International Research Journal of Engineering and Technology (IRJET)
e-ISSN: 2395-0056
Volume: 12 Issue: 05 | May 2025
p-ISSN: 2395-0072
www.irjet.net
DETECTION OF BRAIN TUMORS FROM MRI IMAGE USING YOLO ALGORITHM Prof .M. Kavitha1, Vishali Lakshmanan2, S. Vasuki3, K. Abarna4, M.Harini⁵ 1Assistant Professor, Government College of Engineering Srirangam, Tamil Nadu, India 2,3,4,5UG Student, Department of CSE, Government College of Engineering Srirangam, Tamil Nadu, India
-------------------------------------------------------------------------***-----------------------------------------------------------------------brain that resembles a fibrous web. Approximately 3,540 ABSTRACT
children under the age of 15 are diagnosed with brain tumors this year. It is crucial to have a proper understanding of brain tumors and their stages in order to prevent and treat the illness. An abnormal mass of tissue in which cells grow and multiply uncontrollably, seemingly unchecked by the mechanisms that control normal cells, is called an intracranial tumor, or brain tumor. Although there are over 150 distinct types of brain tumors known to exist, primary and metastatic brain tumors are the two main categories. Tumors that arise from the brain's tissues or the brain's surrounding tissues are referred to as primary brain tumors. Primary tumors can be classified as benign or malignant, glial (made up of glial cells) or non-glial (developed on or in the brain's structures, such as nerves, blood vessels, and glands). Tumors that originate in other parts of the body, like the breast or lungs, and spread to the brain, usually via the bloodstream, are referred to as metastatic brain tumors. Metastatic tumors are malignant and categorized as cancer. The types of tumors are shown in Fig 1.
Due to their complexity and sensitivity, classifying brain diseases is a very difficult task. Because brain tumors are serious and sometimes fatal, early detection and diagnosis are essential for developing an efficient treatment plan. A vital medical imaging tool, magnetic resonance imaging (MRI) allows for the detailed, non-invasive visualization of the internal structures of the brain. When it comes to diagnosing and treating brain tumors,, magnetic resonance imaging (MRI) plays a critical role. Starting with dataset preprocessing, the method applies to MRI scans and clinical data from people with different brain conditions, including cases of tumors and non-tumors. Training and testing sets make up the dataset. MRI tumor detection requires a number of processes, including feature extraction, classification, and image postprocessing. For classifying and detecting brain tumors, the system makes use of the YOLO (You Only Look Once) algorithm with the CNN model, a pre-trained model utilizing the approach of transfer learning. The proposed framework not only uses the pre-trained model to improve the performance of training a better model but also uses thresholding to refine the dataset for better accuracy and data augmentation for increasing the number of images in the dataset. Preliminary outcomes show that the family of YOLO models performs better than previous architectures because it scales all dimensions of depth, width, and resolution of an image using a compound coefficient with a constant ratio. The results also demonstrated that by scaling the baseline architecture, the model is able to capture complicated features, and thus the overall performance of the system is significantly improved.
KEYWORDS:
Brain tumor classification, convolutional neural network, medical imaging, deep learning, YOLO model.
1.INTRODUCTION One of the most vital organs in the human body, the brain aids in decision-making and regulates the operation of all other organs. It is principally in charge of managing the daily voluntary and involuntary bodily functions and serves as the central nervous system's command center. The tumor is an uncontrolled, proliferating mass of unwanted tissue growth inside our
© 2025, IRJET
|
Impact Factor value: 8.315
Fig 1: Brain Tumor Types
2. LITERATURE REVIEW Saeed Mohsen et al.[1] described using hyper-parameter optimization to implement ResNext101_32 × 8d and VGG19 models to improve the accuracy of brain tumor
|
ISO 9001:2008 Certified Journal
|
Page 129