AUTHOR=Tang Jiajia , Jiang Shitao , Ma Jiaojiao , Xi Xuehua , Li Huilin , Wang Liangkai , Zhang Bo 

TITLE=Nomogram based on radiomics analysis of ultrasound images can improve preoperative BRAF mutation diagnosis for papillary thyroid microcarcinoma

JOURNAL=Frontiers in Endocrinology

VOLUME=13

YEAR=2022

URL=https://www.frontiersin.org/journals/endocrinology/articles/10.3389/fendo.2022.915135

DOI=10.3389/fendo.2022.915135

ISSN=1664-2392

ABSTRACT=<sec><title>Background</title><p>The preoperative identification of <italic>BRAF</italic> mutation could assist to make appropriate treatment strategies for patients with papillary thyroid microcarcinoma (PTMC). This study aimed to establish an ultrasound (US) radiomics nomogram for the assessment of <italic>BRAF</italic> status.</p></sec><sec><title>Methods</title><p>A total of 328 PTMC patients at the China-Japan Friendship Hospital between February 2019 and November 2021 were enrolled in this study. They were randomly divided into training (<italic>n</italic> = 232) and validation (<italic>n</italic> = 96) cohorts. Radiomics features were extracted from the US images. The least absolute shrinkage and selection operator (LASSO) regression was applied to select the <italic>BRAF</italic> status-related features and calculate the radiomics score (Rad-score). Univariate and multivariate logistic regression analyses were subsequently performed to identify the independent factors among Rad-score and conventional US features. The US radiomics nomogram was established and its predictive performance was evaluated <italic>via</italic> discrimination, calibration, and clinical usefulness in the training and validation sets.</p></sec><sec><title>Results</title><p>Multivariate analysis indicated that the Rad-score, composition, and aspect ratio were independent predictive factors of <italic>BRAF</italic> status. The US radiomics nomogram which incorporated the three variables showed good calibration. The discrimination of the US radiomics nomogram showed better discriminative ability than the conventional US model both in the training set (AUC 0.685 vs. 0.592) and validation set (AUC 0.651 vs. 0.622). Decision curve analysis indicated the superior clinical applicability of the nomogram compared to the conventional US model.</p></sec><sec><title>Conclusions</title><p>The US radiomics nomogram displayed better performance than the conventional US model in predicting <italic>BRAF</italic> mutation in patients with PTMC.</p></sec>