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

• URL: http://arxiv.org/abs/2607.11986v1
• Date: Mon, 13 Jul 2026 14:03:55 GMT
• Title: SpikeDS: Dual Sparsity Spikformer for Perineural Invasion Prediction in 3D MRI
• Abstract summary: Perineural invasion (PNI) is associated with poor prognosis in cholangiocarcinoma (CCA)<n>Existing deep learning approaches incur prohibitive computational costs on volumetric medical images, limiting their clinical deployment.<n>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.
• Score: 9.308617762081804
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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.

Related papers

• SCINTILLA-SNN: A Spiking Multi-Scale Selective Aggregation Network for Perineural Invasion Prediction [8.986941416850877]
  Preoperative prediction of perineural invasion (PNI) in cholangiocarcinoma is clinically valuable but remains challenging.<n>Standard 3D CNN and transformer architectures process volumetric data in a dense or spatially uniform manner.<n>We propose SCINTILLA-SNN, a 3D spiking network composed of a four-stage hierarchical backbone and a Multi-Scale Spike Aggregation module for PNI prediction.
  arXiv  Detail & Related papers  (2026-09-10T08:36:34Z)
• AsymFeX: A Symmetry-Driven Framework for Ischemic Stroke Segmentation Across Imaging Modalities and Stroke Stages [0.8886706641070187]
  Acute Ischemic Stroke (AIS) lesions are essential for stroke prognosis and treatment planning.<n>Non-contrast CT (NCCT) exhibits subtle infarct contrast, making manual delineation slow and labor-intensive.<n>We propose a two-stage, nnU-Net-compatible 3D segmentation method.
  arXiv  Detail & Related papers  (2026-08-20T08:12:31Z)
• MIRAGE: Multi-scale Lesion-Informed Representation with Auxiliary Guidance for MRI Contrast Enhancement [7.375452467540828]
  We introduce MIRAGE, a residual 2D U-Net that combines global reconstruction and perceptual losses with three forms of lesion-aware supervision.<n>We evaluate the method on 301 cases from the multi-centre MAMA-SYNTH data using eight complementary image-, region-, radiomics-, and segmentation-based metrics.
  arXiv  Detail & Related papers  (2026-07-21T14:26:59Z)
• D3Seg: Dependency-Aware Diffusion for Brain Tumor Segmentation with Missing Modalities [54.87947751720332]
  We propose a novel segmentation model D3Seg to maintain stable performance under missing-modality settings.<n>The proposed model achieves approximately 1.5-2.0% Dice improvement on enhancing tumor (ET) and around 1.0% on tumor core (TC) across multiple missing modality configurations.
  arXiv  Detail & Related papers  (2026-05-21T09:55:42Z)
• DSTAN-Med: Dual-Channel Spatiotemporal Attention with Physiological Plausibility Filtering for False Data Injection Attack Detection in IoT-Based Medical Devices [1.1459450491541954]
  False data injection (FDI) attacks on Internet of Medical Things (IoMT) sensor streams falsify vital signs in transit.<n>Existing deep learning detectors conflate inter-sensor spatial correlations with temporal dependencies in a shared latent space.<n>We propose DSTAN-Med, a supervised framework that routes multivariate sensor windows through independent sensor-wise (SWA) and time-wise (TWA) self-attention pathways.
  arXiv  Detail & Related papers  (2026-05-13T22:39:47Z)
• Maximizing T2-Only Prostate Cancer Localization from Expected Diffusion Weighted Imaging [68.57480103120561]
  Multiparametric MRI is increasingly recommended as a first-line noninvasive approach to detect and localize prostate cancer.<n>Early machine learning attempts using only T2w images have shown promising diagnostic performance in segmenting radiologist-annotated lesions.<n>This work investigates an arguably more challenging application using only T2w at inference, but to localize individual cancers based on independent histopathology labels.
  arXiv  Detail & Related papers  (2026-04-01T14:50:18Z)
• Multimodal Visual Surrogate Compression for Alzheimer's Disease Classification [69.87877580725768]
