RE: The Rise of Radiomics and Implications for Oncologic Management

RE: The Rise of Radiomics and Implications for Oncologic Management Radiomics is the high-throughput extraction of large amounts of image features from radiographic images, as previously defined in 2012 by Lambin and colleagues in the first publication in the field (1). In the July 2017 issue of Journal (2), Verma and colleagues highlighted the rise of radiomics, which may provide new insights into precision medicine in the next decades. Although the general process of radiomics has been well described (3), a major pitfall should be addressed before these methods can be used to personalize treatments: the lack of standardized procedures for radiomics features extraction (2,3). Lambin et al. recently proposed the radiomics quality score (RQS), assessing the quality of radiomics studies (4), to better address this issue of standardization between institutions (2), but the actual extraction methodologies currently available are clearly inconsistent (5). Scientometric analysis of publications can provide an objective overview of knowledge base and network features in this field of research that may be informative for researchers (6). Therefore, using the SCOPUS database, we performed a scientometric analysis of research on radiomics. On December 7, 2017, we searched in article titles, abstracts, and key words for all documents containing the terms “radiomic” or “radiomics.” A total of 391 research items were retrieved from the SCOPUS database, and errata were excluded. The first articles on radiomics were published by Lambin and colleagues in 2012. Since then, the dramatic increase in the number of published research items (Figure 1A) highlights the urgent need to better standardize radiomics methods. The identification of the scientific networks contributing to the research in the field could be used for that purpose. Therefore, the bibliometric data set exported from SCOPUS was cleaned using OpenRefine software (www.openrefine.org) to identify contributing countries for each published item. Interestingly, although the first article on radiomics was published only five years ago, many countries (n = 35) have already contributed to research in the field, and 95 (24%) published items involved international collaborations. Figure 1. View largeDownload slide International scientific collaborations in radiomics research. A) Number of published items and international collaborations over past years since the first publication on radiomics in 2012. B-C) International scientific network worldwide (B) and in Europe (C). The international scientific network was built using Table2Net and then exported to the Gephi software where the “Map of countries” and “geolayout” were used to visualize the network. The network includes nodes (countries) as well as edges (connection of two countries in a collaborative work). Node size is defined by degree, corresponding to the quantity of direct neighbors of a country in the network. Colour figure online: Node color (from light orange to dark purple) is defined by betweenness centrality, corresponding to the measure of how often a country lies on the shortest path between other countries in the network. Blue and red colored lines connect two countries which collaborated once and more than twice respectively. Figure 1. View largeDownload slide International scientific collaborations in radiomics research. A) Number of published items and international collaborations over past years since the first publication on radiomics in 2012. B-C) International scientific network worldwide (B) and in Europe (C). The international scientific network was built using Table2Net and then exported to the Gephi software where the “Map of countries” and “geolayout” were used to visualize the network. The network includes nodes (countries) as well as edges (connection of two countries in a collaborative work). Node size is defined by degree, corresponding to the quantity of direct neighbors of a country in the network. Colour figure online: Node color (from light orange to dark purple) is defined by betweenness centrality, corresponding to the measure of how often a country lies on the shortest path between other countries in the network. Blue and red colored lines connect two countries which collaborated once and more than twice respectively. We then built and analyzed the scientific worldwide networks including all countries contributing to research in this field. To this end, the cleaned bibliometric data set extracted from the SCOPUS database was imported to Table2Net (http://tools.medialab.sciences-po.fr/table2net/), and the network was visualized using Gephi software (Figure 1, B and C). The scientific network worldwide shows the already close-knit network of relations between the United States and other countries worldwide (Figure 1B). The United States, Germany, and the Netherlands are the leading collaborating countries in terms of betweenness centrality, a measure of how often a country lies on the shortest path between nodes in the network. However, we observed slightly fewer connections between European countries (Figure 1C). This should be improved to enhance the quality of studies performed in Europe. The development of international scientific networks, including groups in North and South America, Europe, and Asia, is critical to promote radiomic-driven precision medicine. Following the success of The Cancer Genome Atlas and the International Cancer Genomics Consortium (7), a large effort based on this international scientific network needs to be engaged worldwide. Notes Affiliations of authors: INSERM 1052, CNRS 5286, Centre de Recherche en Cancérologie de Lyon, Centre Léon Bérard, Univ Lyon, Université Claude Bernard Lyon 1, Lyon, France (JPF); Department of Radiation Oncology, Paris Descartes University, Hôpital Européen Georges Pompidou, Paris, France (JPF, CD, PG, JEB); Centre de Recherche des Cordeliers, Team 22: Information Sciences for Personalized Medicine, INSERM, UMRS1138, Paris, France (JEB). The authors have no conflicts of interest to disclose. References 1 Lambin P , Rios-Velazquez E , Leijenaar R et al. , Radiomics: Extracting more information from medical images using advanced feature analysis . Eur J Cancer. 2012 ; 48 ( 4 ): 441 – 446 . Google Scholar CrossRef Search ADS PubMed 2 Verma V , Simone CB 2nd , Krishnan S et al. , The rise of radiomics and implications for oncologic management . J Natl Cancer Inst. 2017 ; 109 ( 7 ):djx055. 3 Limkin EJ , Sun R , Dercle L et al. , Promises and challenges for the implementation of computational medical imaging (radiomics) in oncology . Ann Oncol. 2017 ; 28 ( 6 ): 1191 – 1206 . Google Scholar CrossRef Search ADS PubMed 4 Lambin P , Leijenaar RTH , Deist TM et al. , Radiomics: The bridge between medical imaging and personalized medicine . Nat Rev Clin Oncol. 2017 ; 14 ( 12 ): 749 – 762 . Google Scholar CrossRef Search ADS PubMed 5 Gan J , Wang J , Zhong H et al. , MO-DE-207B-09: A consistent test for radiomics softwares . Med Phys. 2016 ; 43 ( 6 part 30 ): 3706 – 3706 . Google Scholar CrossRef Search ADS 6 Vezyridis P , Timmons S. Evolution of primary care databases in UK: A scientometric analysis of research output . BMJ Open. 2016 ; 6 ( 10 ): e012785 . Google Scholar CrossRef Search ADS PubMed 7 International Cancer Genome Consortium , Hudson TJ , Anderson W et al. , International network of cancer genome projects . Nature. 2010 ; 464 ( 7291 ): 993 – 998 . Google Scholar CrossRef Search ADS PubMed © The Author(s) 2018. Published by Oxford University Press. All rights reserved. For permissions, please email: journals.permissions@oup.com This article is published and distributed under the terms of the Oxford University Press, Standard Journals Publication Model (https://academic.oup.com/journals/pages/about_us/legal/notices) http://www.deepdyve.com/assets/images/DeepDyve-Logo-lg.png JNCI: Journal of the National Cancer Institute Oxford University Press

