scholarly journals SurvCNN: A Discrete Time-to-Event Cancer Survival Estimation Framework Using Image Representations of Omics Data

Cancers ◽  
2021 ◽  
Vol 13 (13) ◽  
pp. 3106
Author(s):  
Yogesh Kalakoti ◽  
Shashank Yadav ◽  
Durai Sundar

The utility of multi-omics in personalized therapy and cancer survival analysis has been debated and demonstrated extensively in the recent past. Most of the current methods still suffer from data constraints such as high-dimensionality, unexplained interdependence, and subpar integration methods. Here, we propose SurvCNN, an alternative approach to process multi-omics data with robust computer vision architectures, to predict cancer prognosis for Lung Adenocarcinoma patients. Numerical multi-omics data were transformed into their image representations and fed into a Convolutional Neural network with a discrete-time model to predict survival probabilities. The framework also dichotomized patients into risk subgroups based on their survival probabilities over time. SurvCNN was evaluated on multiple performance metrics and outperformed existing methods with a high degree of confidence. Moreover, comprehensive insights into the relative performance of various combinations of omics datasets were probed. Critical biological processes, pathways and cell types identified from downstream processing of differentially expressed genes suggested that the framework could elucidate elements detrimental to a patient’s survival. Such integrative models with high predictive power would have a significant impact and utility in precision oncology.

Mathematics ◽  
2020 ◽  
Vol 8 (2) ◽  
pp. 147 ◽  
Author(s):  
Andrius Grigutis ◽  
Jonas Šiaulys

In this paper, we prove recursive formulas for ultimate time survival probability when three random claims X , Y , Z in the discrete time risk model occur in a special way. Namely, we suppose that claim X occurs at each moment of time t ∈ { 1 , 2 , … } , claim Y additionally occurs at even moments of time t ∈ { 2 , 4 , … } and claim Z additionally occurs at every moment of time, which is a multiple of three t ∈ { 3 , 6 , … } . Under such assumptions, the model that is obtained is called the three-risk discrete time model. Such a model is a particular case of a nonhomogeneous risk renewal model. The sequence of claims has the form { X , X + Y , X + Z , X + Y , X , X + Y + Z , … } . Using the recursive formulas, algorithms were developed to calculate the exact values of survival probabilities for the three-risk discrete time model. The running of algorithms is illustrated via numerical examples.


2021 ◽  
Vol 12 (1) ◽  
Author(s):  
Erik van Dijk ◽  
Tom van den Bosch ◽  
Kristiaan J. Lenos ◽  
Khalid El Makrini ◽  
Lisanne E. Nijman ◽  
...  

AbstractSurvival rates of cancer patients vary widely within and between malignancies. While genetic aberrations are at the root of all cancers, individual genomic features cannot explain these distinct disease outcomes. In contrast, intra-tumour heterogeneity (ITH) has the potential to elucidate pan-cancer survival rates and the biology that drives cancer prognosis. Unfortunately, a comprehensive and effective framework to measure ITH across cancers is missing. Here, we introduce a scalable measure of chromosomal copy number heterogeneity (CNH) that predicts patient survival across cancers. We show that the level of ITH can be derived from a single-sample copy number profile. Using gene-expression data and live cell imaging we demonstrate that ongoing chromosomal instability underlies the observed heterogeneity. Analysing 11,534 primary cancer samples from 37 different malignancies, we find that copy number heterogeneity can be accurately deduced and predicts cancer survival across tissues of origin and stages of disease. Our results provide a unifying molecular explanation for the different survival rates observed between cancer types.


1990 ◽  
Vol 112 (4) ◽  
pp. 774-781 ◽  
Author(s):  
R. J. Chang

A practical technique to derive a discrete-time linear state estimator for estimating the states of a nonlinearizable stochastic system involving both state-dependent and external noises through a linear noisy measurement system is presented. The present technique for synthesizing a discrete-time linear state estimator is first to construct an equivalent reference linear model for the nonlinearizable system such that the equivalent model will provide the same stationary covariance response as that of the nonlinear system. From the linear continuous model, a discrete-time state estimator can be directly derived from the corresponding discrete-time model. The synthesizing technique and filtering performance are illustrated and simulated by selecting linear, linearizable, and nonlinearizable systems with state-dependent noise.


2009 ◽  
Vol 33 (6) ◽  
pp. 713-732
Author(s):  
Adam Bobrowski ◽  
Marek Kimmel ◽  
Małgorzata Kubalińska

Sign in / Sign up

Export Citation Format

Share Document