Radiomic Signatures for Predicting Receptor Status in Breast Cancer Brain Metastases
BackgroundsA significant proportion of breast cancer patients showed receptor discordance between primary cancers and breast cancer brain metastases (BCBM), which significantly affected therapeutic decision-making. But it was not always feasible to obtain BCBM tissues. The aim of the present study w...
Main Authors: | , , , , , , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Frontiers Media S.A.
2022-06-01
|
Series: | Frontiers in Oncology |
Subjects: | |
Online Access: | https://www.frontiersin.org/articles/10.3389/fonc.2022.878388/full |
_version_ | 1811244493688537088 |
---|---|
author | Xiao Luo Xiao Luo Hui Xie Hui Xie Yadi Yang Yadi Yang Cheng Zhang Cheng Zhang Yijun Zhang Yijun Zhang Yue Li Yue Li Qiuxia Yang Qiuxia Yang Deling Wang Deling Wang Yingwei Luo Yingwei Luo Zhijun Mai Zhijun Mai Chuanmiao Xie Chuanmiao Xie Shaohan Yin Shaohan Yin |
author_facet | Xiao Luo Xiao Luo Hui Xie Hui Xie Yadi Yang Yadi Yang Cheng Zhang Cheng Zhang Yijun Zhang Yijun Zhang Yue Li Yue Li Qiuxia Yang Qiuxia Yang Deling Wang Deling Wang Yingwei Luo Yingwei Luo Zhijun Mai Zhijun Mai Chuanmiao Xie Chuanmiao Xie Shaohan Yin Shaohan Yin |
author_sort | Xiao Luo |
collection | DOAJ |
description | BackgroundsA significant proportion of breast cancer patients showed receptor discordance between primary cancers and breast cancer brain metastases (BCBM), which significantly affected therapeutic decision-making. But it was not always feasible to obtain BCBM tissues. The aim of the present study was to analyze the receptor status of primary breast cancer and matched brain metastases and establish radiomic signatures to predict the receptor status of BCBM.MethodsThe receptor status of 80 matched primary breast cancers and resected brain metastases were retrospectively analyzed. Radiomic features were extracted using preoperative brain MRI (contrast-enhanced T1-weighted imaging, T2-weighted imaging, T2 fluid-attenuated inversion recovery, and combinations of these sequences) collected from 68 patients (45 and 23 for training and test sets, respectively) with BCBM excision. Using least absolute shrinkage selection operator and logistic regression model, the machine learning-based radiomic signatures were constructed to predict the estrogen receptor (ER), progesterone receptor (PR), and human epidermal growth factor receptor 2 (HER2) status of BCBM.ResultsDiscordance between the primary cancer and BCBM was found in 51.3% of patients, with 27.5%, 27.5%, and 5.0% discordance for ER, PR, and HER2, respectively. Loss of receptor expression was more common (33.8%) than gain (18.8%). The radiomic signatures built using combination sequences had the best performance in the training and test sets. The combination model yielded AUCs of 0.89, 0.88, and 0.87, classification sensitivities of 71.4%, 90%, and 87.5%, specificities of 81.2%, 76.9%, and 71.4%, and accuracies of 78.3%, 82.6%, and 82.6% for ER, PR, and HER2, respectively, in the test set.ConclusionsReceptor conversion in BCBM was common, and radiomic signatures show potential for noninvasively predicting BCBM receptor status. |
first_indexed | 2024-04-12T14:26:02Z |
format | Article |
id | doaj.art-31382cc8fdc64e9a96157832a5e83516 |
institution | Directory Open Access Journal |
issn | 2234-943X |
language | English |
last_indexed | 2024-04-12T14:26:02Z |
publishDate | 2022-06-01 |
publisher | Frontiers Media S.A. |
record_format | Article |
series | Frontiers in Oncology |
