Decoding the molecular subtypes of breast cancer seen on multimodal ultrasound images using an assembled convolutional neural network model: A prospective and multicentre study

Background: Preoperative determination of breast cancer molecular subtypes facilitates individualized treatment plan-making and improves patient prognosis. We aimed to develop an assembled convolutional neural network (ACNN) model for the preoperative prediction of molecular subtypes using multimoda...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Bo-Yang Zhou, Li-Fan Wang, Hao-Hao Yin, Ting-Fan Wu, Tian-Tian Ren, Chuan Peng, De-Xuan Li, Hui Shi, Li-Ping Sun, Chong-Ke Zhao, Hui-Xiong Xu
Formato:	article
Lenguaje:	EN
Publicado:	Elsevier 2021
Materias:	Breast cancer Molecular subtypes Multimodal ultrasound images Assemble convolutional neural network Prediction Medicine R Medicine (General) R5-920
Acceso en línea:	https://doaj.org/article/29369f25cc1f4b5fa9bd98e9c1b2f059
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:29369f25cc1f4b5fa9bd98e9c1b2f059
record_format	dspace
spelling	oai:doaj.org-article:29369f25cc1f4b5fa9bd98e9c1b2f0592021-11-12T04:40:41ZDecoding the molecular subtypes of breast cancer seen on multimodal ultrasound images using an assembled convolutional neural network model: A prospective and multicentre study2352-396410.1016/j.ebiom.2021.103684https://doaj.org/article/29369f25cc1f4b5fa9bd98e9c1b2f0592021-12-01T00:00:00Zhttp://www.sciencedirect.com/science/article/pii/S2352396421004783https://doaj.org/toc/2352-3964Background: Preoperative determination of breast cancer molecular subtypes facilitates individualized treatment plan-making and improves patient prognosis. We aimed to develop an assembled convolutional neural network (ACNN) model for the preoperative prediction of molecular subtypes using multimodal ultrasound (US) images. Methods: This multicentre study prospectively evaluated a dataset of greyscale US, colour Doppler flow imaging (CDFI), and shear-wave elastography (SWE) images in 807 patients with 818 breast cancers from November 2016 to February 2021. The St. Gallen molecular subtypes of breast cancer were confirmed by postoperative immunohistochemical examination. The monomodal ACNN model based on greyscale US images, the dual-modal ACNN model based on greyscale US and CDFI images, and the multimodal ACNN model based on greyscale US and CDFI as well as SWE images were constructed in the training cohort. The performances of three ACNN models in predicting four- and five-classification molecular subtypes and identifying triple negative from non-triple negative subtypes were assessed and compared. The performance of the multimodal ACNN was also compared with preoperative core needle biopsy (CNB). Finding: The performance of the multimodal ACNN model (macroaverage area under the curve [AUC]: 0.89–0.96) was superior to that of the dual-modal ACNN model (macroaverage AUC: 0.81–0.84) and the monomodal ACNN model (macroaverage AUC: 0.73–0.75) in predicting four-classification breast cancer molecular subtypes, which was also better than that of preoperative CNB (AUC: 0.89–0.99 vs. 0.67–0.82, p < 0.05). In addition, the multimodal ACNN model outperformed the other two ACNN models in predicting five-classification molecular subtypes (AUC: 0.87–0.94 vs. 0.78-0.81 vs. 0.71–0.78) and identifying triple negative from non-triple negative breast cancers (AUC: 0.934–0.970 vs. 0.688–0.830 vs. 0.536–0.650, p < 0.05). Moreover, the multimodal ACNN model obtained satisfactory prediction performance for both T1 and non-T1 lesions (AUC: 0.957–0.958 and 0.932–0.985). Interpretation: The multimodal US-based ACNN model is a potential noninvasive decision-making method for the management of patients with breast cancer in clinical practice. Funding: This work was supported in part by the