Fig 1 - uploaded by Mohammed Y. Kamil
Content may be subject to copyright.
Source publication
Brain tumor is serious and life-threatening because it found in a specific area inside the skull. Computed Tomography (CT scan) which be directed into intracranial hole products a complete image of the brain. That image is visually examined by the expert radiologist for diagnosis of brain tumor. This study provides a computer aided method for calcu...
Similar publications
span>This paper primarily focuses on to employ a novel approach to classify the brain tumor and its area. The Tumor is an uncontrolled enlargement of tissues in any portion of the human body. Tumors are of several types and have some different characteristics. According to their characteristics some of them are avoidable and some are unavoidable. B...
The objective of this research is to investigate the abnormal images of brain having diseases of brain tumors using machine learning tool and to measure their texture which involves shape, intensity and texture parameter of brain. All of these images were run by the machine learning tool and compared these results with the normal image of brain. If...
Citations
... All these imaging techniques are shown in Figure 1. Mohammed Kamil (Kamil 2015) presented his framework of a computer aided method that successfully detected the region of brain tumor from s Computed Tomography (CT) scan. The framework used the techniques of image enhancement and mathematical morphology, coupled with thresholding to segment the tumor. ...
Brain tumor is a commonly known medical condition which has a very low survival rate due to delayed diagnosis and treatment. With the advancement of information technology and machine learning, various computer aided techniques have been studied in recent years to segment tumor region from given brain scan for early detection and treatment. However, health workers are still hesitant to adopt those techniques into their clinical systems due to insufficient comprehensive analysis of those techniques. Therefore, in this paper we compare the segmentation results of various computer aided algorithm. First, we present a survey of various segmentation techniques based on region-based, unsupervised learning and classifier approaches for tumor detection from MRI of the brain. These techniques differ based on using proximity and features of pixel for segmenting desired region. Next, we take a well-known and accepted algorithm for each of these categories to test the results. The selected algorithms are Marker Controlled Watershed, K-Means Clustering and Convolutional Neural Networks (CNN). 3D Brain MRI scans are used for the study where the data images are first pre-processed and converted into 155 2D slices for each image. Further, all these 155 2D slices are processed using three chosen algorithms. The results of the three techniques are then compared using evaluation metrices like DICE and IOU. The comparison results show that the classifier-based technique, i.e., CNN outperforms the others with a high accuracy of 83-86%. This research is expected to help medical workers to make an informed decision and implement computer aided systems to their clinical processes to reduce the manual labour and time.
... On the basis of one particular feature, each interior node that includes decision criteria is based. The entropy reduction that presents the purity of samples is used to calculate the features that are in relevance to classification [8]. The classifier through which two classes are separated using a hyper plane is known as Support Vector Machine (SVM). ...
... On the basis of one particular feature, each interior node that includes decision criteria is based. The entropy reduction that presents the purity of samples is used to calculate the features that are in relevance to classification [8]. The classifier through which two classes are separated using a hyper plane is known as Support Vector Machine (SVM). ...
The brain tumor detection is the approach which can detect the tumor portion from the MRI image. To detect tumor from the image various techniques has been proposed in the previous times. The technique which is proposed in this research paper is based on morphological scanning and naïve bayes classification. The morphological scanning will scan the input image and naïve bayes classifier mark the tumor portion from the MRI image. The proposed algorithm is implemented in MATLAB and results are analyzed in terms of PSNR, MSE and accuracy and fault rate.
... 978-1-5386-4844-5/18/$31.00 ©2018 IEEE In this regard, Mohammed Kamil in [12] presented a computer aided method to detect the brain tumor using Computed Tomography (CT) Scan images of brain. The methodology used included the use of threshold values, image enhancement and application of morphological operations. ...
Designing automated systems for brain tumor extraction from a Medical Resonance Image is one of the most researched areas of the era. Automated systems will assist the doctors in automatic and early stage tumor detection which will allow doctors to spend more time on the treatment of the patient. This study uses marker controlled watershed segmentation to segment abnormally grown mass in brain, known as brain tumor, from an input 3D MR Image. 2D MRI give a restricted view of the brain, in this case, having a 3D image, will give a complete and comprehensive insight of any kinds of abnormalities residing inside the brain. The framework presented in this paper not only gives a thorough view of the brain, but also segments the tumor with great accuracy as depicted by the results.
... In this regard, Mohammed Kamil in [12] presented a computer aided method to detect the brain tumor using Computed Tomography (CT) Scan images of brain. The methodology used included the use of threshold values, image enhancement and application of morphological operations. ...
