Deep learning-based whole-body PSMA PET/CT attenuation correction utilizing Pix-2-Pix GAN.

Q2 Medicine Oncotarget Pub Date : 2024-05-07 DOI:10.18632/oncotarget.28583
Kevin C Ma, Esther Mena, Liza Lindenberg, Nathan S Lay, Phillip Eclarinal, Deborah E Citrin, Peter A Pinto, Bradford J Wood, William L Dahut, James L Gulley, Ravi A Madan, Peter L Choyke, Ismail Baris Turkbey, Stephanie A Harmon
{"title":"Deep learning-based whole-body PSMA PET/CT attenuation correction utilizing Pix-2-Pix GAN.","authors":"Kevin C Ma, Esther Mena, Liza Lindenberg, Nathan S Lay, Phillip Eclarinal, Deborah E Citrin, Peter A Pinto, Bradford J Wood, William L Dahut, James L Gulley, Ravi A Madan, Peter L Choyke, Ismail Baris Turkbey, Stephanie A Harmon","doi":"10.18632/oncotarget.28583","DOIUrl":null,"url":null,"abstract":"<p><strong>Purpose: </strong>Sequential PET/CT studies oncology patients can undergo during their treatment follow-up course is limited by radiation dosage. We propose an artificial intelligence (AI) tool to produce attenuation-corrected PET (AC-PET) images from non-attenuation-corrected PET (NAC-PET) images to reduce need for low-dose CT scans.</p><p><strong>Methods: </strong>A deep learning algorithm based on 2D Pix-2-Pix generative adversarial network (GAN) architecture was developed from paired AC-PET and NAC-PET images. <sup>18</sup>F-DCFPyL PSMA PET-CT studies from 302 prostate cancer patients, split into training, validation, and testing cohorts (<i>n</i> = 183, 60, 59, respectively). Models were trained with two normalization strategies: Standard Uptake Value (SUV)-based and SUV-Nyul-based. Scan-level performance was evaluated by normalized mean square error (NMSE), mean absolute error (MAE), structural similarity index (SSIM), and peak signal-to-noise ratio (PSNR). Lesion-level analysis was performed in regions-of-interest prospectively from nuclear medicine physicians. SUV metrics were evaluated using intraclass correlation coefficient (ICC), repeatability coefficient (RC), and linear mixed-effects modeling.</p><p><strong>Results: </strong>Median NMSE, MAE, SSIM, and PSNR were 13.26%, 3.59%, 0.891, and 26.82, respectively, in the independent test cohort. ICC for SUV<sub>max</sub> and SUV<sub>mean</sub> were 0.88 and 0.89, which indicated a high correlation between original and AI-generated quantitative imaging markers. Lesion location, density (Hounsfield units), and lesion uptake were all shown to impact relative error in generated SUV metrics (all <i>p</i> < 0.05).</p><p><strong>Conclusion: </strong>The Pix-2-Pix GAN model for generating AC-PET demonstrates SUV metrics that highly correlate with original images. AI-generated PET images show clinical potential for reducing the need for CT scans for attenuation correction while preserving quantitative markers and image quality.</p>","PeriodicalId":19499,"journal":{"name":"Oncotarget","volume":"15 ","pages":"288-300"},"PeriodicalIF":0.0000,"publicationDate":"2024-05-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11075367/pdf/","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Oncotarget","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.18632/oncotarget.28583","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"Medicine","Score":null,"Total":0}
引用次数: 0

Abstract

Purpose: Sequential PET/CT studies oncology patients can undergo during their treatment follow-up course is limited by radiation dosage. We propose an artificial intelligence (AI) tool to produce attenuation-corrected PET (AC-PET) images from non-attenuation-corrected PET (NAC-PET) images to reduce need for low-dose CT scans.

