Related Experiment Video
Updated: Jul 8, 2026
06:48
Automated Segmentation of Cortical Grey Matter from T1-Weighted MRI Images
Published on: January 7, 2019
8.8K
Explainable artificial intelligence with UNet based segmentation and Bayesian machine learning for classification of
K Lakshmi1, Sibi Amaran2, G Subbulakshmi3
1Department of Information Technology, Sri Manakula Vinayagar Engineering College, Madagadipet, Puducherry, India.
Scientific Reports
|January 3, 2025
Summary
A new AI technique, XAISS-BMLBT, accurately detects brain tumors (BT) using MRI scans. This method enhances early diagnosis and treatment, improving patient survival rates with 97.75% accuracy.
Area of Science:
- Medical Imaging and Artificial Intelligence
- Machine Learning in Oncology
- Neuroscience and Diagnostic Technologies
Background:
- Early detection of brain tumors (BT) significantly improves patient outcomes and treatment efficacy.
- Magnetic Resonance Imaging (MRI) is crucial for detailed brain imaging, but manual analysis is labor-intensive and prone to errors.
- Deep learning, particularly Convolutional Neural Networks (CNNs), shows promise in analyzing medical images for improved diagnostic accuracy.
Purpose of the Study:
- To introduce a novel Explainable Artificial Intelligence with Semantic Segmentation and Bayesian Machine Learning for Brain Tumors (XAISS-BMLBT) technique.
- To enhance the accuracy and efficiency of brain tumor detection and classification from MRI scans.
- To provide a robust and interpretable AI model for clinical decision support in neuro-oncology.
Main Methods:
- Image pre-processing using bilateral filtering to reduce noise in MRI scans.
- Semantic segmentation using MEDU-Net+ to delineate affected brain regions.
- Feature extraction via ResNet50 and classification using a Bayesian Regularized Artificial Neural Network (BRANN).
- Hyperparameter optimization of the BRANN model using an improved radial movement optimization algorithm.
Main Results:
- The XAISS-BMLBT technique achieved a superior accuracy of 97.75% in detecting brain tumors.
- Experimental validation on a benchmark database demonstrated the effectiveness of the proposed method over existing approaches.
- The integrated approach of semantic segmentation, feature extraction, and Bayesian machine learning proved highly effective for BT analysis.
Conclusions:
- The XAISS-BMLBT technique offers a significant advancement in automated brain tumor detection and classification from MRI data.
- This explainable AI approach has the potential to reduce diagnostic errors and expedite patient treatment.
- The high accuracy achieved by XAISS-BMLBT supports its potential clinical utility in improving patient survival rates for brain tumors.
Related Concept Videos
01:24Magnetic Resonance Imaging
Magnetic resonance imaging (MRI) is a noninvasive medical imaging technique based on a phenomenon of nuclear physics discovered in the 1930s, in which matter exposed to magnetic fields and radio waves was found to emit radio signals. In 1970, a physician and researcher named Raymond Damadian noticed that malignant (cancerous) tissue gave off different signals than normal body tissue. He applied for a patent for the first MRI scanning device in clinical use by the early 1980s. The early MRI...
01:14Brain Imaging
Brain imaging technologies provide critical insights into both the structure and function of the human brain, enabling medical professionals and researchers to diagnose, study, and treat neurological disorders or psychiatric disorders more effectively.
These technologies include computerized axial tomography (CAT or CT scans), positron-emission tomography (PET scans), magnetic resonance imaging (MRI), functional magnetic resonance imaging (fMRI), and Transcranial Magnetic Stimulation (TMS).
These technologies include computerized axial tomography (CAT or CT scans), positron-emission tomography (PET scans), magnetic resonance imaging (MRI), functional magnetic resonance imaging (fMRI), and Transcranial Magnetic Stimulation (TMS).