Image Synthesis for Data Augmentation in Medical CT using Deep Reinforcement Learning
This addresses a bottleneck in medical imaging for researchers by enabling data augmentation from limited CT datasets, though it appears incremental as it combines existing methods.
The paper tackled the problem of limited diverse CT image data for training deep learning models by proposing a deep reinforcement learning approach integrated with style-transfer to generate anatomically accurate high-resolution CT images, showing promise for large-scale synthesis even from small datasets.
Deep learning has shown great promise for CT image reconstruction, in particular to enable low dose imaging and integrated diagnostics. These merits, however, stand at great odds with the low availability of diverse image data which are needed to train these neural networks. We propose to overcome this bottleneck via a deep reinforcement learning (DRL) approach that is integrated with a style-transfer (ST) methodology, where the DRL generates the anatomical shapes and the ST synthesizes the texture detail. We show that our method bears high promise for generating novel and anatomically accurate high resolution CT images at large and diverse quantities. Our approach is specifically designed to work with even small image datasets which is desirable given the often low amount of image data many researchers have available to them.