Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
June 13, 2026Frontiers in Bioengineering and BiotechnologyOpen Access

Robust slice-level stroke classification in non-contrast head CT via structural consistency regularization and counterfactual suppression

View Full Paper
Ask AI
Bookmark
Share

Authors

DXDong XuQYQing YaoLQLifeng Qian

Discussion

Loading...

Member takes

Overview

Randomized trial demonstrates improved stroke classification in emergency settings, highlighting clinical applicability.

Key Points

  • To enhance slice-level stroke classification in non-contrast head CT using advanced techniques for stability and accuracy.
  • Integrated structural consistency regularization and counterfactual suppression for feature improvement.
  • Employ multi-branch feature refinement to optimize stroke detection performance.
  • Evaluated on two stroke CT slice datasets to assess classification metrics.
  • Achieved 98.23% accuracy, 97.66% precision, 97.40% recall, 98.05% F1 score, and AUC of 0.9982 on the primary dataset.
  • On the secondary dataset, achieved 96.52% accuracy, 96.88% precision, 97.73% recall, 96.98% F1 score, and AUC of 0.9989.
  • Indicates robust stroke classification even under challenging imaging conditions.

Cite This Study

Xu et al. (2026) studied this question.

synapsesocial.com/papers/6a2cf2a9faef96ed7f0557d5https://doi.org/10.3389/fbioe.2026.1799191
View Full Paper
Ask AI
Bookmark
Share

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

  1. 1Advanced Deep Learning for Stroke Classification Using Multi-Slice CT Image Analysis2025 · 5 citations
  2. 2An Efficient Deep Learning Framework for Brain Stroke Diagnosis Using Computed Tomography (CT) Images2025
  3. 3An Explainable AI Framework for Stroke Classification Based on CT Brain Images2025 · 8 citations
  4. 4Clinically Scalable Deep Learning for Stroke Multicenter Validation of an Ultra-Efficient NCCT-Based Diagnostic Framework2025 · 1 citations
  5. 5Automated ischemic stroke lesion detection on non-contrast brain CT: a large-scale clinical feasibility test AI stroke lesion detection on NCCT2025 · 3 citations