Brain Tumor Detection Based on Deep Learning Approaches and Magnetic Resonance Imaging

Abstract

The rapid development of abnormal brain cells that characterizes a brain tumor is a major health risk for adults since it can cause severe impairment of organ function and even death. These tumors come in a wide variety of sizes, textures, and locations. When trying to locate cancerous tumors, magnetic resonance imaging (MRI) is a crucial tool. However, detecting brain tumors manually is a difficult and time-consuming activity that might lead to inaccuracies. In order to solve this, we provide a refined You Only Look Once version 7 (YOLOv7) model for the accurate detection of meningioma, glioma, and pituitary gland tumors within an improved detection of brain tumors system. The visual representation of the MRI scans is enhanced by the use of image enhancement methods that apply different filters to the original pictures. To further improve the training of our proposed model, we apply data augmentation techniques to the openly accessible brain tumor dataset. The curated data include a wide variety of cases, such as 2548 images of gliomas, 2658 images of pituitary, 2582 images of meningioma, and 2500 images of non-tumors. We included the Convolutional Block Attention Module (CBAM) attention mechanism into YOLOv7 to further enhance its feature extraction capabilities, allowing for better emphasis on salient regions linked with brain malignancies. To further improve the model’s sensitivity, we have added a Spatial Pyramid Pooling Fast+ (SPPF+) layer to the network’s core infrastructure. YOLOv7 now includes decoupled heads, which allow it to efficiently glean useful insights from a wide variety of data. In addition, a Bi-directional Feature Pyramid Network (BiFPN) is used to speed up multi-scale feature fusion and to better collect features associated with tumors. The outcomes verify the efficiency of our suggested method, which achieves a higher overall accuracy in tumor detection than previous state-of-the-art models. As a result, this framework has a lot of potential as a helpful decision-making tool for experts in the field of diagnosing brain tumors.

ContourTL-Net: Contour-Based Transfer Learning Algorithm for Early-Stage Brain Tumor Detection

“…Though this model showed considerable performance, however, for the heterogonous data, it showed a decrease in sensitivity. An advanced deep learning model, YOLOv7, has been operated by [ 31 ] to perform transfer learning on a large MRI collection to detect multitype tumor location precisely and achieve 99.5% accuracy. The convolutional block attention module (CBAM) was added to the YOLOv7 model to obtain these results.…”

Brain tumor classification: a novel approach integrating GLCM, LBP and composite features

“…Another study by Abdusalomov et al. ( 4 ) used YOLOv7 and transfer learning to improve brain tumor diagnosis in MRI scans, they report an outstanding 99.5% accuracy for identifying the most common types of brain tumors Glioma, Meningioma, Pitutary. However, they also acknowledge the need for additional research, particularly for minor tumor identification ( 4 ).…”

“…As discussed by Abdusalomov et al. ( 4 ) Glioma, Meningioma, Pitutary seem to be the common types of brain tumors that look like non-cancerous, but may be. Hence this research intends to study these brain tumors and classify them by incorporating advanced features such as GLCM and LBP, as well as interaction features and statistical analysis.…”

SIENNA: Generalizable Lightweight Machine Learning Platform for Brain Tumor Diagnostics

“…Relying on highly preprocessed public datasets creates challenges for generalizability of the AI platforms for advancing towards AGI [11]. Furthermore, shortcut learning [12,13] has recently emerged as a significant drawback in various ML approaches, alongside the well-known issue of overfitting [14]. In shortcut learning, ML models struggle to capture the desired morphological features of images and instead resort to exploiting undesired patterns to achieve high cross-validation performance.…”