Cancer imaging phenomics toolkit: Quantitative imaging analytics for precision diagnostics and predictive modeling of clinical outcome

Christos Davatzikos, Saima Rathore, Spyridon Bakas, Sarthak Pati, Mark Bergman, Ratheesh Kalarot, Patmaa Sridharan, Aimilia Gastounioti, Nariman Jahani, Eric Cohen, Hamed Akbari, Birkan Tunc, Jimit Doshi, Drew Parker, Michael Hsieh, Aristeidis Sotiras, Hongming Li, Yangming Ou, Robert K. Doot, Michel BilelloYong Fan, Russell T. Shinohara, Paul Yushkevich, Ragini Verma, Despina Kontos

Research output: Contribution to journalArticle

Abstract

The growth of multiparametric imaging protocols has paved the way for quantitative imaging phenotypes that predict treatment response and clinical outcome, reflect underlying cancer molecular characteristics and spatiotemporal heterogeneity, and can guide personalized treatment planning. This growth has underlined the need for efficient quantitative analytics to derive high-dimensional imaging signatures of diagnostic and predictive value in this emerging era of integrated precision diagnostics. This paper presents cancer imaging phenomics toolkit (CaPTk), a new and dynamically growing software platform for analysis of radiographic images of cancer, currently focusing on brain, breast, and lung cancer. CaPTk leverages the value of quantitative imaging analytics along with machine learning to derive phenotypic imaging signatures, based on two-level functionality. First, image analysis algorithms are used to extract comprehensive panels of diverse and complementary features, such as multiparametric intensity histogram distributions, texture, shape, kinetics, connectomics, and spatial patterns. At the second level, these quantitative imaging signatures are fed into multivariate machine learning models to produce diagnostic, prognostic, and predictive biomarkers. Results from clinical studies in three areas are shown: (i) computational neuro-oncology of brain gliomas for precision diagnostics, prediction of outcome, and treatment planning; (ii) prediction of treatment response for breast and lung cancer, and (iii) risk assessment for breast cancer.

Original languageEnglish (US)
Article number011018
JournalJournal of Medical Imaging
Volume5
Issue number1
DOIs
StatePublished - Jan 1 2018

Fingerprint

Breast Neoplasms
Lung Neoplasms
Neoplasms
Connectome
Diagnostic Imaging
Growth
Brain Neoplasms
Glioma
Software
Biomarkers
Phenotype
Brain
Machine Learning
Clinical Studies

Keywords

  • cancer imaging phenomics
  • open source software
  • precision diagnostics
  • radiogenomics
  • radiomics
  • treatment response

ASJC Scopus subject areas

  • Radiology Nuclear Medicine and imaging

Cite this

Cancer imaging phenomics toolkit : Quantitative imaging analytics for precision diagnostics and predictive modeling of clinical outcome. / Davatzikos, Christos; Rathore, Saima; Bakas, Spyridon; Pati, Sarthak; Bergman, Mark; Kalarot, Ratheesh; Sridharan, Patmaa; Gastounioti, Aimilia; Jahani, Nariman; Cohen, Eric; Akbari, Hamed; Tunc, Birkan; Doshi, Jimit; Parker, Drew; Hsieh, Michael; Sotiras, Aristeidis; Li, Hongming; Ou, Yangming; Doot, Robert K.; Bilello, Michel; Fan, Yong; Shinohara, Russell T.; Yushkevich, Paul; Verma, Ragini; Kontos, Despina.

In: Journal of Medical Imaging, Vol. 5, No. 1, 011018, 01.01.2018.

