轻量级网络LFA-Net提升视网膜血管分割精度，适合低算力设备部署
LFA-Net: A Lightweight Network with LiteFusion Attention for Retinal Vessel Segmentation
- 设计轻量化融合注意力模块，兼顾局部与全局特征捕捉
- 参数仅11万，推理耗时4.46 GFLOPs，性能达Dice 87.44%
- 专为医疗边缘设备优化，适合资源受限的临床环境
轻量级视网膜血管分割对早期诊断致盲性疾病及系统性疾病至关重要，尤其在计算资源有限的真实临床场景中。尽管深度学习分割方法持续进步，现有模型仍面临小血管分割困难和高计算开销的挑战。为此，我们提出LFA-Net，引入新型轻量化融合注意力模块LiteFusion-Attention。该模块融合残差连接、受Vision Mamba启发的动态机制与调制注意力，实现高效且轻量的上下文建模。LFA-Net仅需0.11百万参数、0.42 MB内存与4.46 GFLOPs计算量，在DRIVE、STARE和CHASE_DB数据集上分别取得83.28%、87.44%、84.50%的Dice分数，以及72.85%、79.31%、74.70%的Jaccard指数。代码已开源：https://github.com/Mehwish4593/LFA-Net。
原文摘要 · Abstract (English)
Lightweight retinal vessel segmentation is important for the early diagnosis of vision-threatening and systemic diseases, especially in a real-world clinical environment with limited computational resources. Although segmentation methods based on deep learning are improving, existing models are still facing challenges of small vessel segmentation and high computational costs. To address these challenges, we proposed a new vascular segmentation network, LFA-Net, which incorporates a newly designed attention module, LiteFusion-Attention. This attention module incorporates residual learning connections, Vision Mamba-inspired dynamics, and modulation-based attention, enabling the model to capture local and global context efficiently and in a lightweight manner. LFA-Net offers high performance with 0.11 million parameters, 0.42 MB memory size, and 4.46 GFLOPs, which make it ideal for resource-constrained environments. We validated our proposed model on DRIVE, STARE, and CHASE_DB with outstanding performance in terms of dice scores of 83.28, 87.44, and 84.50% and Jaccard indices of 72.85, 79.31, and 74.70%, respectively. The code of LFA-Net is available online https://github.com/Mehwish4593/LFA-Net.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。