ESTRO 37 Abstract book

S1177

ESTRO 37

distance (ASD), Dice index (DSC) and Jaccard index (JSC). Results The HD, ASD, DSC, JSC (mean±SD) were 28.1±18.9mm, 4.39±7.19mm, 0.732±0.157 and 0.598±0.167 for validation dataset; And these indices was 14.9±7.62mm, 2.67±1.46mm, 0.713±0.126 and 0.568±0.148 between two human radiation oncologists. T-test suggested there is no statistically significant difference between automated segmentation and manual segmentation considering DSC (p=0.61), JSC (p=0.47) and ASD (p=0.29). However, significant difference was found for HD (p=0.0029), which was sensitive to extreme value. Those results were summarized in Table 1. Conclusion This study showed that a simple deep learning neural network can perform a human comparable segmentation for rectum cancer based on MRI T2 images. EP-2132 Repeatability and reproducibility of radiomic features: results of a systematic review A. Traverso 1 , L. Wee 1 , A. Dekker 1 , R. Gillies 2 1 Maastricht Radiation Oncology MAASTRO clinic, Purpose or Objective Broadly generalizable predictions from radiomics-assisted models are tainted by concerns about whether the explanatory features are reproducible and repeatable. We performed a systematic review of published peer- reviewed studies that specifically tested the repeatability and/or reproducibility of radiomic features. The primary objective of the review was to provide a qualitative synthesis of factors affecting feature reproducibility and repeatability. Material and Methods The PubMed index was searched using combinations of the broad Haines and Ingui filters along with a set of text words specific to cancer, radiomics (including texture analyses), reproducibility and repeatability. Two reviewers working entirely independently and the review outcomes have been reported in compliance with PRISMA guidelines. Studies included either medical imaging of human subject and/or of radiological phantoms. Detailed analysis on quality of reporting in retrieved studies pointed towards a number of deficiencies. Qualitative synthesis of radiomic feature stability was grouped by cancer type and imaging modality. Results After screening process, the qualitative synthesis was derived from 41 studies, out of which 35 involved human subjects and 6 were exclusively concerning radiological phantoms. The PRISMA flow diagram is shown in Figure 1. Repeatability and reproducibility of radiomic features are sensitive in varying degrees to methodological details such as image acquisition settings, image reconstruction algorithm, digital image pre-processing and the software used to extract features. Intra-class and concordance correlations were the most widely used statistical metric, but arbitrarily selected cut-offs were not consistent. In general, most of the studies did not report adequate information regarding the software used to compute features, nor about the image pre-processing steps. Few studies made either the images or the computed features openly accessible. Overall, first-order radiomic features were more reproducible than either shape metrics or Radiotherapy, Maastricht, The Netherlands 2 Moffitt Cancer Center, Imaging, Tampa, USA

textural features, but with some dependence on the imaging modality. Entropy was consistently one of the most stable first-order features. There was no emergent consensus regarding either shape metrics or textural features, however coarseness and contrast consistently appeared among the least reproducible. The qualitative synthesis has been summarized in Figure 2. Conclusion Investigations of feature repeatability and reproducibility are currently limited to a small number of cancer types. Reporting quality may be improved in regards to details of: feature extraction software, digital image manipulation (pre-processing) and cut-off value used to distinguish stable features. We recommend that authors publish image collections (including delineations) and feature extraction software as open access resources, to accelerate progress in clinical generalizability and independent validation of models.

EP-2133 Automatic Segmentation of the Prostate Using Shape Models T. Ding 1 , D. McLaren 2 , W. Nailon 3 1 The University of Edinburgh- Institute for Digital Communications, School of Engineering, Edinburgh, United Kingdom 2 Edinburgh Cancer Centre- Western General Hospital-, Department of Clinical Oncology, Edinburgh, United Kingdom 3 Edinburgh Cancer Centre- Western General Hospital-, Department of Oncology Physics, Edinburgh, United Kingdom Purpose or Objective In the UK, prostate cancer accounts for 25% of all new cancers in males with radiotherapy one of the main treatments for this disease. Accurate delineation of the prostate is therefore essential to ensure the best treatment outcome, however, manual delineation of the prostate is not only time consuming but requires considerable clinical experience and knowledge on how