RE: The Rise of Radiomics and Implications for Oncologic Management

Loading next page...
 
/lp/ou_press/re-the-rise-of-radiomics-and-implications-for-oncologic-management-0I9J3L8RN3
Publisher
Oxford University Press
Copyright
© The Author(s) 2018. Published by Oxford University Press. All rights reserved. For permissions, please email: journals.permissions@oup.com
ISSN
0027-8874
eISSN
1460-2105
D.O.I.
10.1093/jnci/djy037
Publisher site
See Article on Publisher Site

Abstract

Radiomics is the high-throughput extraction of large amounts of image features from radiographic images, as previously defined in 2012 by Lambin and colleagues in the first publication in the field (1). In the July 2017 issue of Journal (2), Verma and colleagues highlighted the rise of radiomics, which may provide new insights into precision medicine in the next decades. Although the general process of radiomics has been well described (3), a major pitfall should be addressed before these methods can be used to personalize treatments: the lack of standardized procedures for radiomics features extraction (2,3). Lambin et al. recently proposed the radiomics quality score (RQS), assessing the quality of radiomics studies (4), to better address this issue of standardization between institutions (2), but the actual extraction methodologies currently available are clearly inconsistent (5). Scientometric analysis of publications can provide an objective overview of knowledge base and network features in this field of research that may be informative for researchers (6). Therefore, using the SCOPUS database, we performed a scientometric analysis of research on radiomics. On December 7, 2017, we searched in article titles, abstracts, and key words for all documents containing the terms “radiomic” or “radiomics.” A total of 391 research items were retrieved from the SCOPUS database, and errata were excluded. The first articles on radiomics were published by Lambin and colleagues in 2012. Since then, the dramatic increase in the number of published research items (Figure 1A) highlights the urgent need to better standardize radiomics methods. The identification of the scientific networks contributing to the research in the field could be used for that purpose. Therefore, the bibliometric data set exported from SCOPUS was cleaned using OpenRefine software (www.openrefine.org) to identify contributing countries for each published item. Interestingly, although the first article on radiomics was published only five years ago, many countries (n = 35) have already contributed to research in the field, and 95 (24%) published items involved international collaborations. Figure 1. View largeDownload slide International scientific collaborations in radiomics research. A) Number of published items and international collaborations over past years since the first publication on radiomics in 2012. B-C) International scientific network worldwide (B) and in Europe (C). The international scientific network was built using Table2Net and then exported to the Gephi software where the “Map of countries” and “geolayout” were used to visualize the network. The network includes nodes (countries) as well as edges (connection of two countries in a collaborative work). Node size is defined by degree, corresponding to the quantity of direct neighbors of a country in the network. Colour figure online: Node color (from light orange to dark purple) is defined by betweenness centrality, corresponding to the measure of how often a country lies on the shortest path between other countries in the network. Blue and red colored lines connect two countries which collaborated once and more than twice respectively. Figure 1. View largeDownload slide International scientific collaborations in radiomics research. A) Number of published items and international collaborations over past years since the first publication on radiomics in 2012. B-C) International scientific network worldwide (B) and in Europe (C). The international scientific network was built using Table2Net and then exported to the Gephi software where the “Map of countries” and “geolayout” were used to visualize the network. The network includes nodes (countries) as well as edges (connection of two countries in a collaborative work). Node size is defined by degree, corresponding to the quantity of direct neighbors of a country in the network. Colour figure online: Node color (from light orange to dark purple) is defined by betweenness centrality, corresponding to the measure of how often a country lies on the shortest path between other countries in the network. Blue and red colored lines connect two countries which collaborated once and more than twice respectively. We then built and analyzed the scientific worldwide networks including all countries contributing