Affiliation:
1. CVR College of Engineering, India
2. Annamalai University, India
3. Vellore Institute of Technology, India
Abstract
Brain cancer poses a significant challenge to patient survival, necessitating early detection. Recent advancements in computer-aided diagnosis systems, leveraging magnetic resonance imaging (MRI), offer promising solutions for detecting brain tumors. This study introduces a transfer learning approach using deep learning to detect malignant brain tumors from MRI scans. Leveraging the YOLO (You Only Look Once) object detection framework, specifically YOLOv8, known for its efficiency in computational architecture, we present a deep learning-based approach for brain tumor identification and classification. By leveraging MRI analysis, our method aims to enhance detection and precise localization to improve patient prognosis and treatment outcomes. Employing the YOLOv8 model, we achieve a precision of 0.894 and a recall of 0.915 in brain cancer detection and an mAP_0.5 of 0.938 in brain cancer localization, demonstrating the effectiveness of the proposed model.
Reference18 articles.
1. Deep Convolutional Extreme Learning Machine with AlexNet-Based Bone Cancer Classification Using Whole-Body Scan Images
2. AppeS. N.ArulselviG. (2023). Advances in Computational Intelligence and Robotics: Vol. 278–289. G. N., B. Detection and Classification of Dense Tomato Fruits by Integrating Coordinate Attention Mechanism With YOLO Model.
3. An enhanced deep learning method for multi-class brain tumor classification using deep transfer learning
4. Graph CNN-ResNet-CSOA transfer learning architype for an enhanced skin cancer detection and classification scheme in medical image processing.;G. N.Balaji;International Journal of Artificial Intelligence Tools,2023
5. Brain tumor classification using deep CNN features via transfer learning