ESTRO 2020 Abstract book

S903 ESTRO 2020

stratification [1]. External validation studies are required. As many hospitals routinely employ (gold) fiducial markers (FM) based IGRT, we investigated the robustness of CT- based radiomics features in the presence of FM and the associated artefacts. Moreover, to determine the utility of robust features, they were employed in building a risk- group classification model (low vs high) applying the same steps in the original published model [1]. Material and Methods Forty CT scans of 20 PCa patients acquired before and after FM insertion were used in this study. For each patient, a prostate gland only (P) structure was contoured on pre-FM CT and on post-FM CT. Population averaged mean prostate Hounsfield Unit (P HU ± SD ) was calculated from pre-FM scans. To reduce the influence of artefacts, four more structures were created on each post-FM scan; excluding only the FM (P-FM); and extracting associated artefacts by restricting the HU inside the prostate to (P HU ±1SD), (P HU ±2SD) and (P HU ±3SD) via thresholding. Radiomics features based on intensity histograms and texture matrices (GLCM, GLRLM, GLSZM, GLDZM, NGTDM and NGLDM) were extracted from all contoured structure after image pre-processing [1]. Using the pre-FM scan as a reference, intra-class correlation coefficients (ICC) were computed to provide an estimate of robustness (ICC = 0 non-robust, ICC= 1 perfectly robust features). In this analysis, a threshold of ICC > 0.8 was considered to identify robust features. The testing cohort consist of 32 low-risk and 233 high-risk patients. Results On pre-FM scans, the P HU was 36.1±3.3HU and the largest variability (SD) within a patient’s prostate was 21.6HU. This value was subsequently used for thresholding (SD=21.6). The structure that produced the largest number of robust features (306/2808) was (P HU ±1SD). Features extracted from (P) and (P-FM) produced the least number of robust features, Figure (1).

School for Oncology and Developmental Biology- Maastricht University Medical Centre, Maastricht, The Netherlands Purpose or Objective Proton therapy (PrTh) for breast cancer (BC) patients has a potential advantage over standard photon therapy (PhTh) in a selection of patients. In the Netherlands, PrTh is reimbursed for BC patients, if the delta Normal Tissue Complication Probability (NTCP) for an acute coronary event (ACE) between a PrTh-plan and PhTh-plan is ≥ 2%. The NTCP has to be calculated based upon the Darby model (1), applied to the lifetime cardiac risk of Dutch people, specified for age, gender and the presence of cardiac risk factors (RF), as described in the approved national indication protocol. The aim of this study is to determine the percentage of BC patients that qualifies for PrTh using this model-based selection. Material and Methods In the period between March 2019 and October 2019, a plan comparison was made for BC patients with an indication for adjuvant radiotherapy (RT), whose mean heart dose (MHD) with the standard PhTh resulted in a NTCP for ACE of > 2% compared to a MHD of 0 Gy (no RT). Patients were only eligible for PrTh, if optical surface scanning showed < 5 mm motion of the chest wall. The PhTh plan was made using a hybrid technique calculated in ECLIPSE, using the Acuros algorithm on a breath hold CT for left sided BC, and on a free breathing CT for right sided BC. Coverage of the planning target volume (PTV) was evaluated according to ICRU guidelines, i.e. Volume(V)95% of PTV ≥ 98%. For PrTh robust intensity modulated proton plans (IMPT) were made around the Clinical Target Volume (CTV) using Raystation with a Monte Carlo algorithm for the Mevion machine on a free breathing CT. Two to 4 beam directions were used with a set-up uncertainty of 0.5 cm and a range uncertainty of 3% (2). Coverage of the CTV was evaluated in the voxel wise minimum plan, based on 28 scenario’s, and should fulfill V95% (CTV) ≥ 98%. Results 443 BC patients had an indication for adjuvant RT in a single center of which for 18 patients a plan comparison was made. Fifteen patients had a delta NTCP of ≥ 2% (mean delta NTCP of 2.9% with a range 2% - 4.6%) of whom 14 agreed with a PrTh. In total 3.2% of the BC patients (14/443) were selected for PrTh. These patients had a mean age of 48 years (range 30–59) and most of them (12/14) had a cardiac RF. The indication for adjuvant RT in the selection group was variable. Although it was expected that mainly patients with an indication for left sided parasternal RT would be selected, only 5/14 had an indication for parasternal RT, of which 2 had right sided BC. The target volumes in the other 9 patients varied, and included even 3 patients with breast only. The average MHD with PhTh was 4.9 Gy (2.9 Gy – 6.6 Gy) and with PrTh 0.88 GyRBE (0.11 GyRBE – 2.63 GyRBE). Conclusion Approximately 3.2% of the BC patients qualified for proton therapy, when the selection was made using an NTCP model for cardiac toxicity with a delta NTCP of ≥ 2%. (1)Darby et al. NEJM 2013;368(11):987-998 (2)Korevaar et al. Radioth Oncol 2019, in press PO-1574 Robustness of CT-based prostate radiomics features against artefacts from gold fiducial markers S. Osman 1 , S. Jain 1 , A.R. Hounsell 2 , K.M. Prise 1 , C.K. McGarry 2 1 Queen's University Belfast, Centre for Cancer Research & Cell Biology, Belfast, United Kingdom ; 2 Belfast Health and Social Care Trust, Radiotherapy Physics, Belfast, United Kingdom Purpose or Objective A previously published model demonstrated the value of CT-based radiomics for prostate cancer (PCa) risk

In a previous test-retest analysis, 522 features were reported to be robust [1]. The overlap between these 522 features and the currently identified features (306) was 133 features. Using only these features, we trained classifiers for risk group. The results are presented in figure 2. As for the original published model [1], the best classifiers (tested on unseen test dataset) were obtained