Brain Tumor Identification using Improved YOLOv8

TL;DR

This paper introduces an improved YOLOv8 model with RT-DETR, ghost convolution, and a vision transformer backbone for more accurate and faster brain tumor detection in MRI scans, outperforming existing detectors.

Contribution

The paper presents a novel YOLOv8-based model with integrated RT-DETR, ghost convolution, and transformer backbone, enhancing detection accuracy and efficiency for brain tumors in MRI images.

Findings

Achieved 0.91 mAP on brain tumor detection dataset.

Outperformed original YOLOv8 and other object detectors.

Reduced computational costs while maintaining high accuracy.

Abstract

Identifying the extent of brain tumors is a significant challenge in brain cancer treatment. The main difficulty is in the approximate detection of tumor size. Magnetic resonance imaging (MRI) has become a critical diagnostic tool. However, manually detecting the boundaries of brain tumors from MRI scans is a labor-intensive task that requires extensive expertise. Deep learning and computer-aided detection techniques have led to notable advances in machine learning for this purpose. In this paper, we propose a modified You Only Look Once (YOLOv8) model to accurately detect the tumors within the MRI images. The proposed model replaced the Non-Maximum Suppression (NMS) algorithm with a Real-Time Detection Transformer (RT- DETR) in the detection head. NMS filters out redundant or overlapping bounding boxes in the detected tumors, but they are hand-designed and pre-set. RT-DETR removes hand-designed components. The second improvement was made by replacing the normal convolution block with ghost convolution. Ghost Convolution reduces computational and memory costs while maintaining high accuracy and enabling faster inference, making it ideal for resource-constrained environments and real-time applications. The third improvement was made by introducing a vision transformer block in the backbone of YOLOv8 to extract context-aware features. We used a publicly available dataset of brain tumors in the proposed model. The proposed model performed better than the original YOLOv8 model and also performed better than other object detectors (Faster R- CNN, Mask R-CNN, YOLO, YOLOv3, YOLOv4, YOLOv5, SSD, RetinaNet, EfficientDet, and DETR). The proposed model achieved 0.91 mAP (mean Average Precision)@0.5.