Development and evaluation of an open-source software package "cGITA" for quantifying tumor heterogeneity with molecular images

Yu-Hua Dean Fang, Chien Yu Lin, Meng Jung Shih, Hung Ming Wang, Tsung Ying Ho, Chun Ta Liao, Tzu Chen Yen

Research output: Contribution to journalArticle

53 Citations (Scopus)

Abstract

Background. The quantification of tumor heterogeneity with molecular images, by analyzing the local or global variation in the spatial arrangements of pixel intensity with texture analysis, possesses a great clinical potential for treatment planning and prognosis. To address the lack of available software for computing the tumor heterogeneity on the public domain, we develop a software package, namely, Chang-Gung Image Texture Analysis (CGITA) toolbox, and provide it to the research community as a free, open-source project. Methods. With a user-friendly graphical interface, CGITA provides users with an easy way to compute more than seventy heterogeneity indices. To test and demonstrate the usefulness of CGITA, we used a small cohort of eighteen locally advanced oral cavity (ORC) cancer patients treated with definitive radiotherapies. Results. In our case study of ORC data, we found that more than ten of the current implemented heterogeneity indices outperformed SUVmean for outcome prediction in the ROC analysis with a higher area under curve (AUC). Heterogeneity indices provide a better area under the curve up to 0.9 than the SUVmean and TLG (0.6 and 0.52, resp.). Conclusions. CGITA is a free and open-source software package to quantify tumor heterogeneity from molecular images. CGITA is available for free for academic use at http://code.google.com/ p/cgita.

Original languageEnglish
Article number248505
JournalBioMed research international
Volume2014
DOIs
Publication statusPublished - 2014 Jan 1

Fingerprint

Image texture
Software packages
Tumors
Software
Area Under Curve
Mouth
Neoplasms
Public Sector
Mouth Neoplasms
ROC Curve
Radiotherapy
Graphical user interfaces
Research
Textures
Pixels
Open source software
Planning
Therapeutics

All Science Journal Classification (ASJC) codes

  • Immunology and Microbiology(all)
  • Biochemistry, Genetics and Molecular Biology(all)

Cite this

Fang, Yu-Hua Dean ; Lin, Chien Yu ; Shih, Meng Jung ; Wang, Hung Ming ; Ho, Tsung Ying ; Liao, Chun Ta ; Yen, Tzu Chen. / Development and evaluation of an open-source software package "cGITA" for quantifying tumor heterogeneity with molecular images. In: BioMed research international. 2014 ; Vol. 2014.
@article{2896963e70cb4896b122129d02e763a8,
title = "Development and evaluation of an open-source software package {"}cGITA{"} for quantifying tumor heterogeneity with molecular images",
abstract = "Background. The quantification of tumor heterogeneity with molecular images, by analyzing the local or global variation in the spatial arrangements of pixel intensity with texture analysis, possesses a great clinical potential for treatment planning and prognosis. To address the lack of available software for computing the tumor heterogeneity on the public domain, we develop a software package, namely, Chang-Gung Image Texture Analysis (CGITA) toolbox, and provide it to the research community as a free, open-source project. Methods. With a user-friendly graphical interface, CGITA provides users with an easy way to compute more than seventy heterogeneity indices. To test and demonstrate the usefulness of CGITA, we used a small cohort of eighteen locally advanced oral cavity (ORC) cancer patients treated with definitive radiotherapies. Results. In our case study of ORC data, we found that more than ten of the current implemented heterogeneity indices outperformed SUVmean for outcome prediction in the ROC analysis with a higher area under curve (AUC). Heterogeneity indices provide a better area under the curve up to 0.9 than the SUVmean and TLG (0.6 and 0.52, resp.). Conclusions. CGITA is a free and open-source software package to quantify tumor heterogeneity from molecular images. CGITA is available for free for academic use at http://code.google.com/ p/cgita.",
author = "Fang, {Yu-Hua Dean} and Lin, {Chien Yu} and Shih, {Meng Jung} and Wang, {Hung Ming} and Ho, {Tsung Ying} and Liao, {Chun Ta} and Yen, {Tzu Chen}",
year = "2014",
month = "1",
day = "1",
doi = "10.1155/2014/248505",
language = "English",
volume = "2014",
journal = "BioMed Research International",
issn = "2314-6133",
publisher = "Hindawi Publishing Corporation",

