Predicting survival and local control after radiochemotherapy in locally advanced head and neck cancer by means of computed tomography based radiomics

PurposeTo appraise the ability of a radiomics signature to predict clinical outcome after definitive radiochemotherapy (RCT) of stage III–IV head and neck cancer.MethodsA cohort of 110 patients was included in a retrospective analysis. Radiomics texture features were extracted from the gross tumor volumes contoured on planning computed tomography (CT) images. The cohort of patients was randomly divided into a training (70 patients) and a validation (40 patients) cohorts. Textural features were correlated to survival and control data to build predictive models. All the significant predictors of the univariate analysis were included in a multivariate model. The quality of the models was appraised by means of the concordance index (CI).ResultsA signature with 3 features was identified as predictive of overall survival (OS) with CI = 0.88 and 0.90 for the training and validation cohorts, respectively. A signature with 2 features was identified for progression-free survival (PFS; CI = 0.72 and 0.80); 2 features also characterized the signature for local control (LC; CI = 0.72 and 0.82). In all cases, the stratification in high- and low-risk groups for the training and validation cohorts led to significant differences in the actuarial curves. In the validation cohort the mean OS times (in months) were 78.9 ± 2.1 vs 67.4 ± 6.0 in the low- and high-risk groups, respectively, the PFS was 73.1 ± 3.7 and 50.7 ± 7.2, while the LC was 78.7 ± 2.1 and 63.9 ± 6.5.ConclusionCT-based radiomic signatures that correlate with survival and control after RCT were identified and allow low- and high-risk groups of patients to be identified.ZusammenfassungZielsetzungZiel war die Untersuchung der Möglichkeit, mittels einer Radiomics-Signatur klinische Ergebnisse nach definitiver Radiochemotherapie (RCT) von Kopf-Hals-Tumoren im Stadium II–IV vorherzusagen.MethodenEine Kohorte von 110 Patienten wurde in eine retrospektive Analyse einbezogen. Die Radiomics-Texturmerkmale wurden aus den Gross-Tumor-Volume-Konturen der Planungs-CT-Aufnahmen extrahiert. Die Patientengruppe wurde nach dem Zufallsprinzip in eine Trainingskohorte (70 Patienten) und eine Validierungskohorte (40 Patienten) unterteilt. Die Strukturmerkmale wurden mit den Überlebens- und Kontrolldaten korreliert, um Vorhersagemodelle zu erstellen. Alle signifikanten Prädiktoren der univariaten Analyse wurden in ein multivariates Modell aufgenommen. Die Qualität der Modelle wurde anhand des Konkordanzindex (CI) beurteilt.ErgebnisseEine Signatur mit 3 Merkmalen wurde als prädiktiv für das Gesamtüberleben, OS, identifiziert, mit einem CI = 0,88 bzw. 0,90 für die Trainings- bzw. Validierungskohorte. Eine Signatur mit 2 Merkmalen wurde für das progressionsfreie Überleben, PFS, identifiziert (CI = 0,72 bzw. 0,80). Ebenfalls 2 Merkmale charakterisierten die Signatur für die lokale Kontrolle, LC (CI = 0,72 und 0,82). In allen Fällen führt die Stratifizierung in Hoch- und Niedrigrisikogruppen für die Trainings- und Validierungskohorte zu signifikanten Unterschieden in den aktuariellen Überlebenskurven. In der Validierungskohorte betrug die mittlere Überlebenszeit (in Monaten) 78,9 ± 2,1 gegenüber 67,4 ± 6,0 in der Niedrig- bzw. Hochrisikogruppe. Das progressionsfreie Überleben betrug 73,1 ± 3,7 gegenüber 50,7 ± 7,2; bei lokaler Kontrolle von 78,7 ± 2,1 gegenüber 63,9 ± 6,5.SchlussfolgerungEs wurden CT-basierte radiomische Signaturen identifiziert, die mit dem Überleben und der Kontrolle nach RCT korrelieren und es somit ermöglichen, Patienten mit niedrigem und hohem Risiko zu identifizieren.

[1]  Wei-Chung Hsu,et al.  Radiomics based analysis to predict local control and survival in hepatocellular carcinoma patients treated with volumetric modulated arc therapy , 2017, BMC Cancer.

[2]  Pietro Mancosu,et al.  Computed tomography based radiomic signature as predictive of survival and local control after stereotactic body radiation therapy in pancreatic carcinoma , 2019, PloS one.

[3]  Matthias Guckenberger,et al.  Computed Tomography Radiomics Predicts HPV Status and Local Tumor Control After Definitive Radiochemotherapy in Head and Neck Squamous Cell Carcinoma. , 2017, International journal of radiation oncology, biology, physics.

