PURPOSE: Deformable image registration (DIR) is often validated based on a distance-to-agreement (DTA) criterion of automatically propagated anatomical landmarks that were manually identified. Due to human observer variability, however, the performance of the registration method is diluted. The purpose of this study was to evaluate an analysis of variance (ANOVA) based validation to account for such observer variation. METHODS: Weekly cone beam CTs (CBCTs) of ten head and neck cancer patients undergoing five weeks of radiotherapy were used. An expert identified 23 anatomical features (landmarks) on the planning CT. The landmarks were automatically propagated to the CBCT using multiregion-of-interest (mROI) registration. Additionally, two human observers independently localized these landmarks on the CBCTs. Subsequently, ANOVA was used to compute the variance of each observer on the pairwise distance (PWD). RESULTS: ANOVA based analysis demonstrated that a classical DTA approach underestimated the precision for the mROI due to human observer variation by about 25%. The systematic error (accuracy) of mROI ranged from 0.13 to 0.17 mm; the variability (1 SD) (precision) ranged from 1.3 to 1.5 mm demonstrating that its performance is dominated by the precision. CONCLUSIONS: The PWD-ANOVA method accounts for human observer variation allowing a better estimation of the of DIR errors.
PURPOSE: Deformable image registration (DIR) is often validated based on a distance-to-agreement (DTA) criterion of automatically propagated anatomical landmarks that were manually identified. Due to human observer variability, however, the performance of the registration method is diluted. The purpose of this study was to evaluate an analysis of variance (ANOVA) based validation to account for such observer variation. METHODS: Weekly cone beam CTs (CBCTs) of ten head and neck cancerpatients undergoing five weeks of radiotherapy were used. An expert identified 23 anatomical features (landmarks) on the planning CT. The landmarks were automatically propagated to the CBCT using multiregion-of-interest (mROI) registration. Additionally, two human observers independently localized these landmarks on the CBCTs. Subsequently, ANOVA was used to compute the variance of each observer on the pairwise distance (PWD). RESULTS: ANOVA based analysis demonstrated that a classical DTA approach underestimated the precision for the mROI due to human observer variation by about 25%. The systematic error (accuracy) of mROI ranged from 0.13 to 0.17 mm; the variability (1 SD) (precision) ranged from 1.3 to 1.5 mm demonstrating that its performance is dominated by the precision. CONCLUSIONS: The PWD-ANOVA method accounts for human observer variation allowing a better estimation of the of DIR errors.
Authors: He Wang; Lei Dong; Jennifer O'Daniel; Radhe Mohan; Adam S Garden; K Kian Ang; Deborah A Kuban; Mark Bonnen; Joe Y Chang; Rex Cheung Journal: Phys Med Biol Date: 2005-06-01 Impact factor: 3.609
Authors: Jonathan Orban de Xivry; Guillaume Janssens; Geert Bosmans; Mathieu De Craene; André Dekker; Jeroen Buijsen; Angela van Baardwijk; Dirk De Ruysscher; Benoit Macq; Philippe Lambin Journal: Radiother Oncol Date: 2007-10-23 Impact factor: 6.280
Authors: Richard Castillo; Edward Castillo; David Fuentes; Moiz Ahmad; Abbie M Wood; Michelle S Ludwig; Thomas Guerrero Journal: Phys Med Biol Date: 2013-04-10 Impact factor: 3.609
Authors: Ihab S Ramadaan; Karsten Peick; David A Hamilton; Jamie Evans; Douglas Iupati; Anna Nicholson; Lynne Greig; Robert J W Louwe Journal: Radiat Oncol Date: 2015-03-31 Impact factor: 3.481
Authors: Adam C Riegel; Jeffrey G Antone; Honglai Zhang; Prachi Jain; Jagdeep Raince; Anthony Rea; Angelo M Bergamo; Ajay Kapur; Louis Potters Journal: J Appl Clin Med Phys Date: 2016-05-08 Impact factor: 2.102
Authors: Christoph Hoffmann; Sonja Krause; Eva M Stoiber; Angela Mohr; Stefan Rieken; Oliver Schramm; Jürgen Debus; Florian Sterzing; Rolf Bendl; Kristina Giske Journal: J Appl Clin Med Phys Date: 2014-01-06 Impact factor: 2.102