}

Development and evaluation of an open-source software package "cGITA" for quantifying tumor heterogeneity with molecular images. / Fang, Yu-Hua Dean; Lin, Chien Yu; Shih, Meng Jung; Wang, Hung Ming; Ho, Tsung Ying; Liao, Chun Ta; Yen, Tzu Chen.

In: BioMed research international, Vol. 2014, 248505, 01.01.2014.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Development and evaluation of an open-source software package "cGITA" for quantifying tumor heterogeneity with molecular images

AU - Fang, Yu-Hua Dean

AU - Lin, Chien Yu

AU - Shih, Meng Jung

AU - Wang, Hung Ming

AU - Ho, Tsung Ying

AU - Liao, Chun Ta

AU - Yen, Tzu Chen

PY - 2014/1/1

Y1 - 2014/1/1

N2 - Background. The quantification of tumor heterogeneity with molecular images, by analyzing the local or global variation in the spatial arrangements of pixel intensity with texture analysis, possesses a great clinical potential for treatment planning and prognosis. To address the lack of available software for computing the tumor heterogeneity on the public domain, we develop a software package, namely, Chang-Gung Image Texture Analysis (CGITA) toolbox, and provide it to the research community as a free, open-source project. Methods. With a user-friendly graphical interface, CGITA provides users with an easy way to compute more than seventy heterogeneity indices. To test and demonstrate the usefulness of CGITA, we used a small cohort of eighteen locally advanced oral cavity (ORC) cancer patients treated with definitive radiotherapies. Results. In our case study of ORC data, we found that more than ten of the current implemented heterogeneity indices outperformed SUVmean for outcome prediction in the ROC analysis with a higher area under curve (AUC). Heterogeneity indices provide a better area under the curve up to 0.9 than the SUVmean and TLG (0.6 and 0.52, resp.). Conclusions. CGITA is a free and open-source software package to quantify tumor heterogeneity from molecular images. CGITA is available for free for academic use at http://code.google.com/ p/cgita.

AB - Background. The quantification of tumor heterogeneity with molecular images, by analyzing the local or global variation in the spatial arrangements of pixel intensity with texture analysis, possesses a great clinical potential for treatment planning and prognosis. To address the lack of available software for computing the tumor heterogeneity on the public domain, we develop a software package, namely, Chang-Gung Image Texture Analysis (CGITA) toolbox, and provide it to the research community as a free, open-source project. Methods. With a user-friendly graphical interface, CGITA provides users with an easy way to compute more than seventy heterogeneity indices. To test and demonstrate the usefulness of CGITA, we used a small cohort of eighteen locally advanced oral cavity (ORC) cancer patients treated with definitive radiotherapies. Results. In our case study of ORC data, we found that more than ten of the current implemented heterogeneity indices outperformed SUVmean for outcome prediction in the ROC analysis with a higher area under curve (AUC). Heterogeneity indices provide a better area under the curve up to 0.9 than the SUVmean and TLG (0.6 and 0.52, resp.). Conclusions. CGITA is a free and open-source software package to quantify tumor heterogeneity from molecular images. CGITA is available for free for academic use at http://code.google.com/ p/cgita.

UR - http://www.scopus.com/inward/record.url?scp=84897539994&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84897539994&partnerID=8YFLogxK

U2 - 10.1155/2014/248505

DO - 10.1155/2014/248505

M3 - Article

C2 - 24757667

AN - SCOPUS:84897539994

VL - 2014

JO - BioMed Research International

JF - BioMed Research International

SN - 2314-6133

M1 - 248505

ER -