Multiparametric <sup>18</sup>F-FDG PET/MRI-Based Radiomics for Prediction of Pathological Complete Response to Neoadjuvant Chemotherapy in Breast Cancer

Background: The aim of this study was to assess whether multiparametric <sup>18</sup>F-FDG PET/MRI-based radiomics analysis is able to predict pathological complete response in breast cancer patients and hence potentially enhance pretherapeutic patient stratification. Methods: A total of...

Full description

Bibliographic Details
Main Authors: Lale Umutlu, Julian Kirchner, Nils-Martin Bruckmann, Janna Morawitz, Gerald Antoch, Saskia Ting, Ann-Kathrin Bittner, Oliver Hoffmann, Lena Häberle, Eugen Ruckhäberle, Onofrio Antonio Catalano, Michal Chodyla, Johannes Grueneisen, Harald H. Quick, Wolfgang P. Fendler, Christoph Rischpler, Ken Herrmann, Peter Gibbs, Katja Pinker
Format: Article
Language:English
Published: MDPI AG 2022-03-01
Series:Cancers
Subjects:
Online Access:https://www.mdpi.com/2072-6694/14/7/1727
_version_ 1797440111406743552
author Lale Umutlu
Julian Kirchner
Nils-Martin Bruckmann
Janna Morawitz
Gerald Antoch
Saskia Ting
Ann-Kathrin Bittner
Oliver Hoffmann
Lena Häberle
Eugen Ruckhäberle
Onofrio Antonio Catalano
Michal Chodyla
Johannes Grueneisen
Harald H. Quick
Wolfgang P. Fendler
Christoph Rischpler
Ken Herrmann
Peter Gibbs
Katja Pinker
author_facet Lale Umutlu
Julian Kirchner
Nils-Martin Bruckmann
Janna Morawitz
Gerald Antoch
Saskia Ting
Ann-Kathrin Bittner
Oliver Hoffmann
Lena Häberle
Eugen Ruckhäberle
Onofrio Antonio Catalano
Michal Chodyla
Johannes Grueneisen
Harald H. Quick
Wolfgang P. Fendler
Christoph Rischpler
Ken Herrmann
Peter Gibbs
Katja Pinker
author_sort Lale Umutlu
collection DOAJ
description Background: The aim of this study was to assess whether multiparametric <sup>18</sup>F-FDG PET/MRI-based radiomics analysis is able to predict pathological complete response in breast cancer patients and hence potentially enhance pretherapeutic patient stratification. Methods: A total of 73 female patients (mean age 49 years; range 27–77 years) with newly diagnosed, therapy-naive breast cancer underwent simultaneous <sup>18</sup>F-FDG PET/MRI and were included in this retrospective study. All PET/MRI datasets were imported to dedicated software (ITK-SNAP v. 3.6.0) for lesion annotation using a semi-automated method. Pretreatment biopsy specimens were used to determine tumor histology, tumor and nuclear grades, and immunohistochemical status. Histopathological results from surgical tumor specimens were used as the reference standard to distinguish between complete pathological response (pCR) and noncomplete pathological response. An elastic net was employed to select the most important radiomic features prior to model development. Sensitivity, specificity, positive predictive value, negative predictive value, and accuracy were calculated for each model. Results: The best results in terms of AUCs and NPV for predicting complete pathological response in the entire cohort were obtained by the combination of all MR sequences and PET (0.8 and 79.5%, respectively), and no significant differences from the other models were observed. In further subgroup analyses, combining all MR and PET data, the best AUC (0.94) for predicting complete pathologic response was obtained in the HR+/HER2− group. No difference between results with/without the inclusion of PET characteristics was observed in the TN/HER2+ group, each leading to an AUC of 0.92 for all MR and all MR + PET datasets. Conclusion: <sup>18</sup>F-FDG PET/MRI enables comprehensive high-quality radiomics analysis for the prediction of pCR in breast cancer patients, especially in those with HR+/HER2− receptor status.
