August 7, 2025

Brain tumor segmentation by optimizing deep learning U-Net model

Key Points

MAIN FINDING: The U-Net model achieves an accuracy of 99.64% in segmenting brain tumors from MRI images.
KEY EVIDENCE: Dice coefficients of 0.8984 for necrotic core, 0.8431 for edema, and 0.8824 for enhancing tumors support the model's effectiveness.
APPROACH: The architecture uses Leaky ReLU activation and tailored loss functions to manage class imbalance in medical imaging.
SIGNIFICANCE: Enhanced accuracy in brain tumor segmentation could improve diagnostic systems and ultimately patient outcomes.

Abstract

Background Magnetic Resonance Imaging (MRI) is a cornerstone in diagnosing brain tumors. However, the complex nature of these tumors makes accurate segmentation in MRI images a demanding task. Objective Accurate brain tumor segmentation remains a critical challenge in medical image analysis, with early detection crucial for improving patient outcomes. Methods To develop and evaluate a novel UNet-based architecture for improved brain tumor segmentation in MRI images. This paper presents a novel UNet-based architecture for improved brain tumor segmentation. The UNet model architecture incorporates Leaky ReLU activation, batch normalization, and regularization to enhance training and performance. The model consists of varying numbers of layers and kernel sizes to capture different levels of detail. To address the issue of class imbalance in medical image segmentation, we employ focused loss and generalized Dice (GDL) loss functions. Results The proposed model was evaluated on the BraTS’2020 dataset, achieving an accuracy of 99.64% and Dice coefficients of 0.8984, 0.8431, and 0.8824 for necrotic core, edema, and enhancing tumor regions, respectively. Conclusion These findings demonstrate the efficacy of our approach in accurately predicting tumors, which has the potential to enhance diagnostic systems and improve patient outcomes.

Mark Helpful

Bookmark

Relay