- Book学术

发布求助

文献互助智能选刊最新文献

IF 3 2区医学 Q2 RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING

EJNMMI Physics Pub Date : 2025-03-28 DOI:10.1186/s40658-025-00742-7

Kenta Miwa, Shin Yamagishi, Shun Kamitaki, Kouichi Anraku, Shun Sato, Tensho Yamao, Noriaki Miyaji, Kaito Wachi, Naochika Akiya, Kei Wagatsuma, Kazuhiro Oguchi

{"title":"Effects of a deep learning-based image quality enhancement method on a digital-BGO PET/CT system for 18F-FDG whole-body examination.","authors":"Kenta Miwa, Shin Yamagishi, Shun Kamitaki, Kouichi Anraku, Shun Sato, Tensho Yamao, Noriaki Miyaji, Kaito Wachi, Naochika Akiya, Kei Wagatsuma, Kazuhiro Oguchi","doi":"10.1186/s40658-025-00742-7","DOIUrl":null,"url":null,"abstract":"Background: The digital-BGO PET/CT system, Omni Legend 32, incorporates modified block sequential regularized expectation maximization (BSREM) image reconstruction and a deep learning-based time-of-flight (TOF)-like image quality enhancement process called Precision DL (PDL). The present study aimed to define the fundamental characteristics of PDL using phantom and clinical images.Methods: A NEMA IEC body phantom was scanned using the Omni Legend 32 PET/CT system. All PET/CT images were acquired over 60 and 90 s per bed position, with a 384 × 384 matrix. Phantom images were reconstructed using OSEM + PSF and BSREM at β values of 100-1,000, combined with low (LPDL), medium (MPDL), and high (HPDL) PDL. We evaluated contrast recovery, background variability, and the contrast-to-noise ratio (CNR) of a 10 mm hot sphere. Thirty clinical whole-body 18F-FDG PET/CT examinations were included. Clinical images were reconstructed using OSEM + PSF and BSREM at β values of 200, 300, 400, 500, and 600, determined based on findings from the phantom study, combined with the three PDL models. Noise levels, mean SUV (SUVmean), and the signal-to-noise ratio (SNR) of the liver as well as signal-to-background ratios (SBR) and maximum SUV (SUVmax) of lesions were evaluated. Two blinded readers evaluated visual image quality and rated several aspects to complement the analysis.Results: Contrast recovery and background variability decreased as the β value increased. This trend was consistent even when PDL processing was added to BSREM. Increased strength of the PDL models led to higher CNR. Noise levels decreased as a function of increasing β values in BSREM, resulting in a higher SNR, but lower SBR. Combining PDL with BSREM resulted in all β values producing better results in terms of noise, SBR, and SNR than OSEM + PSF. As the PDL increased (LPDL < MPDL < HPDL), noise levels, SBR, and SNR became higher. The β values of 400, 200, 300, and 300 for BSREM, LPDL, MPDL, and HPDL, respectively, resulted in noise equivalent to OSEM + PSF but significantly increased the SUVmax (9%, 15%, 18%, and 27%), SBR (16%, 17%, 20%, and 32%), and SNR (17%, 19%, 31%, and 36%), respectively. The visual evaluation of image quality yielded similar scores across BSREM + PDL reconstructions, although BSREM with β = 600 combined with MPDL delivered the best overall image quality and total mean score.Conclusion: The combination of BSREM and PDL significantly enhanced the SUVmax of lesions and image quality compared with OSEM + PSF. A combination of BSREM at β values of 500-600 and MPDL is recommended for oncological whole-body PET/CT imaging when using PDL on the Omni Legend.","PeriodicalId":11559,"journal":{"name":"EJNMMI Physics","volume":"12 1","pages":"29"},"PeriodicalIF":3.0000,"publicationDate":"2025-03-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11950486/pdf/","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"EJNMMI Physics","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1186/s40658-025-00742-7","RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING","Score":null,"Total":0}

