用稀疏编码和数据自适应、自监督深度学习去噪儿童心脏光子计数CT数据

IF 3.2 2区 医学 Q1 RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING
Medical physics Pub Date : 2025-07-15 DOI:10.1002/mp.17918
Darin P. Clark, Joseph Y. Cao, Cristian T. Badea
{"title":"用稀疏编码和数据自适应、自监督深度学习去噪儿童心脏光子计数CT数据","authors":"Darin P. Clark,&nbsp;Joseph Y. Cao,&nbsp;Cristian T. Badea","doi":"10.1002/mp.17918","DOIUrl":null,"url":null,"abstract":"<div>\n \n \n <section>\n \n <h3> Background</h3>\n \n <p>The judicious use of CT in pediatric cardiac applications is warranted because young patients face the need for repeated imaging and increased lifetime cancer risk after ionizing radiation exposure. The quality of pediatric cardiac CT scans is variable because of limited protocols optimizations for pediatric patients, the common presence of metallic implants following treatment, and disparities in denoising algorithm performance between adult and pediatric scans. Two recent technological developments promise to improve the average quality of pediatric CT scans at fixed or reduced dose: clinical photon-counting CT (PCCT) and deep learning (DL) algorithms for CT image denoising. Given advancements to accommodate variable image quality, these technologies will deliver improved spatial resolution, noise performance, and contrast resolution for pediatric cardiac CT imaging.</p>\n </section>\n \n <section>\n \n <h3> Purpose</h3>\n \n <p>To advance self-supervised DL denoising methods to accommodate variable image quality in pediatric cardiac CT data.</p>\n </section>\n \n <section>\n \n <h3> Methods</h3>\n \n <p>Starting with the popular Vision Transformer (ViT) DL architecture, two targeted architectural changes were made: (1) the multi-layer perceptrons (MLPs) were modified to allow cross-token recombination of encoded image data following attention computations (parallels patch-wise weighting and averaging in non-local means [NLM]), and (2) the network head was replaced with the equivalent of an overcomplete dictionary to perform dictionary sparse coding (SC). This modified, 3D ViT (mViT) was then trained in a dynamic fashion: the balance between data fidelity and representation sparsity was adjusted during training such that the average fidelity error remained consistent with localized estimates of image noise. To demonstrate the newly proposed method, the mViT was trained with pediatric cardiac photon-counting x-ray CT data with variable levels of image noise (NAEOTOM Alpha PCCT scanner; retrospective data from 20 patients scanned at Duke University; ages: 1–18 years; iterative reconstruction noise level in the left ventricle: 20–55 HU). Data from one patient with the highest levels of noise was reserved for validation. Testing data included Alpha data from three additional Duke patients (2 &lt; 1 year old) and a murine cardiac PCCT data set acquired on a preclinical system.</p>\n </section>\n \n <section>\n \n <h3> Results</h3>\n \n <p>The validation denoising results demonstrate that SC with the mViT preserves anatomic structures relevant to the diagnosis and treatment of congenital heart defects (coronary artery origins; valve leaflets; left ventricle boundaries) while achieving similar intensity bias and lower intensity variance values than competing denoising methods (bilateral filtration [BF], NLM, dictionary SC, block matching 4D, orthogonal matching pursuit, Noise2Void). Applying the trained mViT network to preclinical PCCT demonstrated robust generalization performance to high levels of image noise (∼230 HU) and differing image contrast; however, applying the network to clinical PCCT data in younger patients (&lt; 1 year old) demonstrated some smoothing of image details in data already heavily denoised during reconstruction.</p>\n </section>\n \n <section>\n \n <h3> Conclusions</h3>\n \n <p>This work demonstrates robust, self-supervised denoising of pediatric cardiac PCCT data through data adaptation during network training based on local noise estimates. The trained network generalizes to data sets with high levels of noise and differing image contrast relative to the training data, suggesting that self-supervised fine tuning may allow the trained network to address related CT denoising problems.