.<\/p>\n\n\n\n

Feature Extraction<\/strong><\/p>\n\n\n\n

The feature extraction technique extracts relevant information or features from medical images, such as statistics, shape, color, and texture. Feature extraction is a crucial part of medical image processing since it reveals the statistical characteristics of individual regions. The main goal of this phase is to minimize the amount of data used in the computation as it reduces the feature set by removing the redundant features. The extracted features contain relevant visual features that may be extended for future use such as detection and segmentation. Thus, the essential step in achieving a better outcome is to pick the best features derived from the image. Feature’s distinctiveness and integrity are important factors for selecting the best features. The use of feature extraction techniques in machine learning models leads to improved accuracy, reduction in overfitting risk, speed up in training, and improved data visualization 19<\/sup>. Feature extraction can be carried out using Stationary Wavelet Transform (SWT), Discrete Wavelet Transform (DWT), Gray Level Co-occurrence Matrix (GLCM), Gray Level Difference Method (GLDM), Local Binary Pattern (LBP), among others 20<\/sup>.<\/p>\n\n\n\n

Classification<\/strong><\/p>\n\n\n\n

Classification is the most important stage in the CAD system. Classification helps in categorizing the medical images into appropriate classes depending on the characteristics collected from source images or images obtained from previous phases. For brain tumor detection, the classification phase can help in identifying whether a tumor is present in the brain MRI image or not and then identifying the type of tumor if a tumor is present. The different methods available for image classification are Artificial Neural Network (ANN), Back Propagation Neural Network (BPNN), Convolutional Neural Network (CNN), Decision Tree (DT), Support Vector Machine (SVM), Self-Organizing Map (SOM), etc. While selecting a particular classifier for classification, criteria such as reliability, efficiency, and processing capacity need to be considered 21<\/sup> 22<\/sup>.<\/p>\n\n\n\n

Related Work<\/strong><\/p>\n\n\n\n

Timely detection of cancer plays an important\nrole in beneficial therapy and revival of the patient. After studying and\nanalyzing brain tumors and the role of computer-aided methods in their\ndetection, a significant number of recently proposed brain tumor detection\ntechniques have been reviewed. This section gives an in-depth look into\nprevious brain tumor detection approaches that are relevant to the current\nstudy. It showcases the work of numerous researchers in linked and related\nfields, with a focus on segmentation and classification approaches. <\/p>\n\n\n\n

Kalaivani et al.<\/em> 23<\/sup> presented machine learning-based software for the segmentation and\nclassification of tumor types by utilizing brain MRIs. The MRI images were\ninitially enhanced by employing the contrast optimization technique. Then\ndouble thresholding was performed through morphological processes, and finally,\nthe skull stripping method was employed to eliminate undesirable non-cerebral\ntissues from the MR image. Features were also obtained using GLCM. Oversized\naberrant cells were detected and tumor regions were sliced and segmented using\nclassification algorithms such as k-NN, FCM, and K-means. <\/p>\n\n\n\n

Jayadevappa and\nKesava<\/em> 24<\/sup> proposed a Contourlet transform and the Chan-Vese active contour framework\nto automatically segment brain tumors. The Contourlet transform gathers edges\nand clean contours in any configuration and enhances the noise filtration\nprocess. The Contourlet transform, which was adding the property of\ndirectionality, produces high-resolution images. Chan-Vese active contour\nmodels were region-based segmentation algorithms that employ the best piecewise\nlinear approximating algorithm. The proposed model generated precise results as\ncompared to typical segmentation methods.<\/p>\n\n\n\n

Islam et al.<\/em> 25<\/sup> suggested a modified brain tumor detection model based on the\ntemplate-based K-means algorithm combining superpixels as well as Principal\nComponent Analysis (PCA) within the given study. Initially, both the\nsuperpixels and PCA were used to retrieve key features that aid in the accurate\ndetection of brain cancers. The image was then enhanced using a filter that\naids in improving accuracy. Ultimately, to identify the brain tumor,\nsegmentation was done using the template-based K-means clustering technique.\nThe experiments indicated that the suggested strategy for brain tumor detection\nin MR images resulted in higher accuracy of 95%, and sensitivity of 97.36%,\nthus outperforming the other current recent schemes.<\/p>\n\n\n\n

Padlia and Sharma<\/em> 26<\/sup> presented a method for detecting and segmenting brain tumors using\nT1-weighted and FLAIR brain MRI images. The fractional Sobel filter was used to\nreduce noise and improve the appearance of the brain MRI images. The fractional\nSobel filter’s fractional-order provided more flexibility in enhancing\nsegmentation performance. Bhattacharya factors and information gain were used\nto detect asymmetry across hemispheres. The statistical characteristics of a\ngiven window were generated and classified employing SVM for separating the\ntumor region from the tumor hemisphere. The images from the BRATS-2013 database\nwere simulated, and quality factors like accuracy, sensitivity, and specificity\nwere determined. The simulation results showed that the suggested scheme’s\neffectiveness was identical to that of the closest systems.<\/p>\n\n\n\n

