Deep Learning-Based Radiomics of B-Mode Ultrasonography and Shear-Wave Elastography: Improved Performance in Breast Mass Classification
ObjectiveShear-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 b...
Main Authors: | , , , , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Frontiers Media S.A.
2020-08-01
|
Series: | Frontiers in Oncology |
Subjects: | |
Online Access: | https://www.frontiersin.org/article/10.3389/fonc.2020.01621/full |
id |
doaj-73754fae806545f5a3eca0429c9c2756 |
---|---|
record_format |
Article |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Xiang Zhang Xiang Zhang Ming Liang Ming Liang Zehong Yang Zehong Yang Chushan Zheng Chushan Zheng Jiayi Wu Jiayi Wu Bing Ou Bing Ou Haojiang Li Xiaoyan Wu Xiaoyan Wu Baoming Luo Baoming Luo Jun Shen Jun Shen |
spellingShingle |
Xiang Zhang Xiang Zhang Ming Liang Ming Liang Zehong Yang Zehong Yang Chushan Zheng Chushan Zheng Jiayi Wu Jiayi Wu Bing Ou Bing Ou Haojiang Li Xiaoyan Wu Xiaoyan Wu Baoming Luo Baoming Luo Jun Shen Jun Shen Deep Learning-Based Radiomics of B-Mode Ultrasonography and Shear-Wave Elastography: Improved Performance in Breast Mass Classification Frontiers in Oncology deep learning radiomics ultrasonography shear-wave elastography breast neoplasms |
author_facet |
Xiang Zhang Xiang Zhang Ming Liang Ming Liang Zehong Yang Zehong Yang Chushan Zheng Chushan Zheng Jiayi Wu Jiayi Wu Bing Ou Bing Ou Haojiang Li Xiaoyan Wu Xiaoyan Wu Baoming Luo Baoming Luo Jun Shen Jun Shen |
author_sort |
Xiang Zhang |
title |
Deep Learning-Based Radiomics of B-Mode Ultrasonography and Shear-Wave Elastography: Improved Performance in Breast Mass Classification |
title_short |
Deep Learning-Based Radiomics of B-Mode Ultrasonography and Shear-Wave Elastography: Improved Performance in Breast Mass Classification |
title_full |
Deep Learning-Based Radiomics of B-Mode Ultrasonography and Shear-Wave Elastography: Improved Performance in Breast Mass Classification |
title_fullStr |
Deep Learning-Based Radiomics of B-Mode Ultrasonography and Shear-Wave Elastography: Improved Performance in Breast Mass Classification |
title_full_unstemmed |
Deep Learning-Based Radiomics of B-Mode Ultrasonography and Shear-Wave Elastography: Improved Performance in Breast Mass Classification |
title_sort |
deep learning-based radiomics of b-mode ultrasonography and shear-wave elastography: improved performance in breast mass classification |
publisher |
Frontiers Media S.A. |
series |
Frontiers in Oncology |
issn |
2234-943X |
publishDate |
2020-08-01 |
description |
ObjectiveShear-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.Materials and MethodsThis 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 (Emax), mean elasticity (Emean), elasticity ratio (Eratio), and elastic modulus standard deviation (ESD)] by using the McNemar test.ResultsThe single best-performing quantitative SWE parameter, Emax, had a higher specificity than BI-RADS assessment in the training and independent validation cohorts (P < 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 Emax in the training (P < 0.001 for both) and independent validation cohorts (P = 0.02 for both).ConclusionThe 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. |
topic |
deep learning radiomics ultrasonography shear-wave elastography breast neoplasms |
url |
https://www.frontiersin.org/article/10.3389/fonc.2020.01621/full |
work_keys_str_mv |
AT xiangzhang deeplearningbasedradiomicsofbmodeultrasonographyandshearwaveelastographyimprovedperformanceinbreastmassclassification AT xiangzhang deeplearningbasedradiomicsofbmodeultrasonographyandshearwaveelastographyimprovedperformanceinbreastmassclassification AT mingliang deeplearningbasedradiomicsofbmodeultrasonographyandshearwaveelastographyimprovedperformanceinbreastmassclassification AT mingliang deeplearningbasedradiomicsofbmodeultrasonographyandshearwaveelastographyimprovedperformanceinbreastmassclassification AT zehongyang deeplearningbasedradiomicsofbmodeultrasonographyandshearwaveelastographyimprovedperformanceinbreastmassclassification AT zehongyang deeplearningbasedradiomicsofbmodeultrasonographyandshearwaveelastographyimprovedperformanceinbreastmassclassification AT chushanzheng deeplearningbasedradiomicsofbmodeultrasonographyandshearwaveelastographyimprovedperformanceinbreastmassclassification AT chushanzheng deeplearningbasedradiomicsofbmodeultrasonographyandshearwaveelastographyimprovedperformanceinbreastmassclassification AT jiayiwu deeplearningbasedradiomicsofbmodeultrasonographyandshearwaveelastographyimprovedperformanceinbreastmassclassification AT jiayiwu deeplearningbasedradiomicsofbmodeultrasonographyandshearwaveelastographyimprovedperformanceinbreastmassclassification AT bingou deeplearningbasedradiomicsofbmodeultrasonographyandshearwaveelastographyimprovedperformanceinbreastmassclassification AT bingou deeplearningbasedradiomicsofbmodeultrasonographyandshearwaveelastographyimprovedperformanceinbreastmassclassification