ESTRO 2022 - Abstract Book

S1582

Abstract book

ESTRO 2022

Conclusion This study suggest that CT-based radiomics score associated with prognostic clinical factors might be a useful tool to improve the prediction of outcomes in patients with lung lesions treated with radical intention. Validation of the score is needed.

PO-1776 Evaluation of two commercial deep learning OAR segmentation models for prostate cancer treatment

J. Gorgisyan 1 , I. Bengtsson 1 , M. Lempart 1,2 , M. Lerner 1,2 , E. Wieslander 1 , S. Alkner 3,4 , C. Jamtheim Gustafsson 1,2

1 Skåne University Hospital, Department of Hematology, Oncology and Radiation Physics, Lund, Sweden; 2 Lund University, Department of Translational Sciences, Medical Radiation Physics, Malmö, Sweden; 3 Lund University, Department of Clinical Sciences Lund, Oncology and Pathology, Lund, Sweden; 4 Skåne University Hospital, Clinic of Oncology, Department of Hematology, Oncology and Radiation Physics, Lund, Sweden Purpose or Objective To evaluate two commercial, CE labeled deep learning-based models for automatic organs at risk segmentation on planning CT images for prostate cancer radiotherapy. Model evaluation was focused on assessing both geometrical metrics and evaluating a potential time saving. Materials and Methods The evaluated models consisted of RayStation 10B Deep Learning Segmentation (RaySearch Laboratories AB, Stockholm, Sweden) and MVision AI Segmentation Service (MVision, Helsinki, Finland) and were applied to CT images for a dataset of 54 male pelvis patients. The RaySearch model was re-trained with 44 clinic specific patients (Skåne University Hospital, Lund, Sweden) for the femoral head structures to adjust the model to our specific delineation guidelines. The model was evaluated on 10 patients from the same clinic. Dice similarity coefficient (DSC) and Hausdorff distance (95 th percentile) was computed for model evaluation, using an in-house developed Python script. The average time for manual and AI model delineations was recorded. Results Average DSC scores and Hausdorff distances for all patients and both models are presented in Figure 1 and Table 1, respectively. The femoral head segmentations in the re-trained RaySearch model had increased overlap with our clinical data, with a DSC (mean±1 STD) for the right femoral head of 0.55±0.06 (n=53) increasing to 0.91±0.02 (n=10) and mean Hausdorff (mm) decreasing from 55±7 (n=53) to 4±1 (n=10) (similar results for the left femoral head). The deviation in femoral head compared to the RaySearch and MVision original models occurred due to a difference in the femoral head segmentation guideline in the clinic specific data, see Figure 2. Time recording of manual delineation was 13 minutes compared to 0.5 minutes (RaySearch) and 1.4 minutes (MVision) for the AI models, manual correction not included.