Authors:
Zhucheng Zhan
1
;
Noshad Hosseni
2
;
Olivier Poirion
3
;
Maria Westerhoff
4
;
Eun-Young Choi
4
;
Travers Ching
5
and
Lana X. Garmire
2
Affiliations:
1
School of Science and Engineering, Chinese University of Hong Kong, Shenzhen Campus, Shenzhen, P.R. China
;
2
Department of Computational Medicine and Bioinformatics, University of Michigan, Ann Arbor, MI, U.S.A.
;
3
Department of Cellular and Molecular Medicine, UC-San Diego, La Jolla, CA, U.S.A.
;
4
Department of Pathology, University of Michigan, Ann Arbor, MI, U.S.A.
;
5
Adaptive Biotechnologies, Seattle, Washington, U.S.A.
Keyword(s):
Prognosis, Survival, Prediction, Neural Network, Modelling, Cox Proportional Hazards, Pathology, Image, Gene Expression, Omics, RNA-Seq, Data Integration.
Abstract:
Pathological images are easily accessible data type with potential as prognostic biomarkers. Here we extend Cox-nnet, a neural network based prognosis method previously used for transcriptomics data, to predict patient survival using hepatocellular carcinoma (HCC) pathological images. Cox-nnet based imaging predictions are more robust and accurate than Cox proportional hazards model. Moreover, using a novel two-stage Cox-nnet complex model, we are able to combine histopathology image and transcriptomics RNA-Seq data to make impressively accurate prognosis predictions, with C-index close to 0.90 and log-ranked p-value of 4e-21 in the testing dataset. This work provides a new, biologically relevant and relatively interpretable solution to the challenge of integrating multi-modal and multiple types of data, particularly for survival prediction.