G Rodrigues MD FRCPC MSc; A Louie MD; G Videtic MD FRCPC; L Best MD; N Patil MD; A Hallock MD; S Gaede PhD; J Kempe PhD; J Battista PhD; P de Haan MD; G Bauman MD FRCPC.
Radiation Oncology—Original Article
Categorizing segmentation quality using a quantitative quality assurance algorithm
Article first published online: 5 SEP 2012
© 2012 The Authors. Journal of Medical Imaging and Radiation Oncology © 2012 The Royal Australian and New Zealand College of Radiologists
Journal of Medical Imaging and Radiation Oncology
Volume 56, Issue 6, pages 668–678, December 2012
How to Cite
Rodrigues, G., Louie, A., Videtic, G., Best, L., Patil, N., Hallock, A., Gaede, S., Kempe, J., Battista, J., de Haan, P. and Bauman, G. (2012), Categorizing segmentation quality using a quantitative quality assurance algorithm. Journal of Medical Imaging and Radiation Oncology, 56: 668–678. doi: 10.1111/j.1754-9485.2012.02442.x
Conflict of interest: George Rodrigues, Jerry Battista and Glenn Bauman declare a non-financial academic research agreement for access to StructSure software with Standard Imaging Inc. However, no direct conflicts of interest exist with regards to the content of this work with any of the co-authors.
- Issue published online: 5 DEC 2012
- Article first published online: 5 SEP 2012
- Manuscript Accepted: 25 APR 2012
- Manuscript Received: 29 OCT 2011
- quality assurance;
- target volume delineation;
Obtaining high levels of contouring consistency is a major limiting step in optimizing the radiotherapeutic ratio. We describe a novel quantitative methodology for the quality assurance (QA) of contour compliance referenced against a community set of contouring experts.
Two clinical tumour site scenarios (10 lung cases and one prostate case) were used with QA algorithm. For each case, multiple physicians (lung: n = 6, prostate: n = 25) segmented various target/organ at risk (OAR) structures to define a set of community reference contours. For each set of community contours, a consensus contour (Simultaneous Truth and Performance Level Estimation (STAPLE)) was created. Differences between each individual community contour versus the group consensus contour were quantified by consensus-based contouring penalty metric (PM) scores. New observers segmented these same cases to calculate individual PM scores (for each unique target/OAR) for each new observer–STAPLE pair for comparison against the community and consensus contours.
Four physicians contoured the 10 lung cases for a total of 72 contours for quality assurance evaluation against the previously derived community consensus contours. A total of 16 outlier contours were identified by the QA system of which 11 outliers were due to over-contouring discrepancies, three were due to over-/under-contouring discrepancies, and two were due to missing/incorrect nodal contours. In the prostate scenario involving six physicians, the QA system detected a missing penile bulb contour, systematic inner-bladder contouring, and under-contouring of the upper/anterior rectum.
A practical methodology for QA has been demonstrated with future clinical trial credentialing, medical education and auto-contouring assessment applications.