Survival prediction for patients with glioblastoma multiforme using a Cox proportional hazards denoising autoencoder network

This study aimed to establish and validate a prognostic model based on magnetic resonance imaging and clinical features to predict the survival time of patients with glioblastoma multiforme (GBM). In this study, a convolutional denoising autoencoder (DAE) network combined with the loss function of t...

Celý popis

Uloženo v:

Podrobná bibliografie
Vydáno v:	Frontiers in computational neuroscience Ročník 16; s. 916511
Hlavní autoři:	Yan, Ting, Yan, Zhenpeng, Liu, Lili, Zhang, Xiaoyu, Chen, Guohui, Xu, Feng, Li, Ying, Zhang, Lijuan, Peng, Meilan, Wang, Lu, Li, Dandan, Zhao, Dong
Médium:	Journal Article
Jazyk:	angličtina
Vydáno:	Switzerland Frontiers Research Foundation 10.01.2023 Frontiers Media S.A
Témata:	Alzheimer's disease Bias Brain cancer Cox proportional hazard regression Datasets Deep learning denoising autoencoder Edema Glioblastoma Glioblastoma multiforme Magnetic resonance imaging Morphology Neural networks Neuroscience Patients Prediction models Radiomics Risk groups Survival Survival analysis survival prediction time-dependent ROC curve Tumors deep learning glioblastoma multiforme denoising autoencoder survival prediction time-dependent ROC curve Cox proportional hazard regression
ISSN:	1662-5188, 1662-5188
On-line přístup:	Získat plný text
Tagy:	Přidat tag Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!

Popis
Shrnutí:	This study aimed to establish and validate a prognostic model based on magnetic resonance imaging and clinical features to predict the survival time of patients with glioblastoma multiforme (GBM). In this study, a convolutional denoising autoencoder (DAE) network combined with the loss function of the Cox proportional hazard regression model was used to extract features for survival prediction. In addition, the Kaplan-Meier curve, the Schoenfeld residual analysis, the time-dependent receiver operating characteristic curve, the nomogram, and the calibration curve were performed to assess the survival prediction ability. The concordance index (C-index) of the survival prediction model, which combines the DAE and the Cox proportional hazard regression model, reached 0.78 in the training set, 0.75 in the validation set, and 0.74 in the test set. Patients were divided into high- and low-risk groups based on the median prognostic index (PI). Kaplan-Meier curve was used for survival analysis ( = < 2e-16 in the training set, = 3e-04 in the validation set, and = 0.007 in the test set), which showed that the survival probability of different groups was significantly different, and the PI of the network played an influential role in the prediction of survival probability. In the residual verification of the PI, the fitting curve of the scatter plot was roughly parallel to the -axis, and the -value of the test was 0.11, proving that the PI and survival time were independent of each other and the survival prediction ability of the PI was less affected than survival time. The areas under the curve of the training set were 0.843, 0.871, 0.903, and 0.941; those of the validation set were 0.687, 0.895, 1.000, and 0.967; and those of the test set were 0.757, 0.852, 0.683, and 0.898. The survival prediction model, which combines the DAE and the Cox proportional hazard regression model, can effectively predict the prognosis of patients with GBM.
Bibliografie:	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14 content type line 23 Reviewed by: Mehul S. Raval, Ahmedabad University, India; Zhi-Cheng Li, Shenzhen Institutes of Advanced Technology (CAS), China Edited by: Carlos Alberto Silva, University of Minho, Portugal
ISSN:	1662-5188 1662-5188
DOI:	10.3389/fncom.2022.916511