spelling | doaj.art-31382cc8fdc64e9a96157832a5e835162022-12-22T03:29:26ZengFrontiers Media S.A.Frontiers in Oncology2234-943X2022-06-011210.3389/fonc.2022.878388878388Radiomic Signatures for Predicting Receptor Status in Breast Cancer Brain MetastasesXiao Luo0Xiao Luo1Hui Xie2Hui Xie3Yadi Yang4Yadi Yang5Cheng Zhang6Cheng Zhang7Yijun Zhang8Yijun Zhang9Yue Li10Yue Li11Qiuxia Yang12Qiuxia Yang13Deling Wang14Deling Wang15Yingwei Luo16Yingwei Luo17Zhijun Mai18Zhijun Mai19Chuanmiao Xie20Chuanmiao Xie21Shaohan Yin22Shaohan Yin23State Key Laboratory of Oncology in South China, Collaborative Innovation Center for Cancer Medicine, Sun Yat-sen University Cancer Center, Guangzhou, ChinaDepartment of Radiology, Sun Yat-Sen University Cancer Center, Guangzhou, ChinaState Key Laboratory of Oncology in South China, Collaborative Innovation Center for Cancer Medicine, Sun Yat-sen University Cancer Center, Guangzhou, ChinaDepartment of Radiology, Sun Yat-Sen University Cancer Center, Guangzhou, ChinaState Key Laboratory of Oncology in South China, Collaborative Innovation Center for Cancer Medicine, Sun Yat-sen University Cancer Center, Guangzhou, ChinaDepartment of Radiology, Sun Yat-Sen University Cancer Center, Guangzhou, ChinaState Key Laboratory of Oncology in South China, Collaborative Innovation Center for Cancer Medicine, Sun Yat-sen University Cancer Center, Guangzhou, ChinaDepartment of Radiology, Sun Yat-Sen University Cancer Center, Guangzhou, ChinaState Key Laboratory of Oncology in South China, Collaborative Innovation Center for Cancer Medicine, Sun Yat-sen University Cancer Center, Guangzhou, ChinaDepartment of Pathology, Sun Yat-Sen University Cancer Center, Guangzhou, ChinaState Key Laboratory of Oncology in South China, Collaborative Innovation Center for Cancer Medicine, Sun Yat-sen University Cancer Center, Guangzhou, ChinaDepartment of Molecular Diagnostics, Sun Yat-Sen University Cancer Center, Guangzhou, ChinaState Key Laboratory of Oncology in South China, Collaborative Innovation Center for Cancer Medicine, Sun Yat-sen University Cancer Center, Guangzhou, ChinaDepartment of Radiology, Sun Yat-Sen University Cancer Center, Guangzhou, ChinaState Key Laboratory of Oncology in South China, Collaborative Innovation Center for Cancer Medicine, Sun Yat-sen University Cancer Center, Guangzhou, ChinaDepartment of Radiology, Sun Yat-Sen University Cancer Center, Guangzhou, ChinaState Key Laboratory of Oncology in South China, Collaborative Innovation Center for Cancer Medicine, Sun Yat-sen University Cancer Center, Guangzhou, ChinaDepartment of Radiology, Sun Yat-Sen University Cancer Center, Guangzhou, ChinaState Key Laboratory of Oncology in South China, Collaborative Innovation Center for Cancer Medicine, Sun Yat-sen University Cancer Center, Guangzhou, ChinaDepartment of Radiology, Sun Yat-Sen University Cancer Center, Guangzhou, ChinaState Key Laboratory of Oncology in South China, Collaborative Innovation Center for Cancer Medicine, Sun Yat-sen University Cancer Center, Guangzhou, ChinaDepartment of Radiology, Sun Yat-Sen University Cancer Center, Guangzhou, ChinaState Key Laboratory of Oncology in South China, Collaborative Innovation Center for Cancer Medicine, Sun Yat-sen University Cancer Center, Guangzhou, ChinaDepartment of Radiology, Sun Yat-Sen University Cancer Center, Guangzhou, ChinaBackgroundsA significant proportion of breast cancer patients showed receptor discordance between primary cancers and breast cancer brain metastases (BCBM), which significantly affected therapeutic decision-making. But it was not always feasible to obtain BCBM tissues. The aim of the present study was to analyze the receptor status of primary breast cancer and matched brain metastases and establish radiomic signatures to predict the receptor status of BCBM.MethodsThe receptor status of 80 matched primary breast cancers and resected brain metastases were retrospectively analyzed. Radiomic features were extracted using preoperative brain MRI (contrast-enhanced T1-weighted imaging, T2-weighted imaging, T2 fluid-attenuated inversion recovery, and combinations of these sequences) collected from 68 patients (45 and 23 for training and test sets, respectively) with BCBM excision. Using least absolute shrinkage selection operator and logistic regression model, the machine learning-based radiomic signatures were constructed to predict the estrogen receptor (ER), progesterone receptor (PR), and human epidermal growth factor receptor 2 (HER2) status of BCBM.ResultsDiscordance between the primary cancer and BCBM was found in 51.3% of patients, with 27.5%, 27.5%, and 5.0% discordance for ER, PR, and