Clinically Interpretable Radiomics-Based Prediction of Histopathologic Response to Neoadjuvant Chemotherapy in High-Grade Serous Ovarian Carcinoma.
chemotherapy response score
computed tomography
neoadjuvant chemotherapy
ovarian cancer
radiomics
Journal
Frontiers in oncology
ISSN: 2234-943X
Titre abrégé: Front Oncol
Pays: Switzerland
ID NLM: 101568867
Informations de publication
Date de publication:
2022
2022
Historique:
received:
02
02
2022
accepted:
02
05
2022
entrez:
5
7
2022
pubmed:
6
7
2022
medline:
6
7
2022
Statut:
epublish
Résumé
Pathological response to neoadjuvant treatment for patients with high-grade serous ovarian carcinoma (HGSOC) is assessed using the chemotherapy response score (CRS) for omental tumor deposits. The main limitation of CRS is that it requires surgical sampling after initial neoadjuvant chemotherapy (NACT) treatment. Earlier and non-invasive response predictors could improve patient stratification. We developed computed tomography (CT) radiomic measures to predict neoadjuvant response before NACT using CRS as a gold standard. Omental CT-based radiomics models, yielding a simplified fully interpretable radiomic signature, were developed using Elastic Net logistic regression and compared to predictions based on omental tumor volume alone. Models were developed on a single institution cohort of neoadjuvant-treated HGSOC ( The performance of the comprehensive radiomics models and the fully interpretable radiomics model was significantly higher than volume-based predictions of response in both the discovery and external test sets when assessed using G-mean (geometric mean of sensitivity and specificity) and NPV, indicating high generalizability and reliability in identifying non-responders when using radiomics. The performance of a fully interpretable model was similar to that of comprehensive radiomics models. CT-based radiomics allows for predicting response to NACT in a timely manner and without the need for abdominal surgery. Adding pre-NACT radiomics to volumetry improved model performance for predictions of response to NACT in HGSOC and was robust to external testing. A radiomic signature based on five robust predictive features provides improved clinical interpretability and may thus facilitate clinical acceptance and application.
Sections du résumé
Background
UNASSIGNED
Pathological response to neoadjuvant treatment for patients with high-grade serous ovarian carcinoma (HGSOC) is assessed using the chemotherapy response score (CRS) for omental tumor deposits. The main limitation of CRS is that it requires surgical sampling after initial neoadjuvant chemotherapy (NACT) treatment. Earlier and non-invasive response predictors could improve patient stratification. We developed computed tomography (CT) radiomic measures to predict neoadjuvant response before NACT using CRS as a gold standard.
Methods
UNASSIGNED
Omental CT-based radiomics models, yielding a simplified fully interpretable radiomic signature, were developed using Elastic Net logistic regression and compared to predictions based on omental tumor volume alone. Models were developed on a single institution cohort of neoadjuvant-treated HGSOC (
Results
UNASSIGNED
The performance of the comprehensive radiomics models and the fully interpretable radiomics model was significantly higher than volume-based predictions of response in both the discovery and external test sets when assessed using G-mean (geometric mean of sensitivity and specificity) and NPV, indicating high generalizability and reliability in identifying non-responders when using radiomics. The performance of a fully interpretable model was similar to that of comprehensive radiomics models.
Conclusions
UNASSIGNED
CT-based radiomics allows for predicting response to NACT in a timely manner and without the need for abdominal surgery. Adding pre-NACT radiomics to volumetry improved model performance for predictions of response to NACT in HGSOC and was robust to external testing. A radiomic signature based on five robust predictive features provides improved clinical interpretability and may thus facilitate clinical acceptance and application.
Identifiants
pubmed: 35785153
doi: 10.3389/fonc.2022.868265
pmc: PMC9243357
doi:
Types de publication
Journal Article
Langues
eng
Pagination
868265Informations de copyright
Copyright © 2022 Rundo, Beer, Escudero Sanchez, Crispin-Ortuzar, Reinius, McCague, Sahin, Bura, Pintican, Zerunian, Ursprung, Allajbeu, Addley, Martin-Gonzalez, Buddenkotte, Singh, Sahdev, Funingana, Jimenez-Linan, Markowetz, Brenton, Sala and Woitek.
