Quantification of heterogeneity as a biomarker in tumor imaging

A systematic review

Lejla Alic, Wiro J. Niessen, Jifke F. Veenland

Research output: Contribution to journalReview article

68 Citations (Scopus)

Abstract

Background: Many techniques are proposed for the quantification of tumor heterogeneity as an imaging biomarker for differentiation between tumor types, tumor grading, response monitoring and outcome prediction. However, in clinical practice these methods are barely used. This study evaluates the reported performance of the described methods and identifies barriers to their implementation in clinical practice.

Methodology: The Ovid, Embase, and Cochrane Central databases were searched up to 20 September 2013. Heterogeneity analysis methods were classified into four categories, i.e., non-spatial methods (NSM), spatial grey level methods (SGLM), fractal analysis (FA) methods, and filters and transforms (F&T). The performance of the different methods was compared.

Principal Findings: Of the 7351 potentially relevant publications, 209 were included. Of these studies, 58% reported the use of NSM, 49% SGLM, 10% FA, and 28% F&T. Differentiation between tumor types, tumor grading and/or outcome prediction was the goal in 87% of the studies. Overall, the reported area under the curve (AUC) ranged from 0.5 to 1 (median 0.87). No relation was found between the performance and the quantification methods used, or between the performance and the imaging modality. A negative correlation was found between the tumor-feature ratio and the AUC, which is presumably caused by overfitting in small datasets. Cross-validation was reported in 63% of the classification studies. Retrospective analyses were conducted in 57% of the studies without a clear description.

Conclusions: In a research setting, heterogeneity quantification methods can differentiate between tumor types, grade tumors, and predict outcome and monitor treatment effects. To translate these methods to clinical practice, more prospective studies are required that use external datasets for validation: these datasets should be made available to the community to facilitate the development of new and improved methods.

Original languageEnglish
Article numbere110300
JournalPLoS One
Volume9
Issue number10
DOIs
Publication statusPublished - 20 Oct 2014
Externally publishedYes

Fingerprint

systematic review
Biomarkers
Tumor Biomarkers
Tumors
biomarkers
image analysis
Imaging techniques
neoplasms
methodology
Fractals
Neoplasms
Neoplasm Grading
Area Under Curve
prediction
monitoring
Monitoring
prospective studies
Publications
Databases
Prospective Studies

ASJC Scopus subject areas

  • Biochemistry, Genetics and Molecular Biology(all)
  • Agricultural and Biological Sciences(all)

Cite this

Quantification of heterogeneity as a biomarker in tumor imaging : A systematic review. / Alic, Lejla; Niessen, Wiro J.; Veenland, Jifke F.

In: PLoS One, Vol. 9, No. 10, e110300, 20.10.2014.

Research output: Contribution to journalReview article

Alic, Lejla ; Niessen, Wiro J. ; Veenland, Jifke F. / Quantification of heterogeneity as a biomarker in tumor imaging : A systematic review. In: PLoS One. 2014 ; Vol. 9, No. 10.
@article{d813ba50fa14407f8cc92163d1b02abb,
title = "Quantification of heterogeneity as a biomarker in tumor imaging: A systematic review",
abstract = "Background: Many techniques are proposed for the quantification of tumor heterogeneity as an imaging biomarker for differentiation between tumor types, tumor grading, response monitoring and outcome prediction. However, in clinical practice these methods are barely used. This study evaluates the reported performance of the described methods and identifies barriers to their implementation in clinical practice.Methodology: The Ovid, Embase, and Cochrane Central databases were searched up to 20 September 2013. Heterogeneity analysis methods were classified into four categories, i.e., non-spatial methods (NSM), spatial grey level methods (SGLM), fractal analysis (FA) methods, and filters and transforms (F&T). The performance of the different methods was compared.Principal Findings: Of the 7351 potentially relevant publications, 209 were included. Of these studies, 58{\%} reported the use of NSM, 49{\%} SGLM, 10{\%} FA, and 28{\%} F&T. Differentiation between tumor types, tumor grading and/or outcome prediction was the goal in 87{\%} of the studies. Overall, the reported area under the curve (AUC) ranged from 0.5 to 1 (median 0.87). No relation was found between the performance and the quantification methods used, or between the performance and the imaging modality. A negative correlation was found between the tumor-feature ratio and the AUC, which is presumably caused by overfitting in small datasets. Cross-validation was reported in 63{\%} of the classification studies. Retrospective analyses were conducted in 57{\%} of the studies without a clear description.Conclusions: In a research setting, heterogeneity quantification methods can differentiate between tumor types, grade tumors, and predict outcome and monitor treatment effects. To translate these methods to clinical practice, more prospective studies are required that use external datasets for validation: these datasets should be made available to the community to facilitate the development of new and improved methods.",
author = "Lejla Alic and Niessen, {Wiro J.} and Veenland, {Jifke F.}",
year = "2014",
month = "10",
day = "20",
doi = "10.1371/journal.pone.0110300",
language = "English",
volume = "9",
journal = "PLoS One",
issn = "1932-6203",
publisher = "Public Library of Science",
number = "10",

