1
|
Jannusch K, Dietzel F, Bruckmann NM, Morawitz J, Boschheidgen M, Minko P, Bittner AK, Mohrmann S, Quick HH, Herrmann K, Umutlu L, Antoch G, Rubbert C, Kirchner J, Caspers J. Prediction of therapy response of breast cancer patients with machine learning based on clinical data and imaging data derived from breast [ 18F]FDG-PET/MRI. Eur J Nucl Med Mol Imaging 2024; 51:1451-1461. [PMID: 38133687 PMCID: PMC10957677 DOI: 10.1007/s00259-023-06513-9] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/11/2023] [Accepted: 11/06/2023] [Indexed: 12/23/2023]
Abstract
PURPOSE To evaluate if a machine learning prediction model based on clinical and easily assessable imaging features derived from baseline breast [18F]FDG-PET/MRI staging can predict pathologic complete response (pCR) in patients with newly diagnosed breast cancer prior to neoadjuvant system therapy (NAST). METHODS Altogether 143 women with newly diagnosed breast cancer (54 ± 12 years) were retrospectively enrolled. All women underwent a breast [18F]FDG-PET/MRI, a histopathological workup of their breast cancer lesions and evaluation of clinical data. Fifty-six features derived from positron emission tomography (PET), magnetic resonance imaging (MRI), sociodemographic / anthropometric, histopathologic as well as clinical data were generated and used as input for an extreme Gradient Boosting model (XGBoost) to predict pCR. The model was evaluated in a five-fold nested-cross-validation incorporating independent hyper-parameter tuning within the inner loops to reduce the risk of overoptimistic estimations. Diagnostic model-performance was assessed by determining the area under the curve of the receiver operating characteristics curve (ROC-AUC), sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), and accuracy. Furthermore, feature importances of the XGBoost model were evaluated to assess which features contributed most to distinguish between pCR and non-pCR. RESULTS Nested-cross-validation yielded a mean ROC-AUC of 80.4 ± 6.0% for prediction of pCR. Mean sensitivity, specificity, PPV, and NPV of 54.5 ± 21.3%, 83.6 ± 4.2%, 63.6 ± 8.5%, and 77.6 ± 8.1% could be achieved. Histopathological data were the most important features for classification of the XGBoost model followed by PET, MRI, and sociodemographic/anthropometric features. CONCLUSION The evaluated multi-source XGBoost model shows promising results for reliably predicting pathological complete response in breast cancer patients prior to NAST. However, yielded performance is yet insufficient to be implemented in the clinical decision-making process.
Collapse
Affiliation(s)
- Kai Jannusch
- Department of Diagnostic and Interventional Radiology, Medical Faculty and University Hospital Düsseldorf, Heinrich-Heine-University Düsseldorf, Moorenstrasse 5, D-40225, Düsseldorf, Germany
| | - Frederic Dietzel
- Department of Diagnostic and Interventional Radiology, Medical Faculty and University Hospital Düsseldorf, Heinrich-Heine-University Düsseldorf, Moorenstrasse 5, D-40225, Düsseldorf, Germany
| | - Nils Martin Bruckmann
- Department of Diagnostic and Interventional Radiology, Medical Faculty and University Hospital Düsseldorf, Heinrich-Heine-University Düsseldorf, Moorenstrasse 5, D-40225, Düsseldorf, Germany
| | - Janna Morawitz
- Department of Diagnostic and Interventional Radiology, Medical Faculty and University Hospital Düsseldorf, Heinrich-Heine-University Düsseldorf, Moorenstrasse 5, D-40225, Düsseldorf, Germany
| | - Matthias Boschheidgen
- Department of Diagnostic and Interventional Radiology, Medical Faculty and University Hospital Düsseldorf, Heinrich-Heine-University Düsseldorf, Moorenstrasse 5, D-40225, Düsseldorf, Germany
| | - Peter Minko
- Department of Diagnostic and Interventional Radiology, Medical Faculty and University Hospital Düsseldorf, Heinrich-Heine-University Düsseldorf, Moorenstrasse 5, D-40225, Düsseldorf, Germany
| | - Ann-Kathrin Bittner
- Department Gynecology and Obstetrics, University Hospital Essen, University of Duisburg-Essen, D-45147, Essen, Germany
| | - Svjetlana Mohrmann
- Department of Gynecology, Medical Faculty and University Hospital Düsseldorf, Heinrich-Heine-University Düsseldorf, D-40225, Düsseldorf, Germany
| | - Harald H Quick
- High-Field and Hybrid MR Imaging, University Hospital Essen, University Duisburg-Essen, D-45147, Essen, Germany
- Erwin L. Hahn Institute for Magnetic Resonance Imaging, University Duisburg-Essen, D-45141, Essen, Germany
| | - Ken Herrmann
- Department of Nuclear Medicine, University of Duisburg-Essen, and German Cancer Consortium (DKTK)-University Hospital Essen, Essen, Germany
| | - Lale Umutlu
- Department of Diagnostic and Interventional Radiology and Neuroradiology, University Hospital Essen, University of Duisburg-Essen, D-45147, Essen, Germany
| | - Gerald Antoch
- Department of Diagnostic and Interventional Radiology, Medical Faculty and University Hospital Düsseldorf, Heinrich-Heine-University Düsseldorf, Moorenstrasse 5, D-40225, Düsseldorf, Germany
- Center for Integrated Oncology, Aachen Bonn Cologne Düsseldorf (CIO ABCD), Cologne, Germany
| | - Christian Rubbert
- Department of Diagnostic and Interventional Radiology, Medical Faculty and University Hospital Düsseldorf, Heinrich-Heine-University Düsseldorf, Moorenstrasse 5, D-40225, Düsseldorf, Germany.
