Enhanced ResU-Net for brain tumor segmentation using EfficientNetB0, channel attention, and ASPP

Clinical Snapshot

Key Findings

• P Value: Not reported

• Effect Size: Dice coefficient: 0.903 (whole tumor), 0.851 (tumor core)

• Primary Outcome: Dice similarity coefficient for brain tumor segmentation

• Nnt Or Sensitivity: HD95 scores: 9.43 (whole tumor), 3.54 (tumor core)

• Confidence Interval: Not reported

Clinical Application

Requires specialized computational infrastructure and integration with existing imaging workflows Would need validation with Australian imaging protocols and TGA approval for clinical implementation. Integration with existing radiology information systems would be essential Patients requiring brain tumor segmentation for diagnosis and treatment planning

Abstract

Accurate and efficient segmentation of brain tumors is critical for diagnosis, treatment planning, and monitoring in clinical practice. In this study, we present an enhanced ResU-Net architecture for automatic brain tumor segmentation, integrating an EfficientNetB0 encoder, a channel attention mechanism, and an atrous spatial pyramid pooling (ASPP) module. The EfficientNetB0 encoder leverages pre-trained features to improve feature extraction efficiency, while the channel attention mechanism enhances the model's focus on tumor-relevant features. ASPP enables multi-scale contextual learning, which is crucial for handling tumors of varying sizes and shapes. The proposed model was evaluated on two benchmark datasets: The Cancer Genome Atlas Low Grade Glioma and brain tumor segmentation (BraTS-2020). Experimental results demonstrate that our method consistently outperforms the baseline ResU-Net and its EfficientNet variant, achieving dice similarity coefficient of 0.903 and 0.851, and HD95 scores of 9.43 and 3.54 for whole tumor and tumor core (TC) regions on the BraTS 2020 dataset, respectively. Compared to state-of-the-art methods, our approach shows competitive performance, particularly in whole tumor and TC segmentation. These results indicate that combining a powerful encoder with attention mechanisms and ASPP can significantly enhance BraTS performance. The proposed approach holds promise for further optimization and application in other medical image segmentation tasks.

References

1. 1.Behzadpour, M., Azizi, E., Ortiz, B. L., & Wu, K. (2024). Enhanced ResU-Net for brain tumor segmentation using EfficientNetB0, channel attention, and ASPP. Biomedical Physics & Engineering Express. https://doi.org/10.1088/2057-1976/ae6459