National Natural Science Foundation of China (Grants 81725008 and 81927801), Shanghai Municipal Health Commission (Grants 2019LJ21 and SHSLCZDZK03502), and the Science and Technology Commission of Shanghai Municipality (Grants 19441903200, 19DZ2251100, and 21Y11910800).Bo-Yang ZhouLi-Fan WangHao-Hao YinTing-Fan WuTian-Tian RenChuan PengDe-Xuan LiHui ShiLi-Ping SunChong-Ke ZhaoHui-Xiong XuElsevierarticleBreast cancerMolecular subtypesMultimodal ultrasound imagesAssemble convolutional neural networkPredictionMedicineRMedicine (General)R5-920ENEBioMedicine, Vol 74, Iss , Pp 103684- (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Breast cancer Molecular subtypes Multimodal ultrasound images Assemble convolutional neural network Prediction Medicine R Medicine (General) R5-920
spellingShingle	Breast cancer Molecular subtypes Multimodal ultrasound images Assemble convolutional neural network Prediction Medicine R Medicine (General) R5-920 Bo-Yang Zhou Li-Fan Wang Hao-Hao Yin Ting-Fan Wu Tian-Tian Ren Chuan Peng De-Xuan Li Hui Shi Li-Ping Sun Chong-Ke Zhao Hui-Xiong Xu Decoding the molecular subtypes of breast cancer seen on multimodal ultrasound images using an assembled convolutional neural network model: A prospective and multicentre study
description	Background: Preoperative determination of breast cancer molecular subtypes facilitates individualized treatment plan-making and improves patient prognosis. We aimed to develop an assembled convolutional neural network (ACNN) model for the preoperative prediction of molecular subtypes using multimodal ultrasound (US) images. Methods: This multicentre study prospectively evaluated a dataset of greyscale US, colour Doppler flow imaging (CDFI), and shear-wave elastography (SWE) images in 807 patients with 818 breast cancers from November 2016 to February 2021. The St. Gallen molecular subtypes of breast cancer were confirmed by postoperative immunohistochemical examination. The monomodal ACNN model based on greyscale US images, the dual-modal ACNN model based on greyscale US and CDFI images, and the multimodal ACNN model based on greyscale US and CDFI as well as SWE images were constructed in the training cohort. The performances of three ACNN models in predicting four- and five-classification molecular subtypes and identifying triple negative from non-triple negative subtypes were assessed and compared. The performance of the multimodal ACNN was also compared with preoperative core needle biopsy (CNB). Finding: The performance of the multimodal ACNN model (macroaverage area under the curve [AUC]: 0.89–0.96) was superior to that of the dual-modal ACNN model (macroaverage AUC: 0.81–0.84) and the monomodal ACNN model (macroaverage AUC: 0.73–0.75) in predicting four-classification breast cancer molecular subtypes, which was also better than that of preoperative CNB (AUC: 0.89–0.99 vs. 0.67–0.82, p < 0.05). In addition, the multimodal ACNN model outperformed the other two ACNN models in predicting five-classification molecular subtypes (AUC: 0.87–0.94 vs. 0.78-0.81 vs. 0.71–0.78) and identifying triple negative from non-triple negative breast cancers (AUC: 0.934–0.970 vs. 0.688–0.830 vs. 0.536–0.650, p < 0.05). Moreover, the multimodal ACNN model obtained satisfactory prediction performance for both T1 and non-T1 lesions (AUC: 0.957–0.958 and 0.932–0.985). Interpretation: The multimodal US-based ACNN model is a potential noninvasive decision-making method for the management of patients with breast cancer in clinical practice. Funding: This work was supported in part by the National Natural Science Foundation of China (Grants 81725008 and 81927801), Shanghai Municipal Health Commission (Grants 2019LJ21 and SHSLCZDZK03502), and the Science and Technology Commission of Shanghai Municipality (Grants 19441903200, 19DZ2251100, and 21Y11910800).
