Brain Tumor Identification Research Articles

RETRACTED ARTICLE: Brain tumour image classification using improved convolution neural networks

Brain tumour or cancer is one of the most severe forms of cancers since it involves the primary nervous system of the human body. Even a little bit of neuronal damage may have a major impact on a tiny brain. When you have gotten your brain cells tainted with infectious diseases, it is impossible to get certain cells to recover, since the brain is vulnerable and easily harmed. There are two distinct kinds of brain tumours, one which is malignant and one which is benign. There are two forms of cancerous tumours that may be cancerous and benign. The benign tumour is a difference in the form and function of the cells that has to be handled with chemotherapy, but cannot infect the other cells or spread in other parts of the brain. It is a very serious and life-threatening cancer for people. Because of this, it should be operated on and removed instantly. The identification of brain tumours is a complicated and responsive activity that indicated the knowledge of the classifier. The usage of CNN method to identify the brain tumour type is presented in this work. CNN will take up the lessons that the authors have studied and add them to one machine-driven structure. This move will boost the pace and the picture clarity at which brain tumours can be detected. Back-propagation method is a strategy for the classification of brain tumours suggested in this article. The novelty of in this article is the training data are not spoiled by outliers and the objective is to identify if a test case belongs to the regular class or to the irregular class and for this training session, only the final layer was performed.

A Review on Deep Learning Architecture and Methods for MRI Brain Tumour Segmentation

The automatic segmentation of brain tumour from MRI medical images is mainly covered in this review. Recently, state-of-the-art performance is provided by deep learning-based approaches in the field of image classification, segmentation, object detection, and tracking tasks. The core feature deep learning approach is the hierarchical representation of features from images and thus avoiding domain-specific handcrafted features. In this review paper, we have dealt with a Review of Deep Learning Architecture and Methods for MRI Brain Tumour Segmentation. First, we have discussed basic architecture and approaches for deep learning methods. Secondly, we have discussed the literature survey of MRI brain tumour segmentation using deep learning methods and its multimodality fusion. Then, the advantages and disadvantages of each method analyzed and finally concluded the discussion with the merits and challenges of deep learning techniques. The review of brain tumour identification using deep learning Techniques may help the research to have a better focus on it.

Identification of Brain Tumor Using Projection Pursuit Bivariate Multilayer Perceptred Classification

Identification of Brain Tumor Using Projection Pursuit Bivariate Multilayer Perceptred Classification

Brain Tumor Detection using Convolutional Neural Network

Brain tumor is the main threat among the people. But currently, it become more advanced because of the many Machine Learning techniques. Magnetic Resonance Imaging is the greatest technique among all the image processing techniques which scans the human body and gives a clear resolution of the tumors in an improved quality image. The fundamentals of MRI are to develop images based on magnetic field and radio waves of the anatomy of the body. The major area of segmentation of images is medical image processing. Better results are provided by MRI images than CT scan, X-rays etc. Nowadays the automatic tumor detection in large spatial and structural variability. Recently Convolutional Neural Network plays an important role in medical field and computer vision. One of its application is the identification of brain tumor. Here, the pre-processing technique is used to convert normal images to grayscale values because it contains equal intensity but in MRI, RGB content is included. Then filtering is used to remove the unwanted noises using median and high pass filter for better quality of images. The deeper architecture design in CNN is performed using small kernels. Finally, the effect of using this network for segmentation of tumor from MRI images is evaluated with better results.

A Combination of K-Means and Fuzzy C-Means for Brain Tumor Identification

Keywords are the labels of your manuscript and critical to correct indexing and searching. MRI or Magnetic Resonance Imaging is one of the health technologies used to scan the human body in order to get an image of an orgasm in the body. MRI imagery has a lot of noise that blends with the tumor object, so the tumor is quite difficult to detect automatically. In addition, it will be difficult to distinguish tumors from brain texture. Various methods have been carried out in previous studies. The method often used in the previous method is segmentation, but the process is quite heavy and the results that are less accurate are still the main obstacles. This study combines the K-Means method and Fuzzy C-Means (FCM) to detect tumors on MRI. The purpose of the combination is to get the advantages of each algorithm and minimize weaknesses. The method used is Contrast Adjustment using Fast Local Laplacian, K-Means FCM, Canny edge detection, Median Filter, and Morphological Area Selection. The dataset is taken from www.radiopedia.org. Data taken were 73 MRI of the brain, of which 57 MRIs with brain tumors and 16 MRIs of normal brain Evaluation of research results will be calculated using Confusion Matrix. The accuracy obtained is 91.78%.

