MRI Brain Tumor Detection with Computer Vision

TL;DR

This study explores the application of deep learning techniques in the automated detection and segmentation of brain tumors from MRI scans, and investigates the use of U-Net for semantic segmentation and EfficientDet for anchor-based object detection to enhance the localization and identification of tumors.

Abstract

This study explores the application of deep learning techniques in the automated detection and segmentation of brain tumors from MRI scans. We employ several machine learning models, including basic logistic regression, Convolutional Neural Networks (CNNs), and Residual Networks (ResNet) to classify brain tumors effectively. Additionally, we investigate the use of U-Net for semantic segmentation and EfficientDet for anchor-based object detection to enhance the localization and identification of tumors. Our results demonstrate promising improvements in the accuracy and efficiency of brain tumor diagnostics, underscoring the potential of deep learning in medical imaging and its significance in improving clinical outcomes.

Figures (5)

• Figure 1: Classification Class Distribution
• Figure 2: Brain MRI Classification Data
• Figure 3: Results of U-Net training on the test splits of various datasets. Center image shows overlap between label (blue) and prediction (red).
• Figure 4: Segmentation Results
• Figure 5: (A) Anchor classification (B) Anchor regression