TY - JOUR
T1 - Computed tomography-derived radiomic signature of head and neck squamous cell carcinoma (peri)tumoral tissue for the prediction of locoregional recurrence and distant metastasis after concurrent chemoradiotherapy
AU - Keek, Simon
AU - Sanduleanu, Sebastian
AU - Wesseling, Frederik
AU - De Roest, Reinout
AU - Van Den Brekel, Michiel
AU - Van Der Heijden, Martijn
AU - Vens, Conchita
AU - Giuseppina, Calareso
AU - Licitra, Lisa
AU - Scheckenbach, Kathrin
AU - Vergeer, Marije
AU - René Leemans, C.
AU - Brakenhoff, Ruud H.
AU - Nauta, Irene
AU - Cavalieri, Stefano
AU - Woodruff, Henry C.
AU - Poli, Tito
AU - Leijenaar, Ralph
AU - Hoebers, Frank
AU - Lambin, Philippe
N1 - Funding Information: Funded: DESIGN: Alpe d?Huzes/KWF Program Grant A6C 7072. BD2DECIDE: European Union Horizon 2020 research/innovation program (689715). Dr. R Leijenaar received support in the form of a salary from OncoRadiomics. The specific roles of these authors are articulated in the ?author contributions? section. Publisher Copyright: © 2020 Keek et al. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.
PY - 2020/5/1
Y1 - 2020/5/1
N2 - Introduction In this study, we investigate the role of radiomics for prediction of overall survival (OS), locoregional recurrence (LRR) and distant metastases (DM) in stage III and IV HNSCC patients treated by chemoradiotherapy. We hypothesize that radiomic analysis of (peri-)tumoral tissue may detect invasion of surrounding tissues indicating a higher chance of locoregional recurrence and distant metastasis. Methods Two comprehensive data sources were used: the Dutch Cancer Society Database (Alp 7072, DESIGN) and “Big Data To Decide” (BD2Decide). The gross tumor volumes (GTV) were delineated on contrast-enhanced CT. Radiomic features were extracted using the RadiomiX Discovery Toolbox (OncoRadiomics, Liege, Belgium). Clinical patient features such as age, gender, performance status etc. were collected. Two machine learning methods were chosen for their ability to handle censored data: Cox proportional hazards regression and random survival forest (RSF). Multivariable clinical and radiomic Cox/RSF models were generated based on significance in univariable cox regression/RSF analyses on the held out data in the training dataset. Features were selected according to a decreasing hazard ratio for Cox and relative importance for RSF. Results A total of 444 patients with radiotherapy planning CT-scans were included in this study: 301 head and neck squamous cell carcinoma (HNSCC) patients in the training cohort (DESIGN) and 143 patients in the validation cohort (BD2DECIDE). We found that the highest performing model was a clinical model that was able to predict distant metastasis in oropharyngeal cancer cases with an external validation C-index of 0.74 and 0.65 with the RSF and Cox models respectively. Peritumoral radiomics based prediction models performed poorly in the external validation, with C-index values ranging from 0.32 to 0.61 utilizing both feature selection and model generation methods. Conclusion Our results suggest that radiomic features from the peritumoral regions are not useful for the prediction of time to OS, LR and DM.
AB - Introduction In this study, we investigate the role of radiomics for prediction of overall survival (OS), locoregional recurrence (LRR) and distant metastases (DM) in stage III and IV HNSCC patients treated by chemoradiotherapy. We hypothesize that radiomic analysis of (peri-)tumoral tissue may detect invasion of surrounding tissues indicating a higher chance of locoregional recurrence and distant metastasis. Methods Two comprehensive data sources were used: the Dutch Cancer Society Database (Alp 7072, DESIGN) and “Big Data To Decide” (BD2Decide). The gross tumor volumes (GTV) were delineated on contrast-enhanced CT. Radiomic features were extracted using the RadiomiX Discovery Toolbox (OncoRadiomics, Liege, Belgium). Clinical patient features such as age, gender, performance status etc. were collected. Two machine learning methods were chosen for their ability to handle censored data: Cox proportional hazards regression and random survival forest (RSF). Multivariable clinical and radiomic Cox/RSF models were generated based on significance in univariable cox regression/RSF analyses on the held out data in the training dataset. Features were selected according to a decreasing hazard ratio for Cox and relative importance for RSF. Results A total of 444 patients with radiotherapy planning CT-scans were included in this study: 301 head and neck squamous cell carcinoma (HNSCC) patients in the training cohort (DESIGN) and 143 patients in the validation cohort (BD2DECIDE). We found that the highest performing model was a clinical model that was able to predict distant metastasis in oropharyngeal cancer cases with an external validation C-index of 0.74 and 0.65 with the RSF and Cox models respectively. Peritumoral radiomics based prediction models performed poorly in the external validation, with C-index values ranging from 0.32 to 0.61 utilizing both feature selection and model generation methods. Conclusion Our results suggest that radiomic features from the peritumoral regions are not useful for the prediction of time to OS, LR and DM.
UR - http://www.scopus.com/inward/record.url?scp=85085278457&partnerID=8YFLogxK
U2 - https://doi.org/10.1371/journal.pone.0232639
DO - https://doi.org/10.1371/journal.pone.0232639
M3 - Article
C2 - 32442178
SN - 1932-6203
VL - 15
JO - PLOS ONE
JF - PLOS ONE
IS - 5
M1 - e0232639
ER -
