Research map / Detection and segmentation / CNN features
Towards Effective and Efficient Context-aware Nucleus Detection in Histopathology Whole Slide Images
Zhongyi Shui, Honglin Li, Yunlong Zhang, Yuxuan Sun, Yiwen Ye, Pingyi Chen, Ruizhe Guo, Lei Cui, Chenglu Zhu, Lin Yang
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 |
|---|---|---|---|
| add context-aware learning from surrounding patches (ablation) | P2PNet · BRCA | average F1: 66.22 -> 70.79 | Improved |
| add cross-labeling pseudo-labels (ablation) | P2PNet with CA · BRCA | average F1: 70.79 -> 71.23 | Improved |
| add morphology-rich embedding (ablation) | P2PNet with CA and CL · BRCA | average F1: 71.23 -> 72.01 | Improved |
| use cross-labeling instead of self-labeling (ablation) | P2PNet context-aware · BRCA | average F1: 71.10 -> 72.01 | Improved |
| use self-labeling pseudo labels (ablation) | P2PNet context-aware · BRCA | average F1: 70.95 -> 71.10 | No clear effect |
| use cross-attention instead of concatenation for context (ablation) | P2PNet context-aware · BRCA | average F1: 68.85 -> 72.01 | Improved |
| increase context size delta from 1 to 4 (ablation) | context-aware P2PNet · BRCA | average F1: 72.01 -> 72.51 | Improved |
| increase context size delta from 0 to 1 (ablation) | context-aware P2PNet · BRCA | average F1: 66.22 -> 72.01 | Improved |
| increase pooling grid s beyond 6 (ablation) | context-aware P2PNet · BRCA | average F1 | Hurt |
| add positional embeddings to cross-attention (ablation) | context-aware P2PNet · BRCA | average F1 | No clear effect |
| use surrounding window features instead of LFoV patches | MFoV-P2PNet · WSI inference | inference time: 486.20 s -> 205.81 s | Improved |
| use surrounding window context instead of LFoV | MFoV-P2PNet · PUMA | average F1: 74.61 -> 77.36 | Improved |
Closest papers by meaning
- Rethinking Transformer for Long Contextual Histopathology Whole Slide Image Analysis (NeurIPS 2024 · similarity 0.88)
- Dynamic Graph Representation with Knowledge-aware Attention for Histopathology Whole Slide Image Analysis (CVPR 2024 · similarity 0.87)
- Sequential Attention-based Sampling for Histopathological Analysis (NeurIPS 2025 · similarity 0.87)
- PathVQ: Reforming Computational Pathology Foundation Model for Whole Slide Image Analysis via Vector Quantization (NeurIPS 2025 · similarity 0.86)
- MLLM-HWSI: A Multimodal Large Language Model for Hierarchical Whole Slide Image Understanding (CVPR 2026 · similarity 0.86)
- Unsupervised Foundation Model-Agnostic Slide-Level Representation Learning (CVPR 2025 · similarity 0.86)
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.
