Research map / Image generation / Autoregressive and latent generation
A Spatial Regulated Patch-Wise Approach for Cervical Dysplasia Diagnosis
Ying Zhang, Yifang Yin, Zhenguang Liu, Roger Zimmermann
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Use the patch-wise method with weighted patch aggregation and iterative spatial regulation instead of the strongest reported baseline | Cervical dysplasia diagnosis · Costa Rica cervical screening test set | Accuracy: +3.47% | Improved |
| Use the patch-wise method with weighted patch aggregation and iterative spatial regulation instead of the strongest reported baseline | Cervical dysplasia diagnosis · Costa Rica cervical screening test set | F1: +4.59% | Improved |
| Use the patch-wise method with weighted patch aggregation and iterative spatial regulation instead of the strongest reported baseline | Cervical dysplasia diagnosis · Costa Rica cervical screening test set | Recall: +8.54% | Improved |
| Use 0.5xDefault rather than Default patch size (ablation) | Proposed patch-wise method · Costa Rica cervical screening test set | Accuracy: 0.808 -> 0.734 | Hurt |
| Use 2xDefault rather than Default patch size (ablation) | Proposed patch-wise method · Costa Rica cervical screening test set | Accuracy: 0.808 -> 0.791 | Hurt |
| Use 4xDefault rather than Default patch size (ablation) | Proposed patch-wise method · Costa Rica cervical screening test set | Accuracy: 0.808 -> 0.736 | Hurt |
Closest papers by meaning
- SheafStain: Sheaf-Theoretic Schr\"odinger Bridge for Spatially and Biologically Coherent Virtual Staining (NeurIPS 2026 · similarity 0.80)
- PathVQ: Reforming Computational Pathology Foundation Model for Whole Slide Image Analysis via Vector Quantization (NeurIPS 2025 · similarity 0.80)
- LoMix: Learnable Weighted Multi-Scale Logits Mixing for Medical Image Segmentation (NeurIPS 2025 · similarity 0.80)
- CPath-Omni: A Unified Multimodal Foundation Model for Patch and Whole Slide Image Analysis in Computational Pathology (CVPR 2025 · similarity 0.80)
- Quilt-LLaVA: Visual Instruction Tuning by Extracting Localized Narratives from Open-Source Histopathology Videos (CVPR 2024 · similarity 0.79)
- Rotation-Agnostic Image Representation Learning for Digital Pathology (CVPR 2024 · similarity 0.79)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