}

TY - JOUR

T1 - Quantification of heterogeneity as a biomarker in tumor imaging

T2 - A systematic review

AU - Alic, Lejla

AU - Niessen, Wiro J.

AU - Veenland, Jifke F.

PY - 2014/10/20

Y1 - 2014/10/20

N2 - Background: Many techniques are proposed for the quantification of tumor heterogeneity as an imaging biomarker for differentiation between tumor types, tumor grading, response monitoring and outcome prediction. However, in clinical practice these methods are barely used. This study evaluates the reported performance of the described methods and identifies barriers to their implementation in clinical practice.Methodology: The Ovid, Embase, and Cochrane Central databases were searched up to 20 September 2013. Heterogeneity analysis methods were classified into four categories, i.e., non-spatial methods (NSM), spatial grey level methods (SGLM), fractal analysis (FA) methods, and filters and transforms (F&T). The performance of the different methods was compared.Principal Findings: Of the 7351 potentially relevant publications, 209 were included. Of these studies, 58% reported the use of NSM, 49% SGLM, 10% FA, and 28% F&T. Differentiation between tumor types, tumor grading and/or outcome prediction was the goal in 87% of the studies. Overall, the reported area under the curve (AUC) ranged from 0.5 to 1 (median 0.87). No relation was found between the performance and the quantification methods used, or between the performance and the imaging modality. A negative correlation was found between the tumor-feature ratio and the AUC, which is presumably caused by overfitting in small datasets. Cross-validation was reported in 63% of the classification studies. Retrospective analyses were conducted in 57% of the studies without a clear description.Conclusions: In a research setting, heterogeneity quantification methods can differentiate between tumor types, grade tumors, and predict outcome and monitor treatment effects. To translate these methods to clinical practice, more prospective studies are required that use external datasets for validation: these datasets should be made available to the community to facilitate the development of new and improved methods.

AB - Background: Many techniques are proposed for the quantification of tumor heterogeneity as an imaging biomarker for differentiation between tumor types, tumor grading, response monitoring and outcome prediction. However, in clinical practice these methods are barely used. This study evaluates the reported performance of the described methods and identifies barriers to their implementation in clinical practice.Methodology: The Ovid, Embase, and Cochrane Central databases were searched up to 20 September 2013. Heterogeneity analysis methods were classified into four categories, i.e., non-spatial methods (NSM), spatial grey level methods (SGLM), fractal analysis (FA) methods, and filters and transforms (F&T). The performance of the different methods was compared.Principal Findings: Of the 7351 potentially relevant publications, 209 were included. Of these studies, 58% reported the use of NSM, 49% SGLM, 10% FA, and 28% F&T. Differentiation between tumor types, tumor grading and/or outcome prediction was the goal in 87% of the studies. Overall, the reported area under the curve (AUC) ranged from 0.5 to 1 (median 0.87). No relation was found between the performance and the quantification methods used, or between the performance and the imaging modality. A negative correlation was found between the tumor-feature ratio and the AUC, which is presumably caused by overfitting in small datasets. Cross-validation was reported in 63% of the classification studies. Retrospective analyses were conducted in 57% of the studies without a clear description.Conclusions: In a research setting, heterogeneity quantification methods can differentiate between tumor types, grade tumors, and predict outcome and monitor treatment effects. To translate these methods to clinical practice, more prospective studies are required that use external datasets for validation: these datasets should be made available to the community to facilitate the development of new and improved methods.

UR - http://www.scopus.com/inward/record.url?scp=84908191509&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84908191509&partnerID=8YFLogxK

U2 - 10.1371/journal.pone.0110300

DO - 10.1371/journal.pone.0110300

M3 - Review article

VL - 9

JO - PLoS One

JF - PLoS One

SN - 1932-6203

IS - 10

M1 - e110300

ER -