Distributed radiomics as a signature validation study using the Personal Health Train infrastructure

Zhenwei Shi, Ivan Ivan Zhovannik, Alberto Traverso, Frank Dankers, Timo Deist, Petros Kalendralis, Rene Monshouwer, Johan Bussink, Rianne Fijten, Hugo Aerts, Andre Dekker, Leonard Wee

Research output: Contribution to journalArticleAcademicpeer-review

29 Downloads (Pure)

Abstract

Prediction modelling with radiomics is a rapidly developing research topic that requires access to vast amounts of imaging data. Methods that work on decentralized data are urgently needed, because of concerns about patient privacy. Previously published computed tomography medical image sets with gross tumour volume (GTV) outlines for non-small cell lung cancer have been updated with extended follow-up. In a previous study, these were referred to as Lung1 (n = 421) and Lung2 (n = 221). The Lung1 dataset is made publicly accessible via The Cancer Imaging Archive (TCIA; https://www.cancerimagingarchive.net). We performed a decentralized multi-centre study to develop a radiomic signature (hereafter “ZS2019”) in one institution and validated the performance in an independent institution, without the need for data exchange and compared this to an analysis where all data was centralized. The performance of ZS2019 for 2-year overall survival validated in distributed radiomics was not statistically different from the centralized validation (AUC 0.61 vs 0.61; p = 0.52). Although slightly different in terms of data and methods, no statistically significant difference in performance was observed between the new signature and previous work (c-index 0.58 vs 0.65; p = 0.37). Our objective was not the development of a new signature with the best performance, but to suggest an approach for distributed radiomics. Therefore, we used a similar method as an earlier study. We foresee that the Lung1 dataset can be further re-used for testing radiomic models and investigating feature reproducibility.
Original languageEnglish
Article number218
Number of pages8
JournalScientific data
Volume6
DOIs
Publication statusPublished - 22 Oct 2019

Keywords

  • LEVEL DATA
  • MODEL
  • INFORMATION
  • FEATURES
  • IMAGES
  • WEB
  • PET

Cite this

@article{ac0759b3bbaa43ad886c66fa4cdca67a,
title = "Distributed radiomics as a signature validation study using the Personal Health Train infrastructure",
abstract = "Prediction modelling with radiomics is a rapidly developing research topic that requires access to vast amounts of imaging data. Methods that work on decentralized data are urgently needed, because of concerns about patient privacy. Previously published computed tomography medical image sets with gross tumour volume (GTV) outlines for non-small cell lung cancer have been updated with extended follow-up. In a previous study, these were referred to as Lung1 (n = 421) and Lung2 (n = 221). The Lung1 dataset is made publicly accessible via The Cancer Imaging Archive (TCIA; https://www.cancerimagingarchive.net). We performed a decentralized multi-centre study to develop a radiomic signature (hereafter “ZS2019”) in one institution and validated the performance in an independent institution, without the need for data exchange and compared this to an analysis where all data was centralized. The performance of ZS2019 for 2-year overall survival validated in distributed radiomics was not statistically different from the centralized validation (AUC 0.61 vs 0.61; p = 0.52). Although slightly different in terms of data and methods, no statistically significant difference in performance was observed between the new signature and previous work (c-index 0.58 vs 0.65; p = 0.37). Our objective was not the development of a new signature with the best performance, but to suggest an approach for distributed radiomics. Therefore, we used a similar method as an earlier study. We foresee that the Lung1 dataset can be further re-used for testing radiomic models and investigating feature reproducibility.",
keywords = "LEVEL DATA, MODEL, INFORMATION, FEATURES, IMAGES, WEB, PET",
author = "Zhenwei Shi and {Ivan Zhovannik}, Ivan and Alberto Traverso and Frank Dankers and Timo Deist and Petros Kalendralis and Rene Monshouwer and Johan Bussink and Rianne Fijten and Hugo Aerts and Andre Dekker and Leonard Wee",
year = "2019",
month = "10",
day = "22",
doi = "https://doi.org/10.1038/s41597-019-0241-0",
language = "English",
volume = "6",
journal = "Scientific data",
issn = "2052-4463",
publisher = "Nature Publishing Group",

}

Distributed radiomics as a signature validation study using the Personal Health Train infrastructure. / Shi, Zhenwei; Ivan Zhovannik, Ivan; Traverso, Alberto; Dankers, Frank; Deist, Timo; Kalendralis, Petros; Monshouwer, Rene; Bussink, Johan; Fijten, Rianne; Aerts, Hugo; Dekker, Andre; Wee, Leonard.

