Related Experiment Video
Updated: Aug 30, 2025
14:08
Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images
Published on: April 13, 2013
42.8K
A framework for in-vivo human brain tumor detection using image augmentation and hybrid features.
Manika Jha1, Richa Gupta1, Rajiv Saxena1
1Department of Electronics and Communication, Jaypee Institute of Information Technology, Noida, 201309 India.
Health Information Science and Systems
|August 31, 2022
Summary
This study introduces an advanced method for brain tumor classification using Extreme Gradient Boosting (XGBoost) and feature fusion. The approach achieved high accuracy in identifying four brain tumor subtypes from MRI scans.
Area of Science:
- Medical Imaging
- Artificial Intelligence
- Oncology
Background:
- Accurate brain tumor segmentation and classification are challenging due to variations in tumor characteristics.
- Early detection and classification are crucial for effective treatment and improved patient outcomes.
Purpose of the Study:
- To develop and evaluate an Extreme Gradient Boosting (XGBoost) algorithm for classifying four brain tumor subtypes: normal, gliomas, meningiomas, and pituitary tumors.
- To enhance a limited dataset using conditional Generative Adversarial Network (cGAN) for improved model training.
Main Methods:
- Feature extraction through the fusion of deep features, Two-Dimensional Fractional Fourier Transform (2D-FrFT) features, and geometric features from MRI scans.
- Utilizing a conditional Generative Adversarial Network (cGAN) for data augmentation to address dataset limitations.
- Employing an Extreme Gradient Boosting (XGBoost) algorithm for the classification task.
Main Results:
- The proposed model achieved a high classification accuracy of 98.79% and sensitivity of 98.77% on test images.
- Demonstrated significant improvement compared to existing state-of-the-art algorithms on the Kaggle brain tumor dataset.
- Feature fusion proved crucial for enhancing model performance.
Conclusions:
- The study highlights the effectiveness of feature fusion in improving brain tumor detection accuracy.
- XGBoost is established as a suitable classifier for brain tumor detection, demonstrating high accuracy, sensitivity, and Area Under the Receiver Operating Characteristic (AUROC) curve.
