Performance of commercially available deformable image registration platforms for contour propagation using patient-based computational phantoms: A multi-institutional study

G. Loi, M. Fusella, E. Lanzi, E. Cagni, C. Garibaldi, G. Iacoviello, F. Lucio, E. Menghi, R. Miceli, L. C. Orlandini, A. Roggio, F. Rosica, M. Stasi, L. Strigari, S. Strolin, C. Fiandra

Research output: Contribution to journalArticle

Abstract

PURPOSE: To investigate the performance of various algorithms for deformable image registration (DIR) to propagate regions of interest (ROIs) using multiple commercial platforms. METHODS AND MATERIALS: Thirteen institutions participated in the study with six commercial platforms: RayStation (RaySearch Laboratories, Stockholm, Sweden), MIM (Cleveland, OH, USA), VelocityAI and Smart Adapt (Varian Medical Systems, Palo Alto, CA, USA), Mirada XD (Mirada Medical Ltd, Oxford, UK), and ABAS (Elekta AB, Stockholm, Sweden). The DIR algorithms were tested on synthetic images generated with the ImSimQA package (Oncology Systems Limited, Shrewsbury, UK) by applying two specific Deformation Vector Fields (DVF) to real patient data-sets. Head-and-neck (HN), thorax, and pelvis sites were included. The accuracy of the algorithms was assessed by comparing the DIR-mapped ROIs from each center with those of reference, using the Dice Similarity Coefficient (DSC) and Mean Distance to Conformity (MDC) metrics. Statistical inference on validation results was carried out in order to identify the prognostic factors of DIR performances. RESULTS: DVF intensity, anatomic site and participating center were significant prognostic factors of DIR performances. Sub-voxel accuracy was obtained in the HN by all algorithms. Large errors, with MDC ranging up to 6 mm, were observed in low-contrast regions that underwent significant deformation, such as in the pelvis, or large DVF with strong contrast, such as the clinical tumor volume (CTV) in the lung. Under these conditions, the hybrid DIR algorithms performed significantly better than the free-form intensity based algorithms and resulted robust against intercenter variability. CONCLUSIONS: The performances of the systems proved to be site specific, depending on the DVF type and the platforms and the procedures used at the various centers. The pelvis was the most challenging site for most of the algorithms, which failed to achieve sub-voxel accuracy. Improved reproducibility was observed among the centers using the same hybrid registration algorithm.
Original languageEnglish
Pages (from-to)748-757
JournalMedical Physics
Volume45
Issue number2
DOIs
Publication statusPublished - Dec 20 2017

Fingerprint

Pelvis
Sweden
Neck
Head
Tumor Burden
Thorax
Lung

Keywords

  • contouring
  • deformable image registration
  • multi-institution study
  • quality assurance

Cite this

Performance of commercially available deformable image registration platforms for contour propagation using patient-based computational phantoms: A multi-institutional study. / Loi, G.; Fusella, M.; Lanzi, E.; Cagni, E.; Garibaldi, C.; Iacoviello, G.; Lucio, F.; Menghi, E.; Miceli, R.; Orlandini, L. C.; Roggio, A.; Rosica, F.; Stasi, M.; Strigari, L.; Strolin, S.; Fiandra, C.

In: Medical Physics, Vol. 45, No. 2, 20.12.2017, p. 748-757.

