ESTRO 2020 Abstract Book

S282 ESTRO 2020

1. Thing RS, et al. Phys Med Biol. 2016;61(15):5781- 802. 2. Peroni M, et al. Int J Radiat Oncol Biol Phys. 2012;84(3):e427-33. 3. Park YK, et al. Med Phys. 2015;42(8):4449-59. SP-0512 On the crucial importance of image preprocessing and harmonization for robust AI-based models I. Buvat 1 1 Université Paris-Sud- Université Paris-Saclay, LITO- UMR1023 Inserm- Institut Curie, Paris, France Abstract text Artificial intelligence-based models offer great potential to make the most of medical images for patient management and treatment planning. These models are based on engineered or deep features calculated from medical images, aka radiomic features, and designed in such a way that they capture the most relevant information present in the images to perform a task (for instance delineate a tumor or organ at risk), to make a prediction or to classify patients. AI-based radiomic models are derived through a training process most often involving annotated data, ie images associated with a (surrogate) ground truth. They should then be validated on data that have not been used to create the models, and for which a ground truth is also available to characterize the performance of the model. One of the main challenges faced by radiomics lies in the variability in image properties (eg, spatial resolution, signal-to-noise ratio) and quality, as a function of the specific acquisition device and protocol used to produce the images. Such variability has been shown to penalize the ability of the model to generalize, that is to perform well on data acquired in different conditions (Reuzé et al, Oncotarget 2017). To tackle that problem, several approaches can be used, among which training the model based on a large variety of data encompassing a broad range of acquisition conditions, harmonizing the images before training, harmonizing the features before designing the model, or fine tuning the model to the specificities of each dataset. The relevance and applicability of these different approaches will be compared and discussed, and practical solutions will be presented with examples in CT, PET and MR imaging. The impact of harmonization procedures on the robustness of AI-based radiomic models will be described and illustrated.

treats the patient who has the disease” it has been recognised that the patient is an individual and so how we care for each patient should be centred on the person, not the disease. The UK NHS Five Year Forward View 1 advocates a shift in power to patients stating that “The NHS is of the people, by the people and for the people” and that we need to involve them directly in decisions about their care. This is echoed across Europe with the Danish Health Authority describing the focus of quality as “treatment with the patient in the centre” 2 ; and across the world with the Patient Engagement Guidelines for Canadian Radiation Treatment Programs 3 promoting patient engagement and participation at individual, program and agency levels to integrate information and professional advice with the patient’s needs, preferences and abilities. In modern radiotherapy settings this concept is more important than ever as advances and improvements in radiotherapy techniques allow for the production of a highly complex, individualised treatment plan but one that is created remotely, without the patient present. The delivery of these complex plans and advanced techniques can result in a disconnect from the patient and their individual values, wants and needs as staff strive to provide safe, accurate and time efficient treatments. This dissonance between high technology with little or no patient contact 4 and the concept of caring for the patient where there is direct interaction and support creates a difficult dichotomy for RTTs to resolve. Attending for radiotherapy treatment can cause significant distress and anxiety for the patient and the RTT’s objective to provide specific treatment and side effects related information may exacerbate this anxiety if they are not also responsive to the patient’s preferences and values. Patients express dissatisfaction with their care as threats to personal identity including perceptions of being dehumanised, objectified, stereotyped, disempowered and devalued 5 . The RTT is the human interface between the patient and this dehumanising effect of unfamiliar, complex treatments and technology and, as such, can help to demystify and moderate the experience. Individualised person-centred care can lead to improved outcomes and patient satisfaction and can provide improved job satisfaction for the RTT. This talk seeks to examine the ways in which RTTs can provide individualised person-centred care in highly pressured, technological environments. It will present different tools such as Holistic Needs Assessments (HNAs), Patient Recorded Outcome Measures (PROMs) and consultation models that can assist the RTT to achieve this when providing patient education and information sessions. Finally it will present the concept of values-based practice 6 as a key skill for person-centred care that should underpin patient interactions and communication at all points of care. References: 1.NHS England, Public Health England, Health Education England, Monitor, Care Quality Commission, NHS Trust Development Authority (2014) Five Year Forward View. 2.Ministeriet for Sunhed og Forebyggelse, 2015 cited in Moller L (2016) Radiography with the Patient in the Centre; Journal of Radiology Nursing:35; 309-314. 3.Canadian Partnership for Quality Radiotherapy, Patient Engagement Guidelines for Canadian Radiation Treatment Programs. June 8, 2016. www.cpqr.ca . 4.Bolderston A, Lewis D, Chai M (2010) The concept of caring: Perceptions of radiation therapists. Radiography; 16, 198-208. 5.Coyle J, (1999) Exploring the meaning of dissatisfaction with health care: The importance of personal identity threat. Social Health & Illness; 21, 95-123. 6.Strudwick R, Newton- Hughes A et al (2018) Values-based Practice in Diagnostic

Symposium: Individualised radiotherapy

SP-0513 PET-based dose painting in head and neck cancer C. Thomas Guys and St Thomas NHS Foundation Trust, London, UK

Abstract not available

SP-0514 The role of the RTT in individualised patient centric care H. Nisbet 1 1 Oxford University Hospitals NHS Foundation Trust, Radiotherapy Department, Oxford, United Kingdom Abstract text Since Sir William Osler (1849-1919) postulated that “the good physician treats the disease; the great physician