</p>\n </section>\n </div>","PeriodicalId":18384,"journal":{"name":"Medical physics","volume":"52 7","pages":""},"PeriodicalIF":3.2000,"publicationDate":"2025-07-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Denoising pediatric cardiac photon-counting CT data with sparse coding and data-adaptive, self-supervised deep learning\",\"authors\":\"Darin P. Clark,&nbsp;Joseph Y. Cao,&nbsp;Cristian T. Badea\",\"doi\":\"10.1002/mp.17918\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<div>\\n \\n \\n <section>\\n \\n <h3> Background</h3>\\n \\n <p>The judicious use of CT in pediatric cardiac applications is warranted because young patients face the need for repeated imaging and increased lifetime cancer risk after ionizing radiation exposure. The quality of pediatric cardiac CT scans is variable because of limited protocols optimizations for pediatric patients, the common presence of metallic implants following treatment, and disparities in denoising algorithm performance between adult and pediatric scans. Two recent technological developments promise to improve the average quality of pediatric CT scans at fixed or reduced dose: clinical photon-counting CT (PCCT) and deep learning (DL) algorithms for CT image denoising. Given advancements to accommodate variable image quality, these technologies will deliver improved spatial resolution, noise performance, and contrast resolution for pediatric cardiac CT imaging.</p>\\n </section>\\n \\n <section>\\n \\n <h3> Purpose</h3>\\n \\n <p>To advance self-supervised DL denoising methods to accommodate variable image quality in pediatric cardiac CT data.</p>\\n </section>\\n \\n <section>\\n \\n <h3> Methods</h3>\\n \\n <p>Starting with the popular Vision Transformer (ViT) DL architecture, two targeted architectural changes were made: (1) the multi-layer perceptrons (MLPs) were modified to allow cross-token recombination of encoded image data following attention computations (parallels patch-wise weighting and averaging in non-local means [NLM]), and (2) the network head was replaced with the equivalent of an overcomplete dictionary to perform dictionary sparse coding (SC). This modified, 3D ViT (mViT) was then trained in a dynamic fashion: the balance between data fidelity and representation sparsity was adjusted during training such that the average fidelity error remained consistent with localized estimates of image noise. To demonstrate the newly proposed method, the mViT was trained with pediatric cardiac photon-counting x-ray CT data with variable levels of image noise (NAEOTOM Alpha PCCT scanner; retrospective data from 20 patients scanned at Duke University; ages: 1–18 years; iterative reconstruction noise level in the left ventricle: 20–55 HU). Data from one patient with the highest levels of noise was reserved for validation. Testing data included Alpha data from three additional Duke patients (2 &lt; 1 year old) and a murine cardiac PCCT data set acquired on a preclinical system.</p>\\n </section>\\n \\n <section>\\n \\n <h3> Results</h3>\\n \\n <p>The validation denoising results demonstrate that SC with the mViT preserves anatomic structures relevant to the diagnosis and treatment of congenital heart defects (coronary artery origins; valve leaflets; left ventricle boundaries) while achieving similar intensity bias and lower intensity variance values than competing denoising methods (bilateral filtration [BF], NLM, dictionary SC, block matching 4D, orthogonal matching pursuit, Noise2Void). Applying the trained mViT network to preclinical PCCT demonstrated robust generalization performance to high levels of image noise (∼230 HU) and differing image contrast; however, applying the network to clinical PCCT data in younger patients (&lt; 1 year old) demonstrated some smoothing of image details in data already heavily denoised during reconstruction.</p>\\n </section>\\n \\n <section>\\n \\n <h3> Conclusions</h3>\\n \\n <p>This work demonstrates robust, self-supervised denoising of pediatric cardiac PCCT data through data adaptation during network training based on local noise estimates. The trained network generalizes to data sets with high levels of noise and differing image contrast relative to the training data, suggesting that self-supervised fine tuning may allow the trained network to address related CT denoising problems.</p>\\n </section>\\n </div>\",\"PeriodicalId\":18384,\"journal\":{\"name\":\"Medical physics\",\"volume\":\"52 7\",\"pages\":\"\"},\"PeriodicalIF\":3.2000,\"publicationDate\":\"2025-07-15\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Medical physics\",\"FirstCategoryId\":\"3\",\"ListUrlMain\":\"https://onlinelibrary.wiley.com/doi/10.1002/mp.17918\",\"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}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Medical physics","FirstCategoryId":"3","ListUrlMain":"https://onlinelibrary.wiley.com/doi/10.1002/mp.17918","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

