← Back to all news
arXiv AI By Ruochen Liu, Yalin Zheng, Jingxin Liu, Jianfeng Zhang, Shoujun Huang, Dexing Kong, Haofeng Li, Wei Lou

End-to-End Cell Detection via Instance-aware Graph Modeling

Read the original on arXiv AI →

The paper introduces an end‑to‑end framework for detecting and classifying cells in pathology images by jointly modeling visual features and instance‑level interactions. It employs a dynamic graph construction module that builds cell graphs from learnable queries and an instance‑aware graph network that filters and reorganizes features, integrating appearance and relational evidence. Experiments on multiple staining protocols show the method surpasses existing approaches in both detection and classification accuracy.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

Related stories

arXiv Computer Vision
6d ago

Context-aware Skin Cancer Epithelial Cell Classification with Scalable Graph Transformers

The paper introduces scalable Graph Transformers for classifying healthy versus tumor epithelial cells in whole-slide images of cutaneous squamous cell carcinoma. By constructing a full‑WSI cell graph and incorporating morphological, texture, and neighboring cell class features, the proposed SGFormer and DIFFormer models outperform traditional image‑based methods, achieving balanced accuracies above 85% on single‑WSI tests and 83.6% on multi‑WSI evaluations. The study demonstrates that preserving tissue‑level context through graph representations improves classification of morphologically similar cell types.

By Lucas Sanc\'er\'e, No\'emie Moreau, Katarzyna Bozek
llmscomputer-visionbenchmarks
More like this →
arXiv AI
Aug 7

Integrating Implicit and Explicit Relational Biases through Graph-Based Multiple Instance Learning: A Case Study in Skin Lesion Diagnosis

arXiv:2608. 06037v1 Announce Type: new Abstract: Relational inductive biases are essential for capturing structural dependencies among data.

By Rafa{\l} Buler (Gda\'nsk University of Technology), Jakub Buler (Gda\'nsk University of Technology), Maciej Bobowicz (Medical University of Gda\'nsk), Micha{\l} Grochowski (Gda\'nsk University of Technology)
ragcomputer-visionbenchmarks
More like this →
arXiv Machine Learning
6d ago

SpaFactor: Lightweight Spatial Context-Aware Gene Program Modeling for Histology-to-Transcriptomics Inference

SpaFactor is a lightweight framework that predicts spatial gene expression from hematoxylin and eosin images by fusing central spot visuals with multiscale neighborhood context. It uses a residual MLP to map tissue microenvironment to low‑dimensional latent gene programs, which are decoded into coordinated multi‑gene predictions. Across five public cohorts, SpaFactor outperforms existing methods, especially for spatially variable genes, and better recovers biologically organized spatial patterns.

By Shiting Ruan, Xitong Ling, Qiming He, Ziyou Yan, Huaitian Yuan, Tian Guan, Ying Xiao, Xu Guan, Yonghong He
More like this →
arXiv Machine Learning
Sep 17

Interpretable Retinal Disease Prediction Using Biology-Informed Heterogeneous Graph Representations

The paper introduces a biology-informed heterogeneous graph representation that models retinal vessel segments, intercapillary areas, and the foveal avascular zone to predict diabetic retinopathy stages from OCTA images. This graph-based approach reframes staging as a graph-level classification task solved with a graph neural network, achieving AUC-ROC values up to 84% and outperforming biomarker-based classifiers, CNNs, and vision transformers. The method also provides detailed, interpretable explanations by precisely localizing abnormal vessels and non-perfusion areas.

By Laurin Lux, Alexander H. Berger, Maria Romeo Tricas, Richard Rosen, Alaa E. Fayed, Sobha Sivaprasada, Linus Kreitner, Jonas Weidner, Martin J. Menten, Daniel Rueckert, Johannes C. Paetzold
llmsbenchmarkssafety
More like this →