• 文献检索
  • 文档翻译
  • 深度研究
  • 学术资讯
  • Suppr Zotero 插件Zotero 插件
  • 邀请有礼
  • 套餐&价格
  • 历史记录
应用&插件
Suppr Zotero 插件Zotero 插件浏览器插件Mac 客户端Windows 客户端微信小程序
定价
高级版会员购买积分包购买API积分包
服务
文献检索文档翻译深度研究API 文档MCP 服务
关于我们
关于 Suppr公司介绍联系我们用户协议隐私条款
关注我们

Suppr 超能文献

核心技术专利:CN118964589B侵权必究
粤ICP备2023148730 号-1Suppr @ 2026

文献检索

告别复杂PubMed语法,用中文像聊天一样搜索,搜遍4000万医学文献。AI智能推荐,让科研检索更轻松。

立即免费搜索

文件翻译

保留排版,准确专业,支持PDF/Word/PPT等文件格式,支持 12+语言互译。

免费翻译文档

深度研究

AI帮你快速写综述,25分钟生成高质量综述,智能提取关键信息,辅助科研写作。

立即免费体验

使用语义分割技术进行小鼠肠系膜动脉的自动检测和直径估算。

Automated Detection and Diameter Estimation for Mouse Mesenteric Artery Using Semantic Segmentation.

机构信息

Hypertension and Vascular Research Unit, Lady Davis Institute for Medical Research, Montreal, Québec, Canada.

Department of Cardiology, Ehime Prefectural Central Hospital, Matsuyama, Japan.

出版信息

J Vasc Res. 2021;58(6):379-387. doi: 10.1159/000516842. Epub 2021 Jun 28.

DOI:10.1159/000516842
PMID:34182554
Abstract

BACKGROUND

Pressurized myography is useful for the assessment of small artery structures and function. However, this procedure requires technical expertise for sample preparation and effort to choose an appropriate sized artery. In this study, we developed an automatic artery/vein differentiation and a size measurement system utilizing machine learning algorithms.

METHODS AND RESULTS

We used 654 independent mouse mesenteric artery images for model training. The model yielded an Intersection-over-Union of 0.744 ± 0.031 and a Dice coefficient of 0.881 ± 0.016. The vessel size and lumen size calculated from the predicted vessel contours demonstrated a strong linear correlation with manually determined vessel sizes (R = 0.722 ± 0.048, p < 0.001 for vessel size and R = 0.908 ± 0.027, p < 0.001 for lumen size). Last, we assessed the relation between the vessel size before and after dissection using a pressurized myography system. We observed a strong positive correlation between the wall/lumen ratio before dissection and the lumen expansion ratio (R = 0.832, p < 0.01). Using multivariate binary logistic regression, 2 models estimating whether the vessel met the size criteria (lumen size of 160-240 μm) were generated with an area under the receiver operating characteristic curve of 0.761 for the upper limit and 0.747 for the lower limit.

CONCLUSION

The U-Net-based image analysis method could streamline the experimental approach.

摘要

背景

加压血管造影术可用于评估小动脉结构和功能。然而,该程序需要技术专业知识来进行样本准备,并需要努力选择合适大小的动脉。在这项研究中,我们利用机器学习算法开发了一种自动动脉/静脉区分和尺寸测量系统。

方法和结果

我们使用了 654 个独立的鼠标肠系膜动脉图像进行模型训练。该模型的交并比为 0.744 ± 0.031,骰子系数为 0.881 ± 0.016。从预测的血管轮廓计算出的血管尺寸和管腔尺寸与手动确定的血管尺寸显示出很强的线性相关性(R = 0.722 ± 0.048,p < 0.001 用于血管尺寸,R = 0.908 ± 0.027,p < 0.001 用于管腔尺寸)。最后,我们使用加压血管造影系统评估了血管在解剖前后的大小关系。我们观察到在解剖前的管壁/管腔比与管腔扩张比之间存在很强的正相关关系(R = 0.832,p < 0.01)。使用多元二项逻辑回归,生成了两个估计血管是否符合尺寸标准(管腔尺寸为 160-240μm)的模型,上限的受试者工作特征曲线下面积为 0.761,下限的面积为 0.747。

