Improving image quality of sparse-view lung tumor CT images with U-Net.

IF 3.7 Q1 RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING
Annika Ries, Tina Dorosti, Johannes Thalhammer, Daniel Sasse, Andreas Sauter, Felix Meurer, Ashley Benne, Tobias Lasser, Franz Pfeiffer, Florian Schaff, Daniela Pfeiffer
{"title":"Improving image quality of sparse-view lung tumor CT images with U-Net.","authors":"Annika Ries, Tina Dorosti, Johannes Thalhammer, Daniel Sasse, Andreas Sauter, Felix Meurer, Ashley Benne, Tobias Lasser, Franz Pfeiffer, Florian Schaff, Daniela Pfeiffer","doi":"10.1186/s41747-024-00450-4","DOIUrl":null,"url":null,"abstract":"<p><strong>Background: </strong>We aimed to improve the image quality (IQ) of sparse-view computed tomography (CT) images using a U-Net for lung metastasis detection and determine the best tradeoff between number of views, IQ, and diagnostic confidence.</p><p><strong>Methods: </strong>CT images from 41 subjects aged 62.8 ± 10.6 years (mean ± standard deviation, 23 men), 34 with lung metastasis, 7 healthy, were retrospectively selected (2016-2018) and forward projected onto 2,048-view sinograms. Six corresponding sparse-view CT data subsets at varying levels of undersampling were reconstructed from sinograms using filtered backprojection with 16, 32, 64, 128, 256, and 512 views. A dual-frame U-Net was trained and evaluated for each subsampling level on 8,658 images from 22 diseased subjects. A representative image per scan was selected from 19 subjects (12 diseased, 7 healthy) for a single-blinded multireader study. These slices, for all levels of subsampling, with and without U-Net postprocessing, were presented to three readers. IQ and diagnostic confidence were ranked using predefined scales. Subjective nodule segmentation was evaluated using sensitivity and Dice similarity coefficient (DSC); clustered Wilcoxon signed-rank test was used.</p><p><strong>Results: </strong>The 64-projection sparse-view images resulted in 0.89 sensitivity and 0.81 DSC, while their counterparts, postprocessed with the U-Net, had improved metrics (0.94 sensitivity and 0.85 DSC) (p = 0.400). Fewer views led to insufficient IQ for diagnosis. For increased views, no substantial discrepancies were noted between sparse-view and postprocessed images.</p><p><strong>Conclusions: </strong>Projection views can be reduced from 2,048 to 64 while maintaining IQ and the confidence of the radiologists on a satisfactory level.</p><p><strong>Relevance statement: </strong>Our reader study demonstrates the benefit of U-Net postprocessing for regular CT screenings of patients with lung metastasis to increase the IQ and diagnostic confidence while reducing the dose.</p><p><strong>Key points: </strong>• Sparse-projection-view streak artifacts reduce the quality and usability of sparse-view CT images. • U-Net-based postprocessing removes sparse-view artifacts while maintaining diagnostically accurate IQ. • Postprocessed sparse-view CTs drastically increase radiologists' confidence in diagnosing lung metastasis.</p>","PeriodicalId":36926,"journal":{"name":"European Radiology Experimental","volume":"8 1","pages":"54"},"PeriodicalIF":3.7000,"publicationDate":"2024-05-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11065797/pdf/","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"European Radiology Experimental","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1186/s41747-024-00450-4","RegionNum":0,"RegionCategory":null,"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: We aimed to improve the image quality (IQ) of sparse-view computed tomography (CT) images using a U-Net for lung metastasis detection and determine the best tradeoff between number of views, IQ, and diagnostic confidence.

