Nandita M deSouza1, Aad van der Lugt2, Christophe M Deroose3,4, Angel Alberich-Bayarri5, Luc Bidaut6, Laure Fournier7, Lena Costaridou8, Daniela E Oprea-Lager9, Elmar Kotter10, Marion Smits2, Marius E Mayerhoefer11,12, Ronald Boellaard9, Anna Caroli13, Lioe-Fee de Geus-Oei14,15, Wolfgang G Kunz16, Edwin H Oei2, Frederic Lecouvet17, Manuela Franca18, Christian Loewe19, Egesta Lopci20, Caroline Caramella21, Anders Persson22, Xavier Golay23, Marc Dewey24, James P B O'Connor25, Pim deGraaf9, Sergios Gatidis26, Gudrun Zahlmann27. 1. Division of Radiotherapy and Imaging, The Institute of Cancer Research and Royal Marsden NHS Foundation Trust, London, UK. nandita.deSouza@icr.ac.uk. 2. Department of Radiology and Nuclear Medicine, Erasmus MC, University Medical Center, Rotterdam, The Netherlands. 3. Nuclear Medicine, University Hospitals Leuven, Leuven, Belgium. 4. Nuclear Medicine and Molecular Imaging, Department of Imaging and Pathology, KU Leuven, Leuven, Belgium. 5. Quantitative Imaging Biomarkers in Medicine (QUIBIM), Valencia, Spain. 6. College of Science, University of Lincoln, Lincoln, Lincoln, LN6 7TS, UK. 7. INSERM, Radiology Department, AP-HP, Hopital Europeen Georges Pompidou, Université de Paris, PARCC, 75015, Paris, France. 8. School of Medicine, University of Patras, University Campus, Rio, 26 500, Patras, Greece. 9. Department of Radiology and Nuclear Medicine, Amsterdam, UMC, Vrije Universiteit Amsterdam, Amsterdam, The Netherlands. 10. Department of Radiology, University Medical Center Freiburg, Freiburg, Germany. 11. Department of Biomedical Imaging and Image-Guided Therapy, Medical University of Vienna, Vienna, Austria. 12. Memorial Sloan Kettering Cancer Centre, New York, NY, USA. 13. Department of Biomedical Engineering, Istituto di Ricerche Farmacologiche Mario Negri IRCCS, Bergamo, Italy. 14. Department of Radiology, Leiden University Medical Center, Leiden, The Netherlands. 15. Biomedical Photonic Imaging Group, University of Twente, Enschede, The Netherlands. 16. Department of Radiology, University Hospital, LMU Munich, Munich, Germany. 17. Department of Radiology, Institut de Recherche Expérimentale et Clinique (IREC), Cliniques Universitaires Saint Luc, Université Catholique de Louvain (UCLouvain), 10 Avenue Hippocrate, 1200, Brussels, Belgium. 18. Department of Radiology, Centro Hospitalar Universitário do Porto, Instituto de Ciências Biomédicas de Abel Salazar, University of Porto, Porto, Portugal. 19. Division of Cardiovascular and Interventional Radiology, Department for Bioimaging and Image-Guided Therapy, Medical University of Vienna, Vienna, Austria. 20. Nuclear Medicine, IRCCS - Humanitas Research Hospital, via Manzoni 56, Rozzano, MI, Italy. 21. Radiology Department, Hôpital Marie Lannelongue, Institut d'Oncologie Thoracique, Université Paris-Saclay, Le Plessis-Robinson, France. 22. Department of Radiology, and Department of Health, Medicine and Caring Sciences, Center for Medical Image Science and Visualization (CMIV), Linköping University, Linköping, Sweden. 23. Queen Square Institute of Neurology, University College London, London, UK. 24. Department of Radiology, Charité Universitätsmedizin Berlin, Berlin, Germany. 25. Division of Radiotherapy and Imaging, The Institute of Cancer Research and Royal Marsden NHS Foundation Trust, London, UK. 26. Department of Radiology, University of Tubingen, Tübingen, Germany. 27. Radiological Society of North America (RSNA), Oak Brook, IL, USA.
Abstract
BACKGROUND: Lesion/tissue segmentation on digital medical images enables biomarker extraction, image-guided therapy delivery, treatment response measurement, and training/validation for developing artificial intelligence algorithms and workflows. To ensure data reproducibility, criteria for standardised segmentation are critical but currently unavailable. METHODS: A modified Delphi process initiated by the European Imaging Biomarker Alliance (EIBALL) of the European Society of Radiology (ESR) and the European Organisation for Research and Treatment of Cancer (EORTC) Imaging Group was undertaken. Three multidisciplinary task forces addressed modality and image acquisition, segmentation methodology itself, and standards and logistics. Devised survey questions were fed via a facilitator to expert participants. The 58 respondents to Round 1 were invited to participate in Rounds 2-4. Subsequent rounds were informed by responses of previous rounds. RESULTS/ CONCLUSIONS: Items with ≥ 75% consensus are considered a recommendation. These include system performance certification, thresholds for image signal-to-noise, contrast-to-noise and tumour-to-background ratios, spatial resolution, and artefact levels. Direct, iterative, and machine or deep learning reconstruction methods, use of a mixture of CE marked and verified research tools were agreed and use of specified reference standards and validation processes considered essential. Operator training and refreshment were considered mandatory for clinical trials and clinical research. Items with a 60-74% agreement require reporting (site-specific accreditation for clinical research, minimal pixel number within lesion segmented, use of post-reconstruction algorithms, operator training refreshment for clinical practice). Items with ≤ 60% agreement are outside current recommendations for segmentation (frequency of system performance tests, use of only CE-marked tools, board certification of operators, frequency of operator refresher training). Recommendations by anatomical area are also specified.
