Noise-augmented deep denoising: A method to boost CT image denoising networks

IF 3.2 2区医学 Q1 RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING

Medical physics Pub Date : 2025-09-23 DOI:10.1002/mp.18121

Gernot Kristof, Elias Eulig, Marc Kachelrieß

{"title":"Noise-augmented deep denoising: A method to boost CT image denoising networks","authors":"Gernot Kristof, Elias Eulig, Marc Kachelrieß","doi":"10.1002/mp.18121","DOIUrl":null,"url":null,"abstract":"<div>\n \n \n <section>\n \n <h3> Background</h3>\n \n <p>Denoising low dose computed tomography (CT) images can have great advantages for the aim of minimizing the radiation risk of the patients, as it can help lower the effective dose to the patient while providing constant image quality. In recent years, deep denoising methods became a popular way to accomplish this task. Conventional deep denoising algorithms, however, cannot handle the correlation between neighboring pixels or voxels very well, because the noise structure in CT is a resultant of the global attenuation properties of the patient and because the receptive field of most denoising approaches is rather small.</p>\n </section>\n \n <section>\n \n <h3> Purpose</h3>\n \n <p>The purpose of this study is to improve existing denoising networks, by providing them additional information about the image noise.</p>\n </section>\n \n <section>\n \n <h3> Methods</h3>\n \n <p>We here propose to generate <span></span><math>\n <semantics>\n <mi>N</mi>\n <annotation>$N$</annotation>\n </semantics></math> additional noise realizations by simulation, reconstruct them, and use these noise images as additional input into existing denoising networks. This noise augmentation is intended to guide the denoising process. The additional noise realizations are not only required during training, but also during inference. The rationale behind this noise-augmented deep denoising (NADD) is that CT image noise is strongly patient-specific and it is non-local since it depends on the attenuation of X-ray beams. NADD is architecture-agnostic and can thus be used to improve any previously proposed method. We demonstrate NADD using existing denoising networks that we slightly modified in their input layer in order to take the CT image that is to be denoised plus additional noise images as input. To do so, we modified three popular denoising networks, the CNN10, the ResNet, and the WGAN-VGG and apply them to clinical cases with 90% dose reduction.</p>\n </section>\n \n <section>\n \n <h3> Results</h3>\n \n <p>In all cases tested, the denoising networks strongly benefit from the noise augmentation. Noise artifacts that are being misinterpreted by the original networks as being anatomical structures, are correctly removed by the NADD version of the same networks. The more noise images are provided, the better the performance.</p>\n </section>\n \n <section>\n \n <h3> Conclusions</h3>\n \n <p>Providing additional simulated noise realizations helps to significantly improve the performance of CT image denoising networks.</p>\n </section>\n </div>","PeriodicalId":18384,"journal":{"name":"Medical physics","volume":"52 10","pages":""},"PeriodicalIF":3.2000,"publicationDate":"2025-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://aapm.onlinelibrary.wiley.com/doi/epdf/10.1002/mp.18121","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Medical physics","FirstCategoryId":"3","ListUrlMain":"https://aapm.onlinelibrary.wiley.com/doi/10.1002/mp.18121","RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING","Score":null,"Total":0}

引用次数: 0

Abstract

Background

Denoising low dose computed tomography (CT) images can have great advantages for the aim of minimizing the radiation risk of the patients, as it can help lower the effective dose to the patient while providing constant image quality. In recent years, deep denoising methods became a popular way to accomplish this task. Conventional deep denoising algorithms, however, cannot handle the correlation between neighboring pixels or voxels very well, because the noise structure in CT is a resultant of the global attenuation properties of the patient and because the receptive field of most denoising approaches is rather small.

Purpose

The purpose of this study is to improve existing denoising networks, by providing them additional information about the image noise.

Methods

We here propose to generate $N$ additional noise realizations by simulation, reconstruct them, and use these noise images as additional input into existing denoising networks. This noise augmentation is intended to guide the denoising process. The additional noise realizations are not only required during training, but also during inference. The rationale behind this noise-augmented deep denoising (NADD) is that CT image noise is strongly patient-specific and it is non-local since it depends on the attenuation of X-ray beams. NADD is architecture-agnostic and can thus be used to improve any previously proposed method. We demonstrate NADD using existing denoising networks that we slightly modified in their input layer in order to take the CT image that is to be denoised plus additional noise images as input. To do so, we modified three popular denoising networks, the CNN10, the ResNet, and the WGAN-VGG and apply them to clinical cases with 90% dose reduction.

Results

In all cases tested, the denoising networks strongly benefit from the noise augmentation. Noise artifacts that are being misinterpreted by the original networks as being anatomical structures, are correctly removed by the NADD version of the same networks. The more noise images are provided, the better the performance.

Conclusions

Providing additional simulated noise realizations helps to significantly improve the performance of CT image denoising networks.

Abstract Image

查看原文本刊更多论文

噪声增强深度去噪：一种增强CT图像去噪网络的方法。

背景：低剂量计算机断层扫描（CT）图像去噪对于降低患者的辐射风险具有很大的优势，因为它可以帮助降低患者的有效剂量，同时提供恒定的图像质量。近年来，深度去噪方法成为一种流行的方法来完成这项任务。然而，传统的深度去噪算法不能很好地处理相邻像素或体素之间的相关性，因为CT中的噪声结构是患者整体衰减特性的结果，而且大多数去噪方法的接受野相当小。目的：本研究的目的是改善现有的去噪网络，为它们提供有关图像噪声的额外信息。方法：本文提出通过仿真生成N$ N$附加噪声实现，对其进行重构，并将这些噪声图像作为现有去噪网络的附加输入。这种噪声增强旨在指导去噪过程。不仅在训练过程中需要额外的噪声实现，在推理过程中也需要额外的噪声实现。这种噪声增强深度去噪（NADD）背后的基本原理是，CT图像噪声具有很强的患者特异性，并且是非局部的，因为它取决于x射线束的衰减。NADD是与体系结构无关的，因此可以用来改进任何先前提出的方法。我们使用现有的去噪网络来演示NADD，我们对其输入层进行了轻微修改，以便将待去噪的CT图像加上额外的噪声图像作为输入。为此，我们修改了三种流行的去噪网络，CNN10， ResNet和WGAN-VGG，并将它们应用于临床病例，剂量减少了90%。结果：在所有测试情况下，去噪网络都从噪声增强中获益。被原始网络误解为解剖结构的噪声伪影被相同网络的NADD版本正确地去除。提供的噪声图像越多，性能越好。结论：提供额外的模拟噪声实现有助于显著提高CT图像去噪网络的性能。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

Medical physics 医学-核医学

CiteScore

6.80

自引率

15.80%

发文量

660

审稿时长

1.7 months

期刊介绍： Medical Physics publishes original, high impact physics, imaging science, and engineering research that advances patient diagnosis and therapy through contributions in 1) Basic science developments with high potential for clinical translation 2) Clinical applications of cutting edge engineering and physics innovations 3) Broadly applicable and innovative clinical physics developments Medical Physics is a journal of global scope and reach. By publishing in Medical Physics your research will reach an international, multidisciplinary audience including practicing medical physicists as well as physics- and engineering based translational scientists. We work closely with authors of promising articles to improve their quality.