Quantification of intratumoural heterogeneity in mice and patients via machine-learning models trained on PET-MRI data.

Autor: Katiyar P; Werner Siemens Imaging Center, Department of Preclinical Imaging and Radiopharmacy, Eberhard Karls University Tübingen, Tübingen, Germany.; Max Planck Institute for Intelligent Systems, Tübingen, Germany., Schwenck J; Werner Siemens Imaging Center, Department of Preclinical Imaging and Radiopharmacy, Eberhard Karls University Tübingen, Tübingen, Germany.; Cluster of Excellence iFIT (EXC 2180) 'Image Guided and Functionally Instructed Tumor Therapies', Eberhard Karls University Tübingen, Tübingen, Germany.; Department of Nuclear Medicine and Clinical Molecular Imaging, Eberhard Karls University Tübingen, Tübingen, Germany., Frauenfeld L; Institute of Pathology and Neuropathology, Eberhard Karls University Tübingen and Comprehensive Cancer Center, University Hospital Tübingen, Tübingen, Germany., Divine MR; Werner Siemens Imaging Center, Department of Preclinical Imaging and Radiopharmacy, Eberhard Karls University Tübingen, Tübingen, Germany., Agrawal V; Werner Siemens Imaging Center, Department of Preclinical Imaging and Radiopharmacy, Eberhard Karls University Tübingen, Tübingen, Germany.; Max Planck Institute for Intelligent Systems, Tübingen, Germany., Kohlhofer U; Institute of Pathology and Neuropathology, Eberhard Karls University Tübingen and Comprehensive Cancer Center, University Hospital Tübingen, Tübingen, Germany., Gatidis S; Cluster of Excellence iFIT (EXC 2180) 'Image Guided and Functionally Instructed Tumor Therapies', Eberhard Karls University Tübingen, Tübingen, Germany.; Department of Radiology, Eberhard Karls University Tübingen, Tübingen, Germany., Kontermann R; Institute of Cell Biology and Immunology, SRCSB, University of Stuttgart, Stuttgart, Germany., Königsrainer A; Cluster of Excellence iFIT (EXC 2180) 'Image Guided and Functionally Instructed Tumor Therapies', Eberhard Karls University Tübingen, Tübingen, Germany.; Department of General, Visceral and Transplant Surgery, University Hospital Tübingen, Tübingen, Germany., Quintanilla-Martinez L; Cluster of Excellence iFIT (EXC 2180) 'Image Guided and Functionally Instructed Tumor Therapies', Eberhard Karls University Tübingen, Tübingen, Germany.; Institute of Pathology and Neuropathology, Eberhard Karls University Tübingen and Comprehensive Cancer Center, University Hospital Tübingen, Tübingen, Germany., la Fougère C; Cluster of Excellence iFIT (EXC 2180) 'Image Guided and Functionally Instructed Tumor Therapies', Eberhard Karls University Tübingen, Tübingen, Germany.; Department of Nuclear Medicine and Clinical Molecular Imaging, Eberhard Karls University Tübingen, Tübingen, Germany.; German Cancer Consortium (DKTK) and German Cancer Research Center (DKFZ), Heidelberg, Germany., Schölkopf B; Max Planck Institute for Intelligent Systems, Tübingen, Germany.; Cluster of Excellence iFIT (EXC 2180) 'Image Guided and Functionally Instructed Tumor Therapies', Eberhard Karls University Tübingen, Tübingen, Germany., Pichler BJ; Werner Siemens Imaging Center, Department of Preclinical Imaging and Radiopharmacy, Eberhard Karls University Tübingen, Tübingen, Germany. bernd.pichler@med.uni-tuebingen.de.; Cluster of Excellence iFIT (EXC 2180) 'Image Guided and Functionally Instructed Tumor Therapies', Eberhard Karls University Tübingen, Tübingen, Germany. bernd.pichler@med.uni-tuebingen.de.; German Cancer Consortium (DKTK) and German Cancer Research Center (DKFZ), Heidelberg, Germany. bernd.pichler@med.uni-tuebingen.de., Disselhorst JA; Werner Siemens Imaging Center, Department of Preclinical Imaging and Radiopharmacy, Eberhard Karls University Tübingen, Tübingen, Germany.; Cluster of Excellence iFIT (EXC 2180) 'Image Guided and Functionally Instructed Tumor Therapies', Eberhard Karls University Tübingen, Tübingen, Germany.
Jazyk: angličtina
Zdroj: Nature biomedical engineering [Nat Biomed Eng] 2023 Aug; Vol. 7 (8), pp. 1014-1027. Date of Electronic Publication: 2023 Jun 05.
DOI: 10.1038/s41551-023-01047-9
Abstrakt: In oncology, intratumoural heterogeneity is closely linked with the efficacy of therapy, and can be partially characterized via tumour biopsies. Here we show that intratumoural heterogeneity can be characterized spatially via phenotype-specific, multi-view learning classifiers trained with data from dynamic positron emission tomography (PET) and multiparametric magnetic resonance imaging (MRI). Classifiers trained with PET-MRI data from mice with subcutaneous colon cancer quantified phenotypic changes resulting from an apoptosis-inducing targeted therapeutic and provided biologically relevant probability maps of tumour-tissue subtypes. When applied to retrospective PET-MRI data of patients with liver metastases from colorectal cancer, the trained classifiers characterized intratumoural tissue subregions in agreement with tumour histology. The spatial characterization of intratumoural heterogeneity in mice and patients via multimodal, multiparametric imaging aided by machine-learning may facilitate applications in precision oncology.
(© 2023. The Author(s), under exclusive licence to Springer Nature Limited.)
Databáze: MEDLINE
Externí odkaz: