Research map / Label-efficient and robust learning / Recognition and long-tail
Cello: A Universal Cell-wise Feature Aggregation framework for Reliable Pathology Images Analysis
Hengrui Lou, Weihan Li, Jiazhen Yang, Lingxiang Jia, Shengxuming Zhang, Linyun Zhou, Xiuming Zhang, Zhenyang Wang, Mingli Song, Zunlei Feng
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 cell-wise feature learning and alignment (A1) (ablation) | Cello · CPTAC-CCRCC grading | AUC: 0.799 -> 0.832 | Improved |
| add class-level alignment (ablation) | Cello · CPTAC-CCRCC grading | AUC: 0.801 -> 0.832 | Improved |
| add token-level alignment (ablation) | Cello · CPTAC-CCRCC grading | AUC: 0.829 -> 0.832 | No clear effect |
| add dimension mapping (ablation) | Cello · CPTAC-CCRCC grading | AUC: 0.825 -> 0.832 | Improved |
| add local prototype contrast (B2) (ablation) | Cello · CPTAC-CCRCC grading | AUC: 0.801 -> 0.832 | Improved |
| use several prototypes per class instead of s = 1 (ablation) | Cello · CPTAC-CCRCC grading | AUC: 0.830 -> 0.832 | No clear effect |
| add decision-route reliable learning (B3) (ablation) | Cello · CPTAC-CCRCC grading | AUC: 0.812 -> 0.832 | Improved |
| add local-global route calibration (ablation) | Cello · CPTAC-CCRCC grading | AUC: 0.815 -> 0.832 | Improved |
| add cell-local refinement (ablation) | Cello · CPTAC-CCRCC grading | AUC: 0.824 -> 0.832 | Improved |
| add cell-wise aggregation over patch-only encoding (ablation) | Cello · CPTAC-CCRCC diagnosis | AUC: 0.834 -> 0.857 | Improved |
| use Cello instead of best PFM baseline | CHIEF · 4500PCas grading | AUC: +6.0 | Improved |
| use Cello instead of best PFM baseline | CHIEF · TCGA-CRC diagnosis | AUC: +4.6 | Improved |
Closest papers by meaning
- Towards Scalable Context-Aware Single-Cell Spatial Transcriptomics Prediction from Histology Images (NeurIPS 2026 · similarity 0.89)
- MLLM-HWSI: A Multimodal Large Language Model for Hierarchical Whole Slide Image Understanding (CVPR 2026 · similarity 0.87)
- PathVQ: Reforming Computational Pathology Foundation Model for Whole Slide Image Analysis via Vector Quantization (NeurIPS 2025 · similarity 0.87)
- Revisiting End-to-End Learning with Slide-level Supervision in Computational Pathology (NeurIPS 2025 · similarity 0.86)
- Unsupervised Foundation Model-Agnostic Slide-Level Representation Learning (CVPR 2025 · similarity 0.85)
- Sequential Attention-based Sampling for Histopathological Analysis (NeurIPS 2025 · similarity 0.85)
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.