... a) Input brain image with tumor region of MRI b) The input brain image without tumor region of MRI c) The smoothed image using average filter [21]. Fig.2.a) CT-scan image of brain tumor b) after using morphological gradient c) using region of interest [20]. Fig.3.a) ...
Image Enhancement is the utmost substantial and inspiring techniques in the field of medical research. The aim of image enhancement is to strengthen the visual manifestation of an image or to convey an enhanced transmute symbol for automated image processing. Many images like medical images, satellite images, aerial images and even real life photos suffer from poor contrast and noise. One of the most significant stages in medical images detection and analysis is Image Enhancement techniques, increases the eminence of images for human viewing and further analysis. After elimination of blurring and noise and increasing contrast, morphological operations are used for revealing details in enhancement operations. Morphological filters are constructed on a practice of set algebra known as mathematical morphology. Most morphological filters are used in extreme order within a filter window, so they are closely related to order statistic filters. This paper gives a brief review on medical image preprocessing techniques based on morphological operations. Here, the input images are taken from four different medical imaging modalities namely MRI, CT, mammogram, and ultrasound.
... Morphological opening method removes small objects from an image while preserving the shape and size of larger objects in the image. Dilation and erosion are often used in combination to implement image processing operations like morphological opening of an image has been an erosion followed by a dilation, morphological closing of an image, is the reverse: it consists of dilation followed by an erosion with the same structuring element [8,9]. ...
This paper is focused on a study of various techniques of brain tumor detection of MRI images using DIP techniques. The study of various techniques is useful for successful diagnosis and treatment planning of brain tumor. Magnetic Resonance Imaging (MRI) method is used for brain imaging and analyzing internal structures in detail. The accuracy of detecting the brain tumor location and size with good quality takes the most important role of detecting the brain tumor. The brain tumor segmentation carried manually from MRI images is very crucial and time consuming task. Therefore, to avoid that, it needs to use computer aided method for detection of brain tumor. The brain MRI images using various image processing methods like preprocessing, segmentation, morphological operation are used; based on different feature combinations as color (intensity), edge, texture and calculated the tumor area as well as measure the quality of input then output images, it gives a satisfactory result. This research work is helpful in the medical field to detect brain tumors and suggest a treatment plan to the patient .
... Mohammed Y. Kamil[10] extract tumor region and calculates the area of tumor from CT scan images. Contrast-limited adaptive histogram equalized method for image enhancement. ...
In this paper two different problems patient information separation and segmentation of CT scan brain images are handled. Medical images carry patient sensitive information. It restricts the public access to such images. Also segmentation of pathological tissues from medical images is also one of the challenging tasks. This paper presented the simple and effective solution to these two problems. Morphological erosion and dilation is used to separate the patient information from the CT scan brain images and the same image is processed further to extract abnormalities from it.
... Morphological operators have used instead of classical image gradient for edge detection like Prewitt, Sobel, Roberts, Laplacian of Gaussian, Huertas, Medioni, and Canny because these algorithms are sensitive to noise when edge detection [1,2]. Morphological gradient is essentially determined by the difference of morphological dilation and erosion, the dilation defined by permit objects to poke out and connecting disjoint objects, while erosion contract objects by turn away their margins [3,4]. ...
The morphological operations commonly used image gradient for gray level images in medical images. Medical images are usually poorly illuminated and several edges are not visible accurately. This paper have used the morphological gradient (erosion-dilation computation) of the fuzzy mathematical morphology based on Hamacher t-norm and t-conorm, and comparison with classical morphological gradient. The results of evaluation shown clearly of the effectiveness of the fuzzy morphological approach in brain magnetic resonance imaging compared to classical morphological based on statistical image quality.
Brain tumor is one of the most prevalent and life-threatening illness these days. A tumor is an aberrant mass of tissue caused by unrestrained cell proliferation and multiplication. It is important to detect and diagnose brain tumors at the early stages. For disease diagnosis at an initial stage, there is a high demand for accurate analysis of healthcare data. But tumors vary greatly in size, shape, and existence, making it extremely difficult to collect precise measurements in order to properly diagnose them. Digital image processing enacts a crucial role in the analysis of medical images for timely and efficient planning of treatment. This paper provides an insight into brain tumors, the mechanism involved in their detection along with the different image processing steps that can be applied to medical images for automating the brain tumor detection process. This paper reviews a significant number of recently proposed brain tumor detection techniques related to the current study along with their tabulated comparison. This work can help in designing a solution that provides different applications such as detection, localization, or identifying the type of tumor under a single model.
