Patch Triplet Similarity Purification for Guided Real-World Low-Dose CT Image Denoising

TL;DR

This paper introduces a novel patch triplet similarity purification strategy and modifies transformer-based denoising models to effectively utilize non-contrast CT images as guidance, significantly improving real-world low-dose CT denoising performance.

Contribution

It proposes a new PTSP method for selecting highly similar patch triplets and adapts transformer models with cross-attention for guided denoising, addressing misalignment issues in training data.

Findings

Outperforms 15 comparison methods on clinical dataset

PTSP improves training data quality and model performance

Modified transformers with NCCT guidance enhance denoising results

Abstract

Image denoising of low-dose computed tomography (LDCT) is an important problem for clinical diagnosis with reduced radiation exposure. Previous methods are mostly trained with pairs of synthetic or misaligned LDCT and normal-dose CT (NDCT) images. However, trained with synthetic noise or misaligned LDCT/NDCT image pairs, the denoising networks would suffer from blurry structure or motion artifacts. Since non-contrast CT (NCCT) images share the content characteristics to the corresponding NDCT images in a three-phase scan, they can potentially provide useful information for real-world LDCT image denoising. To exploit this aspect, in this paper, we propose to incorporate clean NCCT images as useful guidance for the learning of real-world LDCT image denoising networks. To alleviate the issue of spatial misalignment in training data, we design a new Patch Triplet Similarity Purification (PTSP) strategy to select highly similar patch (instead of image) triplets of LDCT, NDCT, and NCCT images for network training. Furthermore, we modify two image denoising transformers of SwinIR and HAT to accommodate the NCCT image guidance, by replacing vanilla self-attention with cross-attention. On our collected clinical dataset, the modified transformers trained with the data selected by our PTSP strategy show better performance than 15 comparison methods on real-world LDCT image denoising. Ablation studies validate the effectiveness of our NCCT image guidance and PTSP strategy. We will publicly release our data and code.