Intra- and Peritumoral Radiomics Model Based on Early DCE-MRI for Preoperative Prediction of Molecular Subtypes in Invasive Ductal Breast Carcinoma: A Multitask Machine Learning Study
PurposeThe aim of this study is to investigate radiomics features extracted from the optimal peritumoral region and the intratumoral area on the early phase of dynamic contrast-enhanced MRI (DCE-MRI) for predicting molecular subtypes of invasive ductal breast carcinoma (IDBC).MethodsA total of 422 I...
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.2022.905551/full |
_version_ | 1811236152279040000 |
---|---|
author | Shuhai Zhang Xiaolei Wang Zhao Yang Yun Zhu Nannan Zhao Yang Li Jie He Haitao Sun Haitao Sun Zongyu Xie |
author_facet | Shuhai Zhang Xiaolei Wang Zhao Yang Yun Zhu Nannan Zhao Yang Li Jie He Haitao Sun Haitao Sun Zongyu Xie |
author_sort | Shuhai Zhang |
collection | DOAJ |
description | PurposeThe aim of this study is to investigate radiomics features extracted from the optimal peritumoral region and the intratumoral area on the early phase of dynamic contrast-enhanced MRI (DCE-MRI) for predicting molecular subtypes of invasive ductal breast carcinoma (IDBC).MethodsA total of 422 IDBC patients with immunohistochemical and fluorescence in situ hybridization results from two hospitals (Center 1: 327 cases, Center 2: 95 cases) who underwent preoperative DCE-MRI were retrospectively enrolled. After image preprocessing, radiomic features were extracted from the intratumoral area and four peritumoral regions on DCE-MRI from two centers, and selected the optimal peritumoral region. Based on the intratumoral, peritumoral radiomics features, and clinical–radiological characteristics, five radiomics models were constructed through support vector machine (SVM) in multiple classification tasks related to molecular subtypes and visualized by nomogram. The performance of radiomics models was evaluated by receiver operating characteristic curves, confusion matrix, calibration curves, and decision curve analysis.ResultsA 6-mm peritumoral size was defined the optimal peritumoral region in classification tasks of hormone receptor (HR)-positive vs others, triple-negative breast cancer (TNBC) vs others, and HR-positive vs human epidermal growth factor receptor 2 (HER2)-enriched vs TNBC, and 8 mm was applied in HER2-enriched vs others. The combined clinical–radiological and radiomics models in three binary classification tasks (HR-positive vs others, HER2-enriched vs others, TNBC vs others) obtained optimal performance with AUCs of 0.838, 0.848, and 0.930 in the training cohort, respectively; 0.827, 0.813, and 0.879 in the internal test cohort, respectively; and 0.791, 0.707, and 0.852 in the external test cohort, respectively.ConclusionRadiomics features in the intratumoral and peritumoral regions of IDBC on DCE-MRI had a potential to predict the HR-positive, HER2-enriched, and TNBC molecular subtypes preoperatively. |
first_indexed | 2024-04-12T12:03:57Z |
format | Article |
id | doaj.art-d2b2da5cbd3a4afd9f7849b1b7881146 |
institution | Directory Open Access Journal |
issn | 2234-943X |
language | English |
last_indexed | 2024-04-12T12:03:57Z |
publishDate | 2022-06-01 |
publisher | Frontiers Media S.A. |
record_format | Article |
series | Frontiers in Oncology |
spelling | doaj.art-d2b2da5cbd3a4afd9f7849b1b78811462022-12-22T03:33:47ZengFrontiers Media S.A.Frontiers in Oncology2234-943X2022-06-011210.3389/fonc.2022.905551905551Intra- and Peritumoral Radiomics Model Based on Early DCE-MRI for Preoperative Prediction of Molecular Subtypes in Invasive Ductal Breast Carcinoma: A Multitask Machine Learning StudyShuhai Zhang0Xiaolei Wang1Zhao Yang2Yun Zhu3Nannan Zhao4Yang Li5Jie He6Haitao Sun7Haitao Sun8Zongyu Xie9Department of Radiology, The First Affiliated Hospital of Bengbu Medical College, Bengbu, ChinaDepartment of Radiology, The First Affiliated Hospital of Bengbu Medical College, Bengbu, ChinaDepartment of Radiology, The First Affiliated Hospital of Bengbu Medical College, Bengbu, ChinaDepartment of Radiology, The First Affiliated Hospital of Bengbu Medical College, Bengbu, ChinaDepartment of Radiology, The First Affiliated Hospital of Bengbu Medical College, Bengbu, ChinaDepartment of Radiology, The First Affiliated Hospital of Bengbu Medical College, Bengbu, ChinaDepartment of Radiology, Sir Run Run Shaw Hospital, Zhejiang University School of Medicine, Hangzhou, ChinaDepartment of Radiology, Zhongshan Hospital, Fudan University, Shanghai, ChinaShanghai Institute of Medical Imaging, Department of Cancer Center, Zhongshan Hospital, Fudan University, Shanghai, ChinaDepartment of Radiology, The First Affiliated Hospital of Bengbu Medical College, Bengbu, ChinaPurposeThe aim of this study is to investigate radiomics features extracted from the optimal peritumoral region and the intratumoral area on the early phase of dynamic contrast-enhanced MRI (DCE-MRI) for predicting molecular subtypes of invasive ductal breast carcinoma (IDBC).MethodsA total of 422 IDBC patients with immunohistochemical and fluorescence in situ hybridization results from two hospitals (Center 1: 327 cases, Center 2: 95 cases) who underwent preoperative DCE-MRI were retrospectively