Radiomics for clinical decision support system in oncology

Radiomics for clinical decision support system in oncology

Physica Medica 52 (2018) 165–182 Contents lists available at ScienceDirect Physica Medica journal homepage: http://www.physicamedica.com Abstracts ...

155KB Sizes 0 Downloads 38 Views

Physica Medica 52 (2018) 165–182

Contents lists available at ScienceDirect

Physica Medica journal homepage: http://www.physicamedica.com

Abstracts from the Irish Association of Physicists in Medicine 9th Annual Scientific Meeting Plenary Session Guest Lecture 08:45–10:50 Learning from every patient treated Marcel Van Herk, Alan Mcwilliam, Andrew Green, Eliana Vasquez osorio, William Beasley, Ananya Choudhury, Corinne Faivre-Finn The Christie NHS Trust, United Kingdom Modern precision radiotherapy allows small safety margins and dose escalation. Therefore, biological factors become much more important such as CTV delineation and thresholds for organ at risk tolerance. Our aim is to develop image based data mining for exploring voxel-based dose–response relationships in very large patient cohorts. Large numbers of planning CTs are deformably registered to a reference CT. Registration uncertainties are quantified using organ-at-risk contours, dose distributions are smoothed according to these uncertainties and mapped onto the reference. Next outcome measures are correlated voxel-by-voxel with the dose distributions. The resulting correlation maps are tested for significance using a test statistic, e.g. maximum t-value, using randomization to test for significance. We have applied this methodology in several tumour sites and a great strength of this technique is that it allows discovery of sensitive sub-structures of organs. For example, in lung cancer we demonstrated a relationship of dose to the base of the heart with early mortality (1100 patients); while in head and neck cancer, masseter dose correlated most with post treatment trismus. In prostate cancer, obturator dose relates to PSA control. To understand the results, it is important to study inherent correlations in voxel-wise dose distributions that are related to planning techniques that are often ignored in dose-volume based analyses. We conclude that voxel based dose response relationships can be discovered efficiently using deformable registration and novel statistical techniques and that these complement traditional dose–volume analyses, and are suitable for very large patient cohorts. https://doi.org/10.1016/j.ejmp.2018.06.014

Radiomics for clinical decision support system in oncology Sean Walsh MAASTRO Clinic, The Netherlands Radiomics, the high-throughput mining of quantitative image features from (standard-of-care) medical imaging that enables

knowledge extraction and application within clinical-decision support systems to improve diagnostic, prognostic, and predictive accuracy, is gaining importance in oncology. Radiomics utilizes artificial intelligence tools together with medical imaging data (complimentary to clinical, biological/genetic, and cost data) to help make precision medicine a reality. This talk describes the process of radiomics, its challenges, opportunities, and capacity to improve clinical decision making. Currently, radiomics is developing swiftly; though it lacks standardized evaluation criteria of both the scientific veracity and the clinical importance of published studies. Therefore, rigorous evaluation criteria and reporting guidelines need to be established in order for radiomics to mature as a discipline. To this end for both retrospective and prospective studies, the radiomics quality score (RQS: www.radiomics.world) and an online digital phantom (DOI: 10.17195/candat.2016.08.1) are offered to provide guidance and help meet this need in the field of radiomics. https://doi.org/10.1016/j.ejmp.2018.06.015

Diagnostic Parallel Session 11:20–12:50 Managed equipment service – Is it all it’s cracked up to be? Patricia Egan Beacon Hospital, Ireland E-mail address: [email protected] Managed equipment service contracts are not a new concept but have not been widely adopted. This hospital commenced a process in 2015 to select a suitable partner for a 10 year MES contract. Whilst on the face of it it’s all about the equipment there are many other facets of the organization involved – finance, project management, stakeholder engagement, to name a few. Almost two years after implementation MES is under the microscope as to how it serves the radiology department, clinicians and the C-suite. This presentation is a whistle stop tour of how an MES can be approached; what can be achieved by engaging in such a contract; and the integral role that Medical Physicists can play in its implementation. https://doi.org/10.1016/j.ejmp.2018.06.016