Kim, Eunjin
Lee, Geewon
Lee, Seung-hak
Cho, Hwanho
Lee, Ho Yun https://orcid.org/0000-0001-9960-5648
Park, Hyunjin
Funding for this research was provided by:
Samsung medical center (#SMX1210781)
National Research Foundation (NRF-2020M3E5D2A01084892)
Institute for Basic Science (IBS-R015-D1)
Ministry of Science and ICT (IITP-2020-2018-0-01798)
AI Graduate School Support Program (2019-0-00421)
ICT Creative Consilience program (IITP-2020-0-01821)
Artificial Intelligence Innovation Hub program (2021-0-02068)
Article History
Received: 2 December 2021
Revised: 4 April 2022
Accepted: 13 April 2022
First Online: 12 May 2022
Declarations
:
: The scientific guarantor of this publication is Ho Yun Lee.
: The authors of this manuscript declare no relationships with any companies whose products or services may be related to the subject matter of the article.
: One of the authors (HP) has significant statistical expertise.
: Written informed consent was waived by the Institutional Review Board.
: Institutional Review Board approval was obtained.
: Study subjects were part of the large cohort of a previously published article in <i>The Oncologist</i> 2018;23:806–813. In the present study, we extracted radiomics features from a 1-cm spatially extended region of interest adjacent to the tumor; thus, the peri-tumoral region was not defined in the previous study. Furthermore, the subtracted radiomics features were different from the previous study. The present study focused on the incremental benefit of the size-zone matrix features.
: retrospective prognostic study performed at one institution