Detection and Localization of Early-Stage Multiple Brain Tumors Using a Hybrid Technique of Patch-Based Processing, k-means Clustering and Object Counting

Abstract

Brain tumors are a major health problem that a ect the lives of many people. ese tumors are classi ed as benign or cancerous. e latter can be fatal if not properly diagnosed and treated. erefore, the diagnosis of brain tumors at the early stages of their development can signi cantly improve the chances of patient's full recovery a er treatment. In addition to laboratory analyses, clinicians and surgeons extract information from medical images, recorded by various systems such as magnetic resonance imaging (MRI), X-ray, and computed tomography (CT). e extracted information is used to identify the essential characteristics of brain tumors (location, size, and type) in order to achieve an accurate diagnosis to determine the most appropriate treatment protocol. In this paper, we present an automated machine vision technique for the detection and localization of brain tumors in MRI images at their very early stages using a combination of k-means clustering, patch-based image processing, object counting, and tumor evaluation. e technique was tested on twenty real MRI images and was found to be capable of detecting multiple tumors in MRI images regardless of their intensity level variations, size, and location including those with very small sizes. In addition to its use for diagnosis, the technique can be integrated into automated treatment instruments and robotic surgery systems.

Detection and Classification of Knee Injuries from MR Images Using the MRNet Dataset with Progressively Operating Deep Learning Methods

“…Kempen et al [26], for example, presented a comprehensive study analysis of the most prevalent glioma tumour in the brain, which employed machine learning approaches. In addition, Nasor and Obaid [27] developed the diagnosis and localisation of brain tumours through the combination of k-means clustering, object counting and patch-based image processing assessment techniques with computer vision methods. Breast cancer is also one of the most prevalent cancers among women.…”

“…Breast cancer is classified by the regions where tumours are discovered, and the incidence of cancers varies depending on the part of the breast [56,57]. There are also several studies based on the locations of tumours in the brain [27,58]. When diagnosing benign and malignant tumours from MRI image indexes, the image range to be diagnosed in the diagnostic image index can be selected and the suitability for diagnosis can be analysed according to the noise condition if the regions with tumours in the dataset are marked and trained with Model 1.…”

Investigation of Magneto-/Radio-Metric Behavior in Order to Identify an Estimator Model Using K-Means Clustering and Artificial Neural Network (ANN) (Iron Ore Deposit, Yazd, IRAN)

“…Accordingly, it has its applications in each branch of science. The application of clustering methods (e.g., K-means and hierarchical methods) is performed to analyze exploratory data, such as geochemistry and geophysics, to categorize data to achieve a specific goal [11,12]. One of the applications of the clustering method is in the analysis of geochemical data from the sampling of stream sediments.…”

Variable Structure Based Control for the Chemotherapy of Brain Tumor

“…Brain tumor is a life threatening problem. Although there are more than 120 types of brain tumors but they can be categorized into two major types: primary and secondary brain tumors [1]- [3]. Tumor that occurs inside the skull, is termed as primary brain tumor, while in case of a secondary brain tumor, cancer cells spread to brain from other organs, for example, lung or breast, also known as a metastatic brain tumor [1], [4]- [6].…”