Atlas-based segmentation technique incorporating inter-observer delineation uncertainty for whole breast

Micro-Mini & Nano-Dosimetry & Innovative Technologies in Radiation Therapy

Bell, L.R.^1,2 ; Dowling, J.A.^3 ; Pogson, E.M.^1,2 ; Metcalfe, P.^1,2 ; Holloway, L.^1,2,4,5

Centre for Medical Radiation Physics, University of Wollongong, Australia^1

Liverpool and Macarthur Cancer Therapy Centres and Ingham Institute, Liverpool, Australia^2

Australian E-Health Research Centre, CSIRO, QLD, Australia^3

SWSCS, University of New South Wales, Australia^4

Institute of Medical Physics, University of Sydney, Australia^5

关键词: Adaptive radiotherapy;    Atlas-based segmentation;    Auto segmentation;    Body mass index;    Breast radiotherapy;    Clinical efficacy;    Observer variations;    Similarity coefficients;   

Others  :  https://iopscience.iop.org/article/10.1088/1742-6596/777/1/012002/pdf
DOI  :  10.1088/1742-6596/777/1/012002

来源: IOP

【 摘 要 】

Accurate, efficient auto-segmentation methods are essential for the clinical efficacy of adaptive radiotherapy delivered with highly conformal techniques. Current atlas based auto-segmentation techniques are adequate in this respect, however fail to account for inter-observer variation. An atlas-based segmentation method that incorporates inter-observer variation is proposed. This method is validated for a whole breast radiotherapy cohort containing 28 CT datasets with CTVs delineated by eight observers. To optimise atlas accuracy, the cohort was divided into categories by mean body mass index and laterality, with atlas' generated for each in a leave-one-out approach. Observer CTVs were merged and thresholded to generate an auto-segmentation model representing both inter-observer and inter-patient differences. For each category, the atlas was registered to the left-out dataset to enable propagation of the auto-segmentation from atlas space. Auto-segmentation time was recorded. The segmentation was compared to the gold-standard contour using the dice similarity coefficient (DSC) and mean absolute surface distance (MASD). Comparison with the smallest and largest CTV was also made. This atlas-based auto-segmentation method incorporating inter-observer variation was shown to be efficient (0.7, MASD