EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Fine–Coarse Dual Multi-Scale Graph Convolutional Network with Adaptive Edge Construction for Classification and Survival Prediction of Whole-Slide Images

Hongbo Zhu, Yirui Liang, Dongsheng Wang, Le Ha, Yuanguo Bi, Guoxu Wang

Journal of Imaging · 18.11.2026 · 12 (11) · 584

DOI: 10.3390/jimaging12110584 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Imaging, online erschienen am 18.11.2026. Verfasst von Hongbo Zhu und 5 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Department of Science and Technology of Liaoning Province, Educational Department of Liaoning Province.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Whole-slide images (WSIs) provide important morphological evidence for cancer diagnosis and prognostic assessment. However, their gigapixel size, substantial regional heterogeneity, complex spatial organization, and limited fine-grained annotations make it difficult to model the topological relationships among pathological regions, which in turn limits the use of WSI analysis in automated diagnosis and prognosis. We propose AECGCN, a fine–coarse dual multi-scale graph convolutional network with adaptive edge construction, for WSI classification and survival prediction. Patch-level features are first extracted using the pretrained CONCH (CONtrastive learning from Captions for Histopathology) model and compressed by MiniBatch K-Means clustering to construct fine- and coarse-grained graphs. Graph edges are then constructed adaptively by combining spatial distance with feature-based semantic similarity, where the relative weighting is calibrated by Moran’s I spatial autocorrelation statistic, so that tissue topology and pathological relationships are captured jointly. Finally, two task-specific subnets, AECGCN-C for classification and AECGCN-S for survival prediction, integrate local pathological patterns and global tissue structure through dual-branch graph convolutions and cross-scale attention. Evaluated on datasets from The Cancer Genome Atlas (TCGA), AECGCN achieves classification accuracy (ACC) values of 0.944±0.024 on the combined kidney cohort (TCGA-Kidney) and 0.914±0.027 on the breast invasive carcinoma cohort (TCGA-BRCA). For survival prediction, it achieves concordance index (C-index) values of 0.709±0.041 on the kidney renal clear cell carcinoma cohort (TCGA-KIRC) and 0.644±0.043 on TCGA-BRCA. The study provides a research-stage framework for image-based subtype classification and prognostic risk stratification with exploratory attention visualization. External validation, probability calibration, prospective evaluation, and human-in-the-loop review remain necessary before clinical use. Because the framework relies only on slide-level labels and generic patch-level features, the same fine–coarse dual graph design with adaptive edge construction can be extended to other clinical imaging applications and to other multi-scale or gigapixel image analysis tasks.

Förderung

  • Department of Science and Technology of Liaoning Province
  • Educational Department of Liaoning Province

Zitieren

APA

Zhu, H., Liang, Y., Wang, D., Ha, L., Bi, Y., & Wang, G. (2026). Fine–Coarse Dual Multi-Scale Graph Convolutional Network with Adaptive Edge Construction for Classification and Survival Prediction of Whole-Slide Images. Journal of Imaging, 12(11), 584. https://doi.org/10.3390/jimaging12110584

Vancouver

Zhu H, Liang Y, Wang D, Ha L, Bi Y, Wang G. Fine–Coarse Dual Multi-Scale Graph Convolutional Network with Adaptive Edge Construction for Classification and Survival Prediction of Whole-Slide Images. Journal of Imaging. 2026;12(11):584. doi:10.3390/jimaging12110584

BibTeX
@article{Zhu2026,
  author = {Zhu, Hongbo and Liang, Yirui and Wang, Dongsheng and Ha, Le and Bi, Yuanguo and Wang, Guoxu},
  title = {Fine–Coarse Dual Multi-Scale Graph Convolutional Network with Adaptive Edge Construction for Classification and Survival Prediction of Whole-Slide Images},
  journal = {Journal of Imaging},
  year = {2026},
  volume = {12},
  number = {11},
  pages = {584},
  doi = {10.3390/jimaging12110584}
}
Kostenlos starten →