Research output: Contribution to journalArticle

Davatzikos, C, Rathore, S, Bakas, S, Pati, S, Bergman, M, Kalarot, R, Sridharan, P, Gastounioti, A, Jahani, N, Cohen, E, Akbari, H, Tunc, B, Doshi, J, Parker, D, Hsieh, M, Sotiras, A, Li, H, Ou, Y, Doot, RK, Bilello, M, Fan, Y, Shinohara, RT, Yushkevich, P, Verma, R & Kontos, D 2018, 'Cancer imaging phenomics toolkit: Quantitative imaging analytics for precision diagnostics and predictive modeling of clinical outcome', Journal of Medical Imaging, vol. 5, no. 1, 011018. https://doi.org/10.1117/1.JMI.5.1.011018
Davatzikos, Christos ; Rathore, Saima ; Bakas, Spyridon ; Pati, Sarthak ; Bergman, Mark ; Kalarot, Ratheesh ; Sridharan, Patmaa ; Gastounioti, Aimilia ; Jahani, Nariman ; Cohen, Eric ; Akbari, Hamed ; Tunc, Birkan ; Doshi, Jimit ; Parker, Drew ; Hsieh, Michael ; Sotiras, Aristeidis ; Li, Hongming ; Ou, Yangming ; Doot, Robert K. ; Bilello, Michel ; Fan, Yong ; Shinohara, Russell T. ; Yushkevich, Paul ; Verma, Ragini ; Kontos, Despina. / Cancer imaging phenomics toolkit : Quantitative imaging analytics for precision diagnostics and predictive modeling of clinical outcome. In: Journal of Medical Imaging. 2018 ; Vol. 5, No. 1.
@article{5ed23d12b154447e94657dcb93699bdd,
title = "Cancer imaging phenomics toolkit: Quantitative imaging analytics for precision diagnostics and predictive modeling of clinical outcome",
abstract = "The growth of multiparametric imaging protocols has paved the way for quantitative imaging phenotypes that predict treatment response and clinical outcome, reflect underlying cancer molecular characteristics and spatiotemporal heterogeneity, and can guide personalized treatment planning. This growth has underlined the need for efficient quantitative analytics to derive high-dimensional imaging signatures of diagnostic and predictive value in this emerging era of integrated precision diagnostics. This paper presents cancer imaging phenomics toolkit (CaPTk), a new and dynamically growing software platform for analysis of radiographic images of cancer, currently focusing on brain, breast, and lung cancer. CaPTk leverages the value of quantitative imaging analytics along with machine learning to derive phenotypic imaging signatures, based on two-level functionality. First, image analysis algorithms are used to extract comprehensive panels of diverse and complementary features, such as multiparametric intensity histogram distributions, texture, shape, kinetics, connectomics, and spatial patterns. At the second level, these quantitative imaging signatures are fed into multivariate machine learning models to produce diagnostic, prognostic, and predictive biomarkers. Results from clinical studies in three areas are shown: (i) computational neuro-oncology of brain gliomas for precision diagnostics, prediction of outcome, and treatment planning; (ii) prediction of treatment response for breast and lung cancer, and (iii) risk assessment for breast cancer.",
keywords = "cancer imaging phenomics, open source software, precision diagnostics, radiogenomics, radiomics, treatment response",
author = "Christos Davatzikos and Saima Rathore and Spyridon Bakas and Sarthak Pati and Mark Bergman and Ratheesh Kalarot and Patmaa Sridharan and Aimilia Gastounioti and Nariman Jahani and Eric Cohen and Hamed Akbari and Birkan Tunc and Jimit Doshi and Drew Parker and Michael Hsieh and Aristeidis Sotiras and Hongming Li and Yangming Ou and Doot, {Robert K.} and Michel Bilello and Yong Fan and Shinohara, {Russell T.} and Paul Yushkevich and Ragini Verma and Despina Kontos",
year = "2018",
month = "1",
day = "1",
doi = "10.1117/1.JMI.5.1.011018",
language = "English (US)",
volume = "5",
journal = "Journal of Medical Imaging",
issn = "0720-048X",
publisher = "Elsevier Ireland Ltd",
number = "1",

}

TY - JOUR

T1 - Cancer imaging phenomics toolkit

T2 - Quantitative imaging analytics for precision diagnostics and predictive modeling of clinical outcome

AU - Davatzikos, Christos

AU - Rathore, Saima

AU - Bakas, Spyridon

AU - Pati, Sarthak

AU - Bergman, Mark

AU - Kalarot, Ratheesh

AU - Sridharan, Patmaa

AU - Gastounioti, Aimilia

AU - Jahani, Nariman

AU - Cohen, Eric

AU - Akbari, Hamed

AU - Tunc, Birkan

AU - Doshi, Jimit

AU - Parker, Drew

AU - Hsieh, Michael

AU - Sotiras, Aristeidis

AU - Li, Hongming

AU - Ou, Yangming

AU - Doot, Robert K.

