IPv2: An Improved Image Purification Strategy for Real-World Ultra-Low-Dose Lung CT Denoising

2026-02-22

AI Summary

This work addresses the limitations of existing ultra-low-dose lung CT denoising methods, which struggle to effectively suppress noise in both background regions and pulmonary parenchyma and lack a principled strategy for constructing evaluation labels. To overcome these challenges, the authors propose a novel image purification framework employing a three-stage strategy—background removal, controllable noise injection, and denoising—that enhances the model’s joint denoising capability for both regions during training and enables more realistic label construction during testing. This approach represents the first systematic refinement of the image purification pipeline, is compatible with various mainstream denoising architectures, and demonstrates significant improvements in background suppression and lung structure recovery on real patient CT scans acquired at only 2% of standard radiation dose.

Technology Category

• Computer Vision: Segmentation
• Machine Learning: Calibration & Uncertainty Quantification
• Search and Optimization: Mixed Discrete/Continuous Search

Application Category

• Web Mining and Content Analysis: Web data integration and cleaning
• Economics, Online Markets and Human Computation: LLM based quality controls for crowd work
• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation

Abstract

The image purification strategy constructs an intermediate distribution with aligned anatomical structures, which effectively corrects the spatial misalignment between real-world ultra-low-dose CT and normal-dose CT images and significantly enhances the structural preservation ability of denoising models. However, this strategy exhibits two inherent limitations. First, it suppresses noise only in the chest wall and bone regions while leaving the image background untreated. Second, it lacks a dedicated mechanism for denoising the lung parenchyma. To address these issues, we systematically redesign the original image purification strategy and propose an improved version termed IPv2. The proposed strategy introduces three core modules, namely Remove Background, Add noise, and Remove noise. These modules endow the model with denoising capability in both background and lung tissue regions during training data construction and provide a more reasonable evaluation protocol through refined label construction at the testing stage. Extensive experiments on our previously established real-world patient lung CT dataset acquired at 2% radiation dose demonstrate that IPv2 consistently improves background suppression and lung parenchyma restoration across multiple mainstream denoising models. The code is publicly available at https://github.com/MonkeyDadLufy/Image-Purification-Strategy-v2.

Problem

• ultra-low-dose CT
• image denoising
• lung parenchyma
• background suppression
• image purification

Innovation

• Image Purification
• Ultra-Low-Dose CT
• Lung Parenchyma Denoising
• Background Suppression
• Structural Preservation