HER2, respectively. Loss of receptor expression was more common (33.8%) than gain (18.8%). The radiomic signatures built using combination sequences had the best performance in the training and test sets. The combination model yielded AUCs of 0.89, 0.88, and 0.87, classification sensitivities of 71.4%, 90%, and 87.5%, specificities of 81.2%, 76.9%, and 71.4%, and accuracies of 78.3%, 82.6%, and 82.6% for ER, PR, and HER2, respectively, in the test set.ConclusionsReceptor conversion in BCBM was common, and radiomic signatures show potential for noninvasively predicting BCBM receptor status.https://www.frontiersin.org/articles/10.3389/fonc.2022.878388/fullbreast neoplasmsreceptorbrain neoplasmsradiomicsmagnetic resonance imaging |
spellingShingle | Xiao Luo Xiao Luo Hui Xie Hui Xie Yadi Yang Yadi Yang Cheng Zhang Cheng Zhang Yijun Zhang Yijun Zhang Yue Li Yue Li Qiuxia Yang Qiuxia Yang Deling Wang Deling Wang Yingwei Luo Yingwei Luo Zhijun Mai Zhijun Mai Chuanmiao Xie Chuanmiao Xie Shaohan Yin Shaohan Yin Radiomic Signatures for Predicting Receptor Status in Breast Cancer Brain Metastases Frontiers in Oncology breast neoplasms receptor brain neoplasms radiomics magnetic resonance imaging |
title | Radiomic Signatures for Predicting Receptor Status in Breast Cancer Brain Metastases |
title_full | Radiomic Signatures for Predicting Receptor Status in Breast Cancer Brain Metastases |
title_fullStr | Radiomic Signatures for Predicting Receptor Status in Breast Cancer Brain Metastases |
title_full_unstemmed | Radiomic Signatures for Predicting Receptor Status in Breast Cancer Brain Metastases |
title_short | Radiomic Signatures for Predicting Receptor Status in Breast Cancer Brain Metastases |
title_sort | radiomic signatures for predicting receptor status in breast cancer brain metastases |
topic | breast neoplasms receptor brain neoplasms radiomics magnetic resonance imaging |
url | https://www.frontiersin.org/articles/10.3389/fonc.2022.878388/full |
work_keys_str_mv | AT xiaoluo radiomicsignaturesforpredictingreceptorstatusinbreastcancerbrainmetastases AT xiaoluo radiomicsignaturesforpredictingreceptorstatusinbreastcancerbrainmetastases AT huixie radiomicsignaturesforpredictingreceptorstatusinbreastcancerbrainmetastases AT huixie radiomicsignaturesforpredictingreceptorstatusinbreastcancerbrainmetastases AT yadiyang radiomicsignaturesforpredictingreceptorstatusinbreastcancerbrainmetastases AT yadiyang radiomicsignaturesforpredictingreceptorstatusinbreastcancerbrainmetastases AT chengzhang radiomicsignaturesforpredictingreceptorstatusinbreastcancerbrainmetastases AT chengzhang radiomicsignaturesforpredictingreceptorstatusinbreastcancerbrainmetastases AT yijunzhang radiomicsignaturesforpredictingreceptorstatusinbreastcancerbrainmetastases AT yijunzhang radiomicsignaturesforpredictingreceptorstatusinbreastcancerbrainmetastases AT yueli radiomicsignaturesforpredictingreceptorstatusinbreastcancerbrainmetastases AT yueli radiomicsignaturesforpredictingreceptorstatusinbreastcancerbrainmetastases AT qiuxiayang radiomicsignaturesforpredictingreceptorstatusinbreastcancerbrainmetastases AT qiuxiayang radiomicsignaturesforpredictingreceptorstatusinbreastcancerbrainmetastases AT delingwang radiomicsignaturesforpredictingreceptorstatusinbreastcancerbrainmetastases AT delingwang radiomicsignaturesforpredictingreceptorstatusinbreastcancerbrainmetastases AT yingweiluo radiomicsignaturesforpredictingreceptorstatusinbreastcancerbrainmetastases AT yingweiluo radiomicsignaturesforpredictingreceptorstatusinbreastcancerbrainmetastases AT zhijunmai radiomicsignaturesforpredictingreceptorstatusinbreastcancerbrainmetastases AT zhijunmai radiomicsignaturesforpredictingreceptorstatusinbreastcancerbrainmetastases AT chuanmiaoxie radiomicsignaturesforpredictingreceptorstatusinbreastcancerbrainmetastases AT chuanmiaoxie radiomicsignaturesforpredictingreceptorstatusinbreastcancerbrainmetastases AT shaohanyin radiomicsignaturesforpredictingreceptorstatusinbreastcancerbrainmetastases AT shaohanyin radiomicsignaturesforpredictingreceptorstatusinbreastcancerbrainmetastases |