Radiomic combination of spatial and temporal features extracted from DCE-MRI for prostate cancer detection

Catarina Dinis Fernandes; Massimo Mischi; Hessel Wijkstra; Jelle O. Barentsz; Stijn W.T.P.J. Heijmink; Simona Turco

doi:10.1109/EMBC46164.2021.9630015

Radiomic combination of spatial and temporal features extracted from DCE-MRI for prostate cancer detection

Catarina Dinis Fernandes
, Massimo Mischi
, Hessel Wijkstra
, Jelle O. Barentsz
, Stijn W.T.P.J. Heijmink
, Simona Turco

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

2 Citations (Scopus)

Abstract

Multi-parametric MRI is part of the standard prostate cancer (PCa) diagnostic protocol. Recent imaging guidelines (PI-RADS v2) downgraded the value of Dynamic Contrast-Enhanced (DCE)-MRI in the diagnosis of PCa. A purely qualitative analysis of the DCE-MRI time series, as it is generally done by radiologists, might indeed overlook information on the microvascular architecture and function. In this study, we investigate the discriminative power of quantitative imaging features derived from texture and pharmacokinetic analysis of DCE-MRI. In 605 regions of interest (benign and malignant tissue) delineated in 80 patients, we found through independent cross-validation that a subset of quantitative spatial and temporal features extracted from DCE-MRI and incorporated in machine learning classifiers obtains a good diagnostic performance (AUC = 0.80-0.86) in distinguishing malignant from benign regions.Clinical Relevance- These findings highlight the underlying potential of quantitative DCE-derived radiomic features in identifying PCa by MRI.

Original language	English
Title of host publication	2021 43rd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC)
Publisher	Institute of Electrical and Electronics Engineers
Pages	3153-3156
Number of pages	4
ISBN (Electronic)	978-1-7281-1179-7
DOIs	https://doi.org/10.1109/EMBC46164.2021.9630015
Publication status	Published - 9 Dec 2021
Event	43rd Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2021 - Virtual, Mexico Duration: 1 Nov 2021 → 5 Nov 2021 Conference number: 43 https://embc.embs.org/2021/

Conference

Conference	43rd Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2021
Abbreviated title	EMBC 2021
Country/Territory	Mexico
Period	1/11/21 → 5/11/21
Internet address	https://embc.embs.org/2021/

Funding

Research supported by grant 030-203 from the Prostate Cancer Molecular Medicine project, Center for Translational Molecular Medicine.

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 3 Good Health and Well-being

Access to Document

10.1109/EMBC46164.2021.9630015

Cite this

Dinis Fernandes, C., Mischi, M., Wijkstra, H., Barentsz, J. O., Heijmink, S. W. T. P. J., & Turco, S. (2021). Radiomic combination of spatial and temporal features extracted from DCE-MRI for prostate cancer detection. In 2021 43rd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC) (pp. 3153-3156). Article 9630015 Institute of Electrical and Electronics Engineers. https://doi.org/10.1109/EMBC46164.2021.9630015

@inproceedings{db0860bb704c4f599c856de19210452e,

title = "Radiomic combination of spatial and temporal features extracted from DCE-MRI for prostate cancer detection",

abstract = "Multi-parametric MRI is part of the standard prostate cancer (PCa) diagnostic protocol. Recent imaging guidelines (PI-RADS v2) downgraded the value of Dynamic Contrast-Enhanced (DCE)-MRI in the diagnosis of PCa. A purely qualitative analysis of the DCE-MRI time series, as it is generally done by radiologists, might indeed overlook information on the microvascular architecture and function. In this study, we investigate the discriminative power of quantitative imaging features derived from texture and pharmacokinetic analysis of DCE-MRI. In 605 regions of interest (benign and malignant tissue) delineated in 80 patients, we found through independent cross-validation that a subset of quantitative spatial and temporal features extracted from DCE-MRI and incorporated in machine learning classifiers obtains a good diagnostic performance (AUC = 0.80-0.86) in distinguishing malignant from benign regions.Clinical Relevance- These findings highlight the underlying potential of quantitative DCE-derived radiomic features in identifying PCa by MRI.",

author = "\{Dinis Fernandes\}, Catarina and Massimo Mischi and Hessel Wijkstra and Barentsz, \{Jelle O.\} and Heijmink, \{Stijn W.T.P.J.\} and Simona Turco",

year = "2021",

month = dec,

day = "9",

doi = "10.1109/EMBC46164.2021.9630015",

language = "English",

pages = "3153--3156",

booktitle = "2021 43rd Annual International Conference of the IEEE Engineering in Medicine \& Biology Society (EMBC)",