Déclaration de conflit d'intérêts
JB is a shareholder of Tailor Bio Ltd, Rutland, United Kingdom; receives honoraria from GlaxoSmithKline, London, United Kingdom and AstraZeneca, Cambridge, United Kingdom; receives research funding from Aprea Therapeutics AB, Massachusetts, United States; and holds patents for methods for predicting treatment response in cancers. ES receives honoraria from GlaxoSmithKline, London, United Kingdom and GE Healthcare, Illinois, United States, and is co-founder and shareholder of Lucida Medical Ltd, Cambridge, United Kingdom. The remaining authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest.
Références
Ann Oncol. 2019 May 1;30(5):672-705
pubmed: 31046081
AJNR Am J Neuroradiol. 2015 Dec;36(12):2214-8
pubmed: 26359147
Radiology. 2016 Feb;278(2):563-77
pubmed: 26579733
N Engl J Med. 2010 Sep 2;363(10):943-53
pubmed: 20818904
JAMA Netw Open. 2020 Sep 1;3(9):e2017517
pubmed: 32975569
Commun Biol. 2020 Sep 22;3(1):524
pubmed: 32963283
Eur Radiol. 2021 Oct;31(10):7855-7864
pubmed: 33864139
Lancet Oncol. 2021 Feb;22(2):277-288
pubmed: 33357510
Nat Genet. 2018 Sep;50(9):1262-1270
pubmed: 30104763
Nat Commun. 2019 Feb 15;10(1):764
pubmed: 30770825
Cancer Res. 2017 Nov 1;77(21):e104-e107
pubmed: 29092951
Int J Gynecol Pathol. 2017 Mar;36(2):172-179
pubmed: 27362902
Front Oncol. 2021 Apr 13;11:638124
pubmed: 33928029
J Clin Oncol. 2015 Aug 1;33(22):2457-63
pubmed: 26124480
Lancet. 2015 Jul 18;386(9990):249-57
pubmed: 26002111
Eur J Cancer. 2009 Jan;45(2):228-47
pubmed: 19097774
Cancers (Basel). 2020 Nov 17;12(11):
pubmed: 33212885
Br J Radiol. 2009 Aug;82(980):640-4
pubmed: 19332521
Int J Gynecol Cancer. 2019 May 15;:
pubmed: 31097511
Eur J Obstet Gynecol Reprod Biol. 2019 Jun;237:93-99
pubmed: 31029972
Ann Surg Oncol. 2015 May;22(5):1441-6
pubmed: 25727556
Front Oncol. 2021 Mar 25;11:642892
pubmed: 33842352
Cochrane Database Syst Rev. 2021 Jul 30;7:CD005343
pubmed: 34328210
Int J Gynecol Cancer. 2017 Sep;27(7):1534-1542
pubmed: 30814245
Clin Cancer Res. 2014 Nov 1;20(21):5359-64
pubmed: 25204553
Nat Genet. 2020 Jun;52(6):582-593
pubmed: 32483290
Int J Gynecol Cancer. 2019 Feb;29(2):353-356
pubmed: 30683759
BMJ. 1994 Jul 9;309(6947):102
pubmed: 8038641
Sci Rep. 2021 Apr 15;11(1):8262
pubmed: 33859265
Trends Immunol. 2017 Jul;38(7):526-536
pubmed: 28579319
Front Oncol. 2021 Sep 24;11:745808
pubmed: 34631583
Gynecol Oncol. 2019 Aug;154(2):441-448
pubmed: 31118141
Cancers (Basel). 2021 Feb 02;13(3):
pubmed: 33540655
Clin Radiol. 2022 May;77(5):352-359
pubmed: 35264303
Clin Cancer Res. 2020 Aug 15;26(16):4414-4425
pubmed: 32253232
Br J Cancer. 2022 Apr;126(7):1047-1054
pubmed: 34923575
Lancet. 2014 Jul 12;384(9938):164-72
pubmed: 24529560
Comput Biol Med. 2020 May;120:103751
pubmed: 32421652
Eur Radiol. 2017 Sep;27(9):3991-4001
pubmed: 28289945
J Magn Reson Imaging. 2019 Aug;50(2):497-510
pubmed: 30569552
Cancer Imaging. 2020 May 1;20(1):33
pubmed: 32357923
IEEE Trans Biomed Eng. 2014 Mar;61(3):630-7
pubmed: 24108747