Key points are not available for this paper at this time.
The chest X-ray (CXR) imaging has been the most frequently performed radiographic examination for decades, and its demand continues to grow due to their critical role in diagnosing various diseases. However, the image quality of CXR has long been a factor limiting their diagnostic accuracy. As a post-processing procedure, image enhancement can cost-effectively improve image quality. Recently, the successful application of deep learning (DL) algorithms in medical image analysis has prompted researchers to propose and design DL-based CXR image enhancement algorithms. This review examines advancements in CXR image enhancement methods from 2018 to 2023, categorizing them into four groups: bone suppression, image denoising, super-resolution reconstruction, and contrast enhancement. For each group, the unique approaches, strengths, and challenges are analyzed. The review concludes by discussing shared challenges across these methods and proposing directions for future research.
Song et al. (Tue,) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: