Stefan Leger1, Alex Zwanenburg2, Karoline Pilz3, Sebastian Zschaeck4, Klaus Zöphel5, Jörg Kotzerke5, Andreas Schreiber6, Daniel Zips7, Mechthild Krause8, Michael Baumann8, Esther G C Troost8, Christian Richter9, Steffen Löck10. 1. OncoRay National Center for Radiation Research in Oncology, Faculty of Medicine and University Hospital Carl Gustav Carus, Technische Universität Dresden, Helmholtz-Zentrum Dresden - Rossendorf, Germany; German Cancer Research Center (DKFZ), Heidelberg and German Cancer Consortium (DKTK) partner site Dresden, Dresden, Germany; National Center for Tumor Diseases (NCT), Partner Site Dresden, Germany German Cancer Research Center (DKFZ), Heidelberg, Germany, Faculty of Medicine and University Hospital Carl Gustav Carus, Technische Universität Dresden, Dresden, Germany, and Helmholtz Association / Helmholtz-Zentrum Dresden - Rossendorf (HZDR), Dresden, Germany. Electronic address: Stefan.Leger@oncoray.de. 2. OncoRay National Center for Radiation Research in Oncology, Faculty of Medicine and University Hospital Carl Gustav Carus, Technische Universität Dresden, Helmholtz-Zentrum Dresden - Rossendorf, Germany; German Cancer Research Center (DKFZ), Heidelberg and German Cancer Consortium (DKTK) partner site Dresden, Dresden, Germany; National Center for Tumor Diseases (NCT), Partner Site Dresden, Germany German Cancer Research Center (DKFZ), Heidelberg, Germany, Faculty of Medicine and University Hospital Carl Gustav Carus, Technische Universität Dresden, Dresden, Germany, and Helmholtz Association / Helmholtz-Zentrum Dresden - Rossendorf (HZDR), Dresden, Germany. 3. OncoRay National Center for Radiation Research in Oncology, Faculty of Medicine and University Hospital Carl Gustav Carus, Technische Universität Dresden, Helmholtz-Zentrum Dresden - Rossendorf, Germany; German Cancer Research Center (DKFZ), Heidelberg and German Cancer Consortium (DKTK) partner site Dresden, Dresden, Germany; National Center for Tumor Diseases (NCT), Partner Site Dresden, Germany German Cancer Research Center (DKFZ), Heidelberg, Germany, Faculty of Medicine and University Hospital Carl Gustav Carus, Technische Universität Dresden, Dresden, Germany, and Helmholtz Association / Helmholtz-Zentrum Dresden - Rossendorf (HZDR), Dresden, Germany; Department of Radiotherapy, Hospital Dresden-Friedrichstadt, Germany. 4. OncoRay National Center for Radiation Research in Oncology, Faculty of Medicine and University Hospital Carl Gustav Carus, Technische Universität Dresden, Helmholtz-Zentrum Dresden - Rossendorf, Germany; German Cancer Research Center (DKFZ), Heidelberg and German Cancer Consortium (DKTK) partner site Dresden, Dresden, Germany; Department of Radiotherapy and Radiation Oncology, Faculty of Medicine and University Hospital Carl Gustav Carus, Technische Universität Dresden, Germany; Charité Universitätsmedizin Berlin, Department of Radiation Oncology, Germany. 5. Department of Nuclear Medicine, Faculty of Medicine and University Hospital Carl Gustav Carus, Technische Universität Dresden, Germany; Helmholtz-Zentrum Dresden-Rossendorf, PET Center, Institute of Radiopharmaceutical Cancer Research, Germany. 6. Department of Radiotherapy, Hospital Dresden-Friedrichstadt, Germany. 7. Department of Radiation Oncology, Faculty of Medicine and University Hospital Tübingen, Eberhard Karls Universität Tübingen, Germany. 8. OncoRay National Center for Radiation Research in Oncology, Faculty of Medicine and University Hospital Carl Gustav Carus, Technische Universität Dresden, Helmholtz-Zentrum Dresden - Rossendorf, Germany; German Cancer Research Center (DKFZ), Heidelberg and German Cancer Consortium (DKTK) partner site Dresden, Dresden, Germany; National Center for Tumor Diseases (NCT), Partner Site Dresden, Germany German Cancer Research Center (DKFZ), Heidelberg, Germany, Faculty of Medicine and University Hospital Carl Gustav Carus, Technische Universität Dresden, Dresden, Germany, and Helmholtz Association / Helmholtz-Zentrum Dresden - Rossendorf (HZDR), Dresden, Germany; Department of Radiotherapy and Radiation Oncology, Faculty of Medicine and University Hospital Carl Gustav Carus, Technische Universität Dresden, Germany; Helmholtz-Zentrum Dresden - Rossendorf, Institute of Radiooncology OncoRay, Germany. 9. OncoRay National Center for Radiation Research in Oncology, Faculty of Medicine and University Hospital Carl Gustav Carus, Technische Universität Dresden, Helmholtz-Zentrum Dresden - Rossendorf, Germany; German Cancer Research Center (DKFZ), Heidelberg and German Cancer Consortium (DKTK) partner site Dresden, Dresden, Germany; Department of Radiotherapy and Radiation Oncology, Faculty of Medicine and University Hospital Carl Gustav Carus, Technische Universität Dresden, Germany; Helmholtz-Zentrum Dresden - Rossendorf, Institute of Radiooncology OncoRay, Germany. 10. OncoRay National Center for Radiation Research in Oncology, Faculty of Medicine and University Hospital Carl Gustav Carus, Technische Universität Dresden, Helmholtz-Zentrum Dresden - Rossendorf, Germany; German Cancer Research Center (DKFZ), Heidelberg and German Cancer Consortium (DKTK) partner site Dresden, Dresden, Germany; Department of Radiotherapy and Radiation Oncology, Faculty of Medicine and University Hospital Carl Gustav Carus, Technische Universität Dresden, Germany.