format	article
author	Bo-Yang Zhou Li-Fan Wang Hao-Hao Yin Ting-Fan Wu Tian-Tian Ren Chuan Peng De-Xuan Li Hui Shi Li-Ping Sun Chong-Ke Zhao Hui-Xiong Xu
author_facet	Bo-Yang Zhou Li-Fan Wang Hao-Hao Yin Ting-Fan Wu Tian-Tian Ren Chuan Peng De-Xuan Li Hui Shi Li-Ping Sun Chong-Ke Zhao Hui-Xiong Xu
author_sort	Bo-Yang Zhou
title	Decoding the molecular subtypes of breast cancer seen on multimodal ultrasound images using an assembled convolutional neural network model: A prospective and multicentre study
title_short	Decoding the molecular subtypes of breast cancer seen on multimodal ultrasound images using an assembled convolutional neural network model: A prospective and multicentre study
title_full	Decoding the molecular subtypes of breast cancer seen on multimodal ultrasound images using an assembled convolutional neural network model: A prospective and multicentre study
title_fullStr	Decoding the molecular subtypes of breast cancer seen on multimodal ultrasound images using an assembled convolutional neural network model: A prospective and multicentre study
title_full_unstemmed	Decoding the molecular subtypes of breast cancer seen on multimodal ultrasound images using an assembled convolutional neural network model: A prospective and multicentre study
title_sort	decoding the molecular subtypes of breast cancer seen on multimodal ultrasound images using an assembled convolutional neural network model: a prospective and multicentre study
publisher	Elsevier
publishDate	2021
url	https://doaj.org/article/29369f25cc1f4b5fa9bd98e9c1b2f059
work_keys_str_mv	AT boyangzhou decodingthemolecularsubtypesofbreastcancerseenonmultimodalultrasoundimagesusinganassembledconvolutionalneuralnetworkmodelaprospectiveandmulticentrestudy AT lifanwang decodingthemolecularsubtypesofbreastcancerseenonmultimodalultrasoundimagesusinganassembledconvolutionalneuralnetworkmodelaprospectiveandmulticentrestudy AT haohaoyin decodingthemolecularsubtypesofbreastcancerseenonmultimodalultrasoundimagesusinganassembledconvolutionalneuralnetworkmodelaprospectiveandmulticentrestudy AT tingfanwu decodingthemolecularsubtypesofbreastcancerseenonmultimodalultrasoundimagesusinganassembledconvolutionalneuralnetworkmodelaprospectiveandmulticentrestudy AT tiantianren decodingthemolecularsubtypesofbreastcancerseenonmultimodalultrasoundimagesusinganassembledconvolutionalneuralnetworkmodelaprospectiveandmulticentrestudy AT chuanpeng decodingthemolecularsubtypesofbreastcancerseenonmultimodalultrasoundimagesusinganassembledconvolutionalneuralnetworkmodelaprospectiveandmulticentrestudy AT dexuanli decodingthemolecularsubtypesofbreastcancerseenonmultimodalultrasoundimagesusinganassembledconvolutionalneuralnetworkmodelaprospectiveandmulticentrestudy AT huishi decodingthemolecularsubtypesofbreastcancerseenonmultimodalultrasoundimagesusinganassembledconvolutionalneuralnetworkmodelaprospectiveandmulticentrestudy AT lipingsun decodingthemolecularsubtypesofbreastcancerseenonmultimodalultrasoundimagesusinganassembledconvolutionalneuralnetworkmodelaprospectiveandmulticentrestudy AT chongkezhao decodingthemolecularsubtypesofbreastcancerseenonmultimodalultrasoundimagesusinganassembledconvolutionalneuralnetworkmodelaprospectiveandmulticentrestudy AT huixiongxu decodingthemolecularsubtypesofbreastcancerseenonmultimodalultrasoundimagesusinganassembledconvolutionalneuralnetworkmodelaprospectiveandmulticentrestudy
_version_	1718431220108361728

Decoding the molecular subtypes of breast cancer seen on multimodal ultrasound images using an assembled convolutional neural network model: A prospective and multicentre study

Ejemplares similares