International Research Journal of Engineering and Technology (IRJET) Volume: 09 Issue: 11 | Nov 2022
www.irjet.net
e-ISSN: 2395-0056 p-ISSN: 2395-0072
A Comparative Study of Various Machine Learning Techniques for Brain Tumor Detection Prof. Priyanka Shahane1, Devansh Choudhury2, Ankit Kumar3 1Asst. Professor, Department of Computer Engineering, SCTR’s Pune Institute Of Computer Technology, Pune, India. 2Student, Department of Computer Engineering, SCTR’s Pune Institute Of Computer Technology, Pune, India.
Student, Department of Computer Engineering, SCTR’s Pune Institute Of Computer Technology, Pune, India. ---------------------------------------------------------------------***--------------------------------------------------------------------Abstract - Brain tumors are produced by abnormal brain 2. LITERATURE SURVEY 3
cell growth and can be fatal. Early tumor discovery can lower the mortality rate. In recent years, machine learning algorithms have replaced human doctors' proneness to error in diagnosing tumors when it comes to medical imagery and data. Early disease prediction can be done efficiently by using the right data mining categorization technique. Data mining and machine learning techniques have a large place in the medical industry. The accuracy of the system strongly depends on a variety of computations employed in medical processing and imaging. The main objective is to study various Machine Learning techniques for brain tumor detection.
Key Words: Data Mining, Brain tumor Detection, Machine Learning, Classification, Clustering. 1. INTRODUCTION Essentially, a tumor represents the aberrant and unregulated cell development within the body. A brain tumor is a distorted mass of tissue in which the brain tissues experience sudden, uncontrollable cell multiplication. The detection of brain tumors is one of the most difficult jobs involved in the processing of medical pictures. A brain tumor is characterized by an abnormal or unusual growth of brain cells. Grading anomalies, evaluating the tumor, and treating it are all made easier with regular tumor tissue monitoring. For this procedure, the doctors need imaging technology. Images produced by medical resonance imaging (MRI) are clearer and more accurate due to their better spatial resolution. It is essential for figuring out the pathology and size of the tumor. The processes in traditional machine learning classification approaches are often limited to preprocessing, feature extraction, feature selection, dimension reduction, and classification. Despite the astoundingly low number of methods that have been used due to the multiple inherent difficulties, deep learning algorithms, and in particular CNN, have demonstrated extraordinary effectiveness in bioinformatics.
© 2022, IRJET
|
Impact Factor value: 7.529
|
Khairandish et. al. [1] provided an explanation of how brain tumors actually behave, and with the aid of many methodologies and the analysis of research studies using a variety of criteria, it offers a clear image of this stage. The examination is conducted in relation to the dataset, proposed model, proposed model performance, and type of method used in each paper. Between 79 and 97.7% of the publications under study had accurate results. They employed Convolutional Neural Network, K-Nearest Neighbour, K-Means, and Random Forest algorithms, in that sequence (highest frequency of use to lowest). Here Convolutional Neural Network gave the highest accuracy of around 79-97.7% Someswararao et. al. [2] developed a new novel method for detecting tumors in MR images By using machine learning techniques, particularly the CNN model, in this study. This study combined a CNN model classification challenge for determining whether or not a subject has a brain tumor with a computer vision problem to automatically crop the brain from MRI scans. Other techniques used were Convolutional Neural Network, K-Means Clustering and the highest Accuracy is given by Convolutional Neural Network which is around 90%. Choudhury et. al. [3] proposed a new CNN-based system that can distinguish between different brain MRI images and label them as tumorous or not. The model's accuracy was 96.08%, and its f-score was 97.3. The model uses a CNN with three layers and only a few pre-processing steps to yield results in 35 epochs. The goal of this study is to emphasize the significance of predictive therapy and diagnostic machine learning applications. Other techniques used were Support Vector Machine, Convolutional Neural Network, k-Nearest Neighbour, Boosted trees, Random forest and Decision trees. Hemanth et. Al [4] concluded that Data mining and Machine learning techniques have a large place in the medical industry, majority of which is effectively adopted. A list of risk factors that are being tracked down by brain tumor monitoring systems is examined in this study. Additionally, the technique used in brain tumor surveillance systems. For
ISO 9001:2008 Certified Journal
|
Page 726