A Denoising Framework for Real-World Ultra-Low-Dose Lung CT Images Based on an Image Purification Strategy
This addresses the challenge of reducing radiation exposure in clinical CT imaging while maintaining image quality, though it is incremental as it builds on existing AI-based enhancement techniques.
The paper tackled the problem of reconstructing clear images from real-world ultra-low-dose lung CT scans, which suffer from domain-shift issues when using synthetic data, by constructing a paired dataset with only 2% radiation dose and achieving excellent reconstruction performance with a Frequency-domain Flow Matching model.
Computed Tomography (CT) is a vital diagnostic tool in clinical practice, yet the health risks associated with ionizing radiation cannot be overlooked. Low-dose CT (LDCT) helps mitigate radiation exposure but simultaneously leads to reduced image quality. Consequently, researchers have sought to reconstruct clear images from LDCT scans using artificial intelligence-based image enhancement techniques. However, these studies typically rely on synthetic LDCT images for algorithm training, which introduces significant domain-shift issues and limits the practical effectiveness of these algorithms in real-world scenarios. To address this challenge, we constructed a real-world paired lung dataset, referred to as Patient-uLDCT (ultra-low-dose CT), by performing multiple scans on volunteers. The radiation dose for the low-dose images in this dataset is only 2% of the normal dose, substantially lower than the conventional 25% low-dose and 10% ultra-low-dose levels. Furthermore, to resolve the anatomical misalignment between normal-dose and uLDCT images caused by respiratory motion during acquisition, we propose a novel purification strategy to construct corresponding aligned image pairs. Finally, we introduce a Frequency-domain Flow Matching model (FFM) that achieves excellent image reconstruction performance. Code is available at https://github.com/MonkeyDadLufy/flow-matching.