Related Experiment Video
Updated: May 17, 2025
09:29
Live Imaging of Microtubule Dynamics in Glioblastoma Cells Invading the Zebrafish Brain
Published on: July 29, 2022
2.6K
Machine learning fusion for glioma tumor detection
C Gunasundari1, K Selva Bhuvaneswari2
1SRM Institute of Science and Technology, Tiruchirappalli, India. gunasundari.cs@gmail.com.
Scientific Reports
|April 2, 2025
Summary
This study presents a deep learning system for early brain tumor detection and glioma grading using MRI scans. The framework achieves high accuracy in classifying gliomas, promising improved patient care.
Area of Science:
- Medical Imaging
- Artificial Intelligence
- Oncology
Background:
- Early detection of brain tumors is critical for effective treatment and patient quality of life.
- Advanced imaging techniques aid in informed clinical decision-making for brain tumor diagnosis.
Purpose of the Study:
- To introduce a novel framework for a tumor detection system capable of grading gliomas.
- To develop and evaluate a deep learning model for accurate glioma classification.
Main Methods:
- Acquisition and analysis of brain magnetic resonance images (MRI).
- Extraction and independent component classification of key tumor and glioma features.
- Application of a deep learning model for categorizing gliomas into meningioma, pituitary, and glioma types.
Main Results:
- The proposed deep learning model achieved high performance metrics: 99.21% accuracy, 98.3% specificity, and 97.83% sensitivity.
- Successful classification of gliomas into three primary categories.
Conclusions:
- The developed system demonstrates significant potential for accurate and efficient brain tumor detection and grading.
- Further research and clinical validation are necessary to ensure widespread applicability and improve patient survival rates.
