Contrast-Enhanced Ultrasound Quantification: From Kinetic Modeling to Machine Learning

Simona Turco, Peter Frinking, Rogier Wildeboer, Marcel Arditi, Hessel Wijkstra, Jonathan R. Lindner, Massimo Mischi

    Research output: Contribution to journalReview article

    Abstract

    Ultrasound contrast agents (UCAs) have opened up immense diagnostic possibilities by combined use of indicator dilution principles and dynamic contrast-enhanced ultrasound (DCE-US) imaging. UCAs are microbubbles encapsulated in a biocompatible shell. With a rheology comparable to that of red blood cells, UCAs provide an intravascular indicator for functional imaging of the (micro)vasculature by quantitative DCE-US. Several models of the UCA intravascular kinetics have been proposed to provide functional quantitative maps, aiding diagnosis of different pathological conditions. This article is a comprehensive review of the available methods for quantitative DCE-US imaging based on temporal, spatial and spatiotemporal analysis of the UCA kinetics. The recent introduction of novel UCAs that are targeted to specific vascular receptors has advanced DCE-US to a molecular imaging modality. In parallel, new kinetic models of increased complexity have been developed. The extraction of multiple quantitative maps, reflecting complementary variables of the underlying physiological processes, requires an integrative approach to their interpretation. A probabilistic framework based on emerging machine-learning methods represents nowadays the ultimate approach, improving the diagnostic accuracy of DCE-US imaging by optimal combination of the extracted complementary information. The current value and future perspective of all these advances are critically discussed.

    Original languageEnglish (US)
    Pages (from-to)518-543
    Number of pages26
    JournalUltrasound in Medicine and Biology
    Volume46
    Issue number3
    DOIs
    StatePublished - Mar 2020

    Fingerprint

    machine learning
    Contrast Media
    kinetics
    Ultrasonography
    Spatio-Temporal Analysis
    Physiological Phenomena
    Microbubbles
    Spatial Analysis
    Molecular Imaging
    Rheology
    Blood Vessels
    Machine Learning
    Erythrocytes
    erythrocytes
    rheology
    dilution
    emerging

    Keywords

    • Contrast-enhanced ultrasound
    • Indicator dilution theory
    • Kinetic modeling
    • Machine learning
    • Molecular ultrasound
    • Multiparametric ultrasound
    • Quantitative ultrasound
    • Spatiotemporal analysis
    • Time–intensity curves
    • Ultrasound contrast agents

    ASJC Scopus subject areas

    • Biophysics
    • Radiological and Ultrasound Technology
    • Acoustics and Ultrasonics

    Cite this

    Contrast-Enhanced Ultrasound Quantification : From Kinetic Modeling to Machine Learning. / Turco, Simona; Frinking, Peter; Wildeboer, Rogier; Arditi, Marcel; Wijkstra, Hessel; Lindner, Jonathan R.; Mischi, Massimo.

    In: Ultrasound in Medicine and Biology, Vol. 46, No. 3, 03.2020, p. 518-543.

    Research output: Contribution to journalReview article

    Turco, Simona ; Frinking, Peter ; Wildeboer, Rogier ; Arditi, Marcel ; Wijkstra, Hessel ; Lindner, Jonathan R. ; Mischi, Massimo. / Contrast-Enhanced Ultrasound Quantification : From Kinetic Modeling to Machine Learning. In: Ultrasound in Medicine and Biology. 2020 ; Vol. 46, No. 3. pp. 518-543.
    @article{206e2e32ea104724bee81cbb87b34b06,
    title = "Contrast-Enhanced Ultrasound Quantification: From Kinetic Modeling to Machine Learning",
    abstract = "Ultrasound contrast agents (UCAs) have opened up immense diagnostic possibilities by combined use of indicator dilution principles and dynamic contrast-enhanced ultrasound (DCE-US) imaging. UCAs are microbubbles encapsulated in a biocompatible shell. With a rheology comparable to that of red blood cells, UCAs provide an intravascular indicator for functional imaging of the (micro)vasculature by quantitative DCE-US. Several models of the UCA intravascular kinetics have been proposed to provide functional quantitative maps, aiding diagnosis of different pathological conditions. This article is a comprehensive review of the available methods for quantitative DCE-US imaging based on temporal, spatial and spatiotemporal analysis of the UCA kinetics. The recent introduction of novel UCAs that are targeted to specific vascular receptors has advanced DCE-US to a molecular imaging modality. In parallel, new kinetic models of increased complexity have been developed. The extraction of multiple quantitative maps, reflecting complementary variables of the underlying physiological processes, requires an integrative approach to their interpretation. A probabilistic framework based on emerging machine-learning methods represents nowadays the ultimate approach, improving the diagnostic accuracy of DCE-US imaging by optimal combination of the extracted complementary information. The current value and future perspective of all these advances are critically discussed.",
    keywords = "Contrast-enhanced ultrasound, Indicator dilution theory, Kinetic modeling, Machine learning, Molecular ultrasound, Multiparametric ultrasound, Quantitative ultrasound, Spatiotemporal analysis, Time–intensity curves, Ultrasound contrast agents",
    author = "Simona Turco and Peter Frinking and Rogier Wildeboer and Marcel Arditi and Hessel Wijkstra and Lindner, {Jonathan R.} and Massimo Mischi",
    year = "2020",
    month = "3",
    doi = "10.1016/j.ultrasmedbio.2019.11.008",
    language = "English (US)",
    volume = "46",
    pages = "518--543",
    journal = "Ultrasound in Medicine and Biology",
    issn = "0301-5629",
    publisher = "Elsevier USA",
    number = "3",

