ESTRO 2020 Abstract book

S294 ESTRO 2020

for femoral heads are due to the different definition of these structures in the AI training set.

we quantitatively evaluated a deep neural network algorithm which automatically contours lungs, heart, bladder and rectum as organs-at-risk on computed tomography (CT) for radiation treatment planning. Material and Methods Thoracic CT images of 237 patients (for left/right lungs and the heart) and pelvic CT images of 102 patients (for bladder and rectum) were manually contoured by an expert. On the same CT images, a deep image-to-image network (DI2IN) algorithm, which was trained on a dataset acquired from other hospitals, generated the contours automatically without any user interaction. The manual and automatic contours were quantitatively compared using median Dice Similarity Coefficient (mDSC) and mean surface distance (MSD). The contours were also compared visually, and the areas with the biggest discrepancies between manual and automatic delineation were identified. Results In general, we observed high correlation between automatic and manual contours. The best results were obtained for the left/right lungs with a mDSC of 0.98±0.03/0.98±0.02 (standard deviation) and MSD of 1,7±6,9mm/1,3±2,9mm, and the bladder with a mDSC of 0.94±0.08 and MSD of 1,55±1,77mm. Slightly lower correlations were observed for the heart (mDSC of 0.91±0.02, MSD of 2.0±0.8mm) and the rectum (mDSC 0.86±0.09, MSD 2.16±1,3mm). Comparison of boundary values and visual inspection showed that for the heart automatic and manual contours mostly differed at the cranial boundary (with average deviation of 13.5mm), and for the rectum at both the cranial and the caudal boundary, with average deviations of 8.5 mm and 6.75mm, respectively. One possible reason for the deviations could be the fact that the training of the algorithm was based on contours of other hospitals which might have used different contouring guidelines. Conclusion The DI2IN algorithm automatically generated contours for organs at risk in the thorax and pelvis region which were very similar to the manual contours, making the contouring step in radiation treatment planning simpler and faster. Further improvements are expected when the algorithm will be trained or fine-tuned with a dataset generated in the same hospital to mitigate or eliminate deviations stemming from different contouring guidelines. PH-0486 Dosimetric comparison of bone marrow sparing VMAT VS 3DCRT in locally advanced rectal cancer S.M. LAM 1 , W.Y.V. Lee 2 1 Prince of Wales Hospital, Department of Clinical Oncology, Hong Kong, Hong Kong SAR China ; 2 Tuen Mun Hospital, Hong Kong, Hong Kong SAR China Purpose or Objective (1) To explore the association between clinical and dosimetric parameters with acute hematologic toxicity (HT) in locally advanced rectal cancer (LARC) patients treated with Fluorouracil (5-FU) -based preoperative concurrent chemoradiation (CRT); (2) To provide potential predictors for HT in pelvic CRT planning; (3) To ascertain the dosimetric benefits in bone marrow sparing (BMS)- VMAT compared with 3DCRT in the treatment of LARC. Material and Methods Data from 68 LARC patients treated with 5-FU based neoadjuvant CRT were investigated. The pelvic bone marrow (PBM), including lumbosacral (LSBM), iliac (IBM) and lower pelvic (LPBM), were contoured and dose-volume

Manual contouring took on average 54.9 min, editing automatically segmented structures required on average 43.1 min per patient. Therefore, the use of MVision automatic segmentation algorithm reduced the contouring time by 21.5%. When comparing manual contouring time vs MVison produced contour editing vs Mirada Medical produced contour editing for 4 prostate cancer patients, then MVison was requiring 28.1% and Mirada Medical 4.9% less editing time than manual contouring. Dice scores were comparable between MVison and Mirada Medical contouring tools. Conclusion While the manual editing is still needed, AI based contouring reduces the time required. It should be noted that efficiency gain, among other factors, depends on RTT´s experience and therefore, it can be assumed that involving RTTs with less experience would give a better time efficiency gain. The structure definition in the training set is important and could be used to harmonise contouring practices among different clinics. PH-0485 Clinical evaluation of a deep network organ segmentation algorithm for radiation treatment planning S. Marschner 1 , M. Datar 2 , A. Gaasch 1 , Z. Xu 3 , S. Grbic 3 , G. Chabin 3 , B. Geiger 3 , J. Rosenman 4 , S. Corradini 1 , T. Heimann 2 , C. Moehler 5 , F. Vega 5 , C. Belka 1 , C. Thieke 1 1 Department of Radiation Oncology, University Hospital LMU Munich, Munich, Germany ; 2 Digital Technology & Innovation- Artificial Intelligence Germany, Siemens Healthineers, Erlangen, Germany ; 3 Digital Technology & Innovation- Whole Body & Oncology USA, Siemens Healthineers, Princeton NJ, USA ; 4 Department of Radiation Oncology, University of North Carolina at Chapel Hill, Chapel Hill NC, USA ; 5 Advanced Therapies- Cancer Therapy, Siemens Healthineers, Erlangen, Germany Purpose or Objective Auto contouring algorithms in radiotherapy aim at reducing the time needed for organ segmentation and to reduce inter-observer variations. In this work,