| | - Julian Kirchner
- Department of Diagnostic and Interventional Radiology, Medical Faculty and University Hospital Düsseldorf, Heinrich-Heine-University Düsseldorf, Moorenstrasse 5, D-40225, Düsseldorf, Germany
| | - Julian Caspers
- Department of Diagnostic and Interventional Radiology, Medical Faculty and University Hospital Düsseldorf, Heinrich-Heine-University Düsseldorf, Moorenstrasse 5, D-40225, Düsseldorf, Germany
| |
Collapse
|
2
|
Pal R, K M, Matsui A, Kang H, Morita S, Taniguchi H, Kobayashi T, Morita A, Choi HS, Duda DG, Kumar ATN. In vivo quantification of programmed death-ligand-1 expression heterogeneity in tumors using fluorescence lifetime imaging. RESEARCH SQUARE 2023:rs.3.rs-3222037. [PMID: 37961361 PMCID: PMC10635296 DOI: 10.21203/rs.3.rs-3222037/v1] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 11/15/2023]
Abstract
Cancer patient selection for immunotherapy is often based on programmed death-ligand-1 (PD-L1) expression as a biomarker. PD-L1 expression is currently quantified using immunohistochemistry, which can only provide snapshots of PD-L1 expression status in microscopic regions of ex vivo specimens. In vivo imaging using targeted agents can capture dynamic variations of PD-L1 expression in entire tumors within and across multiple subjects. Towards this goal, several PD-L1 targeted molecular imaging probes have been evaluated in murine models and humans. However, clinical translation of these probes has been limited due to a significant non-specific accumulation of the imaging probes and the inability of conventional imaging modalities to provide quantitative readouts that can be compared across multiple subjects. Here we report that in vivo time-domain (TD) fluorescence imaging can provide quantitative estimates of baseline tumor PD-L1 heterogeneity across untreated mice and variations in PD-L1 expression across mice undergoing clinically relevant anti-PD1 treatment. This approach relies on a significantly longer fluorescence lifetime (FLT) of PD-L1 specific anti-PD-L1 antibody tagged to IRDye 800CW (αPDL1-800) compared to nonspecific αPDL1-800. Leveraging this unique FLT contrast, we show that PD-L1 expression can be quantified across mice both in superficial breast tumors using planar FLT imaging, and in deep-seated liver tumors (>5 mm depth) using the asymptotic TD algorithm for fluorescence tomography. Our results suggest that FLT contrast can accelerate the preclinical investigation and clinical translation of novel molecular imaging probes by providing robust quantitative readouts of receptor expression that can be readily compared across subjects.
Collapse
Affiliation(s)
- Rahul Pal
- Department of Radiology, Massachusetts General Hospital, Harvard Medical School, Boston, Massachusetts
| | - Murali K
- Department of Radiology, Massachusetts General Hospital, Harvard Medical School, Boston, Massachusetts
| | - Aya Matsui
- Department of Vascular Physiology, Graduate School of Medical Science, Kanazawa University, Japan
| | - Homan Kang
- Gordon Center for Medical Imaging, Massachusetts General Hospital, Harvard Medical School, Boston, Massachusetts
| | - Satoru Morita
- E. L. Steele Laboratories for Tumor Biology, Department of Radiation Oncology, Massachusetts General Hospital, Harvard Medical School, Boston, Massachusetts
| | - Hajime Taniguchi
- E. L. Steele Laboratories for Tumor Biology, Department of Radiation Oncology, Massachusetts General Hospital, Harvard Medical School, Boston, Massachusetts
- Department of Surgery, Tohoku Graduate School of Medicine, Sendai, Japan
| | - Tatsuya Kobayashi
- E. L. Steele Laboratories for Tumor Biology, Department of Radiation Oncology, Massachusetts General Hospital, Harvard Medical School, Boston, Massachusetts
| | - Atsuyo Morita
- E. L. Steele Laboratories for Tumor Biology, Department of Radiation Oncology, Massachusetts General Hospital, Harvard Medical School, Boston, Massachusetts
| | - Hak Soo Choi
- Gordon Center for Medical Imaging, Massachusetts General Hospital, Harvard Medical School, Boston, Massachusetts
| | - Dan G Duda
- E. L. Steele Laboratories for Tumor Biology, Department of Radiation Oncology, Massachusetts General Hospital, Harvard Medical School, Boston, Massachusetts
| | - Anand T N Kumar
- Department of Radiology, Massachusetts General Hospital, Harvard Medical School, Boston, Massachusetts
| |
Collapse
|