Simon A Keek1, Frederik W R Wesseling2, Henry C Woodruff1,3, Janita E van Timmeren4, Irene H Nauta5, Thomas K Hoffmann6, Stefano Cavalieri7, Giuseppina Calareso8, Sergey Primakov1, Ralph T H Leijenaar9, Lisa Licitra7,10, Marco Ravanelli11, Kathrin Scheckenbach12, Tito Poli13, Davide Lanfranco13, Marije R Vergeer14, C René Leemans5, Ruud H Brakenhoff5, Frank J P Hoebers2, Philippe Lambin1,3. 1. The D-Lab, Department of Precision Medicine, GROW-School for Oncology, Maastricht University, Maastricht, Universiteitssingel 40, 6229 ER Maastricht, The Netherlands. 2. Department of Radiation Oncology (MAASTRO), GROW-School for Oncology and Developmental Biology, Maastricht University Medical Centre+, Postbus 3035, 6202 NA Maastricht, The Netherlands. 3. Department of Radiology and Nuclear Medicine, GROW-School for Oncology, Maastricht University Medical Centre+, P.O. Box 5800, 6202 AZ Maastricht, The Netherlands. 4. Department of Radiation Oncology, University Hospital Zürich, University of Zürich, Rämistrasse 100, 8091 Zürich, Switzerland. 5. Amsterdam UMC, Otolaryngology/Head and Neck Surgery, Cancer Center Amsterdam, Vrije Universiteit Amsterdam, Postbus 7057, 1007 MB Amsterdam, The Netherlands. 6. Department of Otorhinolaryngology, Head Neck Surgery, i2SOUL Consortium, University of Ulm, Frauensteige 14a (Haus 18), 89075 Ulm, Germany. 7. Head and Neck Medical Oncology Unit, Fondazione IRCCS Istituto Nazionale dei Tumori, via Giacomo Venezian, University of Milan, 1 20133 Milano, Italy. 8. Radiology Unit, Fondazione IRCCS Istituto Nazionale dei Tumori via Giacomo Venezian, 1 20133 Milano, Italy. 9. Oncoradiomics SA, Liège, Clos Chanmurly 13, 4000 Liège, Belgium. 10. Department of Oncology and Hemato-Oncology, University of Milan, via S. Sofia 9/1, 20122 Milano, Italy. 11. Department of Medicine and Surgery, University of Brescia, Viale Europa, 11-25123 Brescia, Italy. 12. Department. of Otorhinolaryngology-Head and Neck Surgery, University Hospital Düsseldorf, Moorenstr. 5, 40225 Düsseldorf, Germany. 13. Maxillofacial Surgery Unit, Department of Medicine and Surgery, University of Parma-University Hospital of Parma, via Università, 12-I, 43121 Parma, Italy. 14. Amsterdam UMC, Cancer Center Amsterdam, Department of Radiation Oncology, Vrije Universiteit Amsterdam, Postbus 7057, 1007 MB Amsterdam, The Netherlands.
Abstract
BACKGROUND: Locoregionally advanced head and neck squamous cell carcinoma (HNSCC) patients have high relapse and mortality rates. Imaging-based decision support may improve outcomes 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 multivariable 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 radiomics 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.
BACKGROUND: Locoregionally advanced head and neck squamous cell carcinoma (HNSCC) patients have high relapse and mortality rates. Imaging-based decision support may improve outcomes 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 HNSCCpatients were collected. A multivariable 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 radiomics 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 HNSCCpatients and improves on the current gold standard of TNM8.
Entities:
Keywords:
head and neck cancer; machine learning; precision medicine; radiomics; survival study
Authors: Adam A Dmytriw; Claudia Ortega; Reut Anconina; Ur Metser; Zhihui A Liu; Zijin Liu; Xuan Li; Thiparom Sananmuang; Eugene Yu; Sayali Joshi; John Waldron; Shao Hui Huang; Scott Bratman; Andrew Hope; Patrick Veit-Haibach Journal: Cancers (Basel) Date: 2022-06-24 Impact factor: 6.575