Enhanced TumorNet: Leveraging YOLOv8s and U-net for superior brain tumor detection and segmentation utilizing MRI scans

Abstract

Brain tumors, characterized by abnormal cell growth, pose a significant challenge in clinical imaging due to their complex and diverse structures. Early and accurate identification, classification, localization, and segmentation of these tumors are critical to reducing mortality. However, the extensive data generated by MRI scans makes manual segmentation time-consuming and impractical for clinical use. To address these challenges, we propose, a hybrid deep learning model that precisely segmented tumor regions with U-Net to enable YOLOv8s to efficiently detect, classify and localize tumors. The model was trained and validated using The Cancer Imaging Archive (TCIA) dataset, which includes MRI images of brain tumors, and the Cancer Genome Atlas (CGA) low-grade glioma dataset, which includes data from 110 patients with FLAIR aberrant segmentation masks. The proposed hybrid model was evaluated using several performance metrics, including F1 score, specificity, recall, precision, accuracy, and ROC-AUC score. Hybrid proposed performed highly, achieving a precision of 97.8 %, accuracy of 98.6 %, recall of 95.2 %, F-1 score of 96.3 %, specificity of 89.1 %, and ROC-AUC score of 98.5 %. The integration of YOLOv8s and U-Net in Enhanced TumorNet offers a powerful solution for the automated analysis of brain tumors in MRI scans, significantly improving detection and segmentation accuracy. This hybrid approach holds great potential for clinical applications, enhancing the efficiency and effectiveness of brain tumor diagnosis. • Table 1 summarizes the studies mentioned, describing their techniques and limitations. Our research's primary contribution is the proposed hybrid deep learning model that integrates YOLOv8s with U-Net for tumor detection using MRI scans for precise tumor segmentation. The novelty of our approach is the combination of these two advanced architectures to increase the overall accuracy, efficiency, and robustness of brain tumor analysis, especially in terms of detection and segmentation. This hybrid model aims to overcome the limitations found in existing methods by leveraging the strengths of YOLOv8s in object detection and U-Net in segmentation, leading to high-performance measurements. • To increase efficiency, effectiveness and accuracy, we propose a hybrid approach using transfer learning techniques to YOLOv8s and U-Net with our dataset. This integration leverages the strengths of both architectures for superior results. • YOLOv8s uses bounding boxes for initial tumor identification and position estimation, which offers computational efficiency and suitability for real-time object detection. • By leveraging the bounding box information from YOLOv8s, a region of interest (ROI) containing the identified tumor can be extracted and subsequently processed by U-Net for more accurate segmentation of tumor boundaries. • U-Net's panoptic segmentation combines semantic and instance segmentation, offering detailed and accurate segmentation for all classes, including tumor and background regions. This two-step strategy, combining YOLO for object detection and U-Net for segmentation, ensures reliable and accurate identifying and classifying brain tumors.

Topics & Concepts