[4]  Nathalie Lassau,et al.  Can we trust the calculation of texture indices of CT images? A phantom study , 2018, Medical physics.

[5]  Patrick Granton,et al.  Radiomics: extracting more information from medical images using advanced feature analysis. , 2012, European journal of cancer.

[6]  G. Elisabeta Marai,et al.  Machine Learning Applications in Head and Neck Radiation Oncology: Lessons From Open-Source Radiomics Challenges , 2018, Front. Oncol..

[7]  Brian O'Sullivan,et al.  Development and validation of a radiomic signature to predict HPV (p16) status from standard CT imaging: a multicenter study , 2018, The British journal of radiology.

[8]  Ender Konukoglu,et al.  Post-radiochemotherapy PET radiomics in head and neck cancer - The influence of radiomics implementation on the reproducibility of local control tumor models. , 2017, Radiotherapy and oncology : journal of the European Society for Therapeutic Radiology and Oncology.

[9]  Matthias Guckenberger,et al.  Comparison of PET and CT radiomics for prediction of local tumor control in head and neck squamous cell carcinoma , 2017, Acta oncologica.

[10]  Benjamin Haibe-Kains,et al.  Radiomic feature clusters and Prognostic Signatures specific for Lung and Head & Neck cancer , 2015, Scientific Reports.

[11]  Irène Buvat,et al.  LIFEx: A Freeware for Radiomic Feature Calculation in Multimodality Imaging to Accelerate Advances in the Characterization of Tumor Heterogeneity. , 2018, Cancer research.

[12]  L Cozzi,et al.  PET Radiomics in NSCLC: state of the art and a proposal for harmonization of methodology , 2017, Scientific Reports.

[13]  G. Collins,et al.  Transparent reporting of a multivariable prediction model for individual prognosis or diagnosis (TRIPOD): the TRIPOD statement , 2015, BMJ : British Medical Journal.

[14]  Thomas Frauenfelder,et al.  Influence of inter-observer delineation variability on radiomics stability in different tumor sites , 2018, Acta oncologica.

[15]  A. Riegel,et al.  Variability of gross tumor volume delineation in head-and-neck cancer using CT and PET/CT fusion. , 2005, International journal of radiation oncology, biology, physics.

[16]  Issam El-Naqa,et al.  Radiomics strategies for risk assessment of tumour failure in head-and-neck cancer , 2017, Scientific Reports.

[17]  L. Cozzi,et al.  Prediction of disease-free survival by the PET/CT radiomic signature in non-small cell lung cancer patients undergoing surgery , 2018, European Journal of Nuclear Medicine and Molecular Imaging.

[18]  P. Lambin,et al.  Decoding tumour phenotype by noninvasive imaging using a quantitative radiomics approach , 2014, Nature Communications.

[19]  S. F. Carbone,et al.  Effects of CT FOV displacement and acquisition parameters variation on texture analysis features , 2018, Physics in medicine and biology.

[20]  P. Lambin,et al.  Radiomic Machine-Learning Classifiers for Prognostic Biomarkers of Head and Neck Cancer , 2015, Front. Oncol..

[21]  G. Elisabeta Marai,et al.  Investigation of radiomic signatures for local recurrence using primary tumor texture analysis in oropharyngeal head and neck cancer patients , 2018, Scientific Reports.

[22]  Di Dong,et al.  Magnetic resonance imaging based radiomics signature for the preoperative discrimination of stage I-II and III-IV head and neck squamous cell carcinoma. , 2018, European journal of radiology.

[23]  P. Lambin,et al.  Predicting outcomes in radiation oncology—multifactorial decision support systems , 2013, Nature Reviews Clinical Oncology.

[24]  Odile Casiraghi,et al.  Predictive and prognostic value of CT based radiomics signature in locally advanced head and neck cancers patients treated with concurrent chemoradiotherapy or bioradiotherapy and its added value to Human Papillomavirus status. , 2017, Oral oncology.

[25]  Jayashree Kalpathy-Cramer,et al.  Matched computed tomography segmentation and demographic data for oropharyngeal cancer radiomics challenges , 2017, Scientific Data.

[26]  Benjamin Movsas,et al.  On the impact of smoothing and noise on robustness of CT and CBCT radiomics features for patients with head and neck cancers , 2017, Medical physics.

[27]  Mark Bangert,et al.  Design and Selection of Machine Learning Methods Using Radiomics and Dosiomics for Normal Tissue Complication Probability Modeling of Xerostomia , 2018, Front. Oncol..

[28]  Heng Li,et al.  Practical guidelines for handling head and neck computed tomography artifacts for quantitative image analysis , 2018, Comput. Medical Imaging Graph..