ESTRO 2022 - Abstract Book

S38

Abstract book

ESTRO 2022

https://wiki.cancerimagingarchive.net/display/Public/Lung+CT+Segmentation+Challenge+2017

PD-0065 Corrective-annotation auto-completion enables faster organ contouring

A. Smith 1,2 , J. Petersen 1,2 , I. Wahlstedt 2,5 , S.L. Risumlund 2 , M.V.O. Felter 3 , V.N. Hansen 2 , I.R. Vogelius 2,4

1 University of Copenhagen, Computer Science, Copenhagen, Denmark; 2 Rigshospitalet, Department of Oncology, Copenhagen, Denmark; 3 Herlev and Gentofte Hospital, Department of Oncology, Copenhagen, Denmark; 4 University of Copenhagen, Department of Health and Medical Sciences, Copenhagen, Denmark; 5 Technical University of Denmark, Department of Health Technology, Kongens Lyngby, Denmark Purpose or Objective Corrective-annotation methods have been shown to continually improve segmentation performance and consistency for routine delineation tasks. Correcting auto-generated contours may still be tedious as error regions often span multiple axial slices, requiring similar manual corrections to each slice. We propose to use the ongoing corrective annotation of the current scan as input to the model to refine predictions in subsequent slices, generating real time auto-contour updates as delineation progresses. We evaluate the performance of our contour auto-complete method by comparing it to a baseline method where all corrections are assigned manually without updates to the model prediction during delineation (full-correction). We hypothesize that the auto-complete method will result in reductions in delineation time in comparison to the baseline method whilst maintaining high accuracy. Materials and Methods Both corrective annotation methods (auto-complete and full-correction) were implemented as variations of the open-source RootPainter3D [1] deep learning auto-contouring software, which uses corrective-annotation in training to improve auto- contouring accuracy. We used a dataset of MRI scans which included multiple scans from 31 different patients with liver metastases that had been referred to SBRT. 177 scans were delineated in the same order using both methods. 12 images from the 177 were also delineated by a trained clinician using the MRIdian planning system to enable consistency to be checked between the completed corrective delineations and standard clinical delineations.