摘要

背景:由于年轻患者在电离辐射暴露后需要反复成像和增加终身癌症风险,因此在儿童心脏应用中明智地使用CT是必要的。儿童心脏CT扫描的质量是可变的,因为儿科患者的方案优化有限,治疗后金属植入物的普遍存在,以及成人和儿童扫描之间去噪算法性能的差异。最近的两项技术发展有望提高固定或减少剂量下儿科CT扫描的平均质量:临床光子计数CT (PCCT)和用于CT图像去噪的深度学习(DL)算法。考虑到适应可变图像质量的进步,这些技术将为儿童心脏CT成像提供更好的空间分辨率、噪声性能和对比度分辨率。目的提出自监督深度去噪方法,以适应儿童心脏CT数据中图像质量的变化。方法从流行的Vision Transformer (ViT) DL架构开始,进行了两个有针对性的架构更改:(1)修改多层感知器(mlp),允许在注意力计算后对编码的图像数据进行交叉令牌重组(并行补丁加权和非局部均值平均[NLM]);(2)将网络头部替换为等效的过完备字典,以执行字典稀疏编码(SC)。然后以动态方式训练这种改进的3D ViT (mViT):在训练期间调整数据保真度和表示稀疏度之间的平衡,使平均保真度误差与图像噪声的局部估计保持一致。为了证明新提出的方法,mViT使用具有不同图像噪声水平的儿童心脏光子计数x射线CT数据进行训练(NAEOTOM Alpha PCCT扫描仪;杜克大学扫描的20名患者的回顾性数据;年龄:1-18岁;左心室迭代重建噪声级:20 ~ 55 HU)。保留噪声水平最高的一名患者的数据以供验证。测试数据包括来自另外三名Duke患者的Alpha数据(2 <;1岁)和从临床前系统获得的小鼠心脏PCCT数据集。结果验证去噪结果表明,SC与mViT保留了与先天性心脏缺陷(冠状动脉起源;阀传单;与竞争对手的降噪方法(双边过滤[BF]、NLM、字典SC、块匹配4D、正交匹配追踪、Noise2Void)相比,获得了相似的强度偏差和更低的强度方差值。将训练好的mViT网络应用于临床前PCCT显示出对高水平图像噪声(~ 230 HU)和不同图像对比度的鲁棒泛化性能;然而,将该网络应用于年轻患者的临床PCCT数据(<;1岁)展示了在重建过程中已经严重去噪的数据中图像细节的一些平滑。本研究通过基于局部噪声估计的网络训练过程中的数据适应,证明了儿童心脏PCCT数据的鲁棒性、自监督降噪。训练后的网络泛化到具有高噪声水平和与训练数据不同的图像对比度的数据集,这表明自监督微调可能允许训练后的网络解决相关的CT去噪问题。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Denoising pediatric cardiac photon-counting CT data with sparse coding and data-adaptive, self-supervised deep learning

Background

The judicious use of CT in pediatric cardiac applications is warranted because young patients face the need for repeated imaging and increased lifetime cancer risk after ionizing radiation exposure. The quality of pediatric cardiac CT scans is variable because of limited protocols optimizations for pediatric patients, the common presence of metallic implants following treatment, and disparities in denoising algorithm performance between adult and pediatric scans. Two recent technological developments promise to improve the average quality of pediatric CT scans at fixed or reduced dose: clinical photon-counting CT (PCCT) and deep learning (DL) algorithms for CT image denoising. Given advancements to accommodate variable image quality, these technologies will deliver improved spatial resolution, noise performance, and contrast resolution for pediatric cardiac CT imaging.

Purpose

To advance self-supervised DL denoising methods to accommodate variable image quality in pediatric cardiac CT data.

Methods

Starting with the popular Vision Transformer (ViT) DL architecture, two targeted architectural changes were made: (1) the multi-layer perceptrons (MLPs) were modified to allow cross-token recombination of encoded image data following attention computations (parallels patch-wise weighting and averaging in non-local means [NLM]), and (2) the network head was replaced with the equivalent of an overcomplete dictionary to perform dictionary sparse coding (SC). This modified, 3D ViT (mViT) was then trained in a dynamic fashion: the balance between data fidelity and representation sparsity was adjusted during training such that the average fidelity error remained consistent with localized estimates of image noise. To demonstrate the newly proposed method, the mViT was trained with pediatric cardiac photon-counting x-ray CT data with variable levels of image noise (NAEOTOM Alpha PCCT scanner; retrospective data from 20 patients scanned at Duke University; ages: 1–18 years; iterative reconstruction noise level in the left ventricle: 20–55 HU). Data from one patient with the highest levels of noise was reserved for validation. Testing data included Alpha data from three additional Duke patients (2 < 1 year old) and a murine cardiac PCCT data set acquired on a preclinical system.

Results

The validation denoising results demonstrate that SC with the mViT preserves anatomic structures relevant to the diagnosis and treatment of congenital heart defects (coronary artery origins; valve leaflets; left ventricle boundaries) while achieving similar intensity bias and lower intensity variance values than competing denoising methods (bilateral filtration [BF], NLM, dictionary SC, block matching 4D, orthogonal matching pursuit, Noise2Void). Applying the trained mViT network to preclinical PCCT demonstrated robust generalization performance to high levels of image noise (∼230 HU) and differing image contrast; however, applying the network to clinical PCCT data in younger patients (< 1 year old) demonstrated some smoothing of image details in data already heavily denoised during reconstruction.

Conclusions

This work demonstrates robust, self-supervised denoising of pediatric cardiac PCCT data through data adaptation during network training based on local noise estimates. The trained network generalizes to data sets with high levels of noise and differing image contrast relative to the training data, suggesting that self-supervised fine tuning may allow the trained network to address related CT denoising problems.

求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
Medical physics
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.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:604180095
Book学术官方微信