Introduction to Radiomics

Marius E. Mayerhoefer; Andrzej Materka; Georg Langs; Ida Häggström; Piotr Szczypiński; Peter Gibbs; Gary Cook

doi:10.2967/jnumed.118.222893

Introduction to Radiomics

Marius E. Mayerhoefer, Andrzej Materka, Georg Langs, Ida Häggström, Piotr Szczypiński, Peter Gibbs, Gary Cook

Cancer Imaging

Research output: Contribution to journal › Article › peer-review

807 Citations (Scopus)

Abstract

Radiomics is a rapidly evolving field of research concerned with the extraction of quantitative metrics-the so-called radiomic features-within medical images. Radiomic features capture tissue and lesion characteristics such as heterogeneity and shape and may, alone or in combination with demographic, histologic, genomic, or proteomic data, be used for clinical problem solving. The goal of this continuing education article is to provide an introduction to the field, covering the basic radiomics workflow: feature calculation and selection, dimensionality reduction, and data processing. Potential clinical applications in nuclear medicine that include PET radiomics-based prediction of treatment response and survival will be discussed. Current limitations of radiomics, such as sensitivity to acquisition parameter variations, and common pitfalls will also be covered.

Original language	English
Pages (from-to)	488-495
Number of pages	8
Journal	Journal of nuclear medicine : official publication, Society of Nuclear Medicine
Volume	61
Issue number	4
DOIs	https://doi.org/10.2967/jnumed.118.222893
Publication status	Published - 1 Apr 2020

Keywords

Artificial intelligence
Machine learning
PET
Radiomics
Single-photon emission tomography

Access to Document

10.2967/jnumed.118.222893

Cite this

@article{6fe29e3da0ec47bf9206816f33025d27,

title = "Introduction to Radiomics",

abstract = "Radiomics is a rapidly evolving field of research concerned with the extraction of quantitative metrics-the so-called radiomic features-within medical images. Radiomic features capture tissue and lesion characteristics such as heterogeneity and shape and may, alone or in combination with demographic, histologic, genomic, or proteomic data, be used for clinical problem solving. The goal of this continuing education article is to provide an introduction to the field, covering the basic radiomics workflow: feature calculation and selection, dimensionality reduction, and data processing. Potential clinical applications in nuclear medicine that include PET radiomics-based prediction of treatment response and survival will be discussed. Current limitations of radiomics, such as sensitivity to acquisition parameter variations, and common pitfalls will also be covered.",

keywords = "Artificial intelligence, Machine learning, PET, Radiomics, Single-photon emission tomography",

author = "Mayerhoefer, {Marius E.} and Andrzej Materka and Georg Langs and Ida H{\"a}ggstr{\"o}m and Piotr Szczypi{\'n}ski and Peter Gibbs and Gary Cook",

year = "2020",

month = apr,

day = "1",

doi = "10.2967/jnumed.118.222893",

language = "English",

volume = "61",

pages = "488--495",

journal = "Journal of nuclear medicine : official publication, Society of Nuclear Medicine",

issn = "1535-5667",

publisher = "Society of Nuclear Medicine and Molecular Imaging",

number = "4",

}

TY - JOUR

T1 - Introduction to Radiomics

AU - Mayerhoefer, Marius E.

AU - Materka, Andrzej

AU - Langs, Georg

AU - Häggström, Ida

AU - Szczypiński, Piotr

AU - Gibbs, Peter

AU - Cook, Gary

PY - 2020/4/1

Y1 - 2020/4/1

N2 - Radiomics is a rapidly evolving field of research concerned with the extraction of quantitative metrics-the so-called radiomic features-within medical images. Radiomic features capture tissue and lesion characteristics such as heterogeneity and shape and may, alone or in combination with demographic, histologic, genomic, or proteomic data, be used for clinical problem solving. The goal of this continuing education article is to provide an introduction to the field, covering the basic radiomics workflow: feature calculation and selection, dimensionality reduction, and data processing. Potential clinical applications in nuclear medicine that include PET radiomics-based prediction of treatment response and survival will be discussed. Current limitations of radiomics, such as sensitivity to acquisition parameter variations, and common pitfalls will also be covered.

AB - Radiomics is a rapidly evolving field of research concerned with the extraction of quantitative metrics-the so-called radiomic features-within medical images. Radiomic features capture tissue and lesion characteristics such as heterogeneity and shape and may, alone or in combination with demographic, histologic, genomic, or proteomic data, be used for clinical problem solving. The goal of this continuing education article is to provide an introduction to the field, covering the basic radiomics workflow: feature calculation and selection, dimensionality reduction, and data processing. Potential clinical applications in nuclear medicine that include PET radiomics-based prediction of treatment response and survival will be discussed. Current limitations of radiomics, such as sensitivity to acquisition parameter variations, and common pitfalls will also be covered.

KW - Artificial intelligence

KW - Machine learning

KW - PET

KW - Radiomics

KW - Single-photon emission tomography

UR - http://www.scopus.com/inward/record.url?scp=85082979497&partnerID=8YFLogxK

U2 - 10.2967/jnumed.118.222893

DO - 10.2967/jnumed.118.222893

M3 - Article

C2 - 32060219

SN - 1535-5667

VL - 61

SP - 488

EP - 495

JO - Journal of nuclear medicine : official publication, Society of Nuclear Medicine

JF - Journal of nuclear medicine : official publication, Society of Nuclear Medicine

IS - 4

ER -

Introduction to Radiomics

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this