ESTRO 37 Abstract book

S748

ESTRO 37

21.0), V 5

55.7% (range:12.2-81.8) and V 20

23.7%

Comorbidity Score 6.3) were treated for 56 NSCLC and 44 metastases. Tumors were located centrally (27%) or peripherally (73%). Local control rate after 2 years was 91.9%, without significant difference between NSCLC and metastases (p=0.728) or central and peripheral lesions (p=0.511). Marginal recurrence rate was 3.7%, local progression free survival (PFS) and overall survival (OS) were 53.3% and 62.2%, respectively. >=G3-toxicity was <4%, except dyspnea: with baseline >=G3-dyspnea of 6% there was a maximum increase of 8.5% 2 years after SBRT. There was no significant difference in newly appearing >=G3 toxicity for central and peripheral tumors. Low differentiation status (p=0.034), high SUVmax in pre-therapeutic FDG-PET-scans (p<0.001) and lower prescription dose (p=0.043) predicted for worse local control. Patients with metastases (p=0.027) (especially when deriving from gastro intestinal tumors, p < 0.001) showed lower PFS. Higher age (p=0.032) and T- stage (for NSCLC patients) (p=0.023) were predictive for lower OS, the latter also for local PFS (p=0.050). Patients with lower initial FEV1 had an increased risk of marginal recurrence (p< 0.001). Data on QoL is under evaluation. Conclusion This prospective trial confirms high local control and moderate toxicity of SBRT for elderly and comorbid patients treated with moderate-dose SBRT for pulmonary lesions. EP-1370 Generation of tumor-regression CT during definitive CCRT of the lung cancer using deep learning K.S. Kim 1 , M.Y. Kim 1 , H.Y. Kim 2 , C.W. Choi 1 , K.M. Yang 1 1 Dongnam Institute of Radiological and Medical Sciences, Radiation Oncology, Busan, Korea Republic of 2 Artificial Intelligence Research Institute, Research and Developmet, Seongnamsi, Korea Republic of Purpose or Objective For the utilization of adaptive lung radiotherapy, we generated predicted tumor-regression computed tomography (CT) image using conditional generative The CT images of twenty patients who were treated with definitive concurrent chemo-radiotherapy of the lung cancer were used. Each patient had baseline CT (before treatment) and evaluation CT at radiation dose 40Gy (target CT). These pairs of CT images were aligned using MIM software and tumor-containing slices were used. Training set consisted of 14 patients with 391 images and 6 patients with 154 images were included in the test set. cGAN model can be trained to learn a pix-to-pix mapping to predict tumor-regression CT from baseline CT and target CT using generator networks and discriminator networks. Accuracy of the predicted tumor-regression CT were evaluated against target CT using dice similarity score (DSC) of the tumor lesions and volume of the Training process took 5 hours. Predicted tumor-regression CT showed decreased tumor volume while keeping chest wall, body structures and spinal cord. Tumor volume was reduced to 53 ± 10 % in target CT and 48 ± 20 % in predicted tumor-regression CT. DSC of the tumor volume was 0.61 ± 0.17. DSC of the large tumor was greater than that of the small tumor. adversarial nets (cGAN). Material and Methods tumors. Results

(range:5.1-38.2). All values matched the lung OAR dose constraints of V 20 <35% and MLD<20 Gy that are being applied in our institution except for 6 patients (5.3%). 1 patient (0.9%) had MLD>21 Gy and 5 patients (4.4%) had V 20 >35%. In 31 patients (27.2%) was not possible to achieve V5<65% and in 42 patients (36.8%) V5 was larger than 60%. For those patients who hadn’t met one constraint, the other two were achieved. With a median follow-up of 4 months (range:1–32), one case (0.9%) of RP grade 2 and six cases (5.3%) of RP grade 3 have been identified. No cases of RP grade>3. 53 patients (46.5%) died from other causes. 4 patients with RP grade 3 didn't met the V5<65% constraint: 3 were treated with 60Gy/30s (2 with concomitant chemotherapy and 1 sequential) and 1 with 66Gy/33s RT alone. V5 values were respectively 66.3%, 68.4%, 73.6% and 77.4%. The other two patients with RP grade 3 met V5<65%: one was treated with 60Gy/30s and sequential chemotherapy and one with 66Gy/33s and RT alone. The patient with the largest PTV volume (1507.7 cm 3 ), treated with 60Gy/30s and concomitant chemotherapy, didn't met V5<65% and had RP grade 3. No patient treated with 70Gy/35s developed RP. Conclusion Our degree of compliance with the restriction V5<65% is not entirely satisfactory. The follow up time is still short for some patients but treatments have resulted in low incidence of RP grade 3 (4.4%). Nevertheless 53 patients have died from other causes. Further analysis of late toxicity with longer time of follow-up should be done and efforts are needed to reduce these values by probably implementing new techniques such as respiratory motion management. EP-1369 High local control for lung SBRT of comorbid patients: prospective monocenter phase II STRIPE trial S. Adebahr 1,2,3 , U. Nestle 1,4 , K. Kaier 5 , T. Schimek-Jasch 1 , E. Gkika 1 , F. Momm 6 , G. Becker 7 , A.L. Grosu 1,2,3 1 Medical Center- Faculty of Medicine- University of Freiburg, Department of Radiation Oncology, Freiburg, Germany 2 German Cancer Consortium DKTK, Partner Site Freiburg, Freiburg, Germany 3 German Cancer Research Center, DKFZ, Heidelberg, Germany 4 Kliniken Maria Hilf GmbH Mönchengladbach, Department of Radiation Oncology, Mönchengladbach, Germany 5 Faculty of Medicine and Medical Center - University of Freiburg, Institute of Medical Biometry and Statistics, Freiburg, Germany 6 Ortenau Klinikum Offenburg-Gengenbach, Department of Radio-oncology, Offenburg, Germany 7 Medical Center- Faculty of Medicine- University of Freiburg, Clinic for Palliative Care, Freiburg, Germany Purpose or Objective To investigate efficiency and safety of pulmonary moderate-dose SBRT in elderly and comorbid patients. Material and Methods Elderly or comorbid patients with pulmonary lesion <= 5cm (early stage NSCLC or ≤ 2 pulmonary metastases of a controlled primary tumor) were treated with 4DPET/CT- based SBRT (3x12.5 Gy or 5X 7Gy to 60% isodose) within the prospective, monocenter phase II STRIPE trial, funded by Deutsche Krebshilfe. Follow up was performed at 2 and 7 weeks, then 3-monthly until 2 years after SBRT, including toxicity, quality of life (QoL) and CT assessment, PET/CT in case of suspected progression. Predefined prognostic factors were analyzed. Results From 02/2011 to 11/2014 100 eligible patients (63% male, 27% female, mean age 70.3 years, mean Charlson