Imaging anisotropic layering with Bayesian inversion of multiple data types

This study compares two different empirical research methods for evaluating information visualizations: the traditional benchmark-task method and the insight method. The methods are compared using criteria such as the conclusions about the visualization designs provided by each method, the time participants spent during the study, the time and effort required to analyse the resulting empirical data, and the effect of individual differences between participants on the results. The study compares three graph visualization alternatives that associate bioinformatics microarray time series data to pathway graph vertices in order to investigate the effect of different visual grouping structures in visualization designs that integrate multiple data types. It is confirmed that visual grouping should match task structure, but interactive grouping proves to be a well-rounded alternative. Overall, the results validate the insight method’s ability to confirm results of the task method, but also show advantages of the insight method to illuminate additional types of tasks. Efficiency and insight frequently correlate, but important distinctions are found. Categories: H.5.2 [Information Interfaces and Presentation]: User Interfaces – evaluation/methodology.

Download Full-text

From Medical Imaging to Radiomics: Role of Data Science for Advancing Precision Health

Journal of Personalized Medicine ◽

10.3390/jpm10010015 ◽

2020 ◽

Vol 10 (1) ◽

pp. 15 ◽

Cited By ~ 4

Author(s):

Enrico Capobianco ◽

Marco Dominietto

Keyword(s):

Data Science ◽

Response To Therapy ◽

Data Types ◽

Clinical Value ◽

Multiple Data ◽

Starting Point ◽

Personal Histories ◽

Treatment Plans ◽

Precision Health

Treating disease according to precision health requires the individualization of therapeutic solutions as a cardinal step that is part of a process that typically depends on multiple factors. The starting point is the collection and assembly of data over time to assess the patient’s health status and monitor response to therapy. Radiomics is a very important component of this process. Its main goal is implementing a protocol to quantify the image informative contents by first mining and then extracting the most representative features. Further analysis aims to detect potential disease phenotypes through signs and marks of heterogeneity. As multimodal images hinge on various data sources, and these can be integrated with treatment plans and follow-up information, radiomics is naturally centered on dynamically monitoring disease progression and/or the health trajectory of patients. However, radiomics creates critical needs too. A concise list includes: (a) successful harmonization of intra/inter-modality radiomic measurements to facilitate the association with other data domains (genetic, clinical, lifestyle aspects, etc.); (b) ability of data science to revise model strategies and analytics tools to tackle multiple data types and structures (electronic medical records, personal histories, hospitalization data, genomic from various specimens, imaging, etc.) and to offer data-agnostic solutions for patient outcomes prediction; (c) and model validation with independent datasets to ensure generalization of results, clinical value of new risk stratifications, and support to clinical decisions for highly individualized patient management.

Download Full-text

Bayesian generalized biclustering analysis via adaptive structured shrinkage

Biostatistics ◽

10.1093/biostatistics/kxy081 ◽

2018 ◽

Vol 21 (3) ◽

pp. 610-624

Author(s):

Ziyi Li ◽

Changgee Chang ◽

Suprateek Kundu ◽

Qi Long

Keyword(s):

Negative Binomial ◽

Feature Space ◽

Biological Information ◽

Superior Performance ◽

Data Matrix ◽

Data Types ◽

Binomial Data ◽

Multiple Data ◽

Local Patterns ◽

Shrinkage Prior

Summary Biclustering techniques can identify local patterns of a data matrix by clustering feature space and sample space at the same time. Various biclustering methods have been proposed and successfully applied to analysis of gene expression data. While existing biclustering methods have many desirable features, most of them are developed for continuous data and few of them can efficiently handle -omics data of various types, for example, binomial data as in single nucleotide polymorphism data or negative binomial data as in RNA-seq data. In addition, none of existing methods can utilize biological information such as those from functional genomics or proteomics. Recent work has shown that incorporating biological information can improve variable selection and prediction performance in analyses such as linear regression and multivariate analysis. In this article, we propose a novel Bayesian biclustering method that can handle multiple data types including Gaussian, Binomial, and Negative Binomial. In addition, our method uses a Bayesian adaptive structured shrinkage prior that enables feature selection guided by existing biological information. Our simulation studies and application to multi-omics datasets demonstrate robust and superior performance of the proposed method, compared to other existing biclustering methods.

Download Full-text