AUTHOR=Chen Bin , Zhong Lianzhen , Dong Di , Zheng Jianjun , Fang Mengjie , Yu Chunyao , Dai Qi , Zhang Liwen , Tian Jie , Lu Wei , Jin Yinhua 

TITLE=Computed Tomography Radiomic Nomogram for Preoperative Prediction of Extrathyroidal Extension in Papillary Thyroid Carcinoma

JOURNAL=Frontiers in Oncology

VOLUME=9

YEAR=2019

URL=https://www.frontiersin.org/journals/oncology/articles/10.3389/fonc.2019.00829

DOI=10.3389/fonc.2019.00829

ISSN=2234-943X

ABSTRACT=<p><bold>Objectives:</bold> Determining the presence of extrathyroidal extension (ETE) is important for patients with papillary thyroid carcinoma (PTC) in selecting the proper surgical approaches. This study aimed to explore a radiomic model for preoperative prediction of ETE in patients with PTC.</p><p><bold>Methods:</bold> The study included 624 PTC patients (without ETE, <italic>n</italic> = 448; with minimal ETE, <italic>n</italic> = 52; with gross ETE, <italic>n</italic> = 124) whom were divided randomly into training (<italic>n</italic> = 437) and validation (<italic>n</italic> = 187) cohorts; all data were gathered between January 2016 and November 2017. Radiomic features were extracted from computed tomography (CT) images of PTCs. Key radiomic features were identified and incorporated into a radiomic signature. Combining the radiomic signature with clinical risk factors, a radiomic nomogram was constructed using multivariable logistic regression. Delong test was used to compare different receiver operating characteristic curves.</p><p><bold>Results:</bold> Five key radiomic features were incorporated into the radiomic signature, which were significantly associated with ETE (<italic>p</italic> &lt; 0.001 for both cohorts) and slightly better than clinical model integrating significant clinical risk factors in the training cohort (area under the receiver operating characteristic curve (AUC), 0.791 vs. 0.778; F<sub>1</sub> score, 0.729 vs. 0.714) and validation cohort (AUC, 0.772 vs. 0.756; F<sub>1</sub> score, 0.710 vs. 0.692). The radiomic nomogram significantly improved predictive value in the training cohort (AUC, 0.837, <italic>p</italic> &lt; 0.001; F<sub>1</sub> score, 0.766) and validation cohort (AUC, 0.812, <italic>p</italic> = 0.024; F<sub>1</sub> score, 0.732).</p><p><bold>Conclusions:</bold> The radiomic nomogram significantly improved the preoperative prediction of ETE in PTC patients. It indicated that radiomics could be a valuable method in PTC research.</p>