Research output: Contribution to journalArticle

Loi, G, Fusella, M, Lanzi, E, Cagni, E, Garibaldi, C, Iacoviello, G, Lucio, F, Menghi, E, Miceli, R, Orlandini, LC, Roggio, A, Rosica, F, Stasi, M, Strigari, L, Strolin, S & Fiandra, C 2017, 'Performance of commercially available deformable image registration platforms for contour propagation using patient-based computational phantoms: A multi-institutional study', Medical Physics, vol. 45, no. 2, pp. 748-757. https://doi.org/10.1002/mp.12737 [doi]
Loi, G. ; Fusella, M. ; Lanzi, E. ; Cagni, E. ; Garibaldi, C. ; Iacoviello, G. ; Lucio, F. ; Menghi, E. ; Miceli, R. ; Orlandini, L. C. ; Roggio, A. ; Rosica, F. ; Stasi, M. ; Strigari, L. ; Strolin, S. ; Fiandra, C. / Performance of commercially available deformable image registration platforms for contour propagation using patient-based computational phantoms: A multi-institutional study. In: Medical Physics. 2017 ; Vol. 45, No. 2. pp. 748-757.
@article{9283b75648ee474d8e17dc836943124f,
title = "Performance of commercially available deformable image registration platforms for contour propagation using patient-based computational phantoms: A multi-institutional study",
abstract = "PURPOSE: To investigate the performance of various algorithms for deformable image registration (DIR) to propagate regions of interest (ROIs) using multiple commercial platforms. METHODS AND MATERIALS: Thirteen institutions participated in the study with six commercial platforms: RayStation (RaySearch Laboratories, Stockholm, Sweden), MIM (Cleveland, OH, USA), VelocityAI and Smart Adapt (Varian Medical Systems, Palo Alto, CA, USA), Mirada XD (Mirada Medical Ltd, Oxford, UK), and ABAS (Elekta AB, Stockholm, Sweden). The DIR algorithms were tested on synthetic images generated with the ImSimQA package (Oncology Systems Limited, Shrewsbury, UK) by applying two specific Deformation Vector Fields (DVF) to real patient data-sets. Head-and-neck (HN), thorax, and pelvis sites were included. The accuracy of the algorithms was assessed by comparing the DIR-mapped ROIs from each center with those of reference, using the Dice Similarity Coefficient (DSC) and Mean Distance to Conformity (MDC) metrics. Statistical inference on validation results was carried out in order to identify the prognostic factors of DIR performances. RESULTS: DVF intensity, anatomic site and participating center were significant prognostic factors of DIR performances. Sub-voxel accuracy was obtained in the HN by all algorithms. Large errors, with MDC ranging up to 6 mm, were observed in low-contrast regions that underwent significant deformation, such as in the pelvis, or large DVF with strong contrast, such as the clinical tumor volume (CTV) in the lung. Under these conditions, the hybrid DIR algorithms performed significantly better than the free-form intensity based algorithms and resulted robust against intercenter variability. CONCLUSIONS: The performances of the systems proved to be site specific, depending on the DVF type and the platforms and the procedures used at the various centers. The pelvis was the most challenging site for most of the algorithms, which failed to achieve sub-voxel accuracy. Improved reproducibility was observed among the centers using the same hybrid registration algorithm.",
keywords = "contouring, deformable image registration, multi-institution study, quality assurance",
author = "G. Loi and M. Fusella and E. Lanzi and E. Cagni and C. Garibaldi and G. Iacoviello and F. Lucio and E. Menghi and R. Miceli and Orlandini, {L. C.} and A. Roggio and F. Rosica and M. Stasi and L. Strigari and S. Strolin and C. Fiandra",
note = "LR: 20180109; CI: (c) 2017; JID: 0425746; OTO: NOTNLM; 2017/03/14 00:00 [received]; 2017/10/04 00:00 [revised]; 2017/12/01 00:00 [accepted]; 2017/12/22 06:00 [pubmed]; 2017/12/22 06:00 [medline]; 2017/12/22 06:00 [entrez]; aheadofprint",
year = "2017",
month = "12",
day = "20",
doi = "10.1002/mp.12737 [doi]",
language = "English",
volume = "45",
pages = "748--757",
journal = "Medical Physics",
issn = "0094-2405",
publisher = "John Wiley and Sons Ltd",
number = "2",

}

TY - JOUR

T1 - Performance of commercially available deformable image registration platforms for contour propagation using patient-based computational phantoms: A multi-institutional study

AU - Loi, G.

AU - Fusella, M.

AU - Lanzi, E.

AU - Cagni, E.

AU - Garibaldi, C.

AU - Iacoviello, G.

AU - Lucio, F.

AU - Menghi, E.

AU - Miceli, R.

AU - Orlandini, L. C.

AU - Roggio, A.

AU - Rosica, F.

AU - Stasi, M.

AU - Strigari, L.

AU - Strolin, S.

AU - Fiandra, C.

