Cargando…

Predicting lymphovascular invasion in clinically node-negative breast cancer detected by abbreviated magnetic resonance imaging: Transfer learning vs. radiomics

OBJECTIVE: To compare the performance of abbreviated breast magnetic resonance imaging (AB-MRI)-based transfer learning (TL) algorithm and radionics analysis for lymphovascular invasion (LVI) prediction in patients with clinically node-negative invasive breast cancer (IBC). METHODS: Between November...

Descripción completa

Detalles Bibliográficos
Autores principales: Feng, Bao, Liu, Zhuangsheng, Liu, Yu, Chen, Yehang, Zhou, Haoyang, Cui, Enming, Li, Xiaoping, Chen, Xiangmeng, Li, Ronggang, Yu, Tianyou, Zhang, Ling, Long, Wansheng
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Frontiers Media S.A. 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9520481/
https://www.ncbi.nlm.nih.gov/pubmed/36185309
http://dx.doi.org/10.3389/fonc.2022.890659
_version_ 1784799634029281280
author Feng, Bao
Liu, Zhuangsheng
Liu, Yu
Chen, Yehang
Zhou, Haoyang
Cui, Enming
Li, Xiaoping
Chen, Xiangmeng
Li, Ronggang
Yu, Tianyou
Zhang, Ling
Long, Wansheng
author_facet Feng, Bao
Liu, Zhuangsheng
Liu, Yu
Chen, Yehang
Zhou, Haoyang
Cui, Enming
Li, Xiaoping
Chen, Xiangmeng
Li, Ronggang
Yu, Tianyou
Zhang, Ling
Long, Wansheng
author_sort Feng, Bao
collection PubMed
description OBJECTIVE: To compare the performance of abbreviated breast magnetic resonance imaging (AB-MRI)-based transfer learning (TL) algorithm and radionics analysis for lymphovascular invasion (LVI) prediction in patients with clinically node-negative invasive breast cancer (IBC). METHODS: Between November 2017 and October 2020, 233 clinically node-negative IBCs detected by AB-MRI were retrospectively enrolled. One hundred thirty IBCs from center 1 (37 LVI-positive and 93 LVI-negative) were assigned as the training cohort and 103 from center 2 (25 LVI-positive and 78 LVI-negative) as the validation cohort. Based on AB-MRI, a TL signature (TLS) and a radiomics signature (RS) were built with the least absolute shrinkage and selection operator (LASSO) logistic regression. Their diagnostic performances were validated and compared using areas under the receiver operating curve (AUCs), net reclassification improvement (NRI), integrated discrimination improvement (IDI), decision curve analysis (DCA), and stratification analysis. A convolutional filter visualization technique was used to map the response areas of LVI on the AB-MRI. RESULTS: In the validation cohort, compared with RS, the TLS showed better capability in discriminating LVI-positive from LVI-negative lesions (AUC: 0.852 vs. 0.726, p < 0.001; IDI = 0.092, p < 0.001; NRI = 0.554, p < 0.001). The diagnostic performance of TLS was not affected by the menstrual state, molecular subtype, or contrast agent type (all p > 0.05). Moreover, DCA showed that the TLS added more net benefit than RS for clinical utility. CONCLUSIONS: An AB-MRI-based TLS was superior to RS for preoperative LVI prediction in patients with clinically node-negative IBC.
format Online
Article
Text
id pubmed-9520481
institution National Center for Biotechnology Information
language English
publishDate 2022
publisher Frontiers Media S.A.
record_format MEDLINE/PubMed
spelling pubmed-95204812022-09-30 Predicting lymphovascular invasion in clinically node-negative breast cancer detected by abbreviated magnetic resonance imaging: Transfer learning vs. radiomics Feng, Bao Liu, Zhuangsheng Liu, Yu Chen, Yehang Zhou, Haoyang Cui, Enming Li, Xiaoping Chen, Xiangmeng Li, Ronggang Yu, Tianyou Zhang, Ling Long, Wansheng Front Oncol Oncology OBJECTIVE: To compare the performance of abbreviated breast magnetic resonance imaging (AB-MRI)-based transfer learning (TL) algorithm and radionics analysis for lymphovascular invasion (LVI) prediction in patients with clinically node-negative invasive breast cancer (IBC). METHODS: Between November 2017 and October 2020, 233 clinically node-negative IBCs detected by AB-MRI were retrospectively enrolled. One hundred thirty IBCs from center 1 (37 LVI-positive and 93 LVI-negative) were assigned as the training cohort and 103 from center 2 (25 LVI-positive and 78 LVI-negative) as the validation cohort. Based on AB-MRI, a TL signature (TLS) and a radiomics signature (RS) were built with the least absolute shrinkage and selection operator (LASSO) logistic regression. Their diagnostic performances were validated and compared using areas under the receiver operating curve (AUCs), net reclassification