Presentation Details
MRI to CT synthesis using contrastive learning
ID：51
View Protection：ATTENDEE
Updated Time：2021-10-30 17:37:08 Hits：2001
Poster Presentation
Start Time：2021-11-13 10:15（Asia/Shanghai）
Duration：5min
Session：Pos Poster »
Video
No Permission
Presentation File
Tips: Only the registered participant can access the file. Please sign in first.
Abstract
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.
Keywords
MRI, contrastive learning, pseudo CT
Speaker
江涛 王
中国科学技术大学Submission Author
All Comments
Important Date
-
Conference Date
Nov 13
2021
toNov 14
2021
-
Sep 30 2021
Contribution Submission Deadline
-
Nov 14 2021
Registration deadline
Sponsored By
Medical Physics Branch of Chinese Society of Biomedical Engineering
IEEE Beijing Section
Life Electronics Society of Chinese Institute of Electronics
IEEE Beijing Section
Life Electronics Society of Chinese Institute of Electronics
Organized By
Anhui Biomedical Engineering Society.
University of Science and Technology of China
University of Science and Technology of China
Contact Information
- Mrs. Yang
- ic******@ustc.edu.cn
- +86********
Previous Conferences
-
2017-11-04 China Beijing,China
2017 International Conference on Medical Imaging Physics and Engineering -
2017-11-03 China 海淀区
2017 IEEE 国际医学影像物理和工程大会 -
2013-10-19 China 沈阳市
2013 IEEE International Conference on Medical Imaging Physics and Engineering (ICMIPE)
Submit Comment