EUVIMEDEUVIMED entdecken
Crossref

HIPPA-DGCN: Survival analysis on whole slide images via hyper-image patches and position-aware dense graph convolutional networks

Huhan Xie, Tong Xu, Huaishui Yang, Mengye Lyu, Chunyan Chen, Chengyu Tong, Shaojun Liu

Computer Methods and Programs in Biomedicine · 2026-08 · 282 · 109407

DOI: 10.1016/j.cmpb.2026.109407 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Computer Methods and Programs in Biomedicine, 2026-08. Verfasst von Huhan Xie und 6 weiteren Autor:innen. Beteiligte Einrichtung: College of Health Science and Environmental Engineering, Shenzhen Technology University, Shenzhen 518118, China; School of Applied Technology, Shenzh…. Hauptthemen laut MEDLINE: Neoplasms, Image Processing, Computer-Assisted, Image Interpretation, Computer-Assisted. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 43 Literaturangaben. Gefördert von: National Natural Science Foundation of China.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

BACKGROUND AND OBJECTIVE Whole Slide Images (WSIs) are the gold standard for cancer diagnosis and prognosis. However, the enormous scale of WSIs presents significant challenges for effective information aggregation in survival analysis, limiting prognostic accuracy and clinical applicability. This study aims to develop a computationally efficient framework for accurate and interpretable survival prediction from WSIs. METHODS We propose HIPPA-DGCN, a novel framework that utilizes hyper-image patch clustering for feature distillation and a position-aware dense graph convolutional network for global context modeling. This architecture is designed to efficiently integrate pathological features with their spatial relationships. RESULTS Extensive evaluation on seven public datasets (five from TCGA and two from CPTAC) demonstrates state-of-the-art performance. Our method achieves superior prognostic accuracy while drastically improving computational efficiency, reducing model parameters to 0.73M and computational cost to 0.08 GFLOPs per WSI. The model generates interpretable attention maps that highlight histopathological regions with significant prognostic relevance. CONCLUSIONS HIPPA-DGCN provides an accurate, efficient, and interpretable solution for WSI-based survival analysis. Its lightweight architecture and robust performance make it particularly suitable for clinical deployment in resource-constrained environments, potentially enhancing cancer prognosis workflows.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

NeoplasmsImage Processing, Computer-AssistedImage Interpretation, Computer-AssistedHumansGraph Neural NetworksSurvival AnalysisPrognosisAlgorithmsCluster Analysis

Stichwörter der Autor:innen

Dense graph convolutional networkHyper-image patch clusteringSurvival analysisWhole slide image

Autor:innen und Institutionen

  • College of Health Science and Environmental Engineering, Shenzhen Technology University, Shenzhen 518118, China; School of Applied Technology, Shenzhen University, Shenzhen 518060, China.
  • College of Health Science and Environmental Engineering, Shenzhen Technology University, Shenzhen 518118, China.
  • Shenzhen FuYong People's Hospital, Shenzhen 518103, China.
  • College of Health Science and Environmental Engineering, Shenzhen Technology University, Shenzhen 518118, China. Electronic address: liusj14@tsinghua.org.cn.

Förderung

  • National Natural Science Foundation of China

Zitieren

APA

Xie, H., Xu, T., Yang, H., Lyu, M., Chen, C., Tong, C., & Liu, S. (2026). HIPPA-DGCN: Survival analysis on whole slide images via hyper-image patches and position-aware dense graph convolutional networks. Computer Methods and Programs in Biomedicine, 282, 109407. https://doi.org/10.1016/j.cmpb.2026.109407

Vancouver

Xie H, Xu T, Yang H, Lyu M, Chen C, Tong C, et al. HIPPA-DGCN: Survival analysis on whole slide images via hyper-image patches and position-aware dense graph convolutional networks. Computer Methods and Programs in Biomedicine. 2026;282:109407. doi:10.1016/j.cmpb.2026.109407

BibTeX
@article{Xie2026,
  author = {Xie, Huhan and Xu, Tong and Yang, Huaishui and Lyu, Mengye and Chen, Chunyan and Tong, Chengyu and Liu, Shaojun},
  title = {HIPPA-DGCN: Survival analysis on whole slide images via hyper-image patches and position-aware dense graph convolutional networks},
  journal = {Computer Methods and Programs in Biomedicine},
  year = {2026},
  volume = {282},
  pages = {109407},
  doi = {10.1016/j.cmpb.2026.109407}
}
Kostenlos starten →