BRAIN TUMOR DETECTION USING DEEP LEARNING

Authors

  • Seema Mishra School of Electronics Engineering, KIIT University, Bhubaneswar-751024 Odisha, India Author
  • Sukanta Kumar Sabut School of Electronics Engineering, KIIT University, Bhubaneswar-751024 Odisha, India Author

Keywords:

Brain tumor detection, Convolutional Neural Networks, Deep learning, Machine learning, Medical imaging, Transfer learning, VGG16, MRI analysis.

Abstract

Brain tumor detection and classification remains one of the most critical challenges in medical image analysis. This paper
presents a comprehensive deep learning approach for automated brain tumor detection and classification using Magnetic
Resonance Imaging (MRI) scans. We implement a Convolutional Neural Network (CNN) based on the VGG16 architecture
with transfer learning to classify brain MRI images into four distinct categories: glioma, meningioma, pituitary tumor, and
no tumor. Our implementation achieves 95.73% accuracy on the test dataset, with a weighted F1-score of 0.96. The
proposed system demonstrates robust performance in distinguishing between different tumor types and healthy brain scans,
showing particular strength in identifying no-tumor cases with 99% precision. This research contributes to the growing
field of computer-aided diagnosis systems and offers potential benefits for clinical applications in neurology and radiology.

Downloads

Published

2025-06-30

Issue

Section

Articles