ESTRO 37 Abstract book

S181

ESTRO 37

SP-0356 4D image acquisition: 4D-MRI based evaluation of moving lung tumour target volumes M. McGarry Cork University Hospital, Cork, Ireland

areas of the radiation oncology field ranging from treatment response modelling, treatment planning, image-guidance, motion tracking, and quality assurance in radiation oncology. In this talk, we will briefly review some of the basic principles of machine learning algorithms and provide representative examples of their current application in radiation oncology. We will discuss their advantages and how to avoid some of the common pitfalls (the Do’s and Don’ts of machine learning) with special focus on overfitting issues and best practice strategies. We will highlight some of the current challenges for their application in radiation oncology and potential avenues for future research. SP-0354 Machine learning for image segmentation D. Rueckert 1 1 Imperial College London, Department of Computing, LONDON, United Kingdom Abstract text This talk will introduce the concept of machine learning for medical image segmentation. We will review different deep learning approaches for this task, focusing on different network architectures such as fully connected networks (FCN), U-Net and DeepMedic. We will review the advantages and disadvantages of these different architectures in the context of segmentation in neuroimaging, cardiac imaging and cancer imaging. As these various networks architectures perform differently in real-world applications, with behaviour largely influenced by architectural choices and training settings, we will also explore the concept of Ensembles of Multiple Models and Architectures (EMMA) which enables robust performance through aggregation of predictions from a wide range of methods. The approach reduces the influence of the meta-parameters of individual models and the risk of overfitting the configuration to a particular database. EMMA can be seen as an unbiased, generic deep learning model which has been shown to yield excellent performance in recent segmentation challenges. Finally, we will review unsupervised domain adaptation using adversarial neural networks to train segmentation models which is more invariant to differences in the input data, and which do not require any annotations on the test domain. SP-0355 Machine learning for radiomics and outcome modeling M. Hatt 1 1 INSERM UMR 1101 - LaTIM, Department of Radiation Oncology, Brest, France Abstract text Radiomics has seen an exponential growth as a field of research in cancer outcome modeling. The high- throughput extraction of quantitative data from multimodal medical images opens the way to more discriminative prognostic and predictive models allowing for better patient management. However, numerous challenges still have to be addressed before radiomics- derived multiparametric models can actually be used in clinical practice, including but not limited to: standardization of image analysis and features computation workflow for better reproducibility of studies, machine learning algorithms choice and optimization and multi-centric validation of the developed models. In this talk, a critical review of recently proposed machine learning methods (including deep learning developments) for radiomics will be proposed, as well as insights into the potential future challenges to adress

Abstract not received

SP-0357 Dose precision in MR-only planning workflow R.L. Christiansen 1 1 Odense University Hospital, Radiofysisk Laboratorium, Odense, Denmark Abstract text Current state of the art radiotherapy planning for most indications in the pelvic area consists of a CT scan for dose calculation supplemented by an MRI scan. This provides the soft tissue contrast needed for accurate target definition and often organs at risk (OAR). In many cases additional physiological information through diffusion weighted imaging (DWI) is also used. Numerous approaches to generate an electron density (ED) map, a so-called pseudo CT, from MR data have been undertaken, and some are now commercially available. Thus, an MR only planning workflow will be feasible, eliminating the registration error, as well as saving time and effort. Implementing an MR only planning workflow requires validation of the precision of the dose calculation. When based on a pseudo CT, this precision is affected by geometric accuracy of the underlying MRI as well as the assignment of Hounsfield Units within the pseudo CT. Furthermore, the pseudo CT and DRRs derived from it may not present itself as a standard CT for position verification at treatment. Features such as internal air pockets or implanted fiducials for setup verification may not be visualized in a pseudo CT. A verification study of dosimetric precision of a commercially available pseudo CT product (MRCAT, Philips, Helsinki, Finland), aimed specifically at prostate cancer treatment, was conducted in our clinic. The study included 30 patients and showed good agreement with standard CT calculations in terms of gamma index pass rates. Feasibility of the workflow was proven by patient treatment upon modification of the pseudo CT to include intra-prostatic fiducial markers used for cone beam CT position verification. SP-0358 MRI guided radiotherapy including online treatment planning C. Nomden UMC, Utrecht, the Netherlands SP-0359 Effective medical writing – golden tips for young scientists P. Leventhal 1 1 Medical Writing European Medical Writers Association, Editor in Chief, Lyon, France Abstract text Although you may be a scientific expert and may be able to fulfill a journal's basic requirements for preparing a manuscript, this is not enough to get them published. To be publishable, a manuscript needs to be understandable, interesting, and convincing. Writing clearly and concisely in English is a big part of this, but understanding how to communicate and having a clear focus are just as important. In this talk, I will share some essential grammatical techniques and conceptual methods that will improve your chances of success. Abstract not received Symposium: Medical writing and publishing

Symposium: Advanced image acquisition for planning