Radiomics Score Combined with ACR TI-RADS in Discriminating Benign and Malignant Thyroid Nodules Based on Ultrasound Images: A Retrospective Study.

Peng Luo,Ping Zhang,Hua Zhang,Yang Yang,Lei Su,Jianli Ren,Zheng Fang,Zhigang Wang

doi:10.3390/diagnostics11061011

Abstract

This study aimed to explore the ability of combination model of ultrasound radiomics score (Rad-score) and the thyroid imaging, reporting and data system by the American College of Radiology (ACR TI-RADS) in predicting benign and malignant thyroid nodules (TNs). Up to 286 radiomics features were extracted from ultrasound images of TNs. By using the lowest probability of classification error and average correlation coefficients (POE + ACC) and the least absolute shrinkage and selection operator (LASSO), we finally selected four features to establish Rad-score (Vertl-RLNonUni, Vertl-GLevNonU, WavEnLH-s4 and WavEnHL-s5). DeLong’s test and decision curve analysis (DCA) showed that the method of combining Rad-score and ACR TI-RADS had the best performance (the area under the receiver operating characteristic curve (AUC = 0.913 (95% confidence interval (CI), 0.881–0.939) and 0.899 (95%CI, 0.840–0.942) in the training group and verification group, respectively), followed by ACR TI-RADS (AUC = 0.898 (95%CI, 0.863–0.926) and 0.870 (95%CI, 0.806–0.919) in the training group and verification group, respectively), and followed by Rad-score (AUC = 0.750 (95%CI, 0.704–0.792) and 0.750 (95%CI, 0.672–0.817) in the training group and verification group, respectively). We concluded that the ability of ultrasound Rad-score to distinguish benign and malignant TNs was not as good as that of ACR TI-RADS, and the ability of the combination model of Rad-score and ACR TI-RADS to discriminate benign and malignant TNs was better than ACR TI-RADS or Rad-score alone. Ultrasound Rad-score might play a potential role in improving the differentiation of malignant TNs from benign TNs.

Highlights

Introduction published maps and institutional affilThyroid nodules (TNs) are common diseases in the endocrine system [1]
Our study included 394 TNs from 394 patients, which were all included in the training group to build the models, of which 150 TNs were randomly selected as the verification group
We established three models based on ACR TI-RADS, ultrasound raIn this study, we established three models based on ACRtoTI-RADS, diomics and combining and ultrasound radiomics distinguishultrasound between radiomics and ultrasound to distinguish between benign andcombining malignant TNs

Summary

Introduction

Introduction published maps and institutional affilThyroid nodules (TNs) are common diseases in the endocrine system [1]. With the strengthening of people’s health awareness and the improvement of examination techniques, the detection rate of TNs is increasing year by year, and the incidence of TNs by high-frequency ultrasound among adults is 68% [2]. Large-scale statistics showed that the total prevalence rate of TNs in Beijing was 49.0%, and the age-standardized prevalence rate was 40.1%, which increased significantly with aging [3]. The mortality rate associated with thyroid cancer did not change significantly, but the detection rate of thyroid cancer increased substantially [4,5]. The prognosis and clinical treatment of patients with TNs are mainly related to their pathological states. The pathological states of TNs are usually obtained by fine-needle aspiration (FNA). High-frequency ultrasound is the most commonly used method for thyroid imaging examination. The American College of Radiology thyroid imaging, reporting and data system (ACR TI-RADS) is currently iations

Objectives

Methods

Results

Discussion

Conclusion