Jan C Peeken1, Michael Bernhofer2, Matthew B Spraker3, Daniela Pfeiffer4, Michal Devecka5, Ahmed Thamer5, Mohammed A Shouman5, Armin Ott6, Fridtjof Nüsslin7, Nina A Mayr3, Burkhard Rost2, Matthew J Nyflot8, Stephanie E Combs9. 1. Department of Radiation Oncology, Klinikum rechts der Isar, Technical University of Munich (TUM), Munich, Germany; Institute of Innovative Radiotherapy (iRT), Department of Radiation Sciences (DRS), Helmholtz Zentrum München, Neuherberg, Germany; Deutsches Konsortium für Translationale Krebsforschung (DKTK), Partner Site Munich, Germany. Electronic address: jan.peeken@tum.de. 2. Department for Bioinformatics and Computational Biology, Informatik 12, Technical University of Munich (TUM), Garching, Germany. 3. University of Washington, Department of Radiation Oncology, Seattle, United States. 4. Department of Radiology, Klinikum rechts der Isar, Technical University of Munich (TUM), Munich, Germany. 5. Department of Radiation Oncology, Klinikum rechts der Isar, Technical University of Munich (TUM), Munich, Germany. 6. Institut für Medizinische Statistik und Epidemiologie, Technical University of Munich (TUM), Munich, Germany. 7. Department of Radiation Oncology, Klinikum rechts der Isar, Technical University of Munich (TUM), Munich, Germany; Institute for Advanced Study (IAS), Technical University of Munich (TUM), Germany. 8. University of Washington, Department of Radiation Oncology, Seattle, United States; University of Washington, Department of Radiology, Seattle, United States. 9. Department of Radiation Oncology, Klinikum rechts der Isar, Technical University of Munich (TUM), Munich, Germany; Institute of Innovative Radiotherapy (iRT), Department of Radiation Sciences (DRS), Helmholtz Zentrum München, Neuherberg, Germany; Deutsches Konsortium für Translationale Krebsforschung (DKTK), Partner Site Munich, Germany.
Abstract
PURPOSE: In soft tissue sarcoma (STS) patients systemic progression and survival remain comparably low despite low local recurrence rates. In this work, we investigated whether quantitative imaging features ("radiomics") of radiotherapy planning CT-scans carry a prognostic value for pre-therapeutic risk assessment. METHODS: CT-scans, tumor grade, and clinical information were collected from three independent retrospective cohorts of 83 (TUM), 87 (UW) and 51 (McGill) STS patients, respectively. After manual segmentation and preprocessing, 1358 radiomic features were extracted. Feature reduction and machine learning modeling for the prediction of grading, overall survival (OS), distant (DPFS) and local (LPFS) progression free survival were performed followed by external validation. RESULTS: Radiomic models were able to differentiate grade 3 from non-grade 3 STS (area under the receiver operator characteristic curve (AUC): 0.64). The Radiomic models were able to predict OS (C-index: 0.73), DPFS (C-index: 0.68) and LPFS (C-index: 0.77) in the validation cohort. A combined clinical-radiomics model showed the best prediction for OS (C-index: 0.76). The radiomic scores were significantly associated in univariate and multivariate cox regression and allowed for significant risk stratification for all three endpoints. CONCLUSION: This is the first report demonstrating a prognostic potential and tumor grading differentiation by CT-based radiomics.
PURPOSE: In soft tissue sarcoma (STS) patients systemic progression and survival remain comparably low despite low local recurrence rates. In this work, we investigated whether quantitative imaging features ("radiomics") of radiotherapy planning CT-scans carry a prognostic value for pre-therapeutic risk assessment. METHODS: CT-scans, tumor grade, and clinical information were collected from three independent retrospective cohorts of 83 (TUM), 87 (UW) and 51 (McGill) STS patients, respectively. After manual segmentation and preprocessing, 1358 radiomic features were extracted. Feature reduction and machine learning modeling for the prediction of grading, overall survival (OS), distant (DPFS) and local (LPFS) progression free survival were performed followed by external validation. RESULTS: Radiomic models were able to differentiate grade 3 from non-grade 3 STS (area under the receiver operator characteristic curve (AUC): 0.64). The Radiomic models were able to predict OS (C-index: 0.73), DPFS (C-index: 0.68) and LPFS (C-index: 0.77) in the validation cohort. A combined clinical-radiomics model showed the best prediction for OS (C-index: 0.76). The radiomic scores were significantly associated in univariate and multivariate cox regression and allowed for significant risk stratification for all three endpoints. CONCLUSION: This is the first report demonstrating a prognostic potential and tumor grading differentiation by CT-based radiomics.
Authors: Amani Arthur; Edward W Johnston; Jessica M Winfield; Matthew D Blackledge; Robin L Jones; Paul H Huang; Christina Messiou Journal: Front Oncol Date: 2022-07-01 Impact factor: 5.738
Authors: Jan C Peeken; Matthew B Spraker; Carolin Knebel; Hendrik Dapper; Daniela Pfeiffer; Michal Devecka; Ahmed Thamer; Mohamed A Shouman; Armin Ott; Rüdiger von Eisenhart-Rothe; Fridtjof Nüsslin; Nina A Mayr; Matthew J Nyflot; Stephanie E Combs Journal: EBioMedicine Date: 2019-09-12 Impact factor: 8.143
Authors: Jan C Peeken; Mohamed A Shouman; Markus Kroenke; Isabel Rauscher; Tobias Maurer; Jürgen E Gschwend; Matthias Eiber; Stephanie E Combs Journal: Eur J Nucl Med Mol Imaging Date: 2020-05-28 Impact factor: 9.236