Lather and Singh <\/em>27<\/sup> <\/em>proposed an automated approachto\ndetect the tumor from brain MR images based on segmentation technique. The\nbrain MRI image dataset was initially pre-processed in order to handle the\ndifferent types of noise and improve the quality of the medical images so that\nthe components of the image can be effectively processed and assist in the\nsegmentation phase for detecting the tumor from MRI images. As part of\npre-processing, image quality was enhanced using Minimum Mean Brightness Error\nBi-Histogram Equalization (MMBEBHE) technique and noise was removed from the\nimages using a combination of Wiener and bilateral filters. Next, segmentation\nwas done to extract the tumor region from these pre-processed MRI images. The\nSine Tree Seed Algorithm (STSA) tuned K-means clustering approach was used for\naccurately segmenting the tumor region from the MRI images. In addition to\nthis, the proposed segmentation approach was analyzed for its effectiveness by\nconsidering the impact of Gaussian and speckle noise on the original image. The\nresults demonstrated that the proposed segmentation scheme outperforms the\nexisting techniques in terms of various performance parameters for all the\nthree cases of no noise, speckle, and Gaussian noise.<\/p>\n\n\n\n

Kesav and\nJibukumar<\/em> 28<\/sup> developed a region based Convolutional Neural Network (RCNN)\napproach for brain tumor classification and tumor type object recognition. The\nproposed approach was tested using two publicly available datasets from\nFigshare and Kaggle. Initially, a two-channel CNN was employed to distinguish\nbetween Glioma and a healthy tumor. The features for the RCNN were also\ndetected using two-channel CNN. The RCNN was then used to recognize the tumor\nregions of the previously classified Glioma MRI data. With just an average\nlevel of confidence of 98.83 %, the technique was sufficient to attain a very\nlow execution time when compared to other existing designs.<\/p>\n\n\n\n

Abd El Kader et\nal.<\/em> 29<\/sup> presented a Differential Deep Convolutional Neural Network model\n(differential deep-CNN) in order to categorize various forms of brain tumors.\nThe supplementary differentiated local features inside the original CNN feature\nmaps were produced using differential operators in the differential deep-CNN\narchitecture. The differential deep-CNN model was able to identify a large\ncollection of images with high precision and without technological\ndifficulties, as well as evaluate pixel directional patterns of images using\ncontrast computations. The findings showed that the suggested differential\ndeep-CNN model can be utilized to automatically categorize brain tumors.<\/p>\n\n\n\n

Das et al.<\/em> 30<\/sup> focused on creating a CNN model for diagnosing brain tumors in\nT1-weighted contrast-enhanced MRI images. There were two major phases in the\ndeveloped framework. Initially, various image processing algorithms were used\nto modify the images, and then classification was done using CNN. The study\nused a collection of 3064 medical images that had three different forms of\nbrain tumors (glioma, meningioma, and pituitary). The proposed CNN model\nresulted in high testing accuracy of 94.39%, precision of 93.33%, and recall of\n93%. The proposed work outscored a number of well-known current approaches.<\/p>\n\n\n\n

Xuan and Liao<\/em> 31<\/sup> suggested a tumor segmentation technique that is based on statistical\nstructure analysis. Initially, structural elements were analyzed for three\ntypes of features: intensity, symmetrical, and textural. The structural\nelements were then classified into normal and diseased tissues using an\nAdaBoost classification algorithm which trained itself by picking the most\ndiscriminant features. The proposed scheme resulted in a segmentation accuracy\nof 96.82%<\/p>\n\n\n\n

Cherguif et al.<\/em> 32<\/sup> suggested a Deep Learning approach based on U-Net model. The\nproposed technique was tested on the BRATS 2017 dataset having both HGG and LGG\ncases. In comparison to traditionally defined ground truth, the proposed method\nwas producing a segmentation that was efficient and resilient and resulted in Dice\nSimilarity Coefficient (DSC) values of 0.81805, and 0.8103. <\/p>\n\n\n\n

Garg and Garg<\/em> 33<\/sup> proposed a dynamic ensemble technique centered on the majority\nvoting methodology that utilizes a combined model of Random Forest (RF), k-NN,\nand Decision Tree (DT) methods. Their goal was to calculate the tumor’s\ndiameter and identify benign and malignant brain tumors. At first, Otsu’s\nthreshold approach was used to segment the data. Then the SWT, PCA, and GLCM\nwere used to extract features, yielding thirteen relevant features for the\nclassification phase. Based on the majority voting approach, a hybrid ensemble\nclassifier (kNN-RFDT) was used to classify the data. The suggested method\nresulted in an accuracy of 97.305%.<\/p>\n\n\n\n

