Comparison of radiomics tools for image analyses and clinical prediction in nasopharyngeal carcinoma

• Published in: British journal of radiology 2019-10, Vol.92 (1102), p.20190271-20190271
• Main Authors: Liang, Zhong-Guo, Tan, Hong Qi, Zhang, Fan, Rui Tan, Lloyd Kuan, Lin, Li, Lenkowicz, Jacopo, Wang, Haitao, Wen Ong, Enya Hui, Kusumawidjaja, Grace, Phua, Jun Hao, Gan, Soon Ann, Sin, Sze Yarn, Ng, Yan Yee, Kiat Tan, Terence Wee, Soong, Yoke Lim, Fong, Kam Weng, Park, Sung Yong, Soo, Khee-Chee, Seng Wee, Joseph Tien, Zhu, Xiao-Dong, Valentini, Vincenzo, Boldrini, Luca, Sun, Ying, Kiang Chua, Melvin Lee
• Format: Article
• Language: English
• Subjects: Nasopharyngeal carcinoma special feature: Full paper
• ISSN: 0007-1285; 1748-880X
• DOI: 10.1259/bjr.20190271

OBJECTIVERadiomics pipelines have been developed to extract novel information from radiological images, which may help in phenotypic profiling of tumours that would correlate to prognosis. Here, we compared two publicly available pipelines for radiomics analyses on head and neck CT and MRI in nasopharynx cancer (NPC). METHODS AND MATERIALS100 biopsy-proven NPC cases stratified by T- and N-categories were enrolled in this study. Two radiomics pipeline, Moddicom (v. 0.51) and Pyradiomics (v. 2.1.2) were used to extract radiomics features of CT and MRI. Segmentation of primary gross tumour volume was performed using Velocity v. 4.0 by consensus agreement between three radiation oncologists. Intraclass correlation between common features of the two pipelines was analysed by Spearman's rank correlation. Unsupervised hierarchical clustering was used to determine association between radiomics features and clinical parameters. RESULTSWe observed a high proportion of correlated features in the CT data set, but not for MRI; 76.1% (51 of 67 common between Moddicom and Pyradiomics) of CT features and 28.6% (20 of 70 common) of MRI features were significantly correlated. Of these, 100% were shape-related for both CT and MRI, 100 and 23.5% were first-order-related, 61.9 and 19.0% were texture-related, respectively. This interpipeline heterogeneity affected the downstream clustering with known prognostic clinical parameters of cTN-status and GTVp. Nonetheless, shape features were the most reproducible predictors of clinical parameters among the different radiomics modules. CONCLUSIONHere, we highlighted significant heterogeneity between two publicly available radiomics pipelines that could affect the downstream association with prognostic clinical factors in NPC. ADVANCES IN KNOWLEDGEThe present study emphasized the broader importance of selecting stable radiomics features for disease phenotyping, and it is necessary prior to any investigation of multicentre imaging datasets to validate the stability of CT-related radiomics features for clinical prognostication.