Low-Dose CT Denoising Using a Structure-Preserving Kernel Prediction Network
This work addresses the challenge of improving diagnostic accuracy in low-dose CT imaging for clinical screening, though it appears incremental as it builds on existing kernel prediction networks.
The paper tackled the problem of preserving fine-grained structures while removing non-uniform noise in low-dose CT denoising, and the proposed method achieved superior performance on synthetic and non-synthetic datasets.
Low-dose CT has been a key diagnostic imaging modality to reduce the potential risk of radiation overdose to patient health. Despite recent advances, CNN-based approaches typically apply filters in a spatially invariant way and adopt similar pixel-level losses, which treat all regions of the CT image equally and can be inefficient when fine-grained structures coexist with non-uniformly distributed noises. To address this issue, we propose a Structure-preserving Kernel Prediction Network (StructKPN) that combines the kernel prediction network with a structure-aware loss function that utilizes the pixel gradient statistics and guides the model towards spatially-variant filters that enhance noise removal, prevent over-smoothing and preserve detailed structures for different regions in CT imaging. Extensive experiments demonstrated that our approach achieved superior performance on both synthetic and non-synthetic datasets, and better preserves structures that are highly desired in clinical screening and low-dose protocol optimization.