A survey of the identification strategies of brain tumors for MR images

A substantial rise in medical cases associated with brain tumor has been seen in recent years, making it the 10th most common type of tumor Impacting both children and adults. Due to the rising refining of medical picture technologies, Brain Tumor [BT] and their study are of considerable concern Medical image processing concepts have been used successfully in diagnosis of Tumor. For its non-invasive imaging properties, science is more oriented toward MR. Diagnosis or identification mechanisms assisted by computers have become problematic and are still an Open concern due to heterogeneity in tumor shapes, locations, and sizes. Many experts in medical field have carried out notable study work on automated detection of tumor strategies based on segmentation, grouping and variations of automatic brain tumor detection. Different brain tumor identification methods for MR images are analysed in the manuscript, including the assets and challenges found with all techniques to detect different forms of BT. The survey presented here is aimed at supporting the researchers identify the important features of types of brain tumor and identify different segmentation/classification approaches that are effective in identifying a variety of tumor types of disorders of the brain. The manuscript covers the most important approaches, procedures and operating practices. Brain tumor identification rules, priorities, restrictions, and their potential snags on MR picture.

A Study on Segmenting Brain Tumor MRI Images

Segmentation of image has traditionally been referred to as the initial stage in image processing. A successful segmentation output will make image processing analysis considerably further easier. There are several image segmentation techniques and methodologies available. Clustering is the most widely used segmentation algorithm for image processing. Segmentation of tumor using magnetic resonance imaging (MRI) data is a critical procedure yet time-consuming process manually carried out by medical specialists. Due to the considerable difference in the tumor tissue appearances across patients, as well as their occasionally similar resemblance to normal tissues, automating this procedure is difficult. MRI is a sort of sophisticated medical imaging that offers precise information on the human soft tissues. To identify and segment the brain tumor using MRI images, several brain tumor segmentation and detection approaches are analyzed. The benefits and drawbacks of these approaches for brain tumor identification and segmentation are analyzed, with an emphasis on illuminating the benefits and limitations of these techniques for brain tumor segmentation and detection. The MRI image usage in segmentation and detection on various processes is also covered. This analysis provides an overview of several segmentation methods for identifying brain tumors from MRI images of the brain, as well as the usage of various Clustering Techniques.

HYBRID SHUFFLED FROG LEAPING ALGORITHM WITH PROBABILITY DISPERSAL METHOD FOR TUMOR DETECTION IN 3D MRI BRAINTUMOR IMAGES

In the medical image study, the brain tumor classification using MRIs is difficult due to the brain’s complicated structure and the high variance in tumor tissues’ position. So, the requirement for useful and specific tumor identification methods is developing for medical recognition and regular medical applications. The conventional brain tumor identification performs anatomical knowledge of irregular tissues in the brain, helping the doctor design approach. The research proposes several techniques for brain tumor identification. This work aims to present brain tumor identification methods based on evolutional intelligence and segmentation. Unusual areas in the brain are identified by using the Expectation-Maximization (EM) algorithm. For segmenting the 3D brain MRI data, this work presents a novel hybrid optimization meta-heuristic called the Shuffled Frog Leaping Algorithm (SFLA) with probability dispersal (i.e., SFLA - Stochastic Diffusion Search (SDS)). The efficacy of the suggested 3D SFLA probability dispersal EM in enhancing the performance of the 3D SFLA tabu EM has been proven by empirical outcomes.

A hybrid approach based on multiple Eigenvalues selection (MES) for the automated grading of a brain tumor using MRI

Background and objective:The manual segmentation, identification, and classification of brain tumor using magnetic resonance (MR) images are essential for making a correct diagnosis. It is, however, an exhausting and time consuming task performed by clinical experts and the accuracy of the results is subject to their point of view. Computer aided technology has therefore been developed to computerize these procedures.Methods:In order to improve the outcomes and decrease the complications involved in the process of analysing medical images, this study has investigated several methods. These include: a Local Difference in Intensity - Means (LDI-Means) based brain tumor segmentation, Mutual Information (MI) based feature selection, Singular Value Decomposition (SVD) based dimensionality reduction, and both Support Vector Machine (SVM) and Multi-Layer Perceptron (MLP) based brain tumor classification. Also, this study has presented a new method named Multiple Eigenvalues Selection (MES) to choose the most meaningful features as inputs to the classifiers. This combination between unsupervised and supervised techniques formed an effective system for the grading of brain glioma.Results:The experimental results of the proposed method showed an excellent performance in terms of accuracy, recall, specificity, precision, and error rate. They are 91.02%,86.52%, 94.26%, 87.07%, and 0.0897 respectively.Conclusion:The obtained results prove the significance and effectiveness of the proposed method in comparison to other state-of-the-art techniques and it can have in the contribution to an early diagnosis of brain glioma.

