Related Experiment Video
Updated: Sep 13, 2025
14:08
Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images
Published on: April 13, 2013
42.8K
BrainCNN: Automated brain tumor grading from magnetic resonance images using a convolutional neural network-based
Jing Yang1, Muhammad Abubakar Siddique2, Hafeez Ullah2
1Center of Research for Cyber Security and Network (CSNET), Faculty of Computer Science and Information Technology, Universiti Malaya 50603 Kuala Lumpur, Malaysia.
SLAS Technology
|July 25, 2025
Summary
This study developed an automated deep learning system for brain tumor grading using MRI scans. The novel approach achieved over 99% accuracy in classifying low-grade and high-grade brain tumors.
Area of Science:
- Medical Imaging
- Artificial Intelligence
- Oncology
Background:
- Accurate brain tumor grading is critical for treatment and survival.
- Magnetic Resonance Imaging (MRI) is a key diagnostic tool.
- Automated grading systems can improve efficiency and accuracy.
Purpose of the Study:
- To develop an automated brain tumor grading system using deep learning.
- To classify brain tumors into low-grade (LGT) and high-grade (HGT) categories.
- To enhance diagnostic accuracy and computational efficiency.
Main Methods:
- Utilized a dataset of 293 MRI scans.
- Developed a specialized Convolutional Neural Network (CNN) integrated with pre-trained models.
- Experimented with raw MRI slices, segmented tumor areas, and extracted features.
- Employed machine learning models including SVM, MobileNet, Inception V3, ResNet-50, and a custom CNN.
Main Results:
- Achieved a peak accuracy of 99.45% for brain tumor grading.
- Demonstrated high classification accuracies: 99.56% for LGT and 99.49% for HGT.
- Outperformed traditional methods in accuracy.
- Improved computational efficiency by reducing processing time.
Conclusions:
- The proposed deep learning model offers a highly accurate and efficient solution for automated brain tumor grading.
- This automated system has the potential to significantly improve patient treatment planning and outcomes.
- The integration of CNNs with MRI analysis represents a promising advancement in neuro-oncology diagnostics.
