EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC 4.0

Surformer: An interpretable pattern-perceptive survival transformer for cancer survival prediction from histopathology whole slide images

Zhikang Wang, Qian Gao, Xiaoping Yi, Xinyu Zhang, Yiwen Zhang, Daokun Zhang, Pietro Liò, Chris Bain, Richard Bassed, Shanshan Li, Yuming Guo, Seiya Imoto und 3 weitere

Computer Methods and Programs in Biomedicine · 2023-11 · 241 · 107733

DOI: 10.1016/j.cmpb.2023.107733 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Computer Methods and Programs in Biomedicine, 2023-11. Verfasst von Zhikang Wang und 14 weiteren Autor:innen. Beteiligte Einrichtung: Xiangya Hospital, Central South University, Changsha, Hunan, PR China; Biomedicine Discovery Institute and Department of Biochemistry and Molecular B…. Hauptthemen laut MEDLINE: Neoplasms. Die Arbeit wurde bisher 36-mal zitiert (Crossref) und nennt 31 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0). Gefördert von: Monash University, University of Tokyo, The University of Tokyo Institute of Medical Science.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

BACKGROUND AND OBJECTIVE: High-resolution histopathology whole slide images (WSIs) contain abundant valuable information for cancer prognosis. However, most computational pathology methods for survival prediction have weak interpretability and cannot explain the decision-making processes reasonably. To address this issue, we propose a highly interpretable neural network termed pattern-perceptive survival transformer (Surformer) for cancer survival prediction from WSIs. METHODS: Notably, Surformer can quantify specific histological patterns through bag-level labels without any patch/cell-level auxiliary information. Specifically, the proposed ratio-reserved cross-attention module (RRCA) generates global and local features with the learnable prototypes (pglobal, plocals) as detectors and quantifies the patches correlative to each plocal in the form of ratio factors (rfs). Afterward, multi-head self&cross-attention modules proceed with the computation for feature enhancement against noise. Eventually, the designed disentangling loss function guides multiple local features to focus on distinct patterns, thereby assisting rfs from RRCA in achieving more explicit histological feature quantification. RESULTS: Extensive experiments on five TCGA datasets illustrate that Surformer outperforms existing state-of-the-art methods. In addition, we highlight its interpretation by visualizing rfs distribution across high-risk and low-risk cohorts and retrieving and analyzing critical histological patterns contributing to the survival prediction. CONCLUSIONS: Surformer is expected to be exploited as a useful tool for performing histopathology image data-driven analysis and gaining new insights for interpreting the associations between such images and patient survival states.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

NeoplasmsHumansPerceptionElectric Power SuppliesNeural Networks, ComputerResearch

Stichwörter der Autor:innen

Deep learning interpretationMultiple instance learningSurvival analysisWhole slide image

Autor:innen und Institutionen

  • Xiangya Hospital, Central South University, Changsha, Hunan, PR China; Biomedicine Discovery Institute and Department of Biochemistry and Molecular Biology, Monash University, Melbourne, Australia.
  • Xiangya Hospital, Central South University, Changsha, Hunan, PR China.
  • Faculty of Information Technology, Monash University, Melbourne, Australia.
  • Climate, Air Quality Research Unit, School of Public Health and Preventive Medicine, Monash University, Melbourne, Australia.
  • Department of Computer Science and Technology, The University of Cambridge, Cambridge, United Kingdom.
  • Victorian Institute of Forensic Medicine, Melbourne, Australia.

Förderung

  • Monash University
  • University of Tokyo
  • The University of Tokyo Institute of Medical Science

Zitieren

APA

Wang, Z., Gao, Q., Yi, X., Zhang, X., Zhang, Y., Zhang, D., Liò, P., Bain, C., Bassed, R., Li, S., Guo, Y., Imoto, S., Yao, J., Daly, R. J., & Song, J. (2023). Surformer: An interpretable pattern-perceptive survival transformer for cancer survival prediction from histopathology whole slide images. Computer Methods and Programs in Biomedicine, 241, 107733. https://doi.org/10.1016/j.cmpb.2023.107733

Vancouver

Wang Z, Gao Q, Yi X, Zhang X, Zhang Y, Zhang D, et al. Surformer: An interpretable pattern-perceptive survival transformer for cancer survival prediction from histopathology whole slide images. Computer Methods and Programs in Biomedicine. 2023;241:107733. doi:10.1016/j.cmpb.2023.107733

BibTeX
@article{Wang2023,
  author = {Wang, Zhikang and Gao, Qian and Yi, Xiaoping and Zhang, Xinyu and Zhang, Yiwen and Zhang, Daokun and Liò, Pietro and Bain, Chris and Bassed, Richard and Li, Shanshan and Guo, Yuming and Imoto, Seiya and Yao, Jianhua and Daly, Roger J and Song, Jiangning},
  title = {Surformer: An interpretable pattern-perceptive survival transformer for cancer survival prediction from histopathology whole slide images},
  journal = {Computer Methods and Programs in Biomedicine},
  year = {2023},
  volume = {241},
  pages = {107733},
  doi = {10.1016/j.cmpb.2023.107733}
}
Kostenlos starten →