Myocardial perfusion imaging SPECT left ventricle segmentation with graphs.

IF 3 2区 医学 Q2 RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING EJNMMI Physics Pub Date : 2025-03-10 DOI:10.1186/s40658-025-00728-5
Ádám István Szűcs, Béla Kári, Oszkár Pártos
{"title":"Myocardial perfusion imaging SPECT left ventricle segmentation with graphs.","authors":"Ádám István Szűcs, Béla Kári, Oszkár Pártos","doi":"10.1186/s40658-025-00728-5","DOIUrl":null,"url":null,"abstract":"<p><strong>Purpose: </strong>Various specialized and general collimators are used for myocardial perfusion imaging (MPI) with single-photon emission computed tomography (SPECT) to assess different types of coronary artery disease (CAD). Alongside the wide variability in imaging characteristics, the apriori \"learnt\" information of left ventricular (LV) shape can affect the final diagnosis of the imaging protocol. This study evaluates the effect of prior information incorporation into the segmentation process, compared to deep learning (DL) approaches, as well as the differences of 4 collimation techniques on 5 different datasets.</p><p><strong>Methods: </strong>This study was implemented on 80 patients database. 40 patients were coming from mixed black-box collimators, 10 each, from multi-pinhole (MPH), low energy high resolution (LEHR), CardioC and CardioD collimators. The testing was evaluated on a new continuous graph-based approach, which automatically segments the left ventricular volume with prior information on the cardiac geometry. The technique is based on the continuous max-flow (CMF) min-cut algorithm, which performance was evaluated in precision, recall, IoU and Dice score metrics.</p><p><strong>Results: </strong>In the testing it was shown that, the developed method showed a good improvement over deep learning reaching higher scores in most of the evaluation metrics. Further investigating the different collimation techniques, the evaluation of receiver operating characterstic (ROC) curves showed different stabilities on the various collimators. Running Wilcoxon signed-rank test on the outlines of the LVs showed differentiability between the collimation procedures. To further investigate these phenomena the model parameters of the LVs were reconstructed and evaluated by the uniform manifold approximation and projection (UMAP) method, which further proved that collimators can be differentiated based on the projected LV shapes alone.</p><p><strong>Conclusions: </strong>The results show that prior information incorporation can enhance the performance of segmentation methods and collimation strategies have a high effect on the projected cardiac geometry.</p>","PeriodicalId":11559,"journal":{"name":"EJNMMI Physics","volume":"12 1","pages":"21"},"PeriodicalIF":3.0000,"publicationDate":"2025-03-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11893936/pdf/","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"EJNMMI Physics","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1186/s40658-025-00728-5","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

Abstract

Purpose: Various specialized and general collimators are used for myocardial perfusion imaging (MPI) with single-photon emission computed tomography (SPECT) to assess different types of coronary artery disease (CAD). Alongside the wide variability in imaging characteristics, the apriori "learnt" information of left ventricular (LV) shape can affect the final diagnosis of the imaging protocol. This study evaluates the effect of prior information incorporation into the segmentation process, compared to deep learning (DL) approaches, as well as the differences of 4 collimation techniques on 5 different datasets.

Methods: This study was implemented on 80 patients database. 40 patients were coming from mixed black-box collimators, 10 each, from multi-pinhole (MPH), low energy high resolution (LEHR), CardioC and CardioD collimators. The testing was evaluated on a new continuous graph-based approach, which automatically segments the left ventricular volume with prior information on the cardiac geometry. The technique is based on the continuous max-flow (CMF) min-cut algorithm, which performance was evaluated in precision, recall, IoU and Dice score metrics.

Results: In the testing it was shown that, the developed method showed a good improvement over deep learning reaching higher scores in most of the evaluation metrics. Further investigating the different collimation techniques, the evaluation of receiver operating characterstic (ROC) curves showed different stabilities on the various collimators. Running Wilcoxon signed-rank test on the outlines of the LVs showed differentiability between the collimation procedures. To further investigate these phenomena the model parameters of the LVs were reconstructed and evaluated by the uniform manifold approximation and projection (UMAP) method, which further proved that collimators can be differentiated based on the projected LV shapes alone.

Conclusions: The results show that prior information incorporation can enhance the performance of segmentation methods and collimation strategies have a high effect on the projected cardiac geometry.

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
目的:单光子发射计算机断层扫描(SPECT)心肌灌注成像(MPI)使用了各种专用和普通准直器,以评估不同类型的冠状动脉疾病(CAD)。除了成像特征的巨大差异外,先验 "学习 "的左心室(LV)形状信息也会影响成像方案的最终诊断。与深度学习(DL)方法相比,本研究评估了将先验信息纳入分割过程的效果,以及 4 种准直技术在 5 个不同数据集上的差异:本研究在 80 个患者数据库中进行。40名患者来自混合黑盒子准直仪,多针孔(MPH)、低能量高分辨率(LEHR)、CardioC和CardioD准直仪各10名。测试采用了一种基于连续图的新方法进行评估,该方法利用有关心脏几何形状的先验信息自动分割左心室容积。该技术基于连续最大流(CMF)最小切割算法,通过精确度、召回率、IoU 和 Dice 分数指标对其性能进行评估:测试结果表明,与深度学习相比,所开发的方法有了很好的改进,在大多数评估指标上都获得了更高的分数。在进一步研究不同的准直技术时,接收器操作特性曲线(ROC)的评估显示了不同准直器的不同稳定性。对 LV 的轮廓进行的 Wilcoxon 符号秩检验显示了不同准直程序之间的差异。为了进一步研究这些现象,采用统一流形近似和投影(UMAP)方法重建并评估了左心室的模型参数,进一步证明了可以仅根据投影的左心室形状来区分准直器:结果表明,先验信息的加入可以提高分割方法的性能,而准直策略对投射的心脏几何形状有很大影响。
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
EJNMMI Physics
EJNMMI Physics Physics and Astronomy-Radiation
CiteScore
6.70
自引率
10.00%
发文量
78
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.
期刊最新文献
A novel method for harmonization of PET image spatial resolution without phantoms. Machine-learning based quantification of lung shunt fraction from 99mTc-MAA SPECT/CT for selective internal radiation therapy of liver tumors using TriDFusion (3DF). Automated segmentation of the sacro-iliac joints, posterior spinal joints and discovertebral units on low-dose computed tomography for Na[18F]F PET lesion detection in spondyloarthritis patients. Myocardial perfusion imaging SPECT left ventricle segmentation with graphs. The first human study of add-on PET: A PET-integrated RF coil for 3 T MRI.
×
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