Although there are few data sets available to researchers in cancer imaging compared with other fields, experts are able to make the most of the data they have available, as explained in this interview with Julia Schnabel, PhD, of Kings College London, London, UK. Prof. Schnabel touches upon the modern machinery learning techniques used, such as convolutional neural networks (CNNs), which have a close to human-level of performance for analyzing tumor images. This interview was recorded at the 2017 National Cancer Research Institute (NCRI) Conference, held in Liverpool, UK.