How AI can fool Radiologists

I recently came across the Stanford MedAI Youtube Channel where each week a speaker is invited to give a talk on a topic related to Medical AI, and I would highly recommend you check them out. In this week's talk by Jason Jeong on the applications of Generative Adversarial Networks (GANs) in Medical Imaging, he mentions the paper titled "How to Fool Radiologists with Generative Adversarial Networks?". I was immediately drawn to the clever title and went to check the paper out myself. In this paper published in 2018 by Chuquicusma et al., unsupervised learning with Deep Convolutional Generative Adversarial Networks (DC-GANs) was used to generate realistic-looking images of lung nodules. Two radiologists were then asked to undertake a visual turing test where they were asked to determine whether a lung nodule was fake or real.