Radiomic feature clusters and Prognostic Signatures specific for Lung and Head & Neck cancer

• DOI: 10.1038/srep11044
• Publication Date: 2015-06-05T14:44:44Z
• Authors: Chintan Parmar; Ralph T. H. Leije...; Patrick Grossmann; Emmanuel Rios Vel...; Johan Bussink; Derek Rietveld; Michelle M. Rietb...; Benjamin Haibe-Kains; Philippe Lambin; Hugo J.W.L. Aerts
• Keywords: Lung Neoplasms; 610; Radboudumc 9: Rare cancers RIHS: Radboud Institute for Health Sciences; Prognosis; Article; 3. Good health; 03 medical and health sciences; 0302 clinical medicine; Head and Neck Neoplasms; 616; Biomarkers, Tumor; Humans; Tomography, X-Ray Computed

Abstract Radiomics provides a comprehensive quantification of tumor phenotypes by extracting and mining large number quantitative image features. To reduce the redundancy compare prognostic characteristics radiomic features across cancer types, we investigated cancer-specific feature clusters in four independent Lung Head & Neck (H&N) cohorts (in total 878 patients). Radiomic were extracted from pre-treatment computed tomography (CT) images. Consensus clustering resulted eleven thirteen stable for H&N cancer, respectively. These validated external validation using rand statistic (Lung RS = 0.92, p < 0.001, 0.001). Our analysis indicated both common as well clinical associations Strongest with parameters: Prognosis CI 0.60 ± 0.01, 0.68 0.01; histology AUC 0.56 0.03, stage 0.61 HPV 0.58 0.77 0.02. Full utilization these may further improve biomarkers, providing non-invasive way quantifying monitoring phenotypic practice.