English

SpikeDS: Dual Sparsity Spikformer for Perineural Invasion Prediction in 3D MRI

Computer Vision and Pattern Recognition 2026-07-13 v1 Machine Learning

Abstract

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.

Keywords

Cite

@article{arxiv.2607.11986,
  title  = {SpikeDS: Dual Sparsity Spikformer for Perineural Invasion Prediction in 3D MRI},
  author = {Induk Um and Youngung Han and Kyeonghun Kim and Yului Jeong and Jina Jeong and Hyunsu Go and Dohyun Kweon and Sungha Park and Junga Kim and Anna Jung and Suah Park and Hyuk-Jae Lee and Pa Hong and Woo Kyoung Jeong and Won Jae Lee and Ken Ying-Kai Liao and Nam-Joon Kim},
  journal= {arXiv preprint arXiv:2607.11986},
  year   = {2026}
}