AI 中文总结
研究针对3D MRI中神经周围侵犯预测难题，提出双稀疏Spikformer架构，利用激活与空间稀疏性，引入双稀疏脉冲注意力机制，经实验验证其在临床队列中AUC达0.753且能耗低，有效提升效率且不损诊断性能。
AI 中文摘要
神经周围侵犯（PNI）与胆管癌（CCA）的不良预后相关。然而，从3D MRI中检测PNI具有挑战性，因为肿瘤周边的成像特征细微且空间异质性。捕获此类空间稀疏线索需要对3D MRI进行体积分析，但现有深度学习方法在体积医学图像上计算成本过高，限制了临床应用。我们提出了双稀疏Spikformer（SpikeDS），一种联合利用二进制脉冲通信的激活稀疏性和基于 firing 率的窗口修剪的空间稀疏性的脉冲神经网络架构。SpikeDS引入了双稀疏脉冲注意力（DSSA），它结合了两种互补机制。第一种是基于窗口的专家混合脉冲注意力（W-EMSA），仅对由其 firing 率识别出的显著窗口选择性地应用注意力。第二种是跨窗口脉冲自注意力（CW-SSA），通过一种不对称方案实现全局上下文交换，其中修剪后的窗口仍作为键值源发挥作用。在139名CCA患者的临床队列上通过5折交叉验证进行评估，SpikeDS的AUC为0.753，同时仅消耗14.4 mJ，在AUC和能源效率方面均超过最佳基线。这些结果表明，双稀疏为提高3D脉冲变压器的效率提供了一种有效的硬件感知策略，而不会影响诊断性能。
英文摘要
Perineural invasion (PNI) is associated with poor prognosis in cholangiocarcinoma (CCA). However, its detection from 3D MRI remains challenging due to the subtle and spatially heterogeneous imaging signatures at the tumor periphery. Capturing such spatially sparse cues necessitates volumetric analysis of 3D MRI, but existing deep learning approaches incur prohibitive computational costs on volumetric medical images, limiting their clinical deployment. We propose Dual Sparsity Spikformer (SpikeDS), a spiking neural network architecture that jointly exploits activation sparsity from binary spike communication and spatial sparsity from window pruning based on firing rates. SpikeDS introduces Dual Sparsity Spiking Attention (DSSA), which combines two complementary mechanisms. The first is Window-based Expert Mixture Spiking Attention (W-EMSA), which selectively applies attention only to salient windows identified by their firing rates. The second is Cross-Window Spiking Self-Attention (CW-SSA), which enables global context exchange through an asymmetric scheme in which pruned windows still contribute as key-value sources. Evaluated on a clinical cohort of 139 CCA patients via 5-fold cross-validation, SpikeDS achieves an AUC of 0.753 while consuming only 14.4 mJ, surpassing the best baseline in both AUC and energy efficiency. These results suggest that dual sparsity provides an effective hardware-aware strategy for improving the efficiency of 3D spiking transformers without compromising diagnostic performance.