结论

基于 U-Net 的图像分析方法可以简化实验方法。

相似文献

1
Automated Detection and Diameter Estimation for Mouse Mesenteric Artery Using Semantic Segmentation.使用语义分割技术进行小鼠肠系膜动脉的自动检测和直径估算。
J Vasc Res. 2021;58(6):379-387. doi: 10.1159/000516842. Epub 2021 Jun 28.
2
Quantification of common carotid artery and descending aorta vessel wall thickness from MR vessel wall imaging using a fully automated processing pipeline.使用全自动处理流程从磁共振血管壁成像中定量颈总动脉和降主动脉的血管壁厚度。
J Magn Reson Imaging. 2017 Jan;45(1):215-228. doi: 10.1002/jmri.25332. Epub 2016 Jun 2.
3
Deep morphology aided diagnosis network for segmentation of carotid artery vessel wall and diagnosis of carotid atherosclerosis on black-blood vessel wall MRI.基于深度学习的形态学辅助诊断网络在黑血 MRI 颈动脉血管壁分段及颈动脉粥样硬化诊断中的应用
Med Phys. 2019 Dec;46(12):5544-5561. doi: 10.1002/mp.13739. Epub 2019 Oct 14.
4
Assessing murine resistance artery function using pressure myography.使用压力肌动描记法评估小鼠阻力动脉功能。
J Vis Exp. 2013 Jun 7(76):50328. doi: 10.3791/50328.
5
In vivo validation of image-directed Doppler measurement of superior mesenteric artery blood flow.影像引导下肠系膜上动脉血流多普勒测量的体内验证
J Clin Ultrasound. 1992 Jan;20(1):19-26. doi: 10.1002/jcu.1870200105.
6
Learning-based automated segmentation of the carotid artery vessel wall in dual-sequence MRI using subdivision surface fitting.基于学习的颈动脉血管壁在双序列 MRI 中的自动分割,采用细分曲面拟合。
Med Phys. 2017 Oct;44(10):5244-5259. doi: 10.1002/mp.12476. Epub 2017 Aug 30.
7
Neural Network Vessel Lumen Regression for Automated Lumen Cross-Section Segmentation in Cardiovascular Image-Based Modeling.神经网络血管内腔回归在基于心血管图像建模中的自动内腔横截面分割。
Cardiovasc Eng Technol. 2020 Dec;11(6):621-635. doi: 10.1007/s13239-020-00497-5. Epub 2020 Nov 11.
8
Intracranial Vessel Wall Segmentation Using Convolutional Neural Networks.基于卷积神经网络的颅内血管壁分割。
IEEE Trans Biomed Eng. 2019 Oct;66(10):2840-2847. doi: 10.1109/TBME.2019.2896972. Epub 2019 Feb 1.
9
Mesenteric artery contraction and relaxation studies using automated wire myography.使用自动线肌动描记法进行肠系膜动脉收缩和舒张研究。
J Vis Exp. 2011 Sep 22(55):3119. doi: 10.3791/3119.
10
Transient receptor potential canonical type 3 channels facilitate endothelium-derived hyperpolarization-mediated resistance artery vasodilator activity.瞬时受体电位经典型通道 3 促进内皮细胞衍生的超极化介导的阻力血管舒张活性。
Cardiovasc Res. 2012 Sep 1;95(4):439-47. doi: 10.1093/cvr/cvs208. Epub 2012 Jun 21.

引用本文的文献

1
Computer-assisted image analysis of agonist-mediated microvascular constriction response in mouse cremaster muscle.计算机辅助分析在体小鼠提睾肌激动剂诱导的微血管收缩反应。
PLoS One. 2022 Nov 17;17(11):e0277851. doi: 10.1371/journal.pone.0277851. eCollection 2022.
2
Content-based image retrieval for the diagnosis of myocardial perfusion imaging using a deep convolutional autoencoder.基于内容的图像检索在心肌灌注成像诊断中的应用:使用深度卷积自动编码器。
J Nucl Cardiol. 2023 Apr;30(2):540-549. doi: 10.1007/s12350-022-03030-4. Epub 2022 Jul 8.