first_indexed 2024-03-09T12:02:25Z
format Article
id doaj.art-1f92b4840d364cf7a627c7b577851702
institution Directory Open Access Journal
issn 2072-6694
language English
last_indexed 2024-03-09T12:02:25Z
publishDate 2022-03-01
publisher MDPI AG
record_format Article
series Cancers
spelling doaj.art-1f92b4840d364cf7a627c7b5778517022023-11-30T23:01:13ZengMDPI AGCancers2072-66942022-03-01147172710.3390/cancers14071727Multiparametric <sup>18</sup>F-FDG PET/MRI-Based Radiomics for Prediction of Pathological Complete Response to Neoadjuvant Chemotherapy in Breast CancerLale Umutlu0Julian Kirchner1Nils-Martin Bruckmann2Janna Morawitz3Gerald Antoch4Saskia Ting5Ann-Kathrin Bittner6Oliver Hoffmann7Lena Häberle8Eugen Ruckhäberle9Onofrio Antonio Catalano10Michal Chodyla11Johannes Grueneisen12Harald H. Quick13Wolfgang P. Fendler14Christoph Rischpler15Ken Herrmann16Peter Gibbs17Katja Pinker18Department of Diagnostic and Interventional Radiology and Neuroradiology, University Hospital Essen, University of Duisburg-Essen, 45147 Essen, GermanyDepartment of Diagnostic and Interventional Radiology, University Dusseldorf, Medical Faculty, 40225 Dusseldorf, GermanyDepartment of Diagnostic and Interventional Radiology, University Dusseldorf, Medical Faculty, 40225 Dusseldorf, GermanyDepartment of Diagnostic and Interventional Radiology, University Dusseldorf, Medical Faculty, 40225 Dusseldorf, GermanyDepartment of Diagnostic and Interventional Radiology, University Dusseldorf, Medical Faculty, 40225 Dusseldorf, GermanyInstitute of Pathology, University Hospital Essen, West German Cancer Center, University Duisburg-Essen and the German Cancer Consortium (DKTK), 45147 Essen, GermanyDepartment Gynecology and Obstetrics, University Hospital Essen, University of Duisburg-Essen, 45147 Essen, GermanyDepartment Gynecology and Obstetrics, University Hospital Essen, University of Duisburg-Essen, 45147 Essen, GermanyInstitute of Pathology, Medical Faculty, Heinrich-Heine-University and University Hospital Duesseldorf, 40225 Duesseldorf, GermanyDepartment of Gynecology, University Dusseldorf, Medical Faculty, 40225 Dusseldorf, GermanyDivision of Abdominal Radiology, Massachusetts General Hospital, Boston, MA 02129, USADepartment of Diagnostic and Interventional Radiology and Neuroradiology, University Hospital Essen, University of Duisburg-Essen, 45147 Essen, GermanyDepartment of Diagnostic and Interventional Radiology and Neuroradiology, University Hospital Essen, University of Duisburg-Essen, 45147 Essen, GermanyErwin L. Hahn Institute for Magnetic Resonance Imaging, University of Duisburg-Essen, 45141 Essen, GermanyDepartment of Nuclear Medicine, University of Duisburg-Essen and German Cancer Consortium (DKTK)-University Hospital Essen, 45147 Essen, GermanyDepartment of Nuclear Medicine, University of Duisburg-Essen and German Cancer Consortium (DKTK)-University Hospital Essen, 45147 Essen, GermanyDepartment of Nuclear Medicine, University of Duisburg-Essen and German Cancer Consortium (DKTK)-University Hospital Essen, 45147 Essen, GermanyDepartment of Radiology, Memorial Sloan Kettering Cancer Center, New York, NY 10065, USADepartment of Radiology, Memorial Sloan Kettering Cancer Center, New York, NY 10065, USABackground: The aim of this study was to assess whether multiparametric <sup>18</sup>F-FDG PET/MRI-based radiomics analysis is able to predict pathological complete response in breast cancer patients and hence potentially enhance pretherapeutic patient stratification. Methods: A total of 73 female patients (mean age 49 years; range 27–77 years) with newly diagnosed, therapy-naive breast cancer underwent simultaneous <sup>18</sup>F-FDG PET/MRI and were included in this retrospective study. All PET/MRI datasets were imported to dedicated software (ITK-SNAP v. 3.6.0) for lesion annotation using a semi-automated method. Pretreatment biopsy specimens were used to determine tumor histology, tumor and nuclear grades, and immunohistochemical status. Histopathological results from surgical tumor specimens were used as the reference standard to distinguish between complete pathological response (pCR) and noncomplete pathological response. An elastic net was employed to select the most important radiomic features prior to model development. Sensitivity, specificity, positive predictive value, negative predictive value, and accuracy were calculated for each model. Results: The best results in terms of AUCs and NPV for predicting complete pathological response in the entire cohort were obtained by the combination of all MR sequences and PET (0.8 and 79.5%, respectively), and no significant differences from the other models were observed. In further subgroup analyses, combining all MR and PET data, the best AUC (0.94) for predicting complete pathologic response was obtained in the HR+/HER2− group. No difference between results with/without the inclusion of PET characteristics was observed in the TN/HER2+ group, each leading to an AUC of 0.92 for all MR and all MR + PET datasets. Conclusion: <sup>18</sup>F-FDG PET/MRI enables comprehensive high-quality radiomics analysis for the prediction of pCR in breast cancer patients, especially in those with HR+/HER2− receptor status.https://www.mdpi.com/2072-6694/14/7/1727multiparametric <sup>18</sup>F-FDG PET/MRIradiomicsbreast cancerradiomics-based prediction of pathologic complete response
