Efficient Brain Tumor Segmentation with Lightweight Separable Spatial Convolutional Network

Hao Zhang, Meng Liu, Yuan Qi, Yang Ning, Shunbo Hu, Liqiang Nie, Wenyin Zhang

Abstract: Accurate and automated segmentation of lesions in brain MRI scans is crucial in diagnostics and treatment planning. Despite the signiicant achievements of existing approaches, they often require substantial computational resources and fail to fully exploit the synergy between low-level and high-level features. To address these challenges, we introduce the Separable Spatial Convolutional Network (SSCN), an innovative model that reines the U-Net architecture to achieve eicient brain tumor segmentation with minimal computational cost. SSCN integrates the PocketNet paradigm and replaces standard convolutions with depthwise separable convolutions, resulting in a signiicant reduction in parameters and computational load. Additionally, our feature complementary module enhances the interaction between features across the encoder-decoder structure, facilitating the integration of multi-scale features while maintaining low computational demands. The model also incorporates a separable spatial attention mechanism, enhancing its capability to discern spatial details. Empirical validations on standard datasets demonstrate the efectiveness of our proposed model, especially in segmenting small and medium-sized tumors, with only 0.27M parameters and 3.68GFlops. Our code is available at https://github.com/zzpr/SSCN.