    }

    TY - JOUR

    T1 - Contrast-Enhanced Ultrasound Quantification

    T2 - From Kinetic Modeling to Machine Learning

    AU - Turco, Simona

    AU - Frinking, Peter

    AU - Wildeboer, Rogier

    AU - Arditi, Marcel

    AU - Wijkstra, Hessel

    AU - Lindner, Jonathan R.

    AU - Mischi, Massimo

    PY - 2020/3

    Y1 - 2020/3

    N2 - Ultrasound contrast agents (UCAs) have opened up immense diagnostic possibilities by combined use of indicator dilution principles and dynamic contrast-enhanced ultrasound (DCE-US) imaging. UCAs are microbubbles encapsulated in a biocompatible shell. With a rheology comparable to that of red blood cells, UCAs provide an intravascular indicator for functional imaging of the (micro)vasculature by quantitative DCE-US. Several models of the UCA intravascular kinetics have been proposed to provide functional quantitative maps, aiding diagnosis of different pathological conditions. This article is a comprehensive review of the available methods for quantitative DCE-US imaging based on temporal, spatial and spatiotemporal analysis of the UCA kinetics. The recent introduction of novel UCAs that are targeted to specific vascular receptors has advanced DCE-US to a molecular imaging modality. In parallel, new kinetic models of increased complexity have been developed. The extraction of multiple quantitative maps, reflecting complementary variables of the underlying physiological processes, requires an integrative approach to their interpretation. A probabilistic framework based on emerging machine-learning methods represents nowadays the ultimate approach, improving the diagnostic accuracy of DCE-US imaging by optimal combination of the extracted complementary information. The current value and future perspective of all these advances are critically discussed.

    AB - Ultrasound contrast agents (UCAs) have opened up immense diagnostic possibilities by combined use of indicator dilution principles and dynamic contrast-enhanced ultrasound (DCE-US) imaging. UCAs are microbubbles encapsulated in a biocompatible shell. With a rheology comparable to that of red blood cells, UCAs provide an intravascular indicator for functional imaging of the (micro)vasculature by quantitative DCE-US. Several models of the UCA intravascular kinetics have been proposed to provide functional quantitative maps, aiding diagnosis of different pathological conditions. This article is a comprehensive review of the available methods for quantitative DCE-US imaging based on temporal, spatial and spatiotemporal analysis of the UCA kinetics. The recent introduction of novel UCAs that are targeted to specific vascular receptors has advanced DCE-US to a molecular imaging modality. In parallel, new kinetic models of increased complexity have been developed. The extraction of multiple quantitative maps, reflecting complementary variables of the underlying physiological processes, requires an integrative approach to their interpretation. A probabilistic framework based on emerging machine-learning methods represents nowadays the ultimate approach, improving the diagnostic accuracy of DCE-US imaging by optimal combination of the extracted complementary information. The current value and future perspective of all these advances are critically discussed.

    KW - Contrast-enhanced ultrasound

    KW - Indicator dilution theory

    KW - Kinetic modeling

    KW - Machine learning

    KW - Molecular ultrasound

    KW - Multiparametric ultrasound

    KW - Quantitative ultrasound

    KW - Spatiotemporal analysis

    KW - Time–intensity curves

    KW - Ultrasound contrast agents

    UR - http://www.scopus.com/inward/record.url?scp=85077655323&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=85077655323&partnerID=8YFLogxK

    U2 - 10.1016/j.ultrasmedbio.2019.11.008

    DO - 10.1016/j.ultrasmedbio.2019.11.008

    M3 - Review article

    C2 - 31924424

    AN - SCOPUS:85077655323

    VL - 46

    SP - 518

    EP - 543

    JO - Ultrasound in Medicine and Biology

    JF - Ultrasound in Medicine and Biology

    SN - 0301-5629

    IS - 3

    ER -