Lu et al.<\/em> 34<\/sup> presented an advanced CAD model called PBTNet for the detection of\nprimary brain tumors from MRI images. In the proposed PBTNet model, they used a\npre-trained ResNet-18 as a backbone framework fine-tuning it just for feature\nextraction. Furthermore, in the PBTNet, three randomized NNs named Schmidt,\nrandom vector functional-link, and extreme learning engine acted as detectors.\nThe combination of the outputs from the classi\ufb01ers formed the PBTNet’s\nfinalized forecasts. The performance of the PBTNet classifier was evaluated\nusing 5-fold cross-validation, and the results demonstrated the effectiveness\nof the PBTNet model for the detection of primary brain tumors.<\/p>\n\n\n\n

Rehman et al.<\/em> 35<\/sup> presented an innovative deep learning-based methodology for brain\ntumor identification and tumor type prediction. Initially, a 3D CNN framework\nwas created to extract brain tumors which were then passed to a pre-trained\nmodel for extracting the features. The retrieved features were then fed to a\ncorrelation-based selection technique, resulting in the best features selection\nas an output. Finally, the selected features were confirmed using a\nfeed-forward neural network for the final prediction. For investigations and\nevaluation, three datasets were used, that is, BraTS 2015, BraTS 2017, and\nBraTS 2018.<\/p>\n\n\n\n

Sajjad et al.<\/em> 36<\/sup> presented a novel multi-grade brain tumor classification scheme\nworking on the principle of CNN based network. In the initial stage, deep\nlearning was used to segregate tumor locations from the MRI images. Next,\nconsiderable data augmentation was performed to properly train the created\nmethodology and eliminate the lack of data problems that can occur when\nemploying MRI for multi-grade brain tumor classification. Finally, supplemented\ndata was used to fine-tune a pre-trained CNN model for determining brain tumor\ngrade. The proposed system was realistically evaluated using both enhanced and\noriginal data, demonstrating that it outperforms previous techniques.<\/p>\n\n\n\n

Ismael and Abdel-Qader<\/em> 37<\/sup> presented a classification framework based on statistical features\nand NN models in order to classify the brain tumors in MRI images. Features\nwere selected by using a hybrid approach of 2D DWT, and 2D Gabor filter. To\nanalyze the influence of feature selection, a backpropagation NN classifier was\nchosen for classification. The proposed approach resulted in an accuracy of\n91.9%.<\/p>\n\n\n\n

Lather and Singh <\/em>38<\/sup> <\/em>presented an automated classification\nframeworkto identify tumor presence and tumor type from BraTS 2015\ndataset. The brain MRI image dataset was initially pre-processed to enhance\ncontrast using MMBEBHE method and remove unwanted noise from the images using a\ncombination of Wiener and bilateral filters. Next, classification was done for\ndetecting the presence of the tumor in MRI images as well as identifying the\nclass of the tumor as High Grade Glioma (HGG) or Low Grade Glioma (LGG). The\nDual Decision Voting Mechanism (DDVM) model employing dual classifiers \u2013 CNN,\nand Bi-directional Long Short-Term Memory (Bi-LSTM) was proposed to identify\nwhether a tumor is present or not. Next, the Local Binary Pattern and Phase\nQuantization (LBP2<\/sup>Q) featured SVM model is proposed to identify the\npatterns from the tumor images to classify the type of tumor as HGG or LGG. In\naddition to this, the proposed classification framework was analyzed for its\neffectiveness by considering the impact of Gaussian and speckle noise on the\noriginal image. The results demonstrated that the proposed framework\noutperforms the existing techniques in terms of various performance parameters\nfor all the three cases of no noise, speckle, and Gaussian noise.<\/p>\n\n\n\n

A thorough comparative analysis of the research work of different researchers reviewed above is summarized in Table 1.<\/p>\n\n\n\n

Table 1: Comparison of the reviewed work<\/strong> <\/p>\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n
\n