AT haojiangli deeplearningbasedradiomicsofbmodeultrasonographyandshearwaveelastographyimprovedperformanceinbreastmassclassification AT xiaoyanwu deeplearningbasedradiomicsofbmodeultrasonographyandshearwaveelastographyimprovedperformanceinbreastmassclassification AT xiaoyanwu deeplearningbasedradiomicsofbmodeultrasonographyandshearwaveelastographyimprovedperformanceinbreastmassclassification AT baomingluo deeplearningbasedradiomicsofbmodeultrasonographyandshearwaveelastographyimprovedperformanceinbreastmassclassification AT baomingluo deeplearningbasedradiomicsofbmodeultrasonographyandshearwaveelastographyimprovedperformanceinbreastmassclassification AT junshen deeplearningbasedradiomicsofbmodeultrasonographyandshearwaveelastographyimprovedperformanceinbreastmassclassification AT junshen deeplearningbasedradiomicsofbmodeultrasonographyandshearwaveelastographyimprovedperformanceinbreastmassclassification |
_version_ |
1724459933846470656 |
spelling |
doaj-73754fae806545f5a3eca0429c9c27562020-11-25T03:57:35ZengFrontiers Media S.A.Frontiers in Oncology2234-943X2020-08-011010.3389/fonc.2020.01621560927Deep Learning-Based Radiomics of B-Mode Ultrasonography and Shear-Wave Elastography: Improved Performance in Breast Mass ClassificationXiang Zhang0Xiang Zhang1Ming Liang2Ming Liang3Zehong Yang4Zehong Yang5Chushan Zheng6Chushan Zheng7Jiayi Wu8Jiayi Wu9Bing Ou10Bing Ou11Haojiang Li12Xiaoyan Wu13Xiaoyan Wu14Baoming Luo15Baoming Luo16Jun Shen17Jun Shen18Department of Radiology, Sun Yat-sen Memorial Hospital, Sun Yat-sen University, Guangzhou, ChinaGuangdong Provincial Key Laboratory of Malignant Tumor Epigenetics and Gene Regulation, Medical Research Center, Sun Yat-sen Memorial Hospital, Sun Yat-sen University, Guangzhou, ChinaGuangdong Provincial Key Laboratory of Malignant Tumor Epigenetics and Gene Regulation, Medical Research Center, Sun Yat-sen Memorial Hospital, Sun Yat-sen University, Guangzhou, ChinaDepartment of Ultrasound, Sun Yat-sen Memorial Hospital, Sun Yat-sen University, Guangzhou, ChinaDepartment of Radiology, Sun Yat-sen Memorial Hospital, Sun Yat-sen University, Guangzhou, ChinaGuangdong Provincial Key Laboratory of Malignant Tumor Epigenetics and Gene Regulation, Medical Research Center, Sun Yat-sen Memorial Hospital, Sun Yat-sen University, Guangzhou, ChinaDepartment of Radiology, Sun Yat-sen Memorial Hospital, Sun Yat-sen University, Guangzhou, ChinaGuangdong Provincial Key Laboratory of Malignant Tumor Epigenetics and Gene Regulation, Medical Research Center, Sun Yat-sen Memorial Hospital, Sun Yat-sen University, Guangzhou, ChinaGuangdong Provincial Key Laboratory of Malignant Tumor Epigenetics and Gene Regulation, Medical Research Center, Sun Yat-sen Memorial Hospital, Sun Yat-sen University, Guangzhou, ChinaDepartment of Ultrasound, Sun Yat-sen Memorial Hospital, Sun Yat-sen University, Guangzhou, ChinaGuangdong Provincial Key Laboratory of Malignant Tumor Epigenetics and Gene Regulation, Medical Research Center, Sun Yat-sen Memorial Hospital, Sun Yat-sen University, Guangzhou, ChinaDepartment of Ultrasound, Sun Yat-sen Memorial Hospital, Sun Yat-sen University, Guangzhou, ChinaDepartment of Radiology, Sun Yat-sen University Cancer Center, Sun Yat-sen University, Guangzhou, ChinaDepartment of Radiology, Sun Yat-sen Memorial Hospital, Sun Yat-sen University, Guangzhou, ChinaGuangdong Provincial Key Laboratory of Malignant Tumor Epigenetics and Gene Regulation, Medical Research Center, Sun Yat-sen Memorial Hospital, Sun Yat-sen University, Guangzhou, ChinaGuangdong Provincial Key Laboratory of Malignant Tumor Epigenetics and Gene Regulation, Medical Research Center, Sun Yat-sen Memorial Hospital, Sun Yat-sen University, Guangzhou, ChinaDepartment of Ultrasound, Sun Yat-sen Memorial Hospital, Sun Yat-sen University, Guangzhou, ChinaDepartment of Radiology, Sun Yat-sen Memorial Hospital, Sun Yat-sen University, Guangzhou, ChinaGuangdong Provincial Key Laboratory of Malignant Tumor Epigenetics and Gene Regulation, Medical Research Center, Sun Yat-sen Memorial Hospital, Sun Yat-sen University, Guangzhou, ChinaObjectiveShear-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.Materials and MethodsThis 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 (Emax), mean elasticity (Emean), elasticity ratio (Eratio), and elastic modulus standard deviation (ESD)] by using the McNemar test.ResultsThe single best-performing quantitative SWE parameter, Emax, had a higher specificity than BI-RADS assessment in the training and independent validation cohorts (P < 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 Emax in the training (P < 0.001 for both) and independent validation cohorts (P = 0.02 for both).ConclusionThe 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.https://www.frontiersin.org/article/10.3389/fonc.2020.01621/fulldeep learningradiomicsultrasonographyshear-wave elastographybreast neoplasms |