Radiologic image-based statistical shape analysis of brain tumors

We propose a curve-based Riemannian-geometric approach for general shape-based statistical analyses of tumors obtained from radiologic images. A key component of the framework is a suitable metric that (1) enables comparisons of tumor shapes, (2) provides tools for computing descriptive statistics a...

Full description

Bibliographic Details
Main Authors: Bharath, Karthik, Kurtek, Sebastian, Rao, Arvind, Baladandayuthapani, Veerabhadran
Format: Article
Language:English
Published: Wiley 2018
Subjects:
Online Access:https://eprints.nottingham.ac.uk/49379/
_version_ 1848797983943950336
author Bharath, Karthik
Kurtek, Sebastian
Rao, Arvind
Baladandayuthapani, Veerabhadran
author_facet Bharath, Karthik
Kurtek, Sebastian
Rao, Arvind
Baladandayuthapani, Veerabhadran
author_sort Bharath, Karthik
building Nottingham Research Data Repository
collection Online Access
description We propose a curve-based Riemannian-geometric approach for general shape-based statistical analyses of tumors obtained from radiologic images. A key component of the framework is a suitable metric that (1) enables comparisons of tumor shapes, (2) provides tools for computing descriptive statistics and implementing principal component analysis on the space of tumor shapes, and (3) allows for a rich class of continuous deformations of a tumor shape. The utility of the framework is illustrated through specific statistical tasks on a dataset of radiologic images of patients diagnosed with glioblastoma multiforme, a malignant brain tumor with poor prognosis. In particular, our analysis discovers two patient clusters with very different survival, subtype and genomic characteristics. Furthermore, it is demonstrated that adding tumor shape information into survival models containing clinical and genomic variables results in a significant increase in predictive power.
first_indexed 2025-11-14T20:12:33Z
format Article
id nottingham-49379
institution University of Nottingham Malaysia Campus
institution_category Local University
language English
last_indexed 2025-11-14T20:12:33Z
publishDate 2018
publisher Wiley
recordtype eprints
repository_type Digital Repository
spelling nottingham-493792019-03-15T04:30:17Z https://eprints.nottingham.ac.uk/49379/ Radiologic image-based statistical shape analysis of brain tumors Bharath, Karthik Kurtek, Sebastian Rao, Arvind Baladandayuthapani, Veerabhadran We propose a curve-based Riemannian-geometric approach for general shape-based statistical analyses of tumors obtained from radiologic images. A key component of the framework is a suitable metric that (1) enables comparisons of tumor shapes, (2) provides tools for computing descriptive statistics and implementing principal component analysis on the space of tumor shapes, and (3) allows for a rich class of continuous deformations of a tumor shape. The utility of the framework is illustrated through specific statistical tasks on a dataset of radiologic images of patients diagnosed with glioblastoma multiforme, a malignant brain tumor with poor prognosis. In particular, our analysis discovers two patient clusters with very different survival, subtype and genomic characteristics. Furthermore, it is demonstrated that adding tumor shape information into survival models containing clinical and genomic variables results in a significant increase in predictive power. Wiley 2018-11-30 Article PeerReviewed application/pdf en https://eprints.nottingham.ac.uk/49379/1/paperv5.pdf Bharath, Karthik, Kurtek, Sebastian, Rao, Arvind and Baladandayuthapani, Veerabhadran (2018) Radiologic image-based statistical shape analysis of brain tumors. Journal of the Royal Statistical Society: Series C, 67 (5). pp. 1357-1378. ISSN 1467-9876 Magnetic resonance imaging; Shape manifold; Glioblastoma multiforme; Clustering; Survival analysis http://onlinelibrary.wiley.com/doi/10.1111/rssc.12272/abstract doi:10.1111/rssc.12272 doi:10.1111/rssc.12272
spellingShingle Magnetic resonance imaging; Shape manifold; Glioblastoma multiforme; Clustering; Survival analysis
Bharath, Karthik
Kurtek, Sebastian
Rao, Arvind
Baladandayuthapani, Veerabhadran
Radiologic image-based statistical shape analysis of brain tumors
title Radiologic image-based statistical shape analysis of brain tumors
title_full Radiologic image-based statistical shape analysis of brain tumors
title_fullStr Radiologic image-based statistical shape analysis of brain tumors
title_full_unstemmed Radiologic image-based statistical shape analysis of brain tumors
title_short Radiologic image-based statistical shape analysis of brain tumors
title_sort radiologic image-based statistical shape analysis of brain tumors
topic Magnetic resonance imaging; Shape manifold; Glioblastoma multiforme; Clustering; Survival analysis
url https://eprints.nottingham.ac.uk/49379/
https://eprints.nottingham.ac.uk/49379/
https://eprints.nottingham.ac.uk/49379/