Survival prediction of stomach cancer using expression data and deep learning models with histopathological images.
Cancer Sci
; 114(2): 690-701, 2023 Feb.
Article
em En
| MEDLINE
| ID: mdl-36114747
ABSTRACT
Accurately predicting patient survival is essential for cancer treatment decision. However, the prognostic prediction model based on histopathological images of stomach cancer patients is still yet to be developed. We propose a deep learning-based model (MultiDeepCox-SC) that predicts overall survival in patients with stomach cancer by integrating histopathological images, clinical data, and gene expression data. The MultiDeepCox-SC not only automatedly selects patches with more information for survival prediction, without manual labeling for histopathological images, but also identifies genetic and clinical risk factors associated with survival in stomach cancer. The prognostic accuracy of the MultiDeepCox-SC (C-index = 0.744) surpasses the result only based on histopathological image (C-index = 0.660). The risk score of our model was still an independent predictor of survival outcome after adjustment for potential confounders, including pathologic stage, grade, age, race, and gender on The Cancer Genome Atlas dataset (hazard ratio 1.555, p = 3.53e-08) and the external test set (hazard ratio 2.912, p = 9.42e-4). Our fully automated online prognostic tool based on histopathological images, clinical data, and gene expression data could be utilized to improve pathologists' efficiency and accuracy (https//yu.life.sjtu.edu.cn/DeepCoxSC).
Palavras-chave
Texto completo:
1
Base de dados:
MEDLINE
Assunto principal:
Neoplasias Gástricas
/
Aprendizado Profundo
Tipo de estudo:
Guideline
/
Prognostic_studies
/
Risk_factors_studies
Limite:
Humans
Idioma:
En
Revista:
Cancer Sci
Ano de publicação:
2023
Tipo de documento:
Article
País de afiliação:
China