Abstract
Background: Locoregionally advanced head and neck squamous cell carcinoma (HNSCC) patients have high relapse and mortality rates. Imaging-based decision support may improve out-comes by optimising personalised treatment, and support patient risk stratification. We propose a multifactorial prognostic model including radiomics features to improve risk stratification for advanced HNSCC, compared to TNM eighth edition, the gold standard. Patient and methods: Data of 666 retrospective-and 143 prospective-stage III-IVA/B HNSCC patients were collected. A multivar-iable Cox proportional-hazards model was trained to predict overall survival (OS) using diagnostic CT-based radiomics features extracted from the primary tumour. Separate analyses were performed using TNM8, tumour volume, clinical and biological variables, and combinations thereof with radi-omics features. Patient risk stratification in three groups was assessed through Kaplan–Meier (KM) curves. A log-rank test was performed for significance (p-value < 0.05). The prognostic accuracy was reported through the concordance index (CI). Results: A model combining an 11-feature radiomics signature, clinical and biological variables, TNM8, and volume could significantly stratify the validation cohort into three risk groups (p < 0∙01, CI of 0.79 as validation). Conclusion: A combination of radiomics features with other predictors can predict OS very accurately for advanced HNSCC patients and improves on the current gold standard of TNM8.
Original language | English |
---|---|
Article number | 3271 |
Journal | Cancers |
Volume | 13 |
Issue number | 13 |
DOIs | |
Publication status | Published - 1 Jul 2021 |
Keywords
- Head and neck cancer
- Machine learning
- Precision medicine
- Radiomics
- Survival study
Access to Document
Other files and links
Cite this
- APA
- Author
- BIBTEX
- Harvard
- Standard
- RIS
- Vancouver
}
A prospectively validated prognostic model for patients with locally advanced squamous cell carcinoma of the head and neck based on radiomics of computed tomography images. / Keek, Simon A.; Wesseling, Frederik W.R.; Woodruff, Henry C. et al.
In: Cancers, Vol. 13, No. 13, 3271, 01.07.2021.Research output: Contribution to journal › Article › Academic › peer-review
TY - JOUR
T1 - A prospectively validated prognostic model for patients with locally advanced squamous cell carcinoma of the head and neck based on radiomics of computed tomography images
AU - Keek, Simon A.
AU - Wesseling, Frederik W.R.
AU - Woodruff, Henry C.
AU - van Timmeren, Janita E.
AU - Nauta, Irene H.
AU - Hoffmann, Thomas K.
AU - Cavalieri, Stefano
AU - Calareso, Giuseppina
AU - Primakov, Sergey
AU - Leijenaar, Ralph T.H.
AU - Licitra, Lisa
AU - Ravanelli, Marco
AU - Scheckenbach, Kathrin
AU - Poli, Tito
AU - Lanfranco, Davide
AU - Vergeer, Marije R.
AU - Leemans, C. René
AU - Brakenhoff, Ruud H.
AU - Hoebers, Frank J.P.
AU - Lambin, Philippe
N1 - Funding Information: Funding: This work was supported by the European Union Horizon 2020 Framework Programme [grant number 689715]. Funding Information: Acknowledgments: The authors and the investigators are grateful to Elena Martinelli, project manager of the BD2Decide project, who lead the coordination work. Authors acknowledge financial support from ERC advanced grant (ERC-ADG-2015 n° 694812-Hypoximmuno), ERC-2018-PoC: 813200-CL-IO, ERC-2020-PoC: 957565-AUTO.DISTINCT. Authors also acknowledge financial support from SME Phase 2 (RAIL n°673780), EUROSTARS (DART, DECIDE, COMPACT-12053), the European Union’s Horizon 2020 research and innovation programme under grant agreement: BD2Decide-PHC30-689715, ImmunoSABR n° 733008, MSCA-ITN-PREDICT n° 766276, FETOPEN-SCANnTREAT n° 899549, CHAIMELEON n° 952172, EuCanImage n° 952103, TRANSCAN Joint Transnational Call 2016 (JTC2016 CLEARLY n° UM 2017-8295), Interreg V-A Euregio Meuse-Rhine (EURADIOMICS n° EMR4), and Genmab (n° 1044). This work was supported by the Dutch Cancer Society (KWF Kankerbestrijding), project number 12085/2018–2, KWF-A6C7072 (DESIGN), and KWF project number 12079/2018-2. Dr. Philippe Lambin reports, within and outside the submitted work, grants/sponsored research agreements from Varian medical, Oncoradiomics, ptTheragnostic, Health Innovation Ventures, and DualTpharma. He received an advisor/presenter fee and/or reimbursement of travel costs/external grant writing fee and/or in-kind manpower contribution from Oncoradiomics, BHV, Merck, and Convert pharmaceuticals. Dr. Lambin has shares in the company Oncoradiomics, Convert pharmaceuticals, MedC2, and LivingMed Biotech and is co-inventor of two issued patents with royalties on radiomics (PCT/NL2014/050248, PCT/NL2014/050728) licensed to Oncoradiomics and one issue patent on mtDNA (PCT/EP2014/059089) licensed to ptTheragnos-tic/DNAmito, three non-patentable inventions (software) licensed to ptTheragnostic/ DNAmito, Oncoradiomics and Health Innovation Ventures. Dr. Lisa Licitra further