Related Experiment Video
Updated: Jun 9, 2026
06:48
Automated Segmentation of Cortical Grey Matter from T1-Weighted MRI Images
Published on: January 7, 2019
8.9K
Mask region-based convolutional neural network and VGG-16 inspired brain tumor segmentation
Niha Kamal Basha1, Christo Ananth2,3, K Muthukumaran4
1School of Computer Science and Engineering, Vellore Institute of Technology (VIT), Vellore, Tamil Nadu, India.
Scientific Reports
|July 30, 2024
Summary
This study introduces an effective brain tumour detection method using deep learning on MRI scans. The proposed model achieved nearly 99% accuracy and sensitivity, significantly improving diagnostic capabilities.
Area of Science:
- Medical Imaging Analysis
- Artificial Intelligence in Healthcare
- Neuro-oncology Diagnostics
Background:
- Brain tumour segmentation is crucial for accurate diagnosis and treatment planning.
- Magnetic Resonance Imaging (MRI) is the standard for detecting brain abnormalities.
- Existing methods require enhancement for improved precision in tumour localization.
Purpose of the Study:
- To develop an effective and highly accurate method for brain tumour detection using deep learning.
- To improve diagnostic accuracy for medical professionals.
- To leverage advanced AI techniques for precise tumour segmentation and identification.
Main Methods:
- Utilized region-based Convolutional Neural Network (R-CNN) masks for segmentation.
- Employed Grad-CAM and transfer learning for effective tumour detection.
- Trained models using Inception V3, VGG-16, and ResNet-50 architectures on the Brain MRI Images for Brain Tumour Detection dataset.
Main Results:
- The transfer learning-based model demonstrated high sensitivity and accuracy.
- Achieved approximately 99% accuracy and sensitivity, outperforming current methods.
- Performance was evaluated using recall, specificity, sensitivity, accuracy, precision, and F1 score.
Conclusions:
- The proposed method offers a significant advancement in brain tumour detection accuracy.
- Deep learning models, particularly with VGG-16 influence, show strong potential for clinical application.
- The approach aids clinicians in making highly accurate diagnoses, improving patient outcomes.
