AUTHOR=Zhang Xiang , Liang Ming , Yang Zehong , Zheng Chushan , Wu Jiayi , Ou Bing , Li Haojiang , Wu Xiaoyan , Luo Baoming , Shen Jun 

TITLE=Deep Learning-Based Radiomics of B-Mode Ultrasonography and Shear-Wave Elastography: Improved Performance in Breast Mass Classification

JOURNAL=Frontiers in Oncology

VOLUME=10

YEAR=2020

URL=https://www.frontiersin.org/journals/oncology/articles/10.3389/fonc.2020.01621

DOI=10.3389/fonc.2020.01621

ISSN=2234-943X

ABSTRACT=<sec><title>Objective</title><p>Shear-wave elastography (SWE) can improve the diagnostic specificity of the B-model ultrasonography (US) in breast cancer. However, whether deep learning-based radiomics signatures based on the B-mode US (B-US-RS) or SWE (SWE-RS) could further improve the diagnostic performance remains to be investigated. We aimed to develop the B-US-RS and SWE-RS and determine their performances in classifying breast masses.</p></sec><sec><title>Materials and Methods</title><p>This retrospective study included 291 women (mean age ± standard deviation, 40.9 ± 12.3 years) from two centers who had US-visible solid breast masses and underwent biopsy and/or surgical resection between June 2015 and July 2017. B-mode US and SWE images of the 198 masses in 198 patients (training cohort) from center 1 were segmented, respectively, to construct B-US-RS and SWE-RS using the least absolute shrinkage and selection operator regression and tested in an independent validation cohort of 65 masses in 65 patients from center 1 and in an external validation cohort of 28 masses in 28 patients from center 2. The performances of B-US-RS and SWE-RS were assessed using receiver operating characteristic (ROC) analysis and compared with that of radiologist assessment [Breast Imaging Reporting and Data System (BI-RADS)] and quantitative SWE parameters [maximum elasticity (<italic>E</italic><sub>max</sub>), mean elasticity (<italic>E</italic><sub>mean</sub>), elasticity ratio (<italic>E</italic><sub>ratio</sub>), and elastic modulus standard deviation (<italic>E</italic><sub>SD</sub>)] by using the McNemar test.</p></sec><sec><title>Results</title><p>The single best-performing quantitative SWE parameter, <italic>E</italic><sub>max</sub>, had a higher specificity than BI-RADS assessment in the training and independent validation cohorts (<italic>P</italic> &lt; 0.001 for both). The areas under the ROC curves (AUCs) of B-US-RS and SWE-RS both were 0.99 (95% CI = 0.99–1.00) in the training cohort, 1.00 (95% CI = 1.00–1.00) in the independent validation cohort, and 1.00 (95% CI = 1.00–1.00) in the external validation cohort. The specificities of B-US-RS and SWE-RS were higher than that of <italic>E</italic><sub>max</sub> in the training (<italic>P</italic> &lt; 0.001 for both) and independent validation cohorts (<italic>P</italic> = 0.02 for both).</p></sec><sec><title>Conclusion</title><p>The B-US-RS and SWE-RS outperformed the quantitative SWE parameters and BI-RADS assessment for classifying breast masses. The integration of the deep learning-based radiomics approach would help improve the classification ability of B-mode US and SWE for breast masses.</p></sec>