enrolled. After image preprocessing, radiomic features were extracted from the intratumoral area and four peritumoral regions on DCE-MRI from two centers, and selected the optimal peritumoral region. Based on the intratumoral, peritumoral radiomics features, and clinical–radiological characteristics, five radiomics models were constructed through support vector machine (SVM) in multiple classification tasks related to molecular subtypes and visualized by nomogram. The performance of radiomics models was evaluated by receiver operating characteristic curves, confusion matrix, calibration curves, and decision curve analysis.ResultsA 6-mm peritumoral size was defined the optimal peritumoral region in classification tasks of hormone receptor (HR)-positive vs others, triple-negative breast cancer (TNBC) vs others, and HR-positive vs human epidermal growth factor receptor 2 (HER2)-enriched vs TNBC, and 8 mm was applied in HER2-enriched vs others. The combined clinical–radiological and radiomics models in three binary classification tasks (HR-positive vs others, HER2-enriched vs others, TNBC vs others) obtained optimal performance with AUCs of 0.838, 0.848, and 0.930 in the training cohort, respectively; 0.827, 0.813, and 0.879 in the internal test cohort, respectively; and 0.791, 0.707, and 0.852 in the external test cohort, respectively.ConclusionRadiomics features in the intratumoral and peritumoral regions of IDBC on DCE-MRI had a potential to predict the HR-positive, HER2-enriched, and TNBC molecular subtypes preoperatively.https://www.frontiersin.org/articles/10.3389/fonc.2022.905551/fullbreast cancermagnetic resonance imagingdynamic contrast-enhanced imagingradiomicsmolecular subtype |
spellingShingle | Shuhai Zhang Xiaolei Wang Zhao Yang Yun Zhu Nannan Zhao Yang Li Jie He Haitao Sun Haitao Sun Zongyu Xie Intra- and Peritumoral Radiomics Model Based on Early DCE-MRI for Preoperative Prediction of Molecular Subtypes in Invasive Ductal Breast Carcinoma: A Multitask Machine Learning Study Frontiers in Oncology breast cancer magnetic resonance imaging dynamic contrast-enhanced imaging radiomics molecular subtype |
title | Intra- and Peritumoral Radiomics Model Based on Early DCE-MRI for Preoperative Prediction of Molecular Subtypes in Invasive Ductal Breast Carcinoma: A Multitask Machine Learning Study |
title_full | Intra- and Peritumoral Radiomics Model Based on Early DCE-MRI for Preoperative Prediction of Molecular Subtypes in Invasive Ductal Breast Carcinoma: A Multitask Machine Learning Study |
title_fullStr | Intra- and Peritumoral Radiomics Model Based on Early DCE-MRI for Preoperative Prediction of Molecular Subtypes in Invasive Ductal Breast Carcinoma: A Multitask Machine Learning Study |
title_full_unstemmed | Intra- and Peritumoral Radiomics Model Based on Early DCE-MRI for Preoperative Prediction of Molecular Subtypes in Invasive Ductal Breast Carcinoma: A Multitask Machine Learning Study |
title_short | Intra- and Peritumoral Radiomics Model Based on Early DCE-MRI for Preoperative Prediction of Molecular Subtypes in Invasive Ductal Breast Carcinoma: A Multitask Machine Learning Study |
title_sort | intra and peritumoral radiomics model based on early dce mri for preoperative prediction of molecular subtypes in invasive ductal breast carcinoma a multitask machine learning study |
topic | breast cancer magnetic resonance imaging dynamic contrast-enhanced imaging radiomics molecular subtype |
url | https://www.frontiersin.org/articles/10.3389/fonc.2022.905551/full |
work_keys_str_mv | AT shuhaizhang intraandperitumoralradiomicsmodelbasedonearlydcemriforpreoperativepredictionofmolecularsubtypesininvasiveductalbreastcarcinomaamultitaskmachinelearningstudy AT xiaoleiwang intraandperitumoralradiomicsmodelbasedonearlydcemriforpreoperativepredictionofmolecularsubtypesininvasiveductalbreastcarcinomaamultitaskmachinelearningstudy AT zhaoyang intraandperitumoralradiomicsmodelbasedonearlydcemriforpreoperativepredictionofmolecularsubtypesininvasiveductalbreastcarcinomaamultitaskmachinelearningstudy AT yunzhu intraandperitumoralradiomicsmodelbasedonearlydcemriforpreoperativepredictionofmolecularsubtypesininvasiveductalbreastcarcinomaamultitaskmachinelearningstudy AT nannanzhao intraandperitumoralradiomicsmodelbasedonearlydcemriforpreoperativepredictionofmolecularsubtypesininvasiveductalbreastcarcinomaamultitaskmachinelearningstudy AT yangli intraandperitumoralradiomicsmodelbasedonearlydcemriforpreoperativepredictionofmolecularsubtypesininvasiveductalbreastcarcinomaamultitaskmachinelearningstudy AT jiehe intraandperitumoralradiomicsmodelbasedonearlydcemriforpreoperativepredictionofmolecularsubtypesininvasiveductalbreastcarcinomaamultitaskmachinelearningstudy AT haitaosun intraandperitumoralradiomicsmodelbasedonearlydcemriforpreoperativepredictionofmolecularsubtypesininvasiveductalbreastcarcinomaamultitaskmachinelearningstudy AT haitaosun intraandperitumoralradiomicsmodelbasedonearlydcemriforpreoperativepredictionofmolecularsubtypesininvasiveductalbreastcarcinomaamultitaskmachinelearningstudy AT zongyuxie intraandperitumoralradiomicsmodelbasedonearlydcemriforpreoperativepredictionofmolecularsubtypesininvasiveductalbreastcarcinomaamultitaskmachinelearningstudy |