A Novel Global Context-aware Deep Neural Network for Enhanced Brain Tumor Segmentation using Magnetic Resonance Images
Quick Take
The Global Context-aware Squeeze and Excite Residual UNet (GCSER-UNet) significantly improves brain tumor segmentation from MRI images, achieving a 94% dice score on the TCGA LGG dataset, surpassing the previous state-of-the-art of 91.8%. In the BraTS 2020 dataset, it achieved dice scores of 95%, 92%, and 90% for Whole Tumor, Tumor Core, and Enhancing Tumor, respectively, aiding neurologists in better treatment planning.
Key Points
- GCSER-UNet enhances spatial and channel-wise attention for better segmentation.
- Achieved a 94% dice score on the TCGA LGG dataset, outperforming previous models.
- In BraTS 2020, it scored 95%, 92%, and 90% for different tumor regions.
- Automated segmentation reduces manual identification costs and errors.
- Results support improved management and treatment planning for brain cancer.
Article Content
From source RSS / original summaryarXiv:2605. 30510v1 Announce Type: new Abstract: Brain cancer's severity necessitates precise brain tumor segmentation, which is crucial for effective brain tumor diagnosis. Manual identification, burdened by high costs, labor, and error risks, highlights the need for automated methods.
In this study, we introduce the Global Context-aware Squeeze and Excite Residual UNet (GCSER-UNet), which facilitates a fusion of spatial and channel-wise attention and thus enhances the model's capacity to capture intricate spatial dependencies and contextual information. GCSER-UNet efficiently extracts tumor segments from multimodal MRI slices, delivering exceptional performance.
Evaluations on benchmark databases exhibit its superiority, achieving a notable 94 percent dice score on the TCGA LGG dataset, surpassing the state-of-the-art dice score of 91. 8 percent. In the BraTS 2020 dataset, the proposed GCSER-UNet ensemble approach yielded dice scores of 95 percent, 92 percent, and 90 percent for the tumor regions - Whole Tumor (W), Tumor Core (T), and Enhancing Tumor (E), respectively. The current state-of-the-art dice scores were 94 percent, 93 percent, and 88 percent.
These compelling outcomes highlight the efficacy of GCSER-UNet in precise brain tumor segmentation and thus can aid neurologists in effective brain cancer management and treatment planning.
Reader Mode unavailable (could not extract clean content).
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from arXiv cs.CV
See more →Evi-Steer: Learning to Steer Biomedical Vision-Language Models through Efficient and Generalizable Evidential Tuning
Evi-Steer introduces a novel evidential tuning framework for BiomedCLIP, enabling efficient fine-tuning with only 0.11% parameter updates. It significantly enhances performance in few-shot learning and domain shifts across 15 biomedical imaging datasets, demonstrating robustness for clinical applications.