利用对比性对抗领域泛化技术实现受试者感知的 PET 去噪。

X Liu, T Marin, S Vafay Eslahi, A Tiss, Y Chemli, K A Johson, G El Fakhri, J Ouyang
{"title":"利用对比性对抗领域泛化技术实现受试者感知的 PET 去噪。","authors":"X Liu, T Marin, S Vafay Eslahi, A Tiss, Y Chemli, K A Johson, G El Fakhri, J Ouyang","doi":"10.1109/nss/mic/rtsd57108.2024.10656150","DOIUrl":null,"url":null,"abstract":"<p><p>Recent advances in deep learning (DL) have greatly improved the performance of positron emission tomography (PET) denoising performance. However, DL model performance can vary a lot across subjects, due to the large variability of the count levels and spatial distributions. A generalizable DL model that mitigates the subject-wise variations is highly expected toward a reliable and trustworthy system for clinical application. In this work, we propose a contrastive adversarial learning framework for subject-wise domain generalization (DG). Specifically, we configure a contrastive discriminator in addition to the UNet-based denoising module to check the subject-related information in the bottleneck feature, while the denoising module is adversarially trained to enforce the extraction of subject-invariant features. The sampled low-count realizations from the list-mode data are used as anchor-positive pairs to be close to each other, while the other subjects are used as negative samples to be distributed far away. We evaluated on 97 <sup>18</sup>F-MK6240 tau PET studies, each having 20 noise realizations with 25% fractions of events. Training, validation, and testing were implemented using 1400, 120, and 420 pairs of 3D image volumes in a subject-independent manner. The proposed contrastive adversarial DG demonstrated superior denoising performance than conventional UNet without subject-wise DG and cross-entropy-based adversarial DG.</p>","PeriodicalId":73298,"journal":{"name":"IEEE Nuclear Science Symposium conference record. Nuclear Science Symposium","volume":"2024 ","pages":""},"PeriodicalIF":0.0000,"publicationDate":"2024-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11497478/pdf/","citationCount":"0","resultStr":"{\"title\":\"Subject-aware PET Denoising with Contrastive Adversarial Domain Generalization.\",\"authors\":\"X Liu, T Marin, S Vafay Eslahi, A Tiss, Y Chemli, K A Johson, G El Fakhri, J Ouyang\",\"doi\":\"10.1109/nss/mic/rtsd57108.2024.10656150\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p><p>Recent advances in deep learning (DL) have greatly improved the performance of positron emission tomography (PET) denoising performance. However, DL model performance can vary a lot across subjects, due to the large variability of the count levels and spatial distributions. A generalizable DL model that mitigates the subject-wise variations is highly expected toward a reliable and trustworthy system for clinical application. In this work, we propose a contrastive adversarial learning framework for subject-wise domain generalization (DG). Specifically, we configure a contrastive discriminator in addition to the UNet-based denoising module to check the subject-related information in the bottleneck feature, while the denoising module is adversarially trained to enforce the extraction of subject-invariant features. The sampled low-count realizations from the list-mode data are used as anchor-positive pairs to be close to each other, while the other subjects are used as negative samples to be distributed far away. We evaluated on 97 <sup>18</sup>F-MK6240 tau PET studies, each having 20 noise realizations with 25% fractions of events. Training, validation, and testing were implemented using 1400, 120, and 420 pairs of 3D image volumes in a subject-independent manner. The proposed contrastive adversarial DG demonstrated superior denoising performance than conventional UNet without subject-wise DG and cross-entropy-based adversarial DG.</p>\",\"PeriodicalId\":73298,\"journal\":{\"name\":\"IEEE Nuclear Science Symposium conference record. Nuclear Science Symposium\",\"volume\":\"2024 \",\"pages\":\"\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2024-10-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11497478/pdf/\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"IEEE Nuclear Science Symposium conference record. Nuclear Science Symposium\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/nss/mic/rtsd57108.2024.10656150\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"2024/9/25 0:00:00\",\"PubModel\":\"Epub\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"IEEE Nuclear Science Symposium conference record. Nuclear Science Symposium","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/nss/mic/rtsd57108.2024.10656150","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"2024/9/25 0:00:00","PubModel":"Epub","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

摘要

深度学习(DL)的最新进展大大提高了正电子发射断层扫描(PET)去噪性能。然而,由于计数水平和空间分布的巨大差异,DL 模型在不同受试者身上的表现会有很大不同。为了在临床应用中建立一个可靠、可信的系统,我们非常期待一个可减轻受试者差异的通用 DL 模型。在这项工作中,我们提出了一个对比对抗学习框架,用于主体领域泛化(DG)。具体来说,除了基于 UNet 的去噪模块外,我们还配置了一个对比判别器来检查瓶颈特征中与主体相关的信息,同时对去噪模块进行对抗训练,以强制提取与主体无关的特征。从列表模式数据中抽取的低计数变现作为锚正对,相互靠近,而其他主体作为负样本,分布较远。我们在 97 项 18F-MK6240 tau PET 研究中进行了评估,每项研究有 20 个噪声实现,事件分数为 25%。训练、验证和测试分别使用了 1400、120 和 420 对三维图像卷,与受试者无关。所提出的对比性对抗 DG 比传统的无主题 DG 的 UNet 和基于交叉熵的对抗 DG 显示出更优越的去噪性能。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Subject-aware PET Denoising with Contrastive Adversarial Domain Generalization.

Recent advances in deep learning (DL) have greatly improved the performance of positron emission tomography (PET) denoising performance. However, DL model performance can vary a lot across subjects, due to the large variability of the count levels and spatial distributions. A generalizable DL model that mitigates the subject-wise variations is highly expected toward a reliable and trustworthy system for clinical application. In this work, we propose a contrastive adversarial learning framework for subject-wise domain generalization (DG). Specifically, we configure a contrastive discriminator in addition to the UNet-based denoising module to check the subject-related information in the bottleneck feature, while the denoising module is adversarially trained to enforce the extraction of subject-invariant features. The sampled low-count realizations from the list-mode data are used as anchor-positive pairs to be close to each other, while the other subjects are used as negative samples to be distributed far away. We evaluated on 97 18F-MK6240 tau PET studies, each having 20 noise realizations with 25% fractions of events. Training, validation, and testing were implemented using 1400, 120, and 420 pairs of 3D image volumes in a subject-independent manner. The proposed contrastive adversarial DG demonstrated superior denoising performance than conventional UNet without subject-wise DG and cross-entropy-based adversarial DG.

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
自引率
0.00%
发文量
0
×
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:481959085
Book学术官方微信