BACKGROUND: Lesion/tissue segmentation on digital medical images enables biomarker extraction, image-guided therapy delivery, treatment response measurement, and training/validation for developing artificial intelligence algorithms and workflows. To ensure data reproducibility, criteria for standardised segmentation are critical but currently unavailable. METHODS: A modified Delphi process initiated by the European Imaging Biomarker Alliance (EIBALL) of the European Society of Radiology (ESR) and the European Organisation for Research and Treatment of Cancer (EORTC) Imaging Group was undertaken. Three multidisciplinary task forces addressed modality and image acquisition, segmentation methodology itself, and standards and logistics. Devised survey questions were fed via a facilitator to expert participants. The 58 respondents to Round 1 were invited to participate in Rounds 2-4. Subsequent rounds were informed by responses of previous rounds. RESULTS/ CONCLUSIONS: Items with ≥ 75% consensus are considered a recommendation. These include system performance certification, thresholds for image signal-to-noise, contrast-to-noise and tumour-to-background ratios, spatial resolution, and artefact levels. Direct, iterative, and machine or deep learning reconstruction methods, use of a mixture of CE marked and verified research tools were agreed and use of specified reference standards and validation processes considered essential. Operator training and refreshment were considered mandatory for clinical trials and clinical research. Items with a 60-74% agreement require reporting (site-specific accreditation for clinical research, minimal pixel number within lesion segmented, use of post-reconstruction algorithms, operator training refreshment for clinical practice). Items with ≤ 60% agreement are outside current recommendations for segmentation (frequency of system performance tests, use of only CE-marked tools, board certification of operators, frequency of operator refresher training). Recommendations by anatomical area are also specified.
Authors: Mathieu Hatt; John A Lee; Charles R Schmidtlein; Issam El Naqa; Curtis Caldwell; Elisabetta De Bernardi; Wei Lu; Shiva Das; Xavier Geets; Vincent Gregoire; Robert Jeraj; Michael P MacManus; Osama R Mawlawi; Ursula Nestle; Andrei B Pugachev; Heiko Schöder; Tony Shepherd; Emiliano Spezi; Dimitris Visvikis; Habib Zaidi; Assen S Kirov Journal: Med Phys Date: 2017-05-18 Impact factor: 4.071
Authors: Virginie Frings; Floris H P van Velden; Linda M Velasquez; Wendy Hayes; Peter M van de Ven; Otto S Hoekstra; Ronald Boellaard Journal: Radiology Date: 2014-05-26 Impact factor: 11.105
Authors: Diem Vuong; Marta Bogowicz; Sarah Denzler; Carol Oliveira; Robert Foerster; Florian Amstutz; Hubert S Gabryś; Jan Unkelbach; Sven Hillinger; Sandra Thierstein; Alexandros Xyrafas; Solange Peters; Miklos Pless; Matthias Guckenberger; Stephanie Tanadini-Lang Journal: Med Phys Date: 2020-07-13 Impact factor: 4.071
Authors: Shaojun Zhu; Nader Hirmas; Jeremie Calais; Matthias Eiber; Boris Hadaschik; Martin Stuschke; Ken Herrmann; Johannes Czernin; Amar U Kishan; Nicholas G Nickols; David Elashoff; Wolfgang P Fendler Journal: BMC Cancer Date: 2021-05-07 Impact factor: 4.430
Authors: Chintan Parmar; Emmanuel Rios Velazquez; Ralph Leijenaar; Mohammed Jermoumi; Sara Carvalho; Raymond H Mak; Sushmita Mitra; B Uma Shankar; Ron Kikinis; Benjamin Haibe-Kains; Philippe Lambin; Hugo J W L Aerts Journal: PLoS One Date: 2014-07-15 Impact factor: 3.240
Authors: Alexandra Ljimani; Anna Caroli; Christoffer Laustsen; Susan Francis; Iosif Alexandru Mendichovszky; Octavia Bane; Fabio Nery; Kanishka Sharma; Andreas Pohlmann; Ilona A Dekkers; Jean-Paul Vallee; Katja Derlin; Mike Notohamiprodjo; Ruth P Lim; Stefano Palmucci; Suraj D Serai; Joao Periquito; Zhen Jane Wang; Martijn Froeling; Harriet C Thoeny; Pottumarthi Prasad; Moritz Schneider; Thoralf Niendorf; Pim Pullens; Steven Sourbron; Eric E Sigmund Journal: MAGMA Date: 2019-11-01 Impact factor: 2.310