AU - Bilello, Michel

AU - Fan, Yong

AU - Shinohara, Russell T.

AU - Yushkevich, Paul

AU - Verma, Ragini

AU - Kontos, Despina

PY - 2018/1/1

Y1 - 2018/1/1

N2 - The growth of multiparametric imaging protocols has paved the way for quantitative imaging phenotypes that predict treatment response and clinical outcome, reflect underlying cancer molecular characteristics and spatiotemporal heterogeneity, and can guide personalized treatment planning. This growth has underlined the need for efficient quantitative analytics to derive high-dimensional imaging signatures of diagnostic and predictive value in this emerging era of integrated precision diagnostics. This paper presents cancer imaging phenomics toolkit (CaPTk), a new and dynamically growing software platform for analysis of radiographic images of cancer, currently focusing on brain, breast, and lung cancer. CaPTk leverages the value of quantitative imaging analytics along with machine learning to derive phenotypic imaging signatures, based on two-level functionality. First, image analysis algorithms are used to extract comprehensive panels of diverse and complementary features, such as multiparametric intensity histogram distributions, texture, shape, kinetics, connectomics, and spatial patterns. At the second level, these quantitative imaging signatures are fed into multivariate machine learning models to produce diagnostic, prognostic, and predictive biomarkers. Results from clinical studies in three areas are shown: (i) computational neuro-oncology of brain gliomas for precision diagnostics, prediction of outcome, and treatment planning; (ii) prediction of treatment response for breast and lung cancer, and (iii) risk assessment for breast cancer.

AB - The growth of multiparametric imaging protocols has paved the way for quantitative imaging phenotypes that predict treatment response and clinical outcome, reflect underlying cancer molecular characteristics and spatiotemporal heterogeneity, and can guide personalized treatment planning. This growth has underlined the need for efficient quantitative analytics to derive high-dimensional imaging signatures of diagnostic and predictive value in this emerging era of integrated precision diagnostics. This paper presents cancer imaging phenomics toolkit (CaPTk), a new and dynamically growing software platform for analysis of radiographic images of cancer, currently focusing on brain, breast, and lung cancer. CaPTk leverages the value of quantitative imaging analytics along with machine learning to derive phenotypic imaging signatures, based on two-level functionality. First, image analysis algorithms are used to extract comprehensive panels of diverse and complementary features, such as multiparametric intensity histogram distributions, texture, shape, kinetics, connectomics, and spatial patterns. At the second level, these quantitative imaging signatures are fed into multivariate machine learning models to produce diagnostic, prognostic, and predictive biomarkers. Results from clinical studies in three areas are shown: (i) computational neuro-oncology of brain gliomas for precision diagnostics, prediction of outcome, and treatment planning; (ii) prediction of treatment response for breast and lung cancer, and (iii) risk assessment for breast cancer.

KW - cancer imaging phenomics

KW - open source software

KW - precision diagnostics

KW - radiogenomics

KW - radiomics

KW - treatment response

UR - http://www.scopus.com/inward/record.url?scp=85040819784&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85040819784&partnerID=8YFLogxK

U2 - 10.1117/1.JMI.5.1.011018

DO - 10.1117/1.JMI.5.1.011018

M3 - Article

C2 - 29340286

AN - SCOPUS:85040819784

VL - 5

JO - Journal of Medical Imaging

JF - Journal of Medical Imaging

SN - 0720-048X

IS - 1

M1 - 011018

ER -