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

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

doi:10.3390/cancers14071727

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

Cancers (Basel). 2022 Mar 29;14(7):1727. doi: 10.3390/cancers14071727.

Authors

Lale Umutlu^{1

2}, Julian Kirchner³, Nils-Martin Bruckmann³, Janna Morawitz³, Gerald Antoch³, Saskia Ting⁴, Ann-Kathrin Bittner⁵, Oliver Hoffmann⁵, Lena Häberle⁶, Eugen Ruckhäberle⁷, Onofrio Antonio Catalano⁸, Michal Chodyla¹, Johannes Grueneisen¹, Harald H Quick^{9

10}, Wolfgang P Fendler², Christoph Rischpler², Ken Herrmann², Peter Gibbs¹¹, Katja Pinker¹¹

Affiliations

¹ Department of Diagnostic and Interventional Radiology and Neuroradiology, University Hospital Essen, University of Duisburg-Essen, 45147 Essen, Germany.
² Department of Nuclear Medicine, University of Duisburg-Essen and German Cancer Consortium (DKTK)-University Hospital Essen, 45147 Essen, Germany.
³ Department of Diagnostic and Interventional Radiology, University Dusseldorf, Medical Faculty, 40225 Dusseldorf, Germany.
⁴ Institute of Pathology, University Hospital Essen, West German Cancer Center, University Duisburg-Essen and the German Cancer Consortium (DKTK), 45147 Essen, Germany.
⁵ Department Gynecology and Obstetrics, University Hospital Essen, University of Duisburg-Essen, 45147 Essen, Germany.
⁶ Institute of Pathology, Medical Faculty, Heinrich-Heine-University and University Hospital Duesseldorf, 40225 Duesseldorf, Germany.
⁷ Department of Gynecology, University Dusseldorf, Medical Faculty, 40225 Dusseldorf, Germany.
⁸ Division of Abdominal Radiology, Massachusetts General Hospital, Boston, MA 02129, USA.
⁹ Erwin L. Hahn Institute for Magnetic Resonance Imaging, University of Duisburg-Essen, 45141 Essen, Germany.
¹⁰ High-Field and Hybrid MR Imaging, University Hospital Essen, University of Duisburg-Essen, 45147 Essen, Germany.
¹¹ Department of Radiology, Memorial Sloan Kettering Cancer Center, New York, NY 10065, USA.

Abstract

Background: The aim of this study was to assess whether multiparametric ¹⁸F-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 ¹⁸F-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: ¹⁸F-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.

Keywords: breast cancer; multiparametric 18F-FDG PET/MRI; radiomics; radiomics-based prediction of pathologic complete response.

Abstract

Grants and funding