Brain Tumor Segmentation Using Convolutional Neural Networks in MRI Images

Area of Science:

• Medical Imaging
• Artificial Intelligence
• Neuro-oncology

Background:

• Gliomas are aggressive brain tumors with poor prognosis.
• Manual segmentation of brain tumors from MRI is time-consuming and limits clinical application.
• Automated segmentation methods are crucial for precise quantitative analysis and treatment planning.

Purpose of the Study:

• To develop an automated and reliable method for brain tumor segmentation in MRI.
• To explore the efficacy of Convolutional Neural Networks (CNNs) with small kernels for this task.
• To investigate the impact of intensity normalization and data augmentation on segmentation performance.

Main Methods:

• Proposed an automated segmentation method based on Convolutional Neural Networks (CNNs).
• Utilized small 3x3 kernels to enable deeper architectures and reduce overfitting.
• Incorporated intensity normalization and data augmentation as pre-processing steps.

Main Results:

• Achieved first place in the Brain Tumor Segmentation Challenge 2013 (BRATS 2013) for complete, core, and enhancing tumor regions (Dice scores: 0.88, 0.83, 0.77).
• Secured second place in the BRATS 2015 Challenge with Dice scores of 0.78, 0.65, and 0.75.
• Demonstrated the effectiveness of small kernels, intensity normalization, and data augmentation.

Conclusions:

• The proposed CNN-based method offers a robust and accurate solution for brain tumor segmentation in MRI.
• The findings highlight the potential of deep learning for improving oncological patient care.
• The method's success in multiple challenges validates its clinical applicability.