Brain Tumor identification by Convolution Neural Network with Fuzzy C-mean Model Using MR Brain Images

Medical image computing techniques are essential in helping the doctors to support their decision in the diagnosis of the patients. Due to the complexity of the brain structure, we choose to use MR brain images because of their quality and the highest resolution. The objective of this article is to detect brain tumor using convolution neural network with fuzzy c-means model, the advantage of the proposed model is the ability to achieve excellent performance using accuracy, sensitivity, specificity, overall dice and recall values better than the previous models that are already published. In addition, the novel model can identify the brain tumor, using different types of MR images. The proposed model obtained accuracy with 98%.

WITHDRAWN: Brain tumor identification using deep learning

In today’s world, brain tumor is detected in many people. The count of people affected with brain tumor, increases every day, irrespective of age and gender. The survival rates of brain tumor is very less when compared to other tumor cells. Brain tumor is the abundant growth of thick and unusual cells in brain. Brain tumor perhaps can be malignant tumor or benign. Malignant tumors aggressively spread to distant part of the body. Tumor that does not spread nearby tissue called as benign. Detection of brain tumor using various technologies is still under research. Brain tumor identification and segmentation in recent years is done by Magnetic Resonance Imaging (MRI). Software for accurate identification of brain tumor is still under existence. So, we propose an idea for identification and segmentation of brain tumor using deep learning. The first step will be processing the Magnetic Resonance Imaging (MRI) by giving it as the input, it is analyzed and segmented using various deep learning techniques such as initializing the CNN, pooling, flattening, compiling the CNN using Tensor Flow as backend. Thus, Identification and segmentation of brain tumor can be identified easily and efficiently.

Brain Tumour Detection by Gamma DeNoised Wavelet Segmented Entropy Classifier

Magnetic resonance imaging (MRI) is an essential tool for detecting brain tumours. However, identification of brain tumours in the early stages is a very complex task since MRI images are susceptible to noise and other environmental obstructions. In order to overcome these problems, a Gamma MAP denoised Strömberg wavelet segmentation based on a maximum entropy classifier (GMDSWS-MEC) model is developed for efficient tumour detection with high accuracy and low time consumption. The GMDSWS-MEC model performs three steps, namely pre-processing, segmentation, and classification. Within the GMDSWS-MEC model, the Gamma MAP filter performs the pre-processing task and achieves a significant increase in the peak signal-to-noise ratio by removing noisy artefacts from the input brain image. After pre-processing, Strömberg wavelet transform segmentation is carried out to partition the pre-processed image into a number of blocks based on the features extracted from the image. Finally, the maximum entropy classifier identifies and locates the tumour from the input image based on extracted features with high accuracy and minimal error rate. Using a number of MRI images, experimental evaluation and comparison of the proposed model and existing methods is carried out on the basis of four metrics: peak signal-to-noise ratio, tumour detection accuracy, error rate, and tumour detection time with respect to MRI image size. The proposed model offers superior performance in terms of all four metrics.

Intraoperative real-time near-infrared optical imaging for the identification of metastatic brain tumors via microscope and exoscope.

As chemotherapy and radiotherapy have developed, the role of a neurosurgeon in the treatment of metastatic brain tumors is gradually changing. Real-time intraoperative visualization of brain tumors by near-infrared spectroscopy (NIRS) is feasible. The authors aimed to perform real-time intraoperative visualization of the metastatic tumor in brain surgery using second-window indocyanine green (SWIG) with microscope and exoscope systems. Ten patients with intraparenchymal brain metastatic tumors were administered 5 mg/kg indocyanine green (ICG) 1 day before the surgery. In some patients, a microscope was used to help identify the metastases, whereas in the others, an exoscope was used. NIRS with the exoscope and microscope revealed the tumor location from the brain surface and the tumor itself in all 10 patients. The NIR signal could be detected though the normal brain parenchyma up to 20 mm. While the mean signal-to-background ratio (SBR) from the brain surface was 1.82 ± 1.30, it was 3.35 ± 1.76 from the tumor. The SBR of the tumor (p = 0.030) and the ratio of Gd-enhanced T1 tumor signal to normal brain (T1BR) (p = 0.0040) were significantly correlated with the tumor diameter. The SBR of the tumor was also correlated with the T1BR (p = 0.0020). The tumor was completely removed in 9 of the 10 patients, as confirmed by postoperative Gd-enhanced MRI. This was concomitant with the absence of NIR fluorescence at the end of surgery. SWIG reveals the metastatic tumor location from the brain surface with both the microscope and exoscope systems. The Gd-enhanced T1 tumor signal may predict the NIR signal of the metastatic tumor, thus facilitating tumor resection.