Methods: CT images from 41 subjects aged 62.8 ± 10.6 years (mean ± standard deviation, 23 men), 34 with lung metastasis, 7 healthy, were retrospectively selected (2016-2018) and forward projected onto 2,048-view sinograms. Six corresponding sparse-view CT data subsets at varying levels of undersampling were reconstructed from sinograms using filtered backprojection with 16, 32, 64, 128, 256, and 512 views. A dual-frame U-Net was trained and evaluated for each subsampling level on 8,658 images from 22 diseased subjects. A representative image per scan was selected from 19 subjects (12 diseased, 7 healthy) for a single-blinded multireader study. These slices, for all levels of subsampling, with and without U-Net postprocessing, were presented to three readers. IQ and diagnostic confidence were ranked using predefined scales. Subjective nodule segmentation was evaluated using sensitivity and Dice similarity coefficient (DSC); clustered Wilcoxon signed-rank test was used.

Results: The 64-projection sparse-view images resulted in 0.89 sensitivity and 0.81 DSC, while their counterparts, postprocessed with the U-Net, had improved metrics (0.94 sensitivity and 0.85 DSC) (p = 0.400). Fewer views led to insufficient IQ for diagnosis. For increased views, no substantial discrepancies were noted between sparse-view and postprocessed images.

Conclusions: Projection views can be reduced from 2,048 to 64 while maintaining IQ and the confidence of the radiologists on a satisfactory level.

Relevance statement: Our reader study demonstrates the benefit of U-Net postprocessing for regular CT screenings of patients with lung metastasis to increase the IQ and diagnostic confidence while reducing the dose.

Key points: • Sparse-projection-view streak artifacts reduce the quality and usability of sparse-view CT images. • U-Net-based postprocessing removes sparse-view artifacts while maintaining diagnostically accurate IQ. • Postprocessed sparse-view CTs drastically increase radiologists' confidence in diagnosing lung metastasis.

Abstract Image

利用 U-Net 提高稀疏视图肺部肿瘤 CT 图像的质量
背景:我们的目的是利用 U-Net 提高稀疏视图计算机断层扫描(CT)图像的图像质量(IQ),用于肺转移瘤检测,并确定视图数、IQ 和诊断可信度之间的最佳权衡:回顾性选取(2016-2018 年)41 名年龄为 62.8 ± 10.6 岁(平均 ± 标准差,23 名男性)的受试者的 CT 图像,其中 34 人患有肺转移瘤,7 人健康。使用 16、32、64、128、256 和 512 个视图的滤波反向投影,从正弦曲线重建了不同欠采样水平的六个相应稀疏视图 CT 数据子集。对 22 名患病受试者的 8658 张图像进行了双帧 U-Net 训练,并对每个子采样水平进行了评估。在单盲多读取器研究中,从 19 名受试者(12 名患病者,7 名健康者)的每次扫描中选取一张具有代表性的图像。这些切片在经过或未经过 U-Net 后处理的所有子采样水平下,分别呈现给三位阅读者。使用预先定义的量表对智商和诊断信心进行排名。使用灵敏度和戴斯相似系数(DSC)对主观结节分割进行评估;使用聚类 Wilcoxon 符号秩检验:结果:64 投影稀疏视图图像的灵敏度和 DSC 分别为 0.89 和 0.81,而经过 U-Net 后处理的对应图像的指标有所改善(灵敏度和 DSC 分别为 0.94 和 0.85)(p = 0.400)。视图减少会导致诊断智商不足。对于增加的视图,稀疏视图和后处理图像之间没有发现实质性差异:投影视图可以从 2048 个减少到 64 个,同时保持令人满意的智商和放射医师的信心:我们的读者研究表明,U-Net 后处理可用于肺转移患者的常规 CT 筛查,在降低剂量的同时提高智商和诊断信心:- 稀疏投影视图条纹伪影降低了稀疏视图 CT 图像的质量和可用性。- 基于 U-Net 的后处理可去除稀疏视图伪影,同时保持准确的诊断智商。- 经过后处理的稀疏视图 CT 大幅提高了放射科医生诊断肺转移的信心。
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
European Radiology Experimental
European Radiology Experimental Medicine-Radiology, Nuclear Medicine and Imaging
CiteScore
6.70
自引率
2.60%
发文量
56
审稿时长
18 weeks
×
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