Denoising via Repainting: an image denoising method using layer wise medical image repainting

2025-03-11

AI Summary

Medical image denoising requires simultaneous noise suppression and preservation of anatomical structural integrity. To address this, we propose a coarse-to-fine multi-scale inpainting framework: an anisotropic Gaussian filtering-based scale space is constructed, and parametric Bézier paths are employed for structural redrawing and patch filling on layer-wise segmented components, enabling progressive detail recovery. This work introduces Bézier curve modeling to medical image denoising for the first time, integrating self-intersection–constrained shape consistency optimization to jointly balance structural fidelity and noise reduction. Quantitative evaluation on multiple MRI datasets demonstrates significant improvements in PSNR and SSIM over state-of-the-art methods. The approach exhibits low data dependency, strong cross-domain generalizability, and clinical applicability, as validated by expert radiological assessment.

Technology Category

• Computer Vision: Segmentation
• Machine Learning: Structured Learning
• Search and Optimization: Non-convex Optimization

Application Category

• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• Web Mining and Content Analysis: Robustness and generalizability of Web mining methods
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

Medical image denoising is essential for improving the reliability of clinical diagnosis and guiding subsequent image-based tasks. In this paper, we propose a multi-scale approach that integrates anisotropic Gaussian filtering with progressive Bezier-path redrawing. Our method constructs a scale-space pyramid to mitigate noise while preserving critical structural details. Starting at the coarsest scale, we segment partially denoised images into coherent components and redraw each using a parametric Bezier path with representative color. Through iterative refinements at finer scales, small and intricate structures are accurately reconstructed, while large homogeneous regions remain robustly smoothed. We employ both mean square error and self-intersection constraints to maintain shape coherence during path optimization. Empirical results on multiple MRI datasets demonstrate consistent improvements in PSNR and SSIM over competing methods. This coarse-to-fine framework offers a robust, data-efficient solution for cross-domain denoising, reinforcing its potential clinical utility and versatility. Future work extends this technique to three-dimensional data.

Problem

• Develops a multi-scale medical image denoising method.
• Preserves structural details while reducing noise effectively.
• Improves PSNR and SSIM metrics over existing techniques.

Innovation

• Multi-scale anisotropic Gaussian filtering integration
• Progressive Bezier-path redrawing for image reconstruction
• Scale-space pyramid for noise reduction and detail preservation