• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文会议>International Forum on Medical Imaging in Asia 2019 >Combined Low-dose Simulation and Deep Learning for CT Denoising: Application in Ultra-low-dose Chest CT
【24h】

Combined Low-dose Simulation and Deep Learning for CT Denoising: Application in Ultra-low-dose Chest CT

机译：结合低剂量模拟和深度学习进行CT去噪：在超低剂量胸部CT中的应用

获取原文
获取原文并翻译 | 示例
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

In this study, we present a deep learning approach for denoising of ultra-low-dose chest CT by combining a low-dosesimulation and convolutional neural network (CNN). A total of 18,456 anonymized regular-dose chest CT images wereused for training of the CNN. The training CT images were fed into the low-dose simulation tool to generate a paired setof simulated low-dose CT and synthetic low-dose noise. A modified U-net model with 4x4 kernel size and five layerswas trained with these paired datasets to predict the low-dose noise from the given low-dose CT image. Independent 10ultra-low-dose chest CT scans at 120 kVp and 5 mAs were used for testing the denoising performance of the trained Unet.Denoised CT images were obtained by subtracting the predicted noise image from ultra-low-dose chest CT images.We evaluated the image quality by measuring noise standard deviation of soft tissue and with visual assessment ofbronchial wall, lung fissure, and soft tissue. For comparison, the image quality was assessed on FBP, VEO, and deeplearning-denoised FBP images. The visual assessment made with 4 points scale were 1.0, 3.4 and 4.0 in FBP, VEO, anddeep learning-denoised FBP images. Image noise of soft tissue was 101±28HU, 20±5HU, 28±10HU in FBP, VEO, deeplearning-denoised images.
机译：在这项研究中，我们提出了一种结合低剂量模拟和卷积神经网络（CNN）的超低剂量胸部CT去噪的深度学习方法。总计18,456张匿名的常规剂量胸部CT图像被\ n \护理用于CNN的训练。将训练后的CT图像输入到低剂量模拟工具中，以生成成对的模拟低剂量CT和合成的低剂量噪声。使用这些配对的数据集训练了具有4x4内核大小和五层的改进的U-net模型，以根据给定的低剂量CT图像预测低剂量噪声。通过在120 kVp和5 mAs下进行独立的10 \ r \超低剂量胸部CT扫描来测试训练后的Unet的降噪性能。\ r \ n通过从超低噪声图像中减去预测的噪声图像获得降噪后的CT图像。剂量胸部CT图像。\ r \ n我们通过测量软组织的噪声标准偏差并通过视觉评估\ r \ n支气管壁，肺裂和软组织来评估图像质量。为了进行比较，在FBP，VEO和深度\ r \ n学习消噪的FBP图像上评估了图像质量。在FBP，VEO和深度学习去噪的FBP图像中，用4分制进行的视觉评估分别为1.0、3.4和4.0。在FBP，VEO，深度\ r \ n学习消噪图像中，软组织的图像噪声分别为101±28HU，20±5HU，28±10HU。

著录项

  • 来源
    《International Forum on Medical Imaging in Asia 2019》|2019年|110500E.1-110500E.5|共5页
  • 会议地点 0277-786X;1996-756X
  • 作者

    Chulkyun Ahn; Changyong Heo; Jong Hyo Kim;

  • 作者单位

    Department of Transdisciplinary Studies, Seoul National University, Suwon, Rep, Korea;

    Advanced Institutes of Convergence Technology, Seoul National University, Suwon, Rep. Korea;

    Department of Transdisciplinary Studies, Seoul National University, Suwon, Rep, Korea College of Medicine, Seoul National University, Seoul, Rep. Korea Department of Radiology, Seoul National University Hospital, Seoul, Rep. Korea Advanced Institutes of Convergence Technology, Seoul National University, Suwon, Rep. Korea;

  • 会议组织
  • 原文格式 PDF
  • 正文语种 eng
  • 中图分类
  • 关键词

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱：kefu@zhangqiaokeyan.com

京公网安备：11010802029741号 ICP备案号：京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有

  • 客服微信

  • 服务号