improvement (NRI), integrated discrimination improvement (IDI), decision curve analysis (DCA), and stratification analysis. A convolutional filter visualization technique was used to map the response areas of LVI on the AB-MRI. RESULTS: In the validation cohort, compared with RS, the TLS showed better capability in discriminating LVI-positive from LVI-negative lesions (AUC: 0.852 vs. 0.726, p < 0.001; IDI = 0.092, p < 0.001; NRI = 0.554, p < 0.001). The diagnostic performance of TLS was not affected by the menstrual state, molecular subtype, or contrast agent type (all p > 0.05). Moreover, DCA showed that the TLS added more net benefit than RS for clinical utility. CONCLUSIONS: An AB-MRI-based TLS was superior to RS for preoperative LVI prediction in patients with clinically node-negative IBC. Frontiers Media S.A. 2022-09-15 /pmc/articles/PMC9520481/ /pubmed/36185309 http://dx.doi.org/10.3389/fonc.2022.890659 Text en Copyright © 2022 Feng, Liu, Liu, Chen, Zhou, Cui, Li, Chen, Li, Yu, Zhang and Long https://creativecommons.org/licenses/by/4.0/This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
spellingShingle Oncology
Feng, Bao
Liu, Zhuangsheng
Liu, Yu
Chen, Yehang
Zhou, Haoyang
Cui, Enming
Li, Xiaoping
Chen, Xiangmeng
Li, Ronggang
Yu, Tianyou
Zhang, Ling
Long, Wansheng
Predicting lymphovascular invasion in clinically node-negative breast cancer detected by abbreviated magnetic resonance imaging: Transfer learning vs. radiomics
title Predicting lymphovascular invasion in clinically node-negative breast cancer detected by abbreviated magnetic resonance imaging: Transfer learning vs. radiomics
title_full Predicting lymphovascular invasion in clinically node-negative breast cancer detected by abbreviated magnetic resonance imaging: Transfer learning vs. radiomics
title_fullStr Predicting lymphovascular invasion in clinically node-negative breast cancer detected by abbreviated magnetic resonance imaging: Transfer learning vs. radiomics
title_full_unstemmed Predicting lymphovascular invasion in clinically node-negative breast cancer detected by abbreviated magnetic resonance imaging: Transfer learning vs. radiomics
title_short Predicting lymphovascular invasion in clinically node-negative breast cancer detected by abbreviated magnetic resonance imaging: Transfer learning vs. radiomics
title_sort predicting lymphovascular invasion in clinically node-negative breast cancer detected by abbreviated magnetic resonance imaging: transfer learning vs. radiomics
topic Oncology
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9520481/
https://www.ncbi.nlm.nih.gov/pubmed/36185309
http://dx.doi.org/10.3389/fonc.2022.890659
work_keys_str_mv AT fengbao predictinglymphovascularinvasioninclinicallynodenegativebreastcancerdetectedbyabbreviatedmagneticresonanceimagingtransferlearningvsradiomics
AT liuzhuangsheng predictinglymphovascularinvasioninclinicallynodenegativebreastcancerdetectedbyabbreviatedmagneticresonanceimagingtransferlearningvsradiomics
AT liuyu predictinglymphovascularinvasioninclinicallynodenegativebreastcancerdetectedbyabbreviatedmagneticresonanceimagingtransferlearningvsradiomics
AT chenyehang predictinglymphovascularinvasioninclinicallynodenegativebreastcancerdetectedbyabbreviatedmagneticresonanceimagingtransferlearningvsradiomics
AT zhouhaoyang predictinglymphovascularinvasioninclinicallynodenegativebreastcancerdetectedbyabbreviatedmagneticresonanceimagingtransferlearningvsradiomics
AT cuienming predictinglymphovascularinvasioninclinicallynodenegativebreastcancerdetectedbyabbreviatedmagneticresonanceimagingtransferlearningvsradiomics
AT lixiaoping predictinglymphovascularinvasioninclinicallynodenegativebreastcancerdetectedbyabbreviatedmagneticresonanceimagingtransferlearningvsradiomics
AT chenxiangmeng predictinglymphovascularinvasioninclinicallynodenegativebreastcancerdetectedbyabbreviatedmagneticresonanceimagingtransferlearningvsradiomics
AT lironggang predictinglymphovascularinvasioninclinicallynodenegativebreastcancerdetectedbyabbreviatedmagneticresonanceimagingtransferlearningvsradiomics
AT yutianyou predictinglymphovascularinvasioninclinicallynodenegativebreastcancerdetectedbyabbreviatedmagneticresonanceimagingtransferlearningvsradiomics
AT zhangling predictinglymphovascularinvasioninclinicallynodenegativebreastcancerdetectedbyabbreviatedmagneticresonanceimagingtransferlearningvsradiomics
AT longwansheng predictinglymphovascularinvasioninclinicallynodenegativebreastcancerdetectedbyabbreviatedmagneticresonanceimagingtransferlearningvsradiomics