S. No<\/strong><\/p>\n<\/td>\n

\n

Authors<\/strong><\/p>\n<\/td>\n

\n

Total images\/
<\/strong>Dataset<\/strong><\/p>\n<\/td>\n

\n

Pre-Processing<\/strong><\/p>\n<\/td>\n

\n

Feature Extraction<\/strong><\/p>\n<\/td>\n

\n

Segmentation<\/strong><\/p>\n<\/td>\n

\n

Classification<\/strong><\/p>\n<\/td>\n

\n

Result<\/strong><\/p>\n<\/td>\n<\/tr>\n

\n

1<\/p>\n<\/td>\n

\n

Kalaivani et al. 23<\/sup><\/p>\n<\/td>\n

\n

Chettinadu<\/p>\n

hospitals and research centers<\/p>\n<\/td>\n

\n

Median filtering<\/p>\n

double
thresholding,<\/p>\n

erosion,
region filling<\/p>\n<\/td>\n

\n

GLCM<\/p>\n<\/td>\n

\n

k-NN, FCM,
and
K-means<\/p>\n<\/td>\n

\n

NA<\/p>\n<\/td>\n

\n

Accuracy
= 98.97%
FCM, 89.96%
k-NN, 79.95%
K-means<\/p>\n

\n<\/p><\/td>\n<\/tr>\n

\n

2<\/p>\n<\/td>\n

\n

Jayadevappa and Kesava 24<\/sup><\/p>\n<\/td>\n

\n

brain web database<\/p>\n<\/td>\n

\n

Gaussian
filtering<\/p>\n<\/td>\n

\n

Contourlet
transform<\/p>\n<\/td>\n

\n

Chan-Vese
active contour
model<\/p>\n<\/td>\n

\n

NA<\/p>\n<\/td>\n

\n

NA<\/p>\n<\/td>\n<\/tr>\n

\n

3<\/p>\n<\/td>\n

\n

Islam et al. 25<\/sup><\/p>\n<\/td>\n

\n

Kaggle<\/p>\n<\/td>\n

\n

Mean, and
median
filtering<\/p>\n<\/td>\n

\n

superpixels
and PCA<\/p>\n<\/td>\n

\n

template-based
K-means clustering<\/p>\n<\/td>\n

\n

NA<\/p>\n<\/td>\n

\n

Accuracy
= 95%<\/p>\n

Sensitivity
=97.36%<\/p>\n<\/td>\n<\/tr>\n

\n

4<\/p>\n<\/td>\n

\n

Padlia, and Sharma 26<\/sup><\/p>\n<\/td>\n

\n

BraTS 2013<\/p>\n<\/td>\n

\n

fractional
Sobel filter<\/p>\n<\/td>\n

\n

Statistical features<\/p>\n<\/td>\n

\n

SVM<\/p>\n<\/td>\n

\n

NA<\/p>\n<\/td>\n

\n

Accuracy
= 98.01%<\/p>\n

Sensitivity
=86.59%<\/p>\n<\/td>\n<\/tr>\n

\n

5<\/p>\n<\/td>\n

\n

Lather, and Singh 27<\/sup><\/p>\n<\/td>\n

\n

BraTS 2012<\/p>\n<\/td>\n

\n

MMBEBHE,
Wiener and
bilateral
filters<\/p>\n<\/td>\n

\n

SWT<\/p>\n<\/td>\n

\n

STSA tuned
K-means
clustering<\/p>\n<\/td>\n

\n

NA<\/p>\n<\/td>\n

\n

Accuracy
= 98.91%<\/p>\n

Precision
=99.31%<\/p>\n

Recall
=99.56%<\/p>\n<\/td>\n<\/tr>\n

\n

6<\/p>\n<\/td>\n

\n

Kesav, and Jibukumar 28<\/sup><\/p>\n<\/td>\n

\n

Figshare and Kaggle<\/p>\n<\/td>\n

\n

NA<\/p>\n<\/td>\n

\n

two-channel CNN<\/p>\n<\/td>\n

\n

NA<\/p>\n<\/td>\n

\n

two-channel CNN,  RCNN<\/p>\n<\/td>\n

\n

Accuracy
= 98.83%<\/p>\n<\/td>\n<\/tr>\n

\n

7<\/p>\n<\/td>\n

\n

Abd El Kader et al. 29<\/sup><\/p>\n<\/td>\n

\n

TUCMD database<\/p>\n<\/td>\n

\n

NA<\/p>\n<\/td>\n

\n

differential operators<\/p>\n<\/td>\n

\n

NA<\/p>\n<\/td>\n

\n

differential deep-CNN<\/p>\n<\/td>\n

\n

Accuracy
= 99.25%<\/p>\n

Sensitivity
=95.89%<\/p>\n

Precision
=97.22%<\/p>\n<\/td>\n<\/tr>\n

\n

8<\/p>\n<\/td>\n

\n

Das et al.<\/em> 30<\/sup><\/p>\n<\/td>\n

\n

3064 images<\/p>\n<\/td>\n

\n

Gaussian filtering, Histogram Equalization<\/p>\n<\/td>\n

