ESTRO 2022 - Abstract Book

S670

Abstract book

ESTRO 2022

OC-0756 Development and implementation of a hybrid method for automatic cardiac substructure segmentation

R. Finnegan 1,2,3 , V. Chin 4,5,6 , P. Chlap 4,3,2 , A. Haidar 4,2,3 , J. Otton 4,7 , J. Dowling 8,1 , D. Thwaites 1 , S. Vinod 4,2,6 , G. Delaney 6,4,5 , L. Holloway 9,1,4,3 1 School of Physics, University of Sydney, Institute of Medical Physics, Sydney, Australia; 2 SWSLHD, Liverpool and Macarthur Cancer Therapy Centres, Liverpool, Australia; 3 Ingham Institute for Applied Medical Research, Medical Physics, Liverpool, Australia; 4 University of New South Wales, South Western Sydney Clinical School, Sydney, Australia; 5 SWSLHD, Liverpool and Macarthur Cancer Therapy Centre, Liverpool, Australia; 6 Ingham Institute for Applied Medical Research, Radiation Oncology, Liverpool, Australia; 7 SWSLHD, Department of Cardiolog, Liverpool, Australia; 8 CSIRO, Australian e-Health Research Centre, Herston, Australia; 9 SWSLHD, Liverpool and Macarthur Cancer Therapy Centre, Sydney, Australia Purpose or Objective Current risk models of radiation-related cardiotoxicity are based on whole heart doses. Cardiac substructure doses may have more predictive value, although further research is needed. Automatic segmentation enables analysis of large retrospective datasets, however, existing approaches do not provide a suitable solution for the highly variable imaging from multi-institute, multi-site clinical radiotherapy data. Additionally, delineation of smaller cardiac structures on CT scans remains a challenge for both manual and automatic methods. Our goal was to develop and implement open-source software to automatically delineate cardiac substructures accurately, consistently, and reliably. Materials and Methods We designed a hybrid method using a deep learning (DL) model (nnU-Net) for whole heart delineation and a modified anatomically-guided multi-atlas technique for delineation of large cardiac substructures (chambers and great vessels), and geometry-based algorithms to delineate small structures (coronary arteries, cardiac valves, conduction nodes) [Fig. 1]. The DL network was trained using 300 CT scans and clinical heart contours from 150 breast cancer and 150 lung cancer patients. The heart and cardiac substructures were manually contoured and automatic segmentations were generated on an independent set of 30 CT scans (20 breast cancer and 10 lung cancer patients), including scans specifically selected for variations in imaging (e.g. artefacts, contrast CT). Segmentation accuracy was measured with Dice Similarity Coefficient (DSC), mean distance to agreement (MDA), and Hausdorff distance (HD), calculated between manual and automatic delineations. Values were compared to previously assessed inter-observer contouring variability (IOV). Four DL models (2D, 3D full-res., 3D low-res., ensemble) were evaluated based on accuracy and segmentation failure rate (DSC<0.8), with consideration for execution speed. Fig. 1