ESTRO 2023 - Abstract Book

S13

Saturday 13 May

ESTRO 2023

SP-0036 Deep learning for prostate treatment planning E. Gershkevitsh 1 1 North Estonia Medical Centre, Radiotherapy, Tallinn, Estonia

Purpose To describe steps required to introduce the machine learning treatment planning process into clinical practice. Methods and Material Machine learning treatment planning process was introduced in RayStation version 10A. Prostate cancer treatment plan generation model was created by the vendor based on Princess Margaret Hospital developed model incorporating the local hospital clinical goals and DVH parameters. Six local treatment plans were selected for the model fine-tuning. Ten patients were selected for model validation. After validation two plans (manual and autoplanned) were prospectively created for each prostate cancer patient. The plans were presented to two radiation oncologists who scored the plans and provided a feedback without prior knowledge of which plan is which. Results Initially, only about 25% of the plans selected were autoplanned due to worse PTV coverage and higher dose to the bladder. Moreover, review of 3D dose cube and clinical review has helped to identify the weaknesses and to improve the model further. After four model iterations 60-65% selected plans were autoplanned. Further 15% of plans have had a very minor dose distribution differences. Conclusion Current strategy is to do the autoplan and if the plan meats clinical goals then no manual plan is created. Machine learning treatment planning has improved the overall plan quality, saved time and reduced interplanner plan quality variability. It is important to incorporate into the model not only the DVH parameters, but also clinical feedback and 3D isodose distributions to improve the model during commissioning process. SP-0037 Clinical evaluation of autonomous, unsupervised planning integrated in MR-guided radiotherapy for prostate cancer D. Zips 1 , L. Künzel 2 , M. Nachbar 1 , M. Hagmüller 3 , C. Gani 4 , S. Böke 4 , D. Wegener 4 , F. Paulsen 4 , D. Thorwarth 3 1 Charite, Radiation Oncology, Berlin, Germany; 2 OncoRay, Radiation Oncology, Dresden, Germany; 3 University Hospital Tübingen, Section for Biomedical Physics, Department of Radiation Oncology, Tübingen, Germany; 4 University Hospital Tübingen, Radiation Oncology, Tübingen, Germany Abstract Text In the talk I will present an evaluation of autonomous, unsupervised planning integrated in MR-guided radiotherapy for prostate cancer (PMID: 35134447). Five radiation oncologists scored automatically segmented target volumes and OARs as well as an automatically generated VMAT plans for 10 patients with prostate cancer. I will discuss the results, next steps and potentia l implications for future radiation oncology. SP-0038 Role of music and ambient light and their impact on the patients immobilisation and verification P. Scherer 1 1 County Hospital Salzburg, University Clinic for Radiotherapy and Radiooncology of the Paracelsus Medical University, Salzburg, Austria Abstract Text Cancer patients are confronted with a life-threatening diagnosis and therapeutic options, such as radiation therapy, with which they are unfamiliar. Despite extensive patient education patients experience anxiety, especially at the beginning of therapy. The huge machines and the rather large treatment rooms - traditionally white and sterile – do not create a pleasant, comfortable atmosphere. Especially with the change from dimmed light for positioning to bright light, and the necessity to lie still and half-naked on an uncomfortable treatment couch. Coloured ambient lighting can help the patients to calm down and feel more comfortable. Additional music in the background can distract the patients from the uncomfortable situation and the anxiety. Patients tend to report these as positive and supportive of their well-being. However, in a previously conducted internal study, we did not find significant changes in anxiety scores. Nevertheless, especially radiation therapists working with patients in the treatment room on a daily basis need to be aware of the possible limitations that these installations in treatment rooms can bring; for example, coloured light can impair the assessment of skin reactions and background music can make communication more difficult. Both of these problems can be circumvented by sophisticated installation with the possibility to easily adjust or turn off these additions in-room. An anticipated potential problem was the effect of the coloured light on surface guidance; however, no negative effect could be found with the two systems used in our department. Catchy music also had no significant effect on intrafraction movement, as patients were aware of the need to remain as still as possible. In summary, ambient light and music in the treatment room can help the patients relax and feel comfortable, without significantly affecting the work of the radiation therapist, patient positioning and patient care. Potentially, the positive impact on patient well-being and comfort, as well as the calming effect, could possibly even support patient positioning. Symposium: Immobilisation and verification

SP-0039 Breast radiotherapy immobilisation and verification S. Wickers 1 1 University College London Hospital, Radiotherapy, London, United Kingdom

Abstract Text