\n

NA<\/p>\n<\/td>\n

\n

NA<\/p>\n<\/td>\n

\n

CNN<\/p>\n<\/td>\n

\n

Accuracy
= 94.39%<\/p>\n

Precision
=93.33%<\/p>\n

Recall
=93%<\/p>\n<\/td>\n<\/tr>\n

\n

9<\/p>\n<\/td>\n

\n

Xuan, and Liao 31<\/sup><\/p>\n<\/td>\n

\n

140<\/p>\n

images<\/p>\n<\/td>\n

\n

NA<\/p>\n<\/td>\n

\n

structural features: intensity, symmetrical, textural<\/p>\n<\/td>\n

\n

NA<\/p>\n<\/td>\n

\n

AdaBoost<\/p>\n<\/td>\n

\n

Accuracy
= 96.82%<\/p>\n<\/td>\n<\/tr>\n

\n

10<\/p>\n<\/td>\n

\n

Cherguif et al.<\/em> 32<\/sup><\/p>\n<\/td>\n

\n

BraTS 2017<\/p>\n<\/td>\n

\n

NA<\/p>\n<\/td>\n

\n

NA<\/p>\n<\/td>\n

\n

NA<\/p>\n<\/td>\n

\n

U-Net<\/p>\n<\/td>\n

\n

DSC HGG
=0.81805<\/p>\n

DSC LGG
=0.8103<\/p>\n<\/td>\n<\/tr>\n

\n

11<\/p>\n<\/td>\n

\n

Garg, and Garg 33<\/sup><\/p>\n<\/td>\n

\n

2556<\/p>\n

images<\/p>\n<\/td>\n

\n

NA<\/p>\n<\/td>\n

\n

SWT, PCA, and GLCM<\/p>\n<\/td>\n

\n

Otsu’s
threshold<\/p>\n<\/td>\n

\n

Hybrid ensemble classifier (kNN-RFDT)<\/p>\n<\/td>\n

\n

Accuracy
= 97.30%<\/p>\n<\/td>\n<\/tr>\n

\n

12<\/p>\n<\/td>\n

\n

Lu et al. 34<\/sup><\/p>\n<\/td>\n

\n

Kaggle<\/p>\n<\/td>\n

\n

NA<\/p>\n<\/td>\n

\n

pre-trained ResNet-18<\/p>\n<\/td>\n

\n

NA<\/p>\n<\/td>\n

\n

PBTNet classifier<\/p>\n<\/td>\n

\n

Accuracy
= 97%<\/p>\n

Sensitivity
=99.64%<\/p>\n

Precision
=93.84%<\/p>\n<\/td>\n<\/tr>\n

\n

13<\/p>\n<\/td>\n

\n

Rehman et al. 35<\/sup><\/p>\n<\/td>\n

\n

BraTS 2015, 2017, 2018<\/p>\n<\/td>\n

\n

NA<\/p>\n<\/td>\n

\n

3D CNN<\/p>\n<\/td>\n

\n

NA<\/p>\n<\/td>\n

\n

Feed forward NN<\/p>\n<\/td>\n

\n

Accuracy
= 98.32% for
2015, 96.97%
for 2017, and 92.67% for
2018<\/p>\n<\/td>\n<\/tr>\n

\n

14<\/p>\n<\/td>\n

\n

Sajjad et al. 36<\/sup><\/p>\n<\/td>\n

\n

Brain tumor dataset<\/p>\n<\/td>\n

\n

NA<\/p>\n<\/td>\n

\n

NA<\/p>\n<\/td>\n

\n

Input
Cascade
CNN<\/p>\n<\/td>\n

\n

pre-trained CNN<\/p>\n<\/td>\n

\n

Accuracy
= 94.58%<\/p>\n

Sensitivity
=88.41%<\/p>\n

Specificity =96.12%<\/p>\n<\/td>\n<\/tr>\n

\n

15<\/p>\n<\/td>\n

\n

Ismael, and Abdel-Qader 37<\/sup><\/p>\n<\/td>\n

\n

3064<\/p>\n

images<\/p>\n<\/td>\n

\n

NA<\/p>\n<\/td>\n

\n

hybrid approach of 2D DWT, 2D Gabor filter<\/p>\n<\/td>\n

\n

NA<\/p>\n<\/td>\n

\n

BPNN<\/p>\n<\/td>\n

\n

Accuracy= 91.9%<\/p>\n<\/td>\n<\/tr>\n

\n

16<\/p>\n<\/td>\n

\n

Lather, and Singh 38<\/sup><\/p>\n<\/td>\n

\n

BraTS 2015<\/p>\n<\/td>\n

\n

MMBEBHE,<\/p>\n

Wiener and bilateral filters<\/p>\n<\/td>\n

\n

LBP2<\/sup>Q<\/p>\n<\/td>\n

\n

NA<\/p>\n<\/td>\n

\n

DDVM model using dual classifiers \u2013 CNN, Bi-LSTM to identify tumor presence<\/p>\n

SVM to classify tumor type<\/p>\n<\/td>\n

\n

Tumor Presence<\/p>\n

Accuracy= 98.91%<\/p>\n

Tumor type<\/p>\n

Accuracy= 96.06%<\/p>\n<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n\n\n

