Computer Vision News - December 2020

2 Medical Imaging Technology Talks 36 Medical device manufacturers do not always have the level of expertise needed to fully leverage a deep learning model as it is not their main field of work. Their focus is on getting the best hardware at the cheapest possible price. Whilst some may understand the theory of how to train a model or what parameters to use, they do not have a thorough understanding of the data and annotation process. Before training a deep learning model, it is vital to understand your data . Is it sufficiently variable to cover the application being developed? There are so many factors that come into play here, including the quality of the ultrasound , and characteristics of the patient, such as age, gender, and BMI , which can all effect the size of the organ being imaged. Once the data is ready, you need to work with your echo specialist or radiologist on the best labeling and annotation procedure. It is an iterative process which is partly about the algorithms and partly about the data . Try one approach, train a model, and then give the data back to the echo specialist who will look again and may make further suggestions. At RSIP Vision , we have a highly skilled team, with many years of experience between them of developing and managing artificial intelligence and deep learning projects . It is what we do every day. We also have access to specialists who know how to interpret data and help us to label and prepare it in such a way that we can get the most out of a deep learning model. It is a complex process requiring extensive experience and, it goes without saying, a great deal of patience! Best of MICCAI 2020