ABSTRACT Low‐dose computed tomography (LDCT) is a medical imaging modality designed to minimize ionizing radiation exposure while maintaining the ability to produce detailed cross‐sectional images. It is particularly valuable in scenarios requiring repeated imaging, such as cancer screening, follow‐up examinations or pediatric diagnostics, where reducing radiation dose is critical to patient safety. For example, to reduce noise by half, four times the radiation dose is required in the slice. The goal is to achieve post‐processed LDCT images with comparable quality to those obtained from standard‐dose CT imaging. We start with a brief overview of the CT procedures and their limitations. Then we introduce a novel denoising method based on an asymmetric integration of the ConvNeXt backbone with the U‐Net architecture. This novel approach obtained 2–3 times less noise than the original LDCT, having a 10%–20% increase in performance compared to U‐Net implementation, checked against three metrics MSE, SSIMLoss and combinations of both. The results suggest that: (i) augmenting the images with specific noise, obtained from water phantom CT scan test, while training yields superior results compared to generic noise augmentations; (ii) a larger kernel size better extracts features and (iii) a smaller kernel size was mandatory for feature reconstruction.
Iacob et al. (Thu,) studied this question.