RETRACTED: Automated brain tumor diagnostics: Empowering neuro-oncology with deep learning-based MRI image analysis

Area of Science:

• Medical Imaging
• Artificial Intelligence
• Computational Biology

Background:

• Brain tumors present a significant health challenge, necessitating early detection for effective treatment.
• Magnetic Resonance Imaging (MRI) is crucial for brain tumor diagnosis, but accurate segmentation is difficult due to tumor complexity.
• Precise tumor segmentation is vital for treatment planning and prognosis.

Purpose of the Study:

• To develop a novel hybrid deep learning technique for automated brain tumor segmentation and classification.
• To improve the accuracy and efficiency of brain tumor analysis using MRI data.

Main Methods:

• Utilized the BRATS 2020 dataset for MRI images and tumor segmentations.
• Employed batch normalization and AlexNet for feature extraction.
• Applied Advanced Whale Optimization (AWO) for optimal feature selection.
• Implemented a hybrid ConvNet-ResNeXt101 model for segmentation and classification.

Main Results:

• The ConvNet-ResNeXt101 model achieved 99.27% accuracy for tumor core segmentation.
• Demonstrated superior performance compared to existing methods.
• Achieved a minimum learning elapsed time of 0.53 seconds.

Conclusions:

• The proposed ConvNet-ResNeXt101 hybrid deep learning model offers a highly accurate and efficient solution for brain tumor segmentation and classification.
• This technique has the potential to significantly enhance early brain tumor detection and treatment planning.