B3CARE aims to advance the technology readiness level for screening of the three diseases, lung cancer, Chronic Obstructive Pulmonary Disease (COPD) and Cardiovascular Disease (CVD), by accelerating software development for data post-processing of CT-images. In this presentation, there will be a focus on the training and education work package of the B3CARE project. This work package aims to inform/train technical physicians to be able to understand and use advanced software tools in clinical care. A focus is put on one particular task in this work package: Development of simulator of patient cases. Training of both the physician and of the advanced software is reliant on the amount and variability of patient cases. Therefore, it would be desirable to create them. The objective of the thesis was to investigate to what extent a generative model, in particular a Generative Adversarial Network (GAN), can be created and used to simulate chest CT patient cases with benign or malignant nodules.
This will be accomplished through answering three sub-questions. It will first be considered in what way images can be created and how the type of image and is difficulty can be influenced. Following this, it will be explored in what way the quality of the generated images can be quantitatively assessed and if this corresponds to human judgement. Finally, it will be explored to what degree lung nodules can be recognised and classified using advanced software tools. Lung nodules are created successfully, but their quantitative assessment is still a huge point of discussion.