Generative Residual Attention Network for Disease Detection
This addresses the challenge of data scarcity in medical imaging for computer-aided diagnosis systems, though it is incremental as it builds on existing generative adversarial learning methods.
The paper tackles the problem of limited annotated medical images for disease detection by generating synthetic X-ray images with abnormalities to augment training data, resulting in improved detection performance that surpasses state-of-the-art baselines on the RSNA dataset.
Accurate identification and localization of abnormalities from radiology images serve as a critical role in computer-aided diagnosis (CAD) systems. Building a highly generalizable system usually requires a large amount of data with high-quality annotations, including disease-specific global and localization information. However, in medical images, only a limited number of high-quality images and annotations are available due to annotation expenses. In this paper, we explore this problem by presenting a novel approach for disease generation in X-rays using a conditional generative adversarial learning. Specifically, given a chest X-ray image from a source domain, we generate a corresponding radiology image in a target domain while preserving the identity of the patient. We then use the generated X-ray image in the target domain to augment our training to improve the detection performance. We also present a unified framework that simultaneously performs disease generation and localization.We evaluate the proposed approach on the X-ray image dataset provided by the Radiological Society of North America (RSNA), surpassing the state-of-the-art baseline detection algorithms.