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.
- Pub Date:
- October 2021
- Electrical Engineering and Systems Science - Image and Video Processing;
- Computer Science - Computer Vision and Pattern Recognition;
- Computer Science - Machine Learning
- The paper is about Pneumonia detection using Generative Modeling. It proposes a novel approach to construct pseudo-pair images and a GAN to generate radio-realistic Chest Xray images. Then, the paper propose to leverage the differences between the input and the generated Xray images as an additional attention-map to boost the performance in Pneumonia detection