Conclusion<\/strong><\/p>\n\n\n\n

A tumor is an\naberrant mass of tissues caused by unrestrained cell proliferation and multiplication\ninside the brain or around the brain. A brain tumor not only affects the cells\nin its immediate vicinity, but it can also harm other cells by generating\ninflammation. Brain tumor is the most prevalent and life-threatening illness\nthese days. It is important to detect and diagnose brain tumors at the early\nstages. Early recognition and diagnosis of brain tumors can significantly\nimprove the patient’s chances of survival. In this paper, we discussed about\nbrain tumors, their grading, and classification. We also discussed about the\nmechanism followed to detect the brain tumor along with the different image\nprocessing steps that could be used to automate the brain tumor detection\nprocess. After studying and analyzing brain tumors and the role of\ncomputer-aided methods in their detection, we reviewed a significant number of\nrecently proposed brain tumor detection techniques related to our work along\nwith their tabulated comparison.<\/p>\n\n\n\n

This work can be\nfurther extended to design an adaptive solution, having capabilities to provide\ndifferent applications such as detection of tumor, localization of tumor, or\nidentifying type of tumor under a single model.<\/p>\n\n\n\n

Conflicts of Interest<\/strong><\/p>\n\n\n\n

The authors declare that they have no conflicts of interest.<\/p>\n\n\n\n

Funding sources<\/strong><\/p>\n\n\n\n

This research received no external funding.<\/p>\n\n\n\n

References<\/strong><\/p>\n\n\n\n

  1. What is a tumor? https:\/\/www.healio.com\/news\/hematology-oncology\/20120331\/what-is-a-tumor. Accessed May 21, 2022.<\/li>
  2. Medical Definition of Tumor. MedicineNet. https:\/\/www. medicinenet.com\/ tumor\/definition.htm. Accessed May 21, 2022.<\/li>
  3. Brain Tumor – Introduction. Cancer.Net. https:\/\/www.cancer.net\/ cancer-types\/brain-tumor\/introduction. Published June 25, 2012. Accessed May 21, 2022.<\/li>
  4. frankly-speaking-about-cancer-brain-tumors.pdf. http:\/\/blog. braintumor.org\/files\/public-docs\/frankly-speaking-about-cancer-brain-tumors.pdf. Accessed May 21, 2022.<\/li>
  5. Ghorpade N, Bhapkar H. Brain MRI Segmentation and Tumor Detection: Challenges, Techniques and Applications. 2021 5th International Conference on Intelligent Computing and Control Systems (ICICCS)<\/em>. 2021:1657-1664. doi:10.1109\/ICICCS51141.2021.9432346
    CrossRef <\/a><\/li>
  6. Research Areas: Cancer and Public Health – NCI. https:\/\/www.cancer. gov\/research\/areas\/public-health. Published May 7, 2015. Accessed May 21, 2022.<\/li>
  7. Neurological Exam. https:\/\/www.hopkinsmedicine.org\/ health\/conditions-and-diseases\/neurological-exam. Published November 19, 2019. Accessed May 21, 2022.<\/li>
  8. Brain_scanning_techniques.pdf. https:\/\/psicoterapiabilbao.es\/wp-content\/uploads\/2015\/12\/Brain_scanning_techniques.pdf. Accessed May 21, 2022.<\/li>
  9. Diagnosis – Learn More or Donate Today! | ABTA. https:\/\/www.abta.org\/about-brain-tumors\/brain-tumor-diagnosis\/. Accessed May 21, 2022.<\/li>
  10. Kamil M. Brain Tumor Area Calculation in CT-scan image using Morphological Operations. IOSR Journal of Computer Engineering<\/em>. 2015;17:128-131.<\/li>
  11. Perumal TS, Palanisamy V, Purusothaman T. Performance Analysis of Clustering Algorithms in Brain Tumor Detection of MR Images. European Journal of Scientific Research<\/em>. 2011;62:321-330.<\/li>
  12. Functional Magnetic Resonance Imaging | Radiology | University of Nebraska Medical Center. https:\/\/www.unmc.edu\/ radiology\/research\/clinical\/results\/fmri.html. Accessed January 4, 2023.<\/li>
  13. Castillo M. History and Evolution of Brain Tumor Imaging: Insights through Radiology. Radiology<\/em>. 2014;273(2S):S111-S125. doi:10.1148\/radiol.14140130
     CrossRef <\/a><\/li>
  14. In vivo magnetic resonance spectroscopy. In: Wikipedia<\/em>. ; 2022. https:\/\/en.wikipedia.org\/w\/index.php?title=In_vivo_magnetic_ resonance_ spectroscopy&oldid=1090268293. Accessed January 4, 2023.<\/li>
  15. Verger A, Langen KJ. PET Imaging in Glioblastoma: Use in Clinical Practice. Exon Publications<\/em>. September 2017:155-174. doi:10.15586\/codon.glioblastoma.2017.ch9
     CrossRef <\/a><\/li>
  16. Lather M, Singh P. Investigating Brain Tumor Segmentation and Detection Techniques. Procedia Computer Science<\/em>. 2020;167:121-130. doi:10.1016\/j.procs.2020.03.189
    CrossRef <\/a><\/li>
  17. Kapoor L, Thakur S. A Survey on Brain Tumor Detection using Image Processing Techniques. In: 7th International Conference on Cloud Computing, Data Science & Engineering – Confluence<\/em>. Noida, India: IEEE; 2017:582-585. doi:10.1109\/CONFLUENCE.2017.7943218
     CrossRef <\/a><\/li>
  18. Hassan E, Aboshgifa A. Detecting Brain Tumour from MRI Image Using Matlab GUI Programme. IJCSES<\/em>. 2015;6(6):47-60. doi:10.5121\/ijcses.2015.6604
     CrossRef <\/a><\/li>
  19. Ippolito PP. Feature Extraction Techniques. Medium. https:\/\/towardsdatascience.com\/feature-extraction-techniques-d619b56e31be. Published October 11, 2019. Accessed May 22, 2022.
