摘要详情
  1. 活动首页
  2. 摘要清单
  3. 摘要详情
62 / 2021-10-15 16:02:06
MRI to CT synthesis using contrastive learning
MRI, contrastive learning, pseudo CT
Artificial intelligence (AI) and medical image processing and computer-aided diagnosis Medical image • information management system（PACS/RIS, IHE-RAD/IHE-RO）
终稿
江涛 王 / 中国科学技术大学
新红 吴 / 中国科学技术大学
潇 姜 / 中国科学技术大学
磊 朱 / 中国科学技术大学
Compared with CT, MRI enables more accurate delineation of target and organs-at-risk. But unlike CT, MRI images is not related with electron density for radiotherapy planning. The purpose of this paper is to generate pseudo CT for radiotherapy planning from MRI using deep learning method. Twenty-nine brain cancer patients with planning CT and diagnostic MRI were selected, of which 23 were used for training and 6 for testing. We use a new neural network based on contrast learning, called CUT. Meanwhile, we change the residual block to nine dense blocks and add a structural similarity to the loss function of the generator, the latter network is called denseCUT. We  compare  Hounsfield Unit (HU) discrepancies between pseudo-CT and original  CT  images.  The mean absolute (MAE) errors were 72.0±6.9 HU，72.5±8.0 HU and 65.7±8.0 HU for the cycleGAN, CUT and denseCUT, respectively. Meanwhile, the structure similarity index (SSIM) were 0.91±0.01, 0.91±0.01 and 0.93±0.01, the peak signal-to-noise ratio (PSNR) were 28.5±0.7 dB, 28.5±0.7 dB and 29.4±0.8 dB, respectively. Experimental results show that the proposed denseCUT network is more accurate,  robust,  and  efficient  for  predicting  synthetic  CT  from MR images for MRI-only radiotherapy.
重要日期

  • 会议日期

    11月13日

    2021

    至

    11月14日

    2021

  • 09月30日 2021

    报告提交截止日期

  • 11月14日 2021

    注册截止日期

主办单位
IEEE北京分会
中国生物医学工程学会医学物理分会
中国电子学会生命电子学分会
承办单位
中国科学技术大学
安徽省生物医学工程学会
联系方式
登录查看完整联系方式
历届会议
移动端
在手机上打开
小程序
打开微信小程序
客服
扫码或点此咨询