HVTSurv: Hierarchical Vision Transformer for Patient-Level Survival Prediction from Whole Slide Image
Proceedings of the AAAI Conference on Artificial Intelligence · 26.06.2023 · 37 (2) · 2209-2217
DOI: 10.1609/aaai.v37i2.25315 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 26.06.2023. Verfasst von Zhuchen Shao und 5 weiteren Autor:innen. Die Arbeit wurde bisher 43-mal zitiert (Crossref).
Abstract (Originalsprache)
Survival prediction based on whole slide images (WSIs) is a challenging task for patient-level multiple instance learning (MIL). Due to the vast amount of data for a patient (one or multiple gigapixels WSIs) and the irregularly shaped property of WSI, it is difficult to fully explore spatial, contextual, and hierarchical interaction in the patient-level bag. Many studies adopt random sampling pre-processing strategy and WSI-level aggregation models, which inevitably lose critical prognostic information in the patient-level bag. In this work, we propose a hierarchical vision Transformer framework named HVTSurv, which can encode the local-level relative spatial information, strengthen WSI-level context-aware communication, and establish patient-level hierarchical interaction. Firstly, we design a feature pre-processing strategy, including feature rearrangement and random window masking. Then, we devise three layers to progressively obtain patient-level representation, including a local-level interaction layer adopting Manhattan distance, a WSI-level interaction layer employing spatial shuffle, and a patient-level interaction layer using attention pooling. Moreover, the design of hierarchical network helps the model become more computationally efficient. Finally, we validate HVTSurv with 3,104 patients and 3,752 WSIs across 6 cancer types from The Cancer Genome Atlas (TCGA). The average C-Index is 2.50-11.30% higher than all the prior weakly supervised methods over 6 TCGA datasets. Ablation study and attention visualization further verify the superiority of the proposed HVTSurv. Implementation is available at: https://github.com/szc19990412/HVTSurv.
Zitieren
APA
Shao, Z., Chen, Y., Bian, H., Zhang, J., Liu, G., & Zhang, Y. (2023). HVTSurv: Hierarchical Vision Transformer for Patient-Level Survival Prediction from Whole Slide Image. Proceedings of the AAAI Conference on Artificial Intelligence, 37(2), 2209-2217. https://doi.org/10.1609/aaai.v37i2.25315
Vancouver
Shao Z, Chen Y, Bian H, Zhang J, Liu G, Zhang Y. HVTSurv: Hierarchical Vision Transformer for Patient-Level Survival Prediction from Whole Slide Image. Proceedings of the AAAI Conference on Artificial Intelligence. 2023;37(2):2209-2217. doi:10.1609/aaai.v37i2.25315
BibTeX
@article{Shao2023,
author = {Shao, Zhuchen and Chen, Yang and Bian, Hao and Zhang, Jian and Liu, Guojun and Zhang, Yongbing},
title = {HVTSurv: Hierarchical Vision Transformer for Patient-Level Survival Prediction from Whole Slide Image},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2023},
volume = {37},
number = {2},
pages = {2209--2217},
doi = {10.1609/aaai.v37i2.25315}
}
EUVIMED