Image Processing Techniques for Brain Tumor Identification

At present, treatment of patients requires clinical pictures examination and is becoming a critical field. It fuses a wide scope of imaging procedures Some of them are Computed Tomography channels (CT examines), Magnetic Resonance Imaging (MRIs) and X-columns and so forth. These progressions help us to perceive even the littlest imperfections in the human body. Flighty development of tissues in the mind which sway genuine cerebrum limits is considered as a cerebrum tumour. The standard objective of clinical picture dealing with it is to see precise and vital data utilizing pictures with the base mess up conceivable. X-pillar is overwhelmingly used to get photographs of the human body and risky tissues as a result of its noteworthy norms and better-quality pictures separating other imaging headways. Brain tumor conspicuous bits of proof through MRI pictures is an irksome task because of the multifaceted design of the cerebrum. X-beam pictures can be readied and the psyche tumor can be partitioned. These tumors can be separated using diverse picture division techniques. The path toward recognizing cerebrum tumors through MRI pictures can be masterminded into four extraordinary territories; pre-planning, picture division, incorporate extraction and picture gathering.

Economic evaluation of GPs' direct access to computed tomography for identification of brain tumours.

When GPs suspect a brain tumour, a referral for specialist assessment and subsequent brain imaging is generally the first option. NICE has recommended that GPs have rapid direct access to brain imaging for adults with progressive sub-acute loss of central nervous function; however, no studies have evaluated the cost-effectiveness. We developed a cost-effectiveness model based on data from one region of the UK with direct access computed tomography (DACT), routine data from GP records and the literature, to explore whether unrestricted DACT for patients with suspected brain tumour might be more cost-effective than criteria-based DACT or no DACT. Although criteria-based DACT allows some patients without brain tumour to avoid imaging, our model suggests this may increase costs of diagnosis due to non-specific risk criteria and high costs of diagnosing or 'ruling out' brain tumours by other pathways. For patients diagnosed with tumours, differences in outcomes between the three diagnostic strategies are small. Unrestricted DACT may reduce diagnostic costs; however, the evidence is not strong and further controlled studies are required. Criteria-based access to CT for GPs might reduce demand for DACT, but imperfect sensitivity and specificity of current risk stratification mean that it will not necessarily be cost-effective.

A Review of Various Machine Learning Techniques for Brain Tumor Detection from MRI Images

This paper endeavors to identify an expedient approach for the detection of the brain tumor in MRI images. The detection of tumor is based on i) review of the machine learning approach for the identification of brain tumor and ii) review of a suitable approach for brain tumor detection. This review focuses on different imaging techniques such as X-rays, PET, CT- Scan, and MRI. This survey identifies a different approach with better accuracy for tumor detection. This further includes the image processing method. In most applications, machine learning shows better performance than manual segmentation of the brain tumors from MRI images as it is a difficult and time-consuming task. For fast and better computational results, radiology used a different approach with MRI, CT-scan, X-ray, and PET. Furthermore, summarizing the literature, this paper also provides a critical evaluation of the surveyed literature which reveals new facets of research. The problem faced by the researchers during brain tumor detection techniques and machine learning applications for clinical settings have also been discussed.

BOLD FMRI MAPPING OF ELOQUENT CORTICAL AREAS IN PATIENTS WITH BRAIN TUMOR USING INDEPENDENT PHYSIOLOGICAL PARAMETERS

Introduction . Preoperative fMRI often shows a reduced BOLD response in the areas located perifocal to brain tumors caused by pathological vasoreactivity as a result of neurovascular uncoupling. The aim of this study was an accurate identification of the eloquent cortical areas near brain tumors by measuring vasoreactivity using the breath holding test. Material and methods. 23 patients with brain tumors located near eloquent cortical areas underwent fMRI mapping of the language and / or motor cortical areas depending on the location of the tumor. Breath hold test was also included, the design of which coincided with motor and language block paradigms. Results . A statistical dependency between motor, speech tasks and breath-hold BOLD-response was included into the BOLD analysis using coherence. fMRI activation maps generated by this method showed activation in the eloquent areas adjacent to brain tumors which were not detected by the standard analysis. This study shows that neurovascular uncoupling affects the accuracy of BOLD fMRI in brain tumors. Conclusion. The results of fMRI mapping can be partially improved by the incorporating vasoreactivity measurements into a standard analysis.

