Sensitivity analysis in digital pathology: Handling large number of parameters with compute expensive workflows.

Digital pathology imaging enables valuable quantitative characterizations of tissue state at the sub-cellular level. While there is a growing set of methods for analysis of whole slide tissue images, many of them are sensitive to changes in input parameters. Evaluating how analysis results are affected by variations in input parameters is important for the development of robust methods. Executing algorithm sensitivity analyses by systematically varying input parameters is an expensive task because a single evaluation run with a moderate number of tissue images may take hours or days. Our work investigates the use of Surrogate Models (SMs) along with parallel execution to speed up parameter sensitivity analysis (SA). This approach significantly reduces the SA cost, because the SM execution is inexpensive. The evaluation of several SM strategies with two image segmentation workflows demonstrates that a SA study with SMs attains results close to a SA with real application runs (mean absolute error lower than 0.022), while the SM accelerates the SA execution by 51 × . We also show that, although the number of parameters in the example workflows is high, most of the uncertainty can be associated with a few parameters. In order to identify the impact of variations in segmentation results to downstream analyses, we carried out a survival analysis with 387 Lung Squamous Cell Carcinoma cases. This analysis was repeated using 3 values for the most significant parameters identified by the SA for the two segmentation algorithms; about 600 million cell nuclei were segmented per run. The results show that significance of the survival correlations of patient groups, assessed by a logrank test, are strongly affected by the segmentation parameter changes. This indicates that sensitivity analysis is an important tool for evaluating the stability of conclusions from image analyses.

Uncertainty quantification of 2 models of cardiac electromechanics.

Computational models of the heart have reached a maturity level that render them useful for in silico studies of arrhythmia and other cardiac diseases. However, the translation to the clinic of cardiac simulations critically depends on demonstrating the accuracy, robustness, and reliability of the underlying computational models under the presence of uncertainties. In this work, we study for the first time the effect of parameter uncertainty on 2 state-of-the-art coupled models of excitation-contraction of cardiac tissue. To this end, we perform forward uncertainty propagation and sensitivity analyses to understand how variability in key maximal conductances affect selected quantities of interest, such as the action potential duration (APD90 ), maximum intracellular calcium concentration, cardiac stretch, and stress. Our results suggest a strong linear relationship between selected maximal conductances and quantities of interest for a variability in parameters up to 25%, which justifies the construction of linear response surfaces that are used to compute the empirical probability density functions of all the quantities of interest under study. For both electromechanical models analyzed, uncertainty in the material parameters associated to the passive mechanical response of cardiac tissue does not affect the duration of action potentials, neither the amplitude of intracellular calcium concentrations. Our results confirm the poor mechanoelectric feedback that classical models of cardiac electromechanics have, even under the presence of parameter uncertainty.