Building robust pathology image analyses with uncertainty quantification. (September 2021)

• Record Type: Journal Article
• Authors: Gomes, Jeremias; Kong, Jun; Kurc, Tahsin; Melo, Alba C.M.A.; Ferreira, Renato; Saltz, Joel H.; Teodoro, George
• Is Part Of: Computer methods and programs in biomedicine. Volume 208(2021)
• Publication Date: 2021-09
• Subjects: Whole slide image analysis -- Uncertainty quantification -- Sensitivity analysis -- Microscopy -- Survival analysis; Medicine -- Computer programs -- Periodicals; Biology -- Computer programs -- Periodicals; Computers -- Periodicals; Medicine -- Periodicals; Médecine -- Logiciels -- Périodiques; Biologie -- Logiciels -- Périodiques; Biology -- Computer programs; Medicine -- Computer programs; Periodicals; Electronic journals; 610.28
• DOI: 10.1016/j.cmpb.2021.106291
• Languages: English
• ISSNs: 0169-2607

Abstract

Highlights: Parameter sensitivity analysis (SA) and Uncertainty Quantification (UQ) was evaluated in Pathology image analysis workflows. Efficient methods and high-performance computing systems were used to enable studies in large scale. We demonstrated that most of the application uncertainty could be attributed to a few parameters and impact a small set of features. UQ/SA has enabled filtering out sources of uncertainty (features) and building more reliable analysis. Abstract: Background and Objective: Computerized pathology image analysis is an important tool in research and clinical settings, which enables quantitative tissue characterization and can assist a pathologist's evaluation. The aim of our study is to systematically quantify and minimize uncertainty in output of computer based pathology image analysis. Methods: Uncertainty quantification (UQ) and sensitivity analysis (SA) methods, such as Variance-Based Decomposition (VBD) and Morris One-At-a-Time (MOAT), are employed to track and quantify uncertainty in a real-world application with large Whole Slide Imaging datasets - 943 Breast Invasive Carcinoma (BRCA) and 381 Lung Squamous Cell Carcinoma (LUSC) patients. Because these studies are compute intensive, high-performance computing systems and efficient UQ/SA methods were combined to provide efficient execution. UQ/SA has been able to highlight parameters of the application that impact the results, as well as nuclear features that carry most of the uncertainty. Using this information, we built a method for selecting stable features that minimize application output uncertainty. Results: The results show that input parameter variations significantly impact all stages (segmentation, feature computation, and survival analysis) of the use case application. We then identified and classified features according to their robustness to parameter variation, and using the proposed features selection strategy, for instance, patient grouping stability in survival analysis has been improved from in 17% and 34% for BRCA and LUSC, respectively. Conclusions: This strategy created more robust analyses, demonstrating that SA and UQ are important methods that may increase confidence digital pathology.