N1 - LR: 20180109; CI: (c) 2017; JID: 0425746; OTO: NOTNLM; 2017/03/14 00:00 [received]; 2017/10/04 00:00 [revised]; 2017/12/01 00:00 [accepted]; 2017/12/22 06:00 [pubmed]; 2017/12/22 06:00 [medline]; 2017/12/22 06:00 [entrez]; aheadofprint

PY - 2017/12/20

Y1 - 2017/12/20

N2 - PURPOSE: To investigate the performance of various algorithms for deformable image registration (DIR) to propagate regions of interest (ROIs) using multiple commercial platforms. METHODS AND MATERIALS: Thirteen institutions participated in the study with six commercial platforms: RayStation (RaySearch Laboratories, Stockholm, Sweden), MIM (Cleveland, OH, USA), VelocityAI and Smart Adapt (Varian Medical Systems, Palo Alto, CA, USA), Mirada XD (Mirada Medical Ltd, Oxford, UK), and ABAS (Elekta AB, Stockholm, Sweden). The DIR algorithms were tested on synthetic images generated with the ImSimQA package (Oncology Systems Limited, Shrewsbury, UK) by applying two specific Deformation Vector Fields (DVF) to real patient data-sets. Head-and-neck (HN), thorax, and pelvis sites were included. The accuracy of the algorithms was assessed by comparing the DIR-mapped ROIs from each center with those of reference, using the Dice Similarity Coefficient (DSC) and Mean Distance to Conformity (MDC) metrics. Statistical inference on validation results was carried out in order to identify the prognostic factors of DIR performances. RESULTS: DVF intensity, anatomic site and participating center were significant prognostic factors of DIR performances. Sub-voxel accuracy was obtained in the HN by all algorithms. Large errors, with MDC ranging up to 6 mm, were observed in low-contrast regions that underwent significant deformation, such as in the pelvis, or large DVF with strong contrast, such as the clinical tumor volume (CTV) in the lung. Under these conditions, the hybrid DIR algorithms performed significantly better than the free-form intensity based algorithms and resulted robust against intercenter variability. CONCLUSIONS: The performances of the systems proved to be site specific, depending on the DVF type and the platforms and the procedures used at the various centers. The pelvis was the most challenging site for most of the algorithms, which failed to achieve sub-voxel accuracy. Improved reproducibility was observed among the centers using the same hybrid registration algorithm.

AB - PURPOSE: To investigate the performance of various algorithms for deformable image registration (DIR) to propagate regions of interest (ROIs) using multiple commercial platforms. METHODS AND MATERIALS: Thirteen institutions participated in the study with six commercial platforms: RayStation (RaySearch Laboratories, Stockholm, Sweden), MIM (Cleveland, OH, USA), VelocityAI and Smart Adapt (Varian Medical Systems, Palo Alto, CA, USA), Mirada XD (Mirada Medical Ltd, Oxford, UK), and ABAS (Elekta AB, Stockholm, Sweden). The DIR algorithms were tested on synthetic images generated with the ImSimQA package (Oncology Systems Limited, Shrewsbury, UK) by applying two specific Deformation Vector Fields (DVF) to real patient data-sets. Head-and-neck (HN), thorax, and pelvis sites were included. The accuracy of the algorithms was assessed by comparing the DIR-mapped ROIs from each center with those of reference, using the Dice Similarity Coefficient (DSC) and Mean Distance to Conformity (MDC) metrics. Statistical inference on validation results was carried out in order to identify the prognostic factors of DIR performances. RESULTS: DVF intensity, anatomic site and participating center were significant prognostic factors of DIR performances. Sub-voxel accuracy was obtained in the HN by all algorithms. Large errors, with MDC ranging up to 6 mm, were observed in low-contrast regions that underwent significant deformation, such as in the pelvis, or large DVF with strong contrast, such as the clinical tumor volume (CTV) in the lung. Under these conditions, the hybrid DIR algorithms performed significantly better than the free-form intensity based algorithms and resulted robust against intercenter variability. CONCLUSIONS: The performances of the systems proved to be site specific, depending on the DVF type and the platforms and the procedures used at the various centers. The pelvis was the most challenging site for most of the algorithms, which failed to achieve sub-voxel accuracy. Improved reproducibility was observed among the centers using the same hybrid registration algorithm.

KW - contouring

KW - deformable image registration

KW - multi-institution study

KW - quality assurance

U2 - 10.1002/mp.12737 [doi]

DO - 10.1002/mp.12737 [doi]

M3 - Article

VL - 45

SP - 748

EP - 757

JO - Medical Physics

JF - Medical Physics

SN - 0094-2405

IS - 2

ER -