Abstract
BACKGROUND AND PURPOSE: The development of radiomic risk models to predict clinical outcome is usually based on pre-treatment imaging, such as computed tomography (CT) scans used for radiation treatment planning. Imaging data acquired during the course of treatment may improve their prognostic performance. We compared the performance of radiomic risk models based on the pre-treatment CT and CT scans acquired in the second week of therapy. MATERIAL AND METHODS: Treatment planning and second week CT scans of 78 head and neck squamous cell carcinoma patients treated with primary radiochemotherapy were collected. 1538 image features were extracted from each image. Prognostic models for loco-regional tumour control (LRC) and overall survival (OS) were built using 6 feature selection methods and 6 machine learning algorithms. Prognostic performance was assessed using the concordance index (C-Index). Furthermore, patients were stratified into risk groups and differences in LRC and OS were evaluated by log-rank tests. RESULTS: The performance of radiomic risk model in predicting LRC was improved using the second week CT scans (C-Index: 0.79), in comparison to the pre-treatment CT scans (C-Index: 0.65). This was confirmed by Kaplan-Meier analyses, in which risk stratification based on the second week CT could be improved for LRC (p = 0.002) compared to pre-treatment CT (p = 0.063). CONCLUSION: Incorporation of imaging during treatment may be a promising way to improve radiomic risk models for clinical treatment adaption, i.e., to select patients that may benefit from dose modification.
BACKGROUND AND PURPOSE: The development of radiomic risk models to predict clinical outcome is usually based on pre-treatment imaging, such as computed tomography (CT) scans used for radiation treatment planning. Imaging data acquired during the course of treatment may improve their prognostic performance. We compared the performance of radiomic risk models based on the pre-treatment CT and CT scans acquired in the second week of therapy. MATERIAL AND METHODS: Treatment planning and second week CT scans of 78 head and neck squamous cell carcinomapatients treated with primary radiochemotherapy were collected. 1538 image features were extracted from each image. Prognostic models for loco-regional tumour control (LRC) and overall survival (OS) were built using 6 feature selection methods and 6 machine learning algorithms. Prognostic performance was assessed using the concordance index (C-Index). Furthermore, patients were stratified into risk groups and differences in LRC and OS were evaluated by log-rank tests. RESULTS: The performance of radiomic risk model in predicting LRC was improved using the second week CT scans (C-Index: 0.79), in comparison to the pre-treatment CT scans (C-Index: 0.65). This was confirmed by Kaplan-Meier analyses, in which risk stratification based on the second week CT could be improved for LRC (p = 0.002) compared to pre-treatment CT (p = 0.063). CONCLUSION: Incorporation of imaging during treatment may be a promising way to improve radiomic risk models for clinical treatment adaption, i.e., to select patients that may benefit from dose modification.
Authors: Howard E Morgan; Kai Wang; Michael Dohopolski; Xiao Liang; Michael R Folkert; David J Sher; Jing Wang Journal: Quant Imaging Med Surg Date: 2021-12
Authors: Maryam Gul; Kimberley-Jane C Bonjoc; David Gorlin; Chi Wah Wong; Amirah Salem; Vincent La; Aleksandr Filippov; Abbas Chaudhry; Muhammad H Imam; Ammar A Chaudhry Journal: Front Oncol Date: 2021-07-07 Impact factor: 6.244
Authors: Janna E van Timmeren; Wouter van Elmpt; Ralph T H Leijenaar; Bart Reymen; René Monshouwer; Johan Bussink; Leen Paelinck; Evelien Bogaert; Carlos De Wagter; Elamin Elhaseen; Yolande Lievens; Olfred Hansen; Carsten Brink; Philippe Lambin Journal: Radiother Oncol Date: 2019-04-11 Impact factor: 6.280