A Multilevel Deep Learning Model for Automated Brain Tumor Segmentation Using Magnetic Resonance Images

Area of Science:

• Medical Imaging
• Artificial Intelligence
• Neuroscience

Background:

• Accurate brain tumor segmentation from MRI is crucial for clinical assessment and treatment planning.
• Challenges include complex anatomy, tumor variability, and imbalanced datasets, necessitating automated methods.
• Existing methods often struggle with precise delineation of tumor regions.

Purpose of the Study:

• To develop and evaluate a multilevel deep learning model for automated brain tumor segmentation using MRI.
• To improve segmentation accuracy by addressing the class imbalance inherent in medical imaging datasets.
• To enhance the reliability of automated tumor delineation for clinical applications.

Main Methods:

• Utilized the BraTS dataset for model development and validation.
• Implemented a modified Synthetic Minority Oversampling Technique (SMOTE) to mitigate class imbalance.
• Employed a Multilevel Architecture-Based Modified U-Net to learn multiscale spatial features for pixel-wise segmentation.

Main Results:

• The proposed model demonstrated superior performance compared to BWT-based and conventional U-Net methods across various tumor grades.
• Achieved higher Dice, Jaccard, and Matthews Correlation Coefficient (MCC) values, indicating improved segmentation accuracy.
• Results show better agreement between predicted segmentations and ground truth masks for precise tumor delineation.

Conclusions:

• The multilevel deep learning model offers an effective framework for automated brain tumor segmentation from MRI.
• The combination of imbalance-aware preprocessing and a modified U-Net architecture enhances segmentation performance.
• Future research will involve external dataset validation and comparison with state-of-the-art models.