Identification of Brain Tumor using Image Processing and Neural Networks

Artificial Intelligence (AI) is an umbrella consisting of many small blocks like machine learning, evolution computation, robotics, vision, natural language process and planning, speech processing etc. In the past years AI has developed a lot and given its share to make human life better, easy and compact. The word “technology” is a term which can be defined in many ways. The definition of the word keeps evolving with the continuous development in various fields. Decades ago, it used to take an entire room to accommodate a single computer but now we use the same computer at the ease of our fingertips. With the rapid development in technology mankind’s expectations and needs have also increased. Human race demands accurate results in less time with easier methods. The current rapidly developing field is AI which has also shown some extra ordinary results like the robot Sophie, Alexa, Siri etc. Mankind has very willingly adapted the use of AI in daily life and wants to excel more in the field. Neural Networks which is a very small section of AI but can be used vastly in various fields. The healthcare section has also improved its facilities and increased life expectancy. The motive behind this project is to use neural networks in the medical field for greater accuracy and instant results.

Method of multi‐region tumour segmentation in brain MRI images using grid‐based segmentation and weighted bee swarm optimisation

Multi-region segmentation plays a major role in numerous medical diagnostics especially brain tumour identification and classification in Magnetic Resonance Imaging (MRI). Brain tumour segmentation is used in medical field for early diagnostics and detection of tumour. The main goal of this work is to improve the performance of detection by using grid based techniques with Weighted Bee Swarm Intelligence and K-means clustering. This technique is more effective due to hybrid combination of segmentation and optimisation as it seems to possess specific tasks of image information and detection to obtain a detailed and accurate image analysis. Grid based segmentation balance overall computation time and reduces complexity. Weighted Bee Swarm Optimisation is used to optimise segmentation parameters to get maximum performance. The various informative regions such as cerebrospinal fluid, grey matter, white matter are segmented by using proposed algorithm which will be most useful to study and characterise the tumour. The experimental outcomes show that the proposed strategy enhances performance measures in terms of sensitivity and specificity analysis. The performance of this technique is also improved by a factor of 1.5%.

Interventions to reduce the time to diagnosis of brain tumours.

Brain tumours are recognised as one of the most difficult cancers to diagnose becausepresenting symptoms, such as headache, cognitive symptoms, and seizures, may be more commonly attributable to other, more benign conditions.Interventions to reduce the time to diagnosis of brain tumours include national awareness initiatives, expedited pathways, and protocols to diagnose brain tumours, based on a person's presenting symptoms and signs; and interventions to reduce waiting times for brain imaging pathways. If such interventions reduce the time to diagnosis, it maymake it less likely that people experience clinical deterioration, and different treatment options may be available. To systematically evaluate evidence on the effectiveness of interventions that may influence: symptomatic participants to present early (shortening the patient interval), thresholds for primary care referral (shortening the primary care interval), and time to imaging diagnosis (shortening the secondary care interval and diagnostic interval). To produce a brief economic commentary, summarising the economic evaluations relevant to these interventions. For evidence on effectiveness, we searched CENTRAL, MEDLINE, and Embase from January 2000 to January 2020; Clinicaltrials.gov to May 2020, and conference proceedings from 2014 to 2018. For economic evidence, we searched the UK National Health Services Economic Evaluation Database from 2000 to December 2014. We planned to include studies evaluating any active intervention that may influence the diagnostic pathway, e.g. clinical guidelines, direct access imaging, public health campaigns, educational initiatives, and other interventions that might lead to early identification of primary brain tumours. We planned to include randomised and non-randomised comparative studies. Included studies would include people of any age, with a presentation that might suggest a brain tumour. Two review authors independently assessed titles identified by the search strategy, and the full texts of potentially eligible studies. We resolved discrepancies through discussion or, if required, by consulting another review author. We did not identify any studies for inclusion in this review. We excluded 115 studies. The main reason for exclusion of potentially eligible intervention studies was their study design, due to a lack of control groups. We found no economic evidence to inform a brief economic commentary on this topic. In this version of the review, we did not identify any studies that met the review inclusion criteria for either effectiveness or cost-effectiveness. Therefore, there is no evidence from good quality studies on the best strategies to reduce the time to diagnosis of brain tumours, despite the prioritisation of research on early diagnosis by the James Lind Alliance in 2015. This review highlights the need for research in this area.