动态注意力+轻量化结构，提升前列腺磁共振分割效率与精度
KLO-Net: A Dynamic K-NN Attention U-Net with CSP Encoder for Efficient Prostate Gland Segmentation from MRI
- 动态K近邻注意力自适应调整每位置连接数
- 在PROMISE12和PROSTATEx上达到高精度且计算量更低
- 适合临床实时部署的高效前列腺分割任务
临床工作站中前列腺MRI分割的实时部署常受限于计算负载与内存开销。由于解剖结构差异大，基于深度学习的前列腺腺体分割仍具挑战。为弥补效率差距并保持可靠分割精度，本文提出KLO-Net：一种结合动态K-最近邻注意力与交叉阶段部分（CSP）编码器的U-Net架构。不同于传统K-NN注意力机制，所提动态机制可自适应确定每像素位置的注意力连接数量；CSP模块有效降低计算负载并减少内存消耗。在两个公开数据集（PROMISE12与PROSTATEx）上开展全面实验与消融研究，结果表明该模型在计算效率与分割质量方面均具优势。
原文摘要 · Abstract (English)
Real-time deployment of prostate MRI segmentation on clinical workstations is often bottlenecked by computational load and memory footprint. Deep learning-based prostate gland segmentation approaches remain challenging due to anatomical variability. To bridge this efficiency gap while still maintaining reliable segmentation accuracy, we propose KLO-Net, a dynamic K-Nearest Neighbor attention U-Net with Cross Stage Partial, i.e., CSP, encoder for efficient prostate gland segmentation from MRI scan. Unlike the regular K-NN attention mechanism, the proposed dynamic K-NN attention mechanism allows the model to adaptively determine the number of attention connections for each spatial location within a slice. In addition, CSP blocks address the computational load to reduce memory consumption. To evaluate the model's performance, comprehensive experiments and ablation studies are conducted on two public datasets, i.e., PROMISE12 and PROSTATEx, to validate the proposed architecture. The detailed comparative analysis demonstrates the model's advantage in computational efficiency and segmentation quality.
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。