Measurement and Quantification

Olivier Bernard; Bram Ruijsink; Thomas Grenier; Mathieu De Craene

doi:10.1007/978-3-031-05071-8_4

Measurement and Quantification

Olivier Bernard^*
, Bram Ruijsink
, Thomas Grenier
, Mathieu De Craene

^*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceeding › Chapter › Academic › peer-review

2 Downloads (Pure)

Abstract

This chapter deals with the clinical task of measuring and quantifying cardiac morphology and function. The chapter opens with a clinical introduction, which outlines current clinical workflows, including how they derive and make use of biomarkers as well as their weaknesses and limitations. A technical review is provided that summarises the state-of-the-art in AI for automated measurement and quantification. This technical section describes the common deep learning models that have been proposed for measurement and quantification, and also gives some specific examples of their application. A practical tutorial is provided on a simple CMR segmentation task. The chapter closes with a clinical opinion piece that speculates on the future impact of AI in this area.

Original language	English
Title of host publication	AI and Big Data in Cardiology
Subtitle of host publication	a Practical Guide
Editors	N. Duchateau, A.P. King
Publisher	Springer International Publishing
Chapter	4
Pages	57-84
Number of pages	28
ISBN (Electronic)	9783031050718
ISBN (Print)	9783031050701
DOIs	https://doi.org/10.1007/978-3-031-05071-8_4
Publication status	Published - 2023

Keywords

Biomarker
Deep learning
Measurement
Quantification
Segmentation
U-net

Access to Document

10.1007/978-3-031-05071-8_4

978-3-031-05071-8_4Final published version, 942 KBLicence: Taverne

Cite this

@inbook{90a6dfb7ee6f4227a80caa7db3d3e166,

title = "Measurement and Quantification",

abstract = "This chapter deals with the clinical task of measuring and quantifying cardiac morphology and function. The chapter opens with a clinical introduction, which outlines current clinical workflows, including how they derive and make use of biomarkers as well as their weaknesses and limitations. A technical review is provided that summarises the state-of-the-art in AI for automated measurement and quantification. This technical section describes the common deep learning models that have been proposed for measurement and quantification, and also gives some specific examples of their application. A practical tutorial is provided on a simple CMR segmentation task. The chapter closes with a clinical opinion piece that speculates on the future impact of AI in this area.",

keywords = "Biomarker, Deep learning, Measurement, Quantification, Segmentation, U-net",

author = "Olivier Bernard and Bram Ruijsink and Thomas Grenier and \{De Craene\}, Mathieu",

note = "Publisher Copyright: {\textcopyright} The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Switzerland AG 2023.",

year = "2023",

doi = "10.1007/978-3-031-05071-8\_4",

language = "English",

isbn = "9783031050701",

pages = "57--84",

editor = "N. Duchateau and A.P. King",

booktitle = "AI and Big Data in Cardiology",

publisher = "Springer International Publishing",

address = "Switzerland",

}

TY - CHAP

T1 - Measurement and Quantification

AU - Bernard, Olivier

AU - Ruijsink, Bram

AU - Grenier, Thomas

AU - De Craene, Mathieu

N1 - Publisher Copyright: © The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Switzerland AG 2023.

PY - 2023

Y1 - 2023

N2 - This chapter deals with the clinical task of measuring and quantifying cardiac morphology and function. The chapter opens with a clinical introduction, which outlines current clinical workflows, including how they derive and make use of biomarkers as well as their weaknesses and limitations. A technical review is provided that summarises the state-of-the-art in AI for automated measurement and quantification. This technical section describes the common deep learning models that have been proposed for measurement and quantification, and also gives some specific examples of their application. A practical tutorial is provided on a simple CMR segmentation task. The chapter closes with a clinical opinion piece that speculates on the future impact of AI in this area.

AB - This chapter deals with the clinical task of measuring and quantifying cardiac morphology and function. The chapter opens with a clinical introduction, which outlines current clinical workflows, including how they derive and make use of biomarkers as well as their weaknesses and limitations. A technical review is provided that summarises the state-of-the-art in AI for automated measurement and quantification. This technical section describes the common deep learning models that have been proposed for measurement and quantification, and also gives some specific examples of their application. A practical tutorial is provided on a simple CMR segmentation task. The chapter closes with a clinical opinion piece that speculates on the future impact of AI in this area.

KW - Biomarker

KW - Deep learning

KW - Measurement

KW - Quantification

KW - Segmentation

KW - U-net

UR - https://www.scopus.com/pages/publications/85173848297

U2 - 10.1007/978-3-031-05071-8_4

DO - 10.1007/978-3-031-05071-8_4

M3 - Chapter

AN - SCOPUS:85173848297

SN - 9783031050701

SP - 57

EP - 84

BT - AI and Big Data in Cardiology

A2 - Duchateau, N.

A2 - King, A.P.

PB - Springer International Publishing

ER -

Measurement and Quantification

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this