Gianfranco Loi1, Marco Fusella2, Claudio Vecchi3, Sebastiano Menna4, Federica Rosica5, Eva Gino6, Nicola Maffei7, Enrico Menghi8, Alessandro Savini8, Antonella Roggio9, Lorenzo Radici10, Elisabetta Cagni11, Francesco Lucio12, Lidia Strigari13, Silvia Strolin14, Cristina Garibaldi15, Chiara Romanò15, Marina Piovesan16, Pierfrancesco Franco17, Christian Fiandra18. 1. Department of Medical Physics, University Hospital "Maggiore della Carità," Novara, Italy. 2. Medical Physics Department, Veneto Institute of Oncology IOV-IRCCS, Padua, Italy. Electronic address: marco.fusella@iov.veneto.it. 3. Tecnologie Avanzate, Torino, Italy. 4. Fondazione Policlinico Universitario A. Gemelli IRCCS, UOC di Fisica Sanitaria, Dipartimento di diagnostica per immagini, radioterapia oncologica ed ematologia, Rome, Italy. 5. U.O.C. Fisica Sanitaria, ASL Teramo, Italy. 6. SC Fisica Sanitaria, A.O. Ordine Mauriziano di Torino, Italy. 7. Department of Medical Physics, A.O. U. di Modena, Modena, Italy; University of Turin, Post Graduate School in Medical Physics, Turin, Italy. 8. Medical Physics Department, Istituto Scientifico Romagnolo per lo Studio e la Cura dei Tumori (IRST) IRCCS, Meldola, FC, Italy. 9. Medical Physics Department, Veneto Institute of Oncology IOV-IRCCS, Padua, Italy. 10. Ospedale regionale "Umberto Parini" Azienda USL VDA, Fisica Sanitaria, Italy. 11. Medical Physics Unit, Azienda USL-IRCCS di Reggio Emilia, Reggio Emilia, Italy; School of Engineering, Cardiff University, Cardiff, Wales, UK. 12. ASLCN2 di Alba e Bra, Italy. 13. Department of Medical Physics, St. Orsola-Malpighi Hospital, Bologna, Italy. 14. Radiotherapy unit, INI Città bianca Veroli (FR), Italy. 15. IEO, European Institute of Oncology IRCCS, Unit of Medical Physics, Milan, Italy. 16. U.O.C. di Fisica Medica ULSS 3 Serenissima, Italy. 17. University of Turin, Department of Oncology, Turin, Italy. 18. University of Turin, Department of Oncology, Turin, Italy; School of Bioengineering and Medical-Surgical Sciences, Politecnico di Torino, Turin, Italy.
Abstract
PURPOSE: To investigate the performance of various algorithms for deformable image registration (DIR) for propagating regions of interest (ROIs) using multiple commercial platforms, from computed tomography to cone beam computed tomography (CBCT) and megavoltage computed tomography. METHODS AND MATERIALS: Fourteen institutions participated in the study using 5 commercial platforms: RayStation (RaySearch Laboratories, Stockholm, Sweden), MIM (Cleveland, OH), VelocityAI and SmartAdapt (Varian Medical Systems, Palo Alto, CA), and ABAS (Elekta AB, Stockholm, Sweden). Algorithms were tested on synthetic images generated with the ImSimQA (Oncology Systems Limited, Shrewsbury, UK) package by applying 2 specific deformation vector fields (DVF) to real head and neck patient datasets. On-board images from 3 systems were used: megavoltage computed tomography from Tomotherapy and 2 kinds of CBCT from a clinical linear accelerator. Image quality of the system was evaluated. The algorithms' accuracy was assessed by comparing the DIR-mapped ROIs returned by each center with those of the reference, using the Dice similarity coefficient and mean distance to conformity metrics. Statistical inference on the validation results was carried out to identify the prognostic factors of DIR performance. RESULTS: Analyzing 840 DIR-mapped ROIs returned by the centers, it was demonstrated that DVF intensity and image quality were significant prognostic factors of DIR performance. The accuracy of the propagated contours was generally high, and acceptable DIR performance can be obtained with lower-dose CBCT image protocols. CONCLUSIONS: The performance of the systems proved to be image quality specific, depending on the DVF type and only partially on the platforms. All systems proved to be robust against image artifacts and noise, except the demon-based software.
PURPOSE: To investigate the performance of various algorithms for deformable image registration (DIR) for propagating regions of interest (ROIs) using multiple commercial platforms, from computed tomography to cone beam computed tomography (CBCT) and megavoltage computed tomography. METHODS AND MATERIALS: Fourteen institutions participated in the study using 5 commercial platforms: RayStation (RaySearch Laboratories, Stockholm, Sweden), MIM (Cleveland, OH), VelocityAI and SmartAdapt (Varian Medical Systems, Palo Alto, CA), and ABAS (Elekta AB, Stockholm, Sweden). Algorithms were tested on synthetic images generated with the ImSimQA (Oncology Systems Limited, Shrewsbury, UK) package by applying 2 specific deformation vector fields (DVF) to real head and neck patient datasets. On-board images from 3 systems were used: megavoltage computed tomography from Tomotherapy and 2 kinds of CBCT from a clinical linear accelerator. Image quality of the system was evaluated. The algorithms' accuracy was assessed by comparing the DIR-mapped ROIs returned by each center with those of the reference, using the Dice similarity coefficient and mean distance to conformity metrics. Statistical inference on the validation results was carried out to identify the prognostic factors of DIR performance. RESULTS: Analyzing 840 DIR-mapped ROIs returned by the centers, it was demonstrated that DVF intensity and image quality were significant prognostic factors of DIR performance. The accuracy of the propagated contours was generally high, and acceptable DIR performance can be obtained with lower-dose CBCT image protocols. CONCLUSIONS: The performance of the systems proved to be image quality specific, depending on the DVF type and only partially on the platforms. All systems proved to be robust against image artifacts and noise, except the demon-based software.
Authors: Alex Kubli; Jason Pukala; Amish P Shah; Patrick Kelly; Katja M Langen; Frank J Bova; Rafael R Mañon; Sanford L Meeks Journal: J Appl Clin Med Phys Date: 2021-03-30 Impact factor: 2.102