Streamlined Quantitative Imaging Biomarker Development: Generalization of radiomics through automated machine learning

Martijn Starmans

Streamlined Quantitative Imaging Biomarker Development: Generalization of radiomics through automated machine learning

Martijn Starmans^*

^*Corresponding author for this work

Radiology & Nuclear Medicine

Research output: Types of Thesis › Doctoral Thesis › Internal

121 Downloads (Pure)

Abstract

Radiomics uses quantitative medical imaging features and AI to create predictive models which can be used as biomarkers. In this thesis, we have developped an adaptive radiomics framework to automatically optimize the radiomics workflow per application and demonstrate its use to create biomarkers in eight different clinical applications.

Original language	English
Awarding Institution	Erasmus University Rotterdam
Supervisors/Advisors	Niessen, Wiro, Supervisor Klein, Stefan, Co-supervisor Visser, Jan-Jaap, Co-supervisor
Award date	1 Feb 2022
Place of Publication	Rotterdam
Print ISBNs	978-94-6416-970-6
Publication status	Published - 1 Feb 2022

Bibliographical note

This work is part of the research programme STRaTeGy with project numbers 14929, 14930, and 14932, which is (partly) financed by the Dutch Research Council (NWO).

Access to Document

thesis MPA Starmans - 61c583111826bFinal published version, 105 MBLicence: Unspecified
thesis MPA Starmans embargo version - 61c5831509bd6Other version, 103 MBLicence: Unspecified

Cite this

@phdthesis{64acf78dbc68470ea278eaaeffa2d0b9,

title = "Streamlined Quantitative Imaging Biomarker Development: Generalization of radiomics through automated machine learning",

abstract = "Radiomics uses quantitative medical imaging features and AI to create predictive models which can be used as biomarkers. In this thesis, we have developped an adaptive radiomics framework to automatically optimize the radiomics workflow per application and demonstrate its use to create biomarkers in eight different clinical applications.",

author = "Martijn Starmans",

note = "This work is part of the research programme STRaTeGy with project numbers 14929, 14930, and 14932, which is (partly) financed by the Dutch Research Council (NWO).",

year = "2022",

month = feb,

day = "1",

language = "English",

isbn = "978-94-6416-970-6",

series = "ASCI Dissertation Series",

number = "431",

school = "Erasmus University Rotterdam",

}

TY - BOOK

T1 - Streamlined Quantitative Imaging Biomarker Development

T2 - Generalization of radiomics through automated machine learning

AU - Starmans, Martijn

N1 - This work is part of the research programme STRaTeGy with project numbers 14929, 14930, and 14932, which is (partly) financed by the Dutch Research Council (NWO).

PY - 2022/2/1

Y1 - 2022/2/1

N2 - Radiomics uses quantitative medical imaging features and AI to create predictive models which can be used as biomarkers. In this thesis, we have developped an adaptive radiomics framework to automatically optimize the radiomics workflow per application and demonstrate its use to create biomarkers in eight different clinical applications.

AB - Radiomics uses quantitative medical imaging features and AI to create predictive models which can be used as biomarkers. In this thesis, we have developped an adaptive radiomics framework to automatically optimize the radiomics workflow per application and demonstrate its use to create biomarkers in eight different clinical applications.

M3 - Doctoral Thesis

SN - 978-94-6416-970-6

T3 - ASCI Dissertation Series

CY - Rotterdam

ER -

Streamlined Quantitative Imaging Biomarker Development: Generalization of radiomics through automated machine learning

Abstract

Bibliographical note

Access to Document

Other files and links

Fingerprint

Cite this