Abstract Book

S1195

ESTRO 37

Purpose or Objective To compare the performance of deep neural networks against a technique designed by domain experts in the prediction of gamma passing rates for IMRT QA. Material and Methods 498 Intensity Modulated Radiation Therapy (IMRT) plans representative of all treatment sites were developed in Eclipse version 11 and delivered on Clinac iX or TrueBeam Linacs. 3%/3 mm local dose/distance-to-agreement (DTA) for these plans were obtained using a commercial 2D diode array. 78 physicist-designed metrics that describe different aspects of plan complexity were extracted using the MLC positions and MUs per control point. A generalized Poisson regression model, previously developed, was used to predict DTA using 78 features as input. Separately, fluence maps (not expert designed features) calculated for each plan were used as inputs to a convolution neural network (CNN) and trained by a computer scientist with no knowledge of medical physics, Figure 1. The CNNs were trained using TensorFlow and Keras. A modern architecture, inspired by the convolutional blocks of the VGG-16 ImageNet model, was constructed and implemented. To prevent overfitting and boost performance of the CNNs, synthetic data were generated by rotating and translating the fluence maps during training. Dropout, batch normalization, and data augmentation were utilized to help train the model. The performance of the CNNs was compared to the generalized Poisson regression model that used the 78 expert designed features. Results Deep neural networks without domain knowledge achieved comparable performance to a baseline system designed by domain experts. If an ensemble of deep neural networks is built, then the baseline model (not an ensemble) is outperformed, Figure 2. Conclusion Convolutional neural networks with transfer learning can predict IMRT QA passing rates without the use of expert domain knowledge. EP-2164 Optimising radiation therapy quality assurance (RTQA) in Irish oncology trials N. Wallace 1 , C. Skourou 2 , B. O'Neill 1 , L. O'Sullivan 3 , S. French 4 , M. Cunningham 5 1 St Luke's Radiation Oncology Network- Dublin- Ireland, Beaumont Centre, Dublin 9, Ireland 2 St Luke's Radiation Oncology Network- Dublin- Ireland, Physics, Dublin 9, Ireland 3 Clinical Trials Ireland, Clinical Trials, Dublin, Ireland 4 St Luke's Radiation Oncology Network, Dublin, Ireland 5 St Luke's Radiation Oncology Network, Radiation Oncology, Dublin, Ireland Purpose or Objective RTQA is a critical component in any multicentre radiotherapy trial. It ensures that each participating centre conforms to the standards set by the trial protocol. Ireland’s first RTQA programme was established concurrent with the opening of the CTRIAL-IE (ICORG) 10- 14/Neo-AEGIS clinical trial, the first Irish trial involving radiotherapy to be opened internationally, in 2016. The RTQA programme was designed to provide: • Systematic quality review of the radiotherapy delivered to patients at all participating institutions A solution for the secure transfer of anonymised electronic clinical data pertaining to diagnosis and treatment a method by which the data, including RT treatment plans, can be efficiently and objectively reviewed Material and Methods The RTQA team consists of two consultant radiation oncologists, a radiotherapy medical physicist and a • •

clinical research associate. For each trial, a CT dataset, a structure set (organ and target outlines) and sample RT plans are selected to serve as benchmarks for reference for the performance of other institutions. A secure file transfer system allows for easy and secure exchange of large data sets (including anonymised diagnostic scans, medical reports, RT plans and RT delivery reports) between the participating hospitals and the RTQA team. Finally, Sun Nuclear’s PlanIQ software package provides a platform upon which the transferred data is displayed, reviewed, and assessed for overall treatment plan quality. PlanIQ incorporates a DICOM viewer with scoring algorithms designed to extract and score treatment metrics. Members of the RTQA team meet regularly to qualitatively review and quantitatively evaluate the submitted clinical data and RT plans. Initially, participating centres are asked to complete the benchmark cases. Each submitted plan is processed in PlanIQ where all relevant dose volume metrics are compared against the trial’s expected values. Deviations from trial protocol are highlighted to the participating hospital along with mechanisms for correction This communication continues iteratively until an acceptable plan is achieved. Monitoring of plan quality continues throughout the recruitment period with evaluation of plans from randomly selected patients enrolled in the trial. Results This project has established a programme that provides the framework for the quality assurance and safe delivery of consistent RT treatment across all hospitals participating in Irish-led oncology clinical trials. Since its launch in 2016, two oncology trials have availed of this framework (CTRIAL (ICORG) 10-14/Neo-AEGIS and CTRIAL (ICORG) 12-38/Tri LARC), resulting in the assessment of patient treatments designed by 9 radiation oncologists and dosimetrists in 7 hospitals located in 4 countries. Conclusion This robust and seamless model can easily be adapted for use within any RT clinical trial in Ireland. Its development has enhanced our potential for leadership of clinical trials and ensures high quality and consistency within these trials. EP-2165 Preliminary results of Jarvik 2000 irradiation with high-energy photon beams. R. Gimenez De Lorenzo 1,2 , R. Navarra 2,3 , D. Marinelli 4 , N. Adorante 2 , S. Giancaterino 2 , D. Genovesi 2 , G. Di Giammarco 4 , M.D. Falco 2 1 Azienda Ospedaliera-Universitaria Ospedali Riuniti, Department of Radiation Oncology, Foggia, Italy 2 Università "G. D’Annunzio", Department of Radiation Oncology, Chieti, Italy 3 Università "G. D’Annunzio", Department of Neuroimaging and Cognitive Science, Chieti, Italy 4 Università "G. D’Annunzio", Department of Cardiac Surgery, Chieti, Italy Purpose or Objective Ventricular Assist Device (VAD) improves quality of life in patients with heart failure. However, it is crucial to ensure its functionality if they are exposed to radiotherapy. This work, the first one on Jarvik 2000 VAD, aims at performing measurements of basic operating parameters in vitro setting under high-energy photon beams. Material and Methods The Jarvik 2000 System consisted of a turbine pump (diameter 2.5cm, length 5.5cm, weight 85g) with a neodymium-iron-boron magnet impeller supported by ceramic bearings and housed inside a titanium-welded shell. At 8-12Krpm rotation speed, it generated a5- 7L/min flow rate. Implanted in left ventricle, the VAD