    CrossRef <\/li>
  20. \u00c7al\u0131\u015fkan A. A New Ensemble Approach for Congestive Heart Failure and Arrhythmia Classification Using Shifted One-Dimensional Local Binary Patterns with Long Short-Term Memory. The Computer Journal<\/em>. 2022;65(9):2535-2546. doi:10.1093\/comjnl\/bxac087<\/li>
  21. Kharat KD, Pawar V, Pardeshi SR. Feature Extraction and Selection from MRI Images for the Brain Tumor Classification. In: International Conference on Communication and Electronics Systems (ICCES)<\/em>. ; 2016:1-5. doi:10.1109\/CESYS.2016.7889969
     CrossRef <\/a><\/li>
  22. \u00c7al\u0131\u015fkan A. Detecting Human Activity Types from 3D Posture Data Using Deep Learning Models. Biomedical Signal Processing and Control<\/em>. 2022;81:104479. doi:10.1016\/j.bspc.2022.104479
     CrossRef <\/a><\/li>
  23. Kalaivani I, Oliver AS, Pugalenthi R, Jeipratha PN, Jeena AAS, Saranya G. Brain Tumor Segmentation Using Machine Learning Classifier. In: 2019 Fifth International Conference on Science Technology Engineering and Mathematics (ICONSTEM)<\/em>. Vol 1. ; 2019:85-90. doi:10.1109\/ICONSTEM.2019.8918918
     CrossRef <\/a><\/li>
  24. Jayadevappa D, Kesava TC. Segmentation of Brain Tumor using Contourlet Transform and Chan-Vese Active Contour Model Approach. European Journal of Molecular & Clinical Medicine<\/em>. 2021;8(2):2381-2389. https:\/\/ejmcm.com\/article_8239.html. Accessed May 23, 2022.<\/li>
  25. Islam MK, Ali MS, Miah MS, Rahman MM, Alam MS, Hossain MA. Brain Tumor Detection in MR Image Using Superpixels, Principal Component Analysis and Template Based K-means Clustering Algorithm. Machine Learning with Applications<\/em>. 2021;5:100044. doi:10.1016\/j.mlwa.2021.100044
     CrossRef <\/a><\/li>
  26. Padlia M, Sharma J. Fractional Sobel Filter Based Brain Tumor Detection and Segmentation Using Statistical Features and SVM. In: Nath V, Mandal JK, eds. Nanoelectronics, Circuits and Communication Systems<\/em>. Lecture Notes in Electrical Engineering. Singapore: Springer; 2019:161-175. doi:10.1007\/978-981-13-0776-8_15
     CrossRef <\/a><\/li>
  27. Lather M, Singh P. Tumor Segmentation From Brain MR Images Using STSA Based Modified K-means Clustering Approach. Journal of Intelligent & Fuzzy Systems<\/em>. 2022;43:2579-2595. doi:10.3233\/JIFS-212709
     CrossRef <\/a><\/li>
  28. Kesav N, Jibukumar MG. Efficient and low Complex Architecture for Detection and Classification of Brain Tumor Using RCNN with Two Channel CNN. Journal of King Saud University – Computer and Information Sciences<\/em>. May 2021. doi:10.1016\/j.jksuci.2021.05.008
     CrossRef <\/a><\/li>
  29. Abd El Kader I, Xu G, Shuai Z, Saminu S, Javaid I, Salim Ahmad I. Differential Deep Convolutional Neural Network Model for Brain Tumor Classification. Brain Science<\/em>. 2021;11(3):352. doi:10.3390\/brainsci11030352
     CrossRef <\/a><\/li>
  30. Das S, Aranya OFMRR, Labiba NN. Brain Tumor Classification Using Convolutional Neural Network. In: 2019 1st International Conference on Advances in Science, Engineering and Robotics Technology (ICASERT)<\/em>. ; 2019:1-5. doi:10.1109\/ICASERT.2019.8934603
     CrossRef <\/a><\/li>
  31. Xuan X, Liao Q. Statistical Structure Analysis in MRI Brain Tumor Segmentation. In: Fourth International Conference on Image and Graphics (ICIG 2007)<\/em>. ; 2007:421-426. doi:10.1109\/ICIG.2007.181
     CrossRef <\/a><\/li>
  32. Cherguif H, Riffi J, Mahraz MA, Yahyaouy A, Tairi H. Brain Tumor Segmentation Based on Deep Learning. In: 2019 International Conference on Intelligent Systems and Advanced Computing Sciences (ISACS)<\/em>. ; 2019:1-8. doi:10.1109\/ISACS48493.2019.9068878
     CrossRef <\/a><\/li>
  33. Garg G, Garg R. Brain Tumor Detection and Classification Based on Hybrid Ensemble Classifier<\/em>. arXiv; 2021. doi:10.48550\/arXiv.2101.00216
     CrossRef <\/a><\/li>
  34. Lu SY, Satapathy SC, Wang SH, Zhang YD. PBTNet: A New Computer-Aided Diagnosis System for Detecting Primary Brain Tumors. Front Cell Dev Biol<\/em>. 2021;9:765654. doi:10.3389\/fcell.2021.765654
     CrossRef <\/a><\/li>
  35. Rehman A, Khan MA, Saba T, Mehmood Z, Tariq U, Ayesha N. Microscopic Brain Tumor Detection and Classification Using 3D CNN and Feature Selection Architecture. Microscopy Research and Technique<\/em>. 2021;84(1):133-149. doi:10.1002\/jemt.23597
     CrossRef <\/a><\/li>
  36. Sajjad M, Khan S, Muhammad K, Wu W, Ullah A, Baik SW. Multi-grade Brain Tumor Classification Using Deep CNN with Extensive Data Augmentation. Journal of Computational Science<\/em>. 2019;30:174-182. doi:10.1016\/j.jocs.2018.12.003
     CrossRef <\/a><\/li>
  37. Ismael MR, Abdel-Qader I. Brain Tumor Classification via Statistical Features and Back-Propagation Neural Network. In: 2018 IEEE International Conference on Electro\/Information Technology (EIT)<\/em>. ; 2018:0252-0257. doi:10.1109\/EIT.2018.8500308
     CrossRef <\/a><\/li>
  38. Lather M, Singh P. DDVM: Dual Decision Voting Mechanism for Brain Tumour Identification with LBP2Q-SVM Type Classifier. International Journal of Computational Vision and Robotics<\/em>. 2023;13(1):52-72. doi:10.1504\/IJCVR.2023.127304
    CrossRef<\/a><\/li><\/ol>\n\n\n\n

