Dataset Information

Tree-based Methods for Characterizing Tumor Density Heterogeneity.

ABSTRACT: Solid lesions emerge within diverse tissue environments making their characterization and diagnosis a challenge. With the advent of cancer radiomics, a variety of techniques have been developed to transform images into quantifiable feature sets producing summary statistics that describe the morphology and texture of solid masses. Relying on empirical distribution summaries as well as grey-level co-occurrence statistics, several approaches have been devised to characterize tissue density heterogeneity. This article proposes a novel decision-tree based approach which quantifies the tissue density heterogeneity of a given lesion through its resultant distribution of tree-structured dissimilarity metrics computed with least common ancestor trees under repeated pixel re-sampling. The methodology, based on statistics derived from Galton-Watson trees, produces metrics that are minimally correlated with existing features, adding new information to the feature space and improving quantitative characterization of the extent to which a CT image conveys heterogeneous density distribution. We demonstrate its practical application through a diagnostic study of adrenal lesions. Integrating the proposed with existing features identifies classifiers of three important lesion types; malignant from benign (AUC = 0.78), functioning from non-functioning (AUC = 0.93) and calcified from non-calcified (AUC of 1).

SUBMITTER: Shoemaker K

PROVIDER: S-EPMC5749399 | biostudies-literature | 2018

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Tree-based Methods for Characterizing Tumor Density Heterogeneity.

Shoemaker Katherine K Hobbs Brian P BP Bharath Karthik K Ng Chaan S CS Baladandayuthapani Veerabhadran V

Pacific Symposium on Biocomputing. Pacific Symposium on Biocomputing 20180101

Solid lesions emerge within diverse tissue environments making their characterization and diagnosis a challenge. With the advent of cancer radiomics, a variety of techniques have been developed to transform images into quantifiable feature sets producing summary statistics that describe the morphology and texture of solid masses. Relying on empirical distribution summaries as well as grey-level co-occurrence statistics, several approaches have been devised to characterize tissue density heteroge ...[more]

PMID: 29218883

Similar Datasets

Project description:BackgroundTumor heterogeneity can manifest itself by sub-populations of cells having distinct phenotypic profiles expressed as diverse molecular, morphological and spatial distributions. This inherent heterogeneity poses challenges in terms of diagnosis, prognosis and efficient treatment. Consequently, tools and techniques are being developed to properly characterize and quantify tumor heterogeneity. Multiplexed immunofluorescence (MxIF) is one such technology that offers molecular insight into both inter-individual and intratumor heterogeneity. It enables the quantification of both the concentration and spatial distribution of 60+ proteins across a tissue section. Upon bioimage processing, protein expression data can be generated for each cell from a tissue field of view.ResultsThe Multi-Omics Heterogeneity Analysis (MOHA) tool was developed to compute tissue heterogeneity metrics from MxIF spatially resolved tissue imaging data. This technique computes the molecular state of each cell in a sample based on a pathway or gene set. Spatial states are then computed based on the spatial arrangements of the cells as distinguished by their respective molecular states. MOHA computes tissue heterogeneity metrics from the distributions of these molecular and spatially defined states. A colorectal cancer cohort of approximately 700 subjects with MxIF data is presented to demonstrate the MOHA methodology. Within this dataset, statistically significant correlations were found between the intratumor AKT pathway state diversity and cancer stage and histological tumor grade. Furthermore, intratumor spatial diversity metrics were found to correlate with cancer recurrence.ConclusionsMOHA provides a simple and robust approach to characterize molecular and spatial heterogeneity of tissues. Research projects that generate spatially resolved tissue imaging data can take full advantage of this useful technique. The MOHA algorithm is implemented as a freely available R script (see supplementary information).

Project description:MotivationWith the exponential growth of expression and protein-protein interaction (PPI) data, the identification of functional modules in PPI networks that show striking changes in molecular activity or phenotypic signatures becomes of particular interest to reveal process-specific information that is correlated with cellular or disease states. This requires both the identification of network nodes with reliability scores and the availability of an efficient technique to locate the network regions with the highest scores. In the literature, a number of heuristic methods have been suggested. We propose SEMtree(), a set of tree-based structure discovery algorithms, combining graph and statistically interpretable parameters together with a user-friendly R package based on structural equation models framework.ResultsCondition-specific changes from differential expression and gene-gene co-expression are recovered with statistical testing of node, directed edge, and directed path difference between groups. In the end, from a list of seed (i.e. disease) genes or gene P-values, the perturbed modules with undirected edges are generated with five state-of-the-art active subnetwork detection methods. The latter are supplied to causal additive trees based on Chu-Liu-Edmonds' algorithm (Chow and Liu, Approximating discrete probability distributions with dependence trees. IEEE Trans Inform Theory 1968;14:462-7) in SEMtree() to be converted in directed trees. This conversion allows to compare the methods in terms of directed active subnetworks. We applied SEMtree() to both Coronavirus disease (COVID-19) RNA-seq dataset (GEO accession: GSE172114) and simulated datasets with various differential expression patterns. Compared to existing methods, SEMtree() is able to capture biologically relevant subnetworks with simple visualization of directed paths, good perturbation extraction, and classifier performance.Availability and implementationSEMtree() function is implemented in the R package SEMgraph, easily available at https://CRAN.R-project.org/package=SEMgraph.

Dataset Information

Tree-based Methods for Characterizing Tumor Density Heterogeneity.

Publications

Tree-based Methods for Characterizing Tumor Density Heterogeneity.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets