DEMARCATE: density-based magnetic resonance image clustering for assessing tumor heterogeneity in cancer

Tumor heterogeneity is a crucial area of cancer research wherein inter- and intra-tumor differences are investigated to assess and monitor disease development and progression, especially in cancer. The proliferation of imaging and linked genomic data has enabled us to evaluate tumor heterogeneity on...

Full description

Bibliographic Details
Main Authors: Saha, Abhijoy, Banerjee, Sayantan, Kurtek, Sebastian, Narang, Shivali, Lee, Joonsang, Rao, Ganesh, Martinez, Juan, Bharath, Karthik, Baladandayuthapani, Veerabhadran
Format: Article
Published: Elsevier 2016
Subjects:
Online Access:https://eprints.nottingham.ac.uk/44896/
_version_ 1848797022861131776
author Saha, Abhijoy
Banerjee, Sayantan
Kurtek, Sebastian
Narang, Shivali
Lee, Joonsang
Rao, Ganesh
Martinez, Juan
Bharath, Karthik
Baladandayuthapani, Veerabhadran
author_facet Saha, Abhijoy
Banerjee, Sayantan
Kurtek, Sebastian
Narang, Shivali
Lee, Joonsang
Rao, Ganesh
Martinez, Juan
Bharath, Karthik
Baladandayuthapani, Veerabhadran
author_sort Saha, Abhijoy
building Nottingham Research Data Repository
collection Online Access
description Tumor heterogeneity is a crucial area of cancer research wherein inter- and intra-tumor differences are investigated to assess and monitor disease development and progression, especially in cancer. The proliferation of imaging and linked genomic data has enabled us to evaluate tumor heterogeneity on multiple levels. In this work, we examine magnetic resonance imaging (MRI) in patients with brain cancer to assess image-based tumor heterogeneity. Standard approaches to this problem use scalar summary measures (e.g., intensity-based histogram statistics) that do not adequately capture the complete and finer scale information in the voxel-level data. In this paper, we introduce a novel technique, DEMARCATE (DEnsity-based MAgnetic Resonance image Clustering for Assessing Tumor hEterogeneity) to explore the entire tumor heterogeneity density profiles (THDPs) obtained from the full tumor voxel space. THDPs are smoothed representations of the probability density function of the tumor images. We develop tools for analyzing such objects under the Fisher–Rao Riemannian framework that allows us to construct metrics for THDP comparisons across patients, which can be used in conjunction with standard clustering approaches. Our analyses of The Cancer Genome Atlas (TCGA) based Glioblastoma dataset reveal two significant clusters of patients with marked differences in tumor morphology, genomic characteristics and prognostic clinical outcomes. In addition, we see enrichment of image-based clusters with known molecular subtypes of glioblastoma multiforme, which further validates our representation of tumor heterogeneity and subsequent clustering techniques.
first_indexed 2025-11-14T19:57:16Z
format Article
id nottingham-44896
institution University of Nottingham Malaysia Campus
institution_category Local University
last_indexed 2025-11-14T19:57:16Z
publishDate 2016
publisher Elsevier
recordtype eprints
repository_type Digital Repository
spelling nottingham-448962020-05-04T17:50:04Z https://eprints.nottingham.ac.uk/44896/ DEMARCATE: density-based magnetic resonance image clustering for assessing tumor heterogeneity in cancer Saha, Abhijoy Banerjee, Sayantan Kurtek, Sebastian Narang, Shivali Lee, Joonsang Rao, Ganesh Martinez, Juan Bharath, Karthik Baladandayuthapani, Veerabhadran Tumor heterogeneity is a crucial area of cancer research wherein inter- and intra-tumor differences are investigated to assess and monitor disease development and progression, especially in cancer. The proliferation of imaging and linked genomic data has enabled us to evaluate tumor heterogeneity on multiple levels. In this work, we examine magnetic resonance imaging (MRI) in patients with brain cancer to assess image-based tumor heterogeneity. Standard approaches to this problem use scalar summary measures (e.g., intensity-based histogram statistics) that do not adequately capture the complete and finer scale information in the voxel-level data. In this paper, we introduce a novel technique, DEMARCATE (DEnsity-based MAgnetic Resonance image Clustering for Assessing Tumor hEterogeneity) to explore the entire tumor heterogeneity density profiles (THDPs) obtained from the full tumor voxel space. THDPs are smoothed representations of the probability density function of the tumor images. We develop tools for analyzing such objects under the Fisher–Rao Riemannian framework that allows us to construct metrics for THDP comparisons across patients, which can be used in conjunction with standard clustering approaches. Our analyses of The Cancer Genome Atlas (TCGA) based Glioblastoma dataset reveal two significant clusters of patients with marked differences in tumor morphology, genomic characteristics and prognostic clinical outcomes. In addition, we see enrichment of image-based clusters with known molecular subtypes of glioblastoma multiforme, which further validates our representation of tumor heterogeneity and subsequent clustering techniques. Elsevier 2016-05-27 Article PeerReviewed Saha, Abhijoy, Banerjee, Sayantan, Kurtek, Sebastian, Narang, Shivali, Lee, Joonsang, Rao, Ganesh, Martinez, Juan, Bharath, Karthik and Baladandayuthapani, Veerabhadran (2016) DEMARCATE: density-based magnetic resonance image clustering for assessing tumor heterogeneity in cancer. NeuroImage: Clinical, 12 . pp. 132-143. ISSN 2213-1582 Glioblastoma; Medical imaging; Tumor heterogeneity; Density estimation; Clustering; Fisher–Rao metric http://www.sciencedirect.com/science/article/pii/S2213158216300882 doi:10.1016/j.nicl.2016.05.012 doi:10.1016/j.nicl.2016.05.012
spellingShingle Glioblastoma; Medical imaging; Tumor heterogeneity; Density estimation; Clustering; Fisher–Rao metric
Saha, Abhijoy
Banerjee, Sayantan
Kurtek, Sebastian
Narang, Shivali
Lee, Joonsang
Rao, Ganesh
Martinez, Juan
Bharath, Karthik
Baladandayuthapani, Veerabhadran
DEMARCATE: density-based magnetic resonance image clustering for assessing tumor heterogeneity in cancer
title DEMARCATE: density-based magnetic resonance image clustering for assessing tumor heterogeneity in cancer
title_full DEMARCATE: density-based magnetic resonance image clustering for assessing tumor heterogeneity in cancer
title_fullStr DEMARCATE: density-based magnetic resonance image clustering for assessing tumor heterogeneity in cancer
title_full_unstemmed DEMARCATE: density-based magnetic resonance image clustering for assessing tumor heterogeneity in cancer
title_short DEMARCATE: density-based magnetic resonance image clustering for assessing tumor heterogeneity in cancer
title_sort demarcate: density-based magnetic resonance image clustering for assessing tumor heterogeneity in cancer
topic Glioblastoma; Medical imaging; Tumor heterogeneity; Density estimation; Clustering; Fisher–Rao metric
url https://eprints.nottingham.ac.uk/44896/
https://eprints.nottingham.ac.uk/44896/
https://eprints.nottingham.ac.uk/44896/