  Multimodal Visual Surrogate Compression (MVSC) learns to compress and adapt large 3D sMRI volumes into compact 2D features.<n>MVSC has two key components: a Volume Context that captures global cross-slice context under textual guidance, and an Adaptive Slice Fusion module that aggregates slice-level information in a text-enhanced, patch-wise manner.
  arXiv  Detail & Related papers  (2026-01-29T13:05:46Z)
• A Novel Attention-Augmented Wavelet YOLO System for Real-time Brain Vessel Segmentation on Transcranial Color-coded Doppler [49.03919553747297]
  We propose an AI-powered, real-time CoW auto-segmentation system capable of efficiently capturing cerebral arteries.<n>No prior studies have explored AI-driven cerebrovascular segmentation using Transcranial Color-coded Doppler (TCCD)<n>The proposed AAW-YOLO demonstrated strong performance in segmenting both ipsilateral and contralateral CoW vessels.
  arXiv  Detail & Related papers  (2025-08-19T14:41:22Z)
• UKAN-EP: Enhancing U-KAN with Efficient Attention and Pyramid Aggregation for 3D Multi-Modal MRI Brain Tumor Segmentation [1.7582682214679273]
  UKAN-EP is a novel 3D extension of the original 2D U-KAN model for multi-modal MRI brain tumor segmentation.<n>UKAN-EP achieves superior segmentation performance while requiring substantially fewer computational resources.
  arXiv  Detail & Related papers  (2024-08-01T04:27:10Z)
• Weakly supervised segmentation of intracranial aneurysms using a novel 3D focal modulation UNet [0.5106162890866905]
  We propose FocalSegNet, a novel 3D focal modulation UNet, to detect an aneurysm and offer an initial, coarse segmentation of it from time-of-flight MRA image patches. We trained and evaluated our model on a public dataset, and in terms of UIA detection, our model showed a low false-positive rate of 0.21 and a high sensitivity of 0.80.
  arXiv  Detail & Related papers  (2023-08-06T03:28:08Z)
• Z-SSMNet: Zonal-aware Self-supervised Mesh Network for Prostate Cancer Detection and Diagnosis with Bi-parametric MRI [14.101371684361675]
  We propose a Zonal-aware Self-supervised Mesh Network (Z-SSMNet) Z-SSMNet adaptively integrates multi-dimensional (2D/2.5D/3D) convolutions to learn dense intra-slice information and sparse inter-slice information of the anisotropic bpMRI. A self-supervised learning (SSL) technique is proposed to pre-train our network using large-scale unlabeled data.
  arXiv  Detail & Related papers  (2022-12-12T10:08:46Z)
• MEDS-Net: Self-Distilled Multi-Encoders Network with Bi-Direction Maximum Intensity projections for Lung Nodule Detection [5.923156939373596]
  We propose a lung nodule detection scheme which fully incorporates the clinic workflow of radiologists. We exploit Bi-Directional Maximum intensity projection (MIP) images of various thicknesses along with a 3D patch of CT scan. The proposed scheme has been rigorously evaluated on 888 scans of LUNA16 dataset and obtained a CPM score of 93.6%.
  arXiv  Detail & Related papers  (2022-10-30T05:55:45Z)
• The KFIoU Loss for Rotated Object Detection [115.334070064346]
  In this paper, we argue that one effective alternative is to devise an approximate loss who can achieve trend-level alignment with SkewIoU loss. Specifically, we model the objects as Gaussian distribution and adopt Kalman filter to inherently mimic the mechanism of SkewIoU. The resulting new loss called KFIoU is easier to implement and works better compared with exact SkewIoU.
  arXiv  Detail & Related papers  (2022-01-29T10:54:57Z)
• Deep Q-Network-Driven Catheter Segmentation in 3D US by Hybrid Constrained Semi-Supervised Learning and Dual-UNet [74.22397862400177]
  We propose a novel catheter segmentation approach, which requests fewer annotations than the supervised learning method. Our scheme considers a deep Q learning as the pre-localization step, which avoids voxel-level annotation. With the detected catheter, patch-based Dual-UNet is applied to segment the catheter in 3D volumetric data.
  arXiv  Detail & Related papers  (2020-06-25T21:10:04Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.