Prospective randomized double-blind study of atlas-based organ-at-risk autosegmentation-assisted radiation planning in head and neck cancer

• Published in: Radiotherapy and oncology 2014-09, Vol.112 (3), p.321-325
• Main Authors: Walker, Gary V, Awan, Musaddiq, Tao, Randa, Koay, Eugene J, Boehling, Nicholas S, Grant, Jonathan D, Sittig, Dean F, Gunn, Gary Brandon, Garden, Adam S, Phan, Jack, Morrison, William H, Rosenthal, David I, Mohamed, Abdallah Sherif Radwan, Fuller, Clifton David
• Format: Article
• Language: English
• Subjects: Analysis of Variance; Atlas-based autosegmentation; Autocontouring; Automatic segmentation; Cervical Atlas; Double-Blind Method; Feasibility Studies; Female; Head - diagnostic imaging; Head and neck; Head and Neck Neoplasms - diagnostic imaging; Head and Neck Neoplasms - radiotherapy; Hematology, Oncology and Palliative Medicine; Humans; Male; Middle Aged; Neck - diagnostic imaging; Normal tissue; Organs at Risk - diagnostic imaging; Organs-at-risk; Prospective Studies; Radiotherapy Planning, Computer-Assisted - methods; Radiotherapy, Intensity-Modulated - methods; Tomography, X-Ray Computed - methods
• ISSN: 0167-8140; 1879-0887
• DOI: 10.1016/j.radonc.2014.08.028

Abstract Background and purpose Target volumes and organs-at-risk (OARs) for radiotherapy (RT) planning are manually defined, which is a tedious and inaccurate process. We sought to assess the feasibility, time reduction, and acceptability of an atlas-based autosegmentation (AS) compared to manual segmentation (MS) of OARs. Materials and methods A commercial platform generated 16 OARs. Resident physicians were randomly assigned to modify AS OAR (AS + R) or to draw MS OAR followed by attending physician correction. Dice similarity coefficient (DSC) was used to measure overlap between groups compared with attending approved OARs (DSC = 1 means perfect overlap). 40 cases were segmented. Results Mean ± SD segmentation time in the AS + R group was 19.7 ± 8.0 min, compared to 28.5 ± 8.0 min in the MS cohort, amounting to a 30.9% time reduction (Wilcoxon p < 0.01). For each OAR, AS DSC was statistically different from both AS + R and MS ROIs (all Steel–Dwass p < 0.01) except the spinal cord and the mandible, suggesting oversight of AS/MS processes is required; AS + R and MS DSCs were non-different. AS compared to attending approved OAR DSCs varied considerably, with a chiasm mean ± SD DSC of 0.37 ± 0.32 and brainstem of 0.97 ± 0.03. Conclusions Autosegmentation provides a time savings in head and neck regions of interest generation. However, attending physician approval remains vital.