文献速递技术与安全CT

使用卷积神经网络将单能CT转换为双能CT的参数图

Conversion of single-energy CT to parametric maps of dual-energy CT using convolutional neural network.
PubMed 文献 · Br J Radiol · 2024-01-01

本研究提出基于卷积神经网络的多任务深度学习框架,将单能CT的120 kVp图像直接转换为双能CT的虚拟单色图像(70、120、200 keV)、有效原子序数和相对电子密度三种参数图。使用2019至2020年收集的67例患者数据训练和验证,转换后的虚拟单色图像绝对差为9.02 HU、相对差为0.41%,有效原子序数绝对差0.29、相对差1.99%,相对电子密度绝对差0.96、相对差0.50%。作者认为该模型可在无双能CT设备时从单能CT生成参数信息,并有助于回顾性研究单能CT的参数信息。

要点

  • 卷积神经网络可将单能CT的120 kVp图像转换为70、120、200 keV虚拟单色图像,绝对差9.02 HU、相对差0.41%。
  • 同一框架还可转换为有效原子序数(绝对差0.29、相对差1.99%)和相对电子密度(绝对差0.96、相对差0.50%)。
  • 作者认为该模型可在无双能CT设备时从单能CT生成参数信息,并有助于回顾性研究单能CT的参数信息。

核心结论

  • 单能CT图像可被直接转换为双能CT的三种参数图(虚拟单色图像、有效原子序数、相对电子密度);作者认为该模型可在无双能CT设备时从单能CT生成参数信息,并有助于回顾性研究单能CT的参数信息。

研究设计与样本

  • 深度学习多任务学习框架研究,使用卷积神经网络,训练和验证共纳入2019至2020年收集的67例患者;输入为双能CT(IQon光谱CT;Philips Healthcare,阿姆斯特丹,荷兰)采集的120 kVp单层CT图像,目标为同一设备采集的虚拟单色图像、有效原子序数和相对电子密度;性能以绝对差和相对差评估。

诊断标准与关键数值

  • VMI-Net将120 kVp单能CT转换为虚拟单色图像,与真实虚拟单色图像相比绝对差9.02 Hounsfield Unit、相对差0.41%;转换的有效原子序数绝对差0.29、相对差1.99%;转换的相对电子密度绝对差0.96、相对差0.50%。

临床应用与阅片要点

  • 作者认为该模型可在无双能CT设备时从单能CT生成参数信息。
  • 作者认为该模型有助于回顾性研究单能CT的参数信息。

局限性

  • 原文未报告局限性。

以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。

英文原文(摘要)· 点击展开

OBJECTIVES: We propose a deep learning (DL) multitask learning framework using convolutional neural network for a direct conversion of single-energy CT (SECT) to 3 different parametric maps of dual-energy CT (DECT): virtual-monochromatic image (VMI), effective atomic number (EAN), and relative electron density (RED).

METHODS: We propose VMI-Net for conversion of SECT to 70, 120, and 200 keV VMIs. In addition, EAN-Net and RED-Net were also developed to convert SECT to EAN and RED. We trained and validated our model using 67 patients collected between 2019 and 2020. Single-layer CT images with 120 kVp acquired by the DECT (IQon spectral CT; Philips Healthcare, Amsterdam, Netherlands) were used as input, while the VMIs, EAN, and RED acquired by the same device were used as target. The performance of the DL framework was evaluated by absolute difference (AD) and relative difference (RD).

RESULTS: The VMI-Net converted 120 kVp SECT to the VMIs with AD of 9.02 Hounsfield Unit, and RD of 0.41% compared to the ground truth VMIs. The ADs of the converted EAN and RED were 0.29 and 0.96, respectively, while the RDs were 1.99% and 0.50% for the converted EAN and RED, respectively.

CONCLUSIONS: SECT images were directly converted to the 3 parametric maps of DECT (ie, VMIs, EAN, and RED). By using this model, one can generate the parametric information from SECT images without DECT device. Our model can help investigate the parametric information from SECT retrospectively.

ADVANCES IN KNOWLEDGE: DL framework enables converting SECT to various high-quality parametric maps of DECT.

来源:Br J Radiol,查看原文。版权归原作者所有。

引用

  1. Kim S, Lee J, Kim J, et al. Conversion of single-energy CT to parametric maps of dual-energy CT using convolutional neural network. Br J Radiol. 2024. PMID: 38597871. doi:10.1093/bjr/tqae076

供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。