    <\/p>\n","protected":false},"excerpt":{"rendered":"

    Introduction A tumor is an aberrant mass of tissue caused […]<\/p>\n","protected":false},"author":15,"featured_media":0,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[111],"tags":[],"class_list":["post-53227","post","type-post","status-publish","format-standard","hentry","category-vol16no4"],"_links":{"self":[{"href":"https:\/\/biomedpharmajournal.org\/staging\/wp-json\/wp\/v2\/posts\/53227","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/biomedpharmajournal.org\/staging\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/biomedpharmajournal.org\/staging\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/biomedpharmajournal.org\/staging\/wp-json\/wp\/v2\/users\/15"}],"replies":[{"embeddable":true,"href":"https:\/\/biomedpharmajournal.org\/staging\/wp-json\/wp\/v2\/comments?post=53227"}],"version-history":[{"count":5,"href":"https:\/\/biomedpharmajournal.org\/staging\/wp-json\/wp\/v2\/posts\/53227\/revisions"}],"predecessor-version":[{"id":55033,"href":"https:\/\/biomedpharmajournal.org\/staging\/wp-json\/wp\/v2\/posts\/53227\/revisions\/55033"}],"wp:attachment":[{"href":"https:\/\/biomedpharmajournal.org\/staging\/wp-json\/wp\/v2\/media?parent=53227"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/biomedpharmajournal.org\/staging\/wp-json\/wp\/v2\/categories?post=53227"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/biomedpharmajournal.org\/staging\/wp-json\/wp\/v2\/tags?post=53227"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}