引用次数: 0

摘要

背景：数字 BGO PET/CT 系统 Omni Legend 32 采用了改进的块序列正则化期望最大化（BSREM）图像重建和基于深度学习的飞行时间（TOF）类图像质量增强过程，称为 Precision DL（PDL）。本研究旨在利用人体模型和临床图像确定 PDL 的基本特征：方法：使用 Omni Legend 32 PET/CT 系统扫描 NEMA IEC 人体模型。所有 PET/CT 图像均以 384 × 384 矩阵采集，每个床位采集时间分别为 60 秒和 90 秒。使用 OSEM + PSF 和 BSREM 对模型图像进行重建，β 值为 100-1,000，并结合低（LPDL）、中（MPDL）和高（HPDL）PDL。我们评估了对比度恢复、背景变异性和 10 毫米热球的对比度-噪声比 (CNR)。我们纳入了 30 例临床全身 18F-FDG PET/CT 检查。临床图像使用 OSEM + PSF 和 BSREM 重建，β 值分别为 200、300、400、500 和 600（根据模型研究结果确定），并结合三种 PDL 模型。对噪声水平、平均 SUV（SUVmean）、肝脏的信噪比（SNR）以及病变的信噪比（SBR）和最大 SUV（SUVmax）进行了评估。两名盲人读者对视觉图像质量进行了评估，并对多个方面进行了评分，以补充分析结果：结果：对比度恢复和背景变异性随着β值的增加而降低。即使在 BSREM 中加入 PDL 处理，这一趋势也是一致的。增加 PDL 模型的强度可提高 CNR。随着 BSREM β 值的增加，噪声水平也随之降低，从而导致更高的信噪比（SNR），但 SBR 却降低了。与 OSEM + PSF 相比，将 PDL 与 BSREM 结合后，所有 β 值都能产生更好的噪声、SBR 和 SNR 结果。随着 PDL 的增加（LPDL 最大值分别为 9%、15%、18% 和 27%），SBR 分别为 16%、17%、20% 和 32%，信噪比分别为 17%、19%、31% 和 36%）。BSREM + PDL 重建的图像质量目测评估得分相近，但 β = 600 的 BSREM 结合 MPDL 的总体图像质量和平均总分最好：与 OSEM + PSF 相比，BSREM 和 PDL 的组合能显著提高病变的 SUVmax 和图像质量。在 Omni Legend 上使用 PDL 时，建议在肿瘤全身 PET/CT 成像中结合使用 β 值为 500-600 的 BSREM 和 MPDL。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

查看原文本刊更多论文

Effects of a deep learning-based image quality enhancement method on a digital-BGO PET/CT system for ¹⁸F-FDG whole-body examination.

Background: The digital-BGO PET/CT system, Omni Legend 32, incorporates modified block sequential regularized expectation maximization (BSREM) image reconstruction and a deep learning-based time-of-flight (TOF)-like image quality enhancement process called Precision DL (PDL). The present study aimed to define the fundamental characteristics of PDL using phantom and clinical images.

Methods: A NEMA IEC body phantom was scanned using the Omni Legend 32 PET/CT system. All PET/CT images were acquired over 60 and 90 s per bed position, with a 384 × 384 matrix. Phantom images were reconstructed using OSEM + PSF and BSREM at β values of 100-1,000, combined with low (LPDL), medium (MPDL), and high (HPDL) PDL. We evaluated contrast recovery, background variability, and the contrast-to-noise ratio (CNR) of a 10 mm hot sphere. Thirty clinical whole-body ¹⁸F-FDG PET/CT examinations were included. Clinical images were reconstructed using OSEM + PSF and BSREM at β values of 200, 300, 400, 500, and 600, determined based on findings from the phantom study, combined with the three PDL models. Noise levels, mean SUV (SUV_mean), and the signal-to-noise ratio (SNR) of the liver as well as signal-to-background ratios (SBR) and maximum SUV (SUV_max) of lesions were evaluated. Two blinded readers evaluated visual image quality and rated several aspects to complement the analysis.

Results: Contrast recovery and background variability decreased as the β value increased. This trend was consistent even when PDL processing was added to BSREM. Increased strength of the PDL models led to higher CNR. Noise levels decreased as a function of increasing β values in BSREM, resulting in a higher SNR, but lower SBR. Combining PDL with BSREM resulted in all β values producing better results in terms of noise, SBR, and SNR than OSEM + PSF. As the PDL increased (LPDL < MPDL < HPDL), noise levels, SBR, and SNR became higher. The β values of 400, 200, 300, and 300 for BSREM, LPDL, MPDL, and HPDL, respectively, resulted in noise equivalent to OSEM + PSF but significantly increased the SUV_max (9%, 15%, 18%, and 27%), SBR (16%, 17%, 20%, and 32%), and SNR (17%, 19%, 31%, and 36%), respectively. The visual evaluation of image quality yielded similar scores across BSREM + PDL reconstructions, although BSREM with β = 600 combined with MPDL delivered the best overall image quality and total mean score.

Conclusion: The combination of BSREM and PDL significantly enhanced the SUV_max of lesions and image quality compared with OSEM + PSF. A combination of BSREM at β values of 500-600 and MPDL is recommended for oncological whole-body PET/CT imaging when using PDL on the Omni Legend.

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

EJNMMI Physics Physics and Astronomy-Radiation

CiteScore

6.70

自引率

10.00%

发文量

审稿时长

13 weeks

期刊介绍： EJNMMI Physics is an international platform for scientists, users and adopters of nuclear medicine with a particular interest in physics matters. As a companion journal to the European Journal of Nuclear Medicine and Molecular Imaging, this journal has a multi-disciplinary approach and welcomes original materials and studies with a focus on applied physics and mathematics as well as imaging systems engineering and prototyping in nuclear medicine. This includes physics-driven approaches or algorithms supported by physics that foster early clinical adoption of nuclear medicine imaging and therapy.