Explainable survival analysis with uncertainty using convolution-involved vision transformer
Computerized Medical Imaging and Graphics · 2023-12 · 110 · 102302
DOI: 10.1016/j.compmedimag.2023.102302 ↗Kurz gefasst
Fachartikel in der Zeitschrift Computerized Medical Imaging and Graphics, 2023-12. Verfasst von Zhihao Tang und 10 weiteren Autor:innen. Beteiligte Einrichtung: Key Laboratory of Trustworthy Distributed Computing and Service (MoE), Beijing University of Posts and Telecommunications, Beijing, China. Electronic…. Hauptthemen laut MEDLINE: Neoplasms. Die Arbeit wurde bisher 15-mal zitiert (Crossref) und nennt 48 Literaturangaben.
Abstract (Originalsprache)
Image-based precision medicine research is able to help doctors make better decisions on treatments. Among all kinds of medical images, a special form is called Whole Slide Image (WSI), which is used for diagnosing patients with cancer, aiming to enable more accurate survival prediction with its high resolution. However, One unique challenge of the WSI-based prediction models is processing the gigabyte-size or even terabyte-size WSIs, which would make most models computationally infeasible. Although existing models mostly use a pre-selected subset of key patches or patch clusters as input, they might discard some important morphology information, making the prediction inferior. Another challenge is improving the prediction models' explainability, which is crucial to help doctors understand the predictions given by the models and make faithful decisions with high confidence. To address the above two challenges, in this work, we propose a novel explainable survival prediction model based on Vision Transformer. Specifically, we adopt dual-channel convolutional layers to utilize the complete WSIs for more accurate predictions. We also introduce the aleatoric uncertainty into our model to understand its limitation and avoid overconfidence in using the prediction results. Additionally, we present a post-hoc explainable method to identify the most salient patches and distinct morphology features as supporting evidence for predictions. Evaluations of two large cancer datasets show that our proposed model is able to make survival predictions more effectively and has better explainability for cancer diagnosis.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Key Laboratory of Trustworthy Distributed Computing and Service (MoE), Beijing University of Posts and Telecommunications, Beijing, China. Electronic address: innerone@bupt.edu.cn.
- Department of Pathology, National Cancer Center/National Clinical Research Center for Cancer/Cancer Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing, China. Electronic address: 157…
- Key Laboratory of Trustworthy Distributed Computing and Service (MoE), Beijing University of Posts and Telecommunications, Beijing, China. Electronic address: shenyifan@bupt.edu.cn.
- Key Laboratory of Trustworthy Distributed Computing and Service (MoE), Beijing University of Posts and Telecommunications, Beijing, China. Electronic address: zongyi_chen@bupt.edu.cn.
- Department of Computer Science, University of Illinois at Chicago, Chicago, USA. Electronic address: guixiang.ma@intel.com.
- Department of Pathology, National Cancer Center/National Clinical Research Center for Cancer/Cancer Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing, China. Electronic address: djy…
Zitieren
APA
Tang, Z., Liu, L., Shen, Y., Chen, Z., Ma, G., Dong, J., Sun, X., Zhang, X., Li, C., Zheng, Q., & Yang, L. (2023). Explainable survival analysis with uncertainty using convolution-involved vision transformer. Computerized Medical Imaging and Graphics, 110, 102302. https://doi.org/10.1016/j.compmedimag.2023.102302
Vancouver
Tang Z, Liu L, Shen Y, Chen Z, Ma G, Dong J, et al. Explainable survival analysis with uncertainty using convolution-involved vision transformer. Computerized Medical Imaging and Graphics. 2023;110:102302. doi:10.1016/j.compmedimag.2023.102302
BibTeX
@article{Tang2023,
author = {Tang, Zhihao and Liu, Li and Shen, Yifan and Chen, Zongyi and Ma, Guixiang and Dong, Jiyan and Sun, Xujie and Zhang, Xi and Li, Chaozhuo and Zheng, Qingfeng and Yang, Lin},
title = {Explainable survival analysis with uncertainty using convolution-involved vision transformer},
journal = {Computerized Medical Imaging and Graphics},
year = {2023},
volume = {110},
pages = {102302},
doi = {10.1016/j.compmedimag.2023.102302}
}
EUVIMED