acknowledges grant/research support from AstraZeneca, BMS, Boehringer Ingelheim, Celgene International, Debiopharm International SA, Eisai, Exelixis Inc, Hoffmann-La Roche Ltd, IRX Therapeutics inc, Medpace Inc, Merck–Serono, MSD, Novartis, Pfizer, Roche, honoraria/consultation fees from AstraZeneca, Bayer, BMS, Eisai, MSD, Merck–Serono, Boehringer Ingelheim, Novartis, Roche, Debiopharm International SA, Sobi, Ipsen, Incyte Biosciences Italy srl, Doxa Pharma, Amgen, Nanobiotics Sa, and GSK, and fees for public speaking/teaching from AccMed, Medical Science Foundation G. Lorenzini, Associ-azione Sinapsi, Think 2 IT, Aiom Servizi, Prime Oncology, WMA Congress Education, Fasi, DueCi promotion Srl, MI&T, Net Congress & Education, PRMA Consulting, Kura Oncology, Health & Life srl, Immuno-Oncology Hub. Dr. Henry C. Woodruff has (minority) shares in the company Oncora-diomics. Dr. Ralph T.H. Leijenaar is a salaried employee of the company Oncoradiomics, has shares in the company Oncoradiomics and is co-inventor of an issued patent with royalties on radiomics (PCT/NL2014/050728) licensed to Oncoradiomics. Dr. C. René Leemans is an advisory board member at Merk & Co., Inc. and Rakuten Medical, and has received a research grant from Bristol Myers-Squibb. RH Brakenhoff PhD, received research grants from GenMab, Bristol Myers-Squibb, and In-teRNA BV, and has collaborated with MSD. Publisher Copyright: © 2021 by the authors. Li-censee MDPI, Basel, Switzerland. Copyright: Copyright 2021 Elsevier B.V., All rights reserved.
PY - 2021/7/1
Y1 - 2021/7/1
N2 - Background: Locoregionally advanced head and neck squamous cell carcinoma (HNSCC) patients have high relapse and mortality rates. Imaging-based decision support may improve out-comes by optimising personalised treatment, and support patient risk stratification. We propose a multifactorial prognostic model including radiomics features to improve risk stratification for advanced HNSCC, compared to TNM eighth edition, the gold standard. Patient and methods: Data of 666 retrospective-and 143 prospective-stage III-IVA/B HNSCC patients were collected. A multivar-iable Cox proportional-hazards model was trained to predict overall survival (OS) using diagnostic CT-based radiomics features extracted from the primary tumour. Separate analyses were performed using TNM8, tumour volume, clinical and biological variables, and combinations thereof with radi-omics features. Patient risk stratification in three groups was assessed through Kaplan–Meier (KM) curves. A log-rank test was performed for significance (p-value < 0.05). The prognostic accuracy was reported through the concordance index (CI). Results: A model combining an 11-feature radiomics signature, clinical and biological variables, TNM8, and volume could significantly stratify the validation cohort into three risk groups (p < 0∙01, CI of 0.79 as validation). Conclusion: A combination of radiomics features with other predictors can predict OS very accurately for advanced HNSCC patients and improves on the current gold standard of TNM8.
AB - Background: Locoregionally advanced head and neck squamous cell carcinoma (HNSCC) patients have high relapse and mortality rates. Imaging-based decision support may improve out-comes by optimising personalised treatment, and support patient risk stratification. We propose a multifactorial prognostic model including radiomics features to improve risk stratification for advanced HNSCC, compared to TNM eighth edition, the gold standard. Patient and methods: Data of 666 retrospective-and 143 prospective-stage III-IVA/B HNSCC patients were collected. A multivar-iable Cox proportional-hazards model was trained to predict overall survival (OS) using diagnostic CT-based radiomics features extracted from the primary tumour. Separate analyses were performed using TNM8, tumour volume, clinical and biological variables, and combinations thereof with radi-omics features. Patient risk stratification in three groups was assessed through Kaplan–Meier (KM) curves. A log-rank test was performed for significance (p-value < 0.05). The prognostic accuracy was reported through the concordance index (CI). Results: A model combining an 11-feature radiomics signature, clinical and biological variables, TNM8, and volume could significantly stratify the validation cohort into three risk groups (p < 0∙01, CI of 0.79 as validation). Conclusion: A combination of radiomics features with other predictors can predict OS very accurately for advanced HNSCC patients and improves on the current gold standard of TNM8.
KW - Head and neck cancer
KW - Machine learning
KW - Precision medicine
KW - Radiomics
KW - Survival study
UR - http://www.scopus.com/inward/record.url?scp=85108676254&partnerID=8YFLogxK
U2 - https://doi.org/10.3390/cancers13133271
DO - https://doi.org/10.3390/cancers13133271
M3 - Article
C2 - 34210048
SN - 2072-6694
VL - 13
JO - Cancers
JF - Cancers
IS - 13
M1 - 3271
ER -