publisher = "Institute of Electrical and Electronics Engineers",

address = "United States",

note = "43rd Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2021<br/>, EMBC 2021 ; Conference date: 01-11-2021 Through 05-11-2021",

url = "https://embc.embs.org/2021/",

}

Dinis Fernandes, C , Mischi, M , Wijkstra, H, Barentsz, JO, Heijmink, SWTPJ & Turco, S 2021, Radiomic combination of spatial and temporal features extracted from DCE-MRI for prostate cancer detection. in 2021 43rd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC)., 9630015, Institute of Electrical and Electronics Engineers, pp. 3153-3156, 43rd Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2021
, Mexico, 1/11/21. https://doi.org/10.1109/EMBC46164.2021.9630015

Radiomic combination of spatial and temporal features extracted from DCE-MRI for prostate cancer detection. / Dinis Fernandes, Catarina ; Mischi, Massimo ; Wijkstra, Hessel et al.
2021 43rd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC). Institute of Electrical and Electronics Engineers, 2021. p. 3153-3156 9630015.

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

TY - GEN

T1 - Radiomic combination of spatial and temporal features extracted from DCE-MRI for prostate cancer detection

AU - Dinis Fernandes, Catarina

AU - Mischi, Massimo

AU - Wijkstra, Hessel

AU - Barentsz, Jelle O.

AU - Heijmink, Stijn W.T.P.J.

AU - Turco, Simona

N1 - Conference code: 43

PY - 2021/12/9

Y1 - 2021/12/9

N2 - Multi-parametric MRI is part of the standard prostate cancer (PCa) diagnostic protocol. Recent imaging guidelines (PI-RADS v2) downgraded the value of Dynamic Contrast-Enhanced (DCE)-MRI in the diagnosis of PCa. A purely qualitative analysis of the DCE-MRI time series, as it is generally done by radiologists, might indeed overlook information on the microvascular architecture and function. In this study, we investigate the discriminative power of quantitative imaging features derived from texture and pharmacokinetic analysis of DCE-MRI. In 605 regions of interest (benign and malignant tissue) delineated in 80 patients, we found through independent cross-validation that a subset of quantitative spatial and temporal features extracted from DCE-MRI and incorporated in machine learning classifiers obtains a good diagnostic performance (AUC = 0.80-0.86) in distinguishing malignant from benign regions.Clinical Relevance- These findings highlight the underlying potential of quantitative DCE-derived radiomic features in identifying PCa by MRI.

AB - Multi-parametric MRI is part of the standard prostate cancer (PCa) diagnostic protocol. Recent imaging guidelines (PI-RADS v2) downgraded the value of Dynamic Contrast-Enhanced (DCE)-MRI in the diagnosis of PCa. A purely qualitative analysis of the DCE-MRI time series, as it is generally done by radiologists, might indeed overlook information on the microvascular architecture and function. In this study, we investigate the discriminative power of quantitative imaging features derived from texture and pharmacokinetic analysis of DCE-MRI. In 605 regions of interest (benign and malignant tissue) delineated in 80 patients, we found through independent cross-validation that a subset of quantitative spatial and temporal features extracted from DCE-MRI and incorporated in machine learning classifiers obtains a good diagnostic performance (AUC = 0.80-0.86) in distinguishing malignant from benign regions.Clinical Relevance- These findings highlight the underlying potential of quantitative DCE-derived radiomic features in identifying PCa by MRI.

UR - https://www.scopus.com/pages/publications/85122550342

U2 - 10.1109/EMBC46164.2021.9630015

DO - 10.1109/EMBC46164.2021.9630015

M3 - Conference contribution

C2 - 34891910

SP - 3153

EP - 3156

BT - 2021 43rd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC)

PB - Institute of Electrical and Electronics Engineers

T2 - 43rd Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2021<br/>

Y2 - 1 November 2021 through 5 November 2021

ER -

Dinis Fernandes C , Mischi M , Wijkstra H, Barentsz JO, Heijmink SWTPJ, Turco S. Radiomic combination of spatial and temporal features extracted from DCE-MRI for prostate cancer detection. In 2021 43rd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC). Institute of Electrical and Electronics Engineers. 2021. p. 3153-3156. 9630015 doi: 10.1109/EMBC46164.2021.9630015

Radiomic combination of spatial and temporal features extracted from DCE-MRI for prostate cancer detection

Abstract

Conference

Funding

UN SDGs

Access to Document

Other files and links

Fingerprint

Cite this