to research in this field. To this end, the cleaned bibliometric data set extracted from the SCOPUS database was imported to Table2Net (http://tools.medialab.sciences-po.fr/table2net/), and the network was visualized using Gephi software (Figure 1, B and C). The scientific network worldwide shows the already close-knit network of relations between the United States and other countries worldwide (Figure 1B). The United States, Germany, and the Netherlands are the leading collaborating countries in terms of betweenness centrality, a measure of how often a country lies on the shortest path between nodes in the network. However, we observed slightly fewer connections between European countries (Figure 1C). This should be improved to enhance the quality of studies performed in Europe. The development of international scientific networks, including groups in North and South America, Europe, and Asia, is critical to promote radiomic-driven precision medicine. Following the success of The Cancer Genome Atlas and the International Cancer Genomics Consortium (7), a large effort based on this international scientific network needs to be engaged worldwide. Notes Affiliations of authors: INSERM 1052, CNRS 5286, Centre de Recherche en Cancérologie de Lyon, Centre Léon Bérard, Univ Lyon, Université Claude Bernard Lyon 1, Lyon, France (JPF); Department of Radiation Oncology, Paris Descartes University, Hôpital Européen Georges Pompidou, Paris, France (JPF, CD, PG, JEB); Centre de Recherche des Cordeliers, Team 22: Information Sciences for Personalized Medicine, INSERM, UMRS1138, Paris, France (JEB). The authors have no conflicts of interest to disclose. References 1 Lambin P , Rios-Velazquez E , Leijenaar R et al. , Radiomics: Extracting more information from medical images using advanced feature analysis . Eur J Cancer. 2012 ; 48 ( 4 ): 441 – 446 . Google Scholar CrossRef Search ADS PubMed 2 Verma V , Simone CB 2nd , Krishnan S et al. , The rise of radiomics and implications for oncologic management . J Natl Cancer Inst. 2017 ; 109 ( 7 ):djx055. 3 Limkin EJ , Sun R , Dercle L et al. , Promises and challenges for the implementation of computational medical imaging (radiomics) in oncology . Ann Oncol. 2017 ; 28 ( 6 ): 1191 – 1206 . Google Scholar CrossRef Search ADS PubMed 4 Lambin P , Leijenaar RTH , Deist TM et al. , Radiomics: The bridge between medical imaging and personalized medicine . Nat Rev Clin Oncol. 2017 ; 14 ( 12 ): 749 – 762 . Google Scholar CrossRef Search ADS PubMed 5 Gan J , Wang J , Zhong H et al. , MO-DE-207B-09: A consistent test for radiomics softwares . Med Phys. 2016 ; 43 ( 6 part 30 ): 3706 – 3706 . Google Scholar CrossRef Search ADS 6 Vezyridis P , Timmons S. Evolution of primary care databases in UK: A scientometric analysis of research output . BMJ Open. 2016 ; 6 ( 10 ): e012785 . Google Scholar CrossRef Search ADS PubMed 7 International Cancer Genome Consortium , Hudson TJ , Anderson W et al. , International network of cancer genome projects . Nature. 2010 ; 464 ( 7291 ): 993 – 998 . Google Scholar CrossRef Search ADS PubMed © The Author(s) 2018. Published by Oxford University Press. All rights reserved. For permissions, please email: journals.permissions@oup.com This article is published and distributed under the terms of the Oxford University Press, Standard Journals Publication Model (https://academic.oup.com/journals/pages/about_us/legal/notices)

Journal

JNCI: Journal of the National Cancer InstituteOxford University Press

Published: Mar 12, 2018

There are no references for this article.

You’re reading a free preview. Subscribe to read the entire article.


DeepDyve is your
personal research library

It’s your single place to instantly
discover and read the research
that matters to you.

Enjoy affordable access to
over 18 million articles from more than
15,000 peer-reviewed journals.

All for just $49/month

Explore the DeepDyve Library

Search

Query the DeepDyve database, plus search all of PubMed and Google Scholar seamlessly

Organize

Save any article or search result from DeepDyve, PubMed, and Google Scholar... all in one place.

Access

Get unlimited, online access to over 18 million full-text articles from more than 15,000 scientific journals.

Your journals are on DeepDyve

Read from thousands of the leading scholarly journals from SpringerNature, Elsevier, Wiley-Blackwell, Oxford University Press and more.

All the latest content is available, no embargo periods.

See the journals in your area

DeepDyve

Freelancer

DeepDyve

Pro

Price

FREE

$49/month
$360/year

Save searches from
Google Scholar,
PubMed

Create lists to
organize your research

Export lists, citations

Read DeepDyve articles

Abstract access only

Unlimited access to over
18 million full-text articles

Print

20 pages / month

PDF Discount

20% off