In: Scientific data, Vol. 6, 218, 22.10.2019.

Research output: Contribution to journalArticleAcademicpeer-review

TY - JOUR

T1 - Distributed radiomics as a signature validation study using the Personal Health Train infrastructure

AU - Shi, Zhenwei

AU - Ivan Zhovannik, Ivan

AU - Traverso, Alberto

AU - Dankers, Frank

AU - Deist, Timo

AU - Kalendralis, Petros

AU - Monshouwer, Rene

AU - Bussink, Johan

AU - Fijten, Rianne

AU - Aerts, Hugo

AU - Dekker, Andre

AU - Wee, Leonard

PY - 2019/10/22

Y1 - 2019/10/22

N2 - Prediction modelling with radiomics is a rapidly developing research topic that requires access to vast amounts of imaging data. Methods that work on decentralized data are urgently needed, because of concerns about patient privacy. Previously published computed tomography medical image sets with gross tumour volume (GTV) outlines for non-small cell lung cancer have been updated with extended follow-up. In a previous study, these were referred to as Lung1 (n = 421) and Lung2 (n = 221). The Lung1 dataset is made publicly accessible via The Cancer Imaging Archive (TCIA; https://www.cancerimagingarchive.net). We performed a decentralized multi-centre study to develop a radiomic signature (hereafter “ZS2019”) in one institution and validated the performance in an independent institution, without the need for data exchange and compared this to an analysis where all data was centralized. The performance of ZS2019 for 2-year overall survival validated in distributed radiomics was not statistically different from the centralized validation (AUC 0.61 vs 0.61; p = 0.52). Although slightly different in terms of data and methods, no statistically significant difference in performance was observed between the new signature and previous work (c-index 0.58 vs 0.65; p = 0.37). Our objective was not the development of a new signature with the best performance, but to suggest an approach for distributed radiomics. Therefore, we used a similar method as an earlier study. We foresee that the Lung1 dataset can be further re-used for testing radiomic models and investigating feature reproducibility.

AB - Prediction modelling with radiomics is a rapidly developing research topic that requires access to vast amounts of imaging data. Methods that work on decentralized data are urgently needed, because of concerns about patient privacy. Previously published computed tomography medical image sets with gross tumour volume (GTV) outlines for non-small cell lung cancer have been updated with extended follow-up. In a previous study, these were referred to as Lung1 (n = 421) and Lung2 (n = 221). The Lung1 dataset is made publicly accessible via The Cancer Imaging Archive (TCIA; https://www.cancerimagingarchive.net). We performed a decentralized multi-centre study to develop a radiomic signature (hereafter “ZS2019”) in one institution and validated the performance in an independent institution, without the need for data exchange and compared this to an analysis where all data was centralized. The performance of ZS2019 for 2-year overall survival validated in distributed radiomics was not statistically different from the centralized validation (AUC 0.61 vs 0.61; p = 0.52). Although slightly different in terms of data and methods, no statistically significant difference in performance was observed between the new signature and previous work (c-index 0.58 vs 0.65; p = 0.37). Our objective was not the development of a new signature with the best performance, but to suggest an approach for distributed radiomics. Therefore, we used a similar method as an earlier study. We foresee that the Lung1 dataset can be further re-used for testing radiomic models and investigating feature reproducibility.

KW - LEVEL DATA

KW - MODEL

KW - INFORMATION

KW - FEATURES

KW - IMAGES

KW - WEB

KW - PET

U2 - https://doi.org/10.1038/s41597-019-0241-0

DO - https://doi.org/10.1038/s41597-019-0241-0

M3 - Article

VL - 6

JO - Scientific data

JF - Scientific data

SN - 2052-4463

M1 - 218

ER -