Methods: A deep learning algorithm based on 2D Pix-2-Pix generative adversarial network (GAN) architecture was developed from paired AC-PET and NAC-PET images. 18F-DCFPyL PSMA PET-CT studies from 302 prostate cancer patients, split into training, validation, and testing cohorts (n = 183, 60, 59, respectively). Models were trained with two normalization strategies: Standard Uptake Value (SUV)-based and SUV-Nyul-based. Scan-level performance was evaluated by normalized mean square error (NMSE), mean absolute error (MAE), structural similarity index (SSIM), and peak signal-to-noise ratio (PSNR). Lesion-level analysis was performed in regions-of-interest prospectively from nuclear medicine physicians. SUV metrics were evaluated using intraclass correlation coefficient (ICC), repeatability coefficient (RC), and linear mixed-effects modeling.

Results: Median NMSE, MAE, SSIM, and PSNR were 13.26%, 3.59%, 0.891, and 26.82, respectively, in the independent test cohort. ICC for SUVmax and SUVmean were 0.88 and 0.89, which indicated a high correlation between original and AI-generated quantitative imaging markers. Lesion location, density (Hounsfield units), and lesion uptake were all shown to impact relative error in generated SUV metrics (all p < 0.05).

Conclusion: The Pix-2-Pix GAN model for generating AC-PET demonstrates SUV metrics that highly correlate with original images. AI-generated PET images show clinical potential for reducing the need for CT scans for attenuation correction while preserving quantitative markers and image quality.

查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
利用 Pix-2-Pix GAN 进行基于深度学习的全身 PSMA PET/CT 衰减校正。
目的:由于辐射剂量的限制,肿瘤患者在治疗随访过程中可以进行连续的 PET/CT 研究。我们提出了一种人工智能(AI)工具,从非衰减校正 PET(NAC-PET)图像生成衰减校正 PET(AC-PET)图像,以减少对低剂量 CT 扫描的需求:方法:根据成对的 AC-PET 和 NAC-PET 图像,开发了一种基于 2D Pix-2-Pix 生成式对抗网络 (GAN) 架构的深度学习算法。18F-DCFPyL PSMA PET-CT 研究来自 302 名前列腺癌患者,分为训练组、验证组和测试组(n = 183、60、59)。模型采用两种归一化策略进行训练:基于标准摄取值 (SUV) 的模型和基于 SUV-Nyul 的模型。扫描水平性能通过归一化均方误差(NMSE)、平均绝对误差(MAE)、结构相似性指数(SSIM)和峰值信噪比(PSNR)进行评估。病灶级分析是由核医学医生在感兴趣区进行的前瞻性分析。使用类内相关系数(ICC)、重复性系数(RC)和线性混合效应模型对 SUV 指标进行评估:独立测试队列的中位 NMSE、MAE、SSIM 和 PSNR 分别为 13.26%、3.59%、0.891 和 26.82。SUVmax和SUVmean的ICC分别为0.88和0.89,这表明原始和人工智能生成的定量成像标记之间具有很高的相关性。病变位置、密度(Hounsfield 单位)和病变摄取都会影响生成的 SUV 指标的相对误差(所有 p < 0.05):用于生成 AC-PET 的 Pix-2-Pix GAN 模型显示了与原始图像高度相关的 SUV 指标。人工智能生成的 PET 图像具有临床潜力,可减少 CT 扫描衰减校正的需要,同时保留定量标记和图像质量。
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 去求助
来源期刊
Oncotarget
Oncotarget Oncogenes-CELL BIOLOGY
CiteScore
6.60
自引率
0.00%
发文量
129
审稿时长
1.5 months
期刊介绍: Information not localized
期刊最新文献
Advancements in cell-penetrating monoclonal antibody treatment. B7-H4: A potential therapeutic target in adenoid cystic carcinoma. Computed tomography-based radiomics and body composition model for predicting hepatic decompensation. Mesenchymal stem cells - the secret agents of cancer immunotherapy: Promises, challenges, and surprising twists. Retraction: Hyperglycemia via activation of thromboxane A2 receptor impairs the integrity and function of blood-brain barrier in microvascular endothelial cells.
×
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
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 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 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1