Radiologists and pathologists frequently make highly consequential perceptual decisions. For example, visually searching for a tumor and recognizing whether it is malignant can have a life-changing impact on a patient. Unfortunately, all human perceivers— even radiologists—have perceptual biases. Because human perceivers (medical doctors) will, for the foreseeable future, be the final judges of whether a tumor is malignant, understanding and mitigating human perceptual biases is important. While there has been research on perceptual biases in medical image perception tasks, the stimuli used for these studies were highly artificial and often critiqued. Realistic stimuli have not been used because it has not been possible to generate or control them for psychophysical experiments. Here, we propose to use Generative Adversarial Networks (GAN) to create vivid and realistic medical image stimuli that can be used in psychophysical and computer vision studies of medical image perception. Our model can generate tumor-like stimuli with specified shapes and realistic textures in a controlled manner. Various experiments showed the authenticity of our GAN-generated stimuli and the controllability of our model.
According to the CDC, over three thousand people die every year from drowning in the United States. Many of these fatalities are preventable with properly trained lifeguards. Traditional lifeguard training relies on videos and mock rescues. While these methods are important, they have their shortcomings. Videos are static and do not build muscle memory. Mock rescues are labor-intensive and potentially put others in danger. Virtual reality (VR) can be used as an alternative training tool, building muscle memory in a fully controlled and safe environment. With full control over variables such as weather, population, and other distractions, lifeguards can be better equipped to respond to any situation. The single most important aspect of life guarding is finding the victim. This head rotation skill can be practiced and perfected in VR before guards ever get onto the stand. It also allows guards to practice in uncommon but nevertheless dangerous conditions such as fog and large crowds. VR also allows the user to get immediate feedback about performance and where they can improve.