ESTRO 2022 - Abstract Book

S1384

Abstract book

ESTRO 2022

Conclusion Paired training networks are challenged by the residual registration errors when forming GT data. The output of the Unet showed large anatomical deviations from the daily CBCT. However, the unpaired trained CycleGAN architecture performed much better in preserving the structural information of the daily CBCT and is therefore preferred for CBCT-guided adaptive prostate radiotherapy. [1] DOI: 10.1002/mp.13978 [2] DOI: 10.1016/j.phro.2020.04.002

PO-1600 Development of simplified auto-segmentable functional cardiac atlas

P. Loap 1 , L. De Marzi 1 , K. Kirov 2 , V. Servois 3 , A. Fourquet 1 , A. Khoubeyb 2 , Y. Kirova 1

1 Institut Curie, Department of Radiation Oncology, Paris, France; 2 Institut Curie, Department of Anesthesiology, Paris, France; 3 Institut Curie, Department of Radiology, Paris, France Purpose or Objective There are increasing evidences that radiation doses to specific cardiac substructures are associated with cardiac adverse events. Manual delineation of cardiac substructures is time consuming, and auto-segmentation of cardiac substructure atlases has consequently been evaluated. However, proper delineation of small substructures, such as the left anterior descending coronary artery (LADCA), is challenging and conduction system substructures have never been considered, despite frequent reports of radiation-induced arrhythmias for thoracic irradiation. The aim of this study was to propose and evaluate a simplified auto-segmentable functional cardiac atlas. Materials and Methods We created a cardiac substructure atlas from 20 breast cancer patients’ CT scans consisting of the four cardiac cavities, of a high-risk cardiac zone (HRCZ) as a LADCA surrogate and of the two cardiac conduction nodes. Performance evaluation of atlas-based auto-segmentation (ABAS) was evaluated on a validation data set consisting of 20 additional CT scans. Dice similarity coefficients (DSC) were used to evaluate the concordance level between the manual and the automatic segmentations. Results The average duration of manual segmentation of the proposed cardiac atlas (illustrated in Figure 1 ) ranged between fifteen to twenty minutes, while ABAS lasted two minutes. The median DSC for the delineated cardiac substructures was 0.718 ( Figure 2 ). The highest similarity between manual and automatic segmentation was observed for the left ventricle with a median DSC of 0.87, while the lowest similarity between manual and automatic segmentation was observed for the NAV with a median DSC of 0.15. Regardless of the considered cardiac substructure, auto-segmentation tended to result into smaller volumes than manual segmentation . While smaller, the auto-segmented NAV and SAN were systematically localized within the manual contours. The auto-segmented NAV could be approximated by a 1.6-cm sphere and the auto-segmented SAN by a 1.0-cm sphere.