spellingShingle Lale Umutlu
Julian Kirchner
Nils-Martin Bruckmann
Janna Morawitz
Gerald Antoch
Saskia Ting
Ann-Kathrin Bittner
Oliver Hoffmann
Lena Häberle
Eugen Ruckhäberle
Onofrio Antonio Catalano
Michal Chodyla
Johannes Grueneisen
Harald H. Quick
Wolfgang P. Fendler
Christoph Rischpler
Ken Herrmann
Peter Gibbs
Katja Pinker
Multiparametric <sup>18</sup>F-FDG PET/MRI-Based Radiomics for Prediction of Pathological Complete Response to Neoadjuvant Chemotherapy in Breast Cancer
Cancers
multiparametric <sup>18</sup>F-FDG PET/MRI
radiomics
breast cancer
radiomics-based prediction of pathologic complete response
title Multiparametric <sup>18</sup>F-FDG PET/MRI-Based Radiomics for Prediction of Pathological Complete Response to Neoadjuvant Chemotherapy in Breast Cancer
title_full Multiparametric <sup>18</sup>F-FDG PET/MRI-Based Radiomics for Prediction of Pathological Complete Response to Neoadjuvant Chemotherapy in Breast Cancer
title_fullStr Multiparametric <sup>18</sup>F-FDG PET/MRI-Based Radiomics for Prediction of Pathological Complete Response to Neoadjuvant Chemotherapy in Breast Cancer
title_full_unstemmed Multiparametric <sup>18</sup>F-FDG PET/MRI-Based Radiomics for Prediction of Pathological Complete Response to Neoadjuvant Chemotherapy in Breast Cancer
title_short Multiparametric <sup>18</sup>F-FDG PET/MRI-Based Radiomics for Prediction of Pathological Complete Response to Neoadjuvant Chemotherapy in Breast Cancer
title_sort multiparametric sup 18 sup f fdg pet mri based radiomics for prediction of pathological complete response to neoadjuvant chemotherapy in breast cancer
topic multiparametric <sup>18</sup>F-FDG PET/MRI
radiomics
breast cancer
radiomics-based prediction of pathologic complete response
url https://www.mdpi.com/2072-6694/14/7/1727
work_keys_str_mv AT laleumutlu multiparametricsup18supffdgpetmribasedradiomicsforpredictionofpathologicalcompleteresponsetoneoadjuvantchemotherapyinbreastcancer
AT juliankirchner multiparametricsup18supffdgpetmribasedradiomicsforpredictionofpathologicalcompleteresponsetoneoadjuvantchemotherapyinbreastcancer
AT nilsmartinbruckmann multiparametricsup18supffdgpetmribasedradiomicsforpredictionofpathologicalcompleteresponsetoneoadjuvantchemotherapyinbreastcancer
AT jannamorawitz multiparametricsup18supffdgpetmribasedradiomicsforpredictionofpathologicalcompleteresponsetoneoadjuvantchemotherapyinbreastcancer
AT geraldantoch multiparametricsup18supffdgpetmribasedradiomicsforpredictionofpathologicalcompleteresponsetoneoadjuvantchemotherapyinbreastcancer
AT saskiating multiparametricsup18supffdgpetmribasedradiomicsforpredictionofpathologicalcompleteresponsetoneoadjuvantchemotherapyinbreastcancer
AT annkathrinbittner multiparametricsup18supffdgpetmribasedradiomicsforpredictionofpathologicalcompleteresponsetoneoadjuvantchemotherapyinbreastcancer
AT oliverhoffmann multiparametricsup18supffdgpetmribasedradiomicsforpredictionofpathologicalcompleteresponsetoneoadjuvantchemotherapyinbreastcancer
AT lenahaberle multiparametricsup18supffdgpetmribasedradiomicsforpredictionofpathologicalcompleteresponsetoneoadjuvantchemotherapyinbreastcancer
AT eugenruckhaberle multiparametricsup18supffdgpetmribasedradiomicsforpredictionofpathologicalcompleteresponsetoneoadjuvantchemotherapyinbreastcancer
AT onofrioantoniocatalano multiparametricsup18supffdgpetmribasedradiomicsforpredictionofpathologicalcompleteresponsetoneoadjuvantchemotherapyinbreastcancer
AT michalchodyla multiparametricsup18supffdgpetmribasedradiomicsforpredictionofpathologicalcompleteresponsetoneoadjuvantchemotherapyinbreastcancer
AT johannesgrueneisen multiparametricsup18supffdgpetmribasedradiomicsforpredictionofpathologicalcompleteresponsetoneoadjuvantchemotherapyinbreastcancer
AT haraldhquick multiparametricsup18supffdgpetmribasedradiomicsforpredictionofpathologicalcompleteresponsetoneoadjuvantchemotherapyinbreastcancer
AT wolfgangpfendler multiparametricsup18supffdgpetmribasedradiomicsforpredictionofpathologicalcompleteresponsetoneoadjuvantchemotherapyinbreastcancer
AT christophrischpler multiparametricsup18supffdgpetmribasedradiomicsforpredictionofpathologicalcompleteresponsetoneoadjuvantchemotherapyinbreastcancer
AT kenherrmann multiparametricsup18supffdgpetmribasedradiomicsforpredictionofpathologicalcompleteresponsetoneoadjuvantchemotherapyinbreastcancer
AT petergibbs multiparametricsup18supffdgpetmribasedradiomicsforpredictionofpathologicalcompleteresponsetoneoadjuvantchemotherapyinbreastcancer
AT katjapinker multiparametricsup18supffdgpetmribasedradiomicsforpredictionofpathologicalcompleteresponsetoneoadjuvantchemotherapyinbreastcancer