Degenerative Adversarial NeuroImage Nets for 4D Simulations: Application in Longitudinal MRI
Accurate and realistic simulation of medical images is a growing area of research relevant to many healthcare applications. However, current image simulators have been unsuccessful when deployed on longitudinal clinical data --- for example, disease progression modelling designed to generate 3D MRI sequences (4D). Failures are typically due to inability to produce subject-specific simulation, and inefficient implementations incapable of synthesizing spatiotemporal images in high resolution. Memory limitations preclude training of the full-4D model, necessitating techniques that discard spatiotemporal information, such as 2D slice-by-slice implementations or patch-based approaches. Here we introduce a novel technique to address this challenge, called Profile Weight Functions (PWF). We demonstrate the power of PWFs by extending a recent framework for neuroimage simulation from 2D (plus time) to 3D (plus time), which is not currently available. To our knowledge, we are the first to implement a disease progression simulator able to predict accurate sequences of realistic, high-resolution, 3D medical images. We demonstrate our framework by training a model using 9652 T1-weighted MRI from the Alzheimer's Disease Neuroimaging Initiative dataset. We validate our results on a separate test set of 1216 MRI, demonstrating the capability to synthesize a personalized time-series of images given a single-time point and other metadata.