TY - GEN
T1 - PET Denoising and Uncertainty Estimation Based on NVAE Model
AU - Cui, Jianan
AU - Xie, Yutong
AU - Gong, Kuang
AU - Kim, Kyungsang
AU - Yang, Jaewon
AU - Larson, Peder
AU - Hope, Thomas
AU - Behr, Spencer
AU - Seo, Youngho
AU - Liu, Huafeng
AU - Li, Quanzheng
N1 - Funding Information:
Manuscript received November 11, 2021. This work was supported in part by the National Key Technology Research and Development Program of China (No: 2017YFE0104000,2016YFC1300302) and by the National Natural Science Foundation of China (No: U1809204, 81873908, 61701436, 62101488), by the Key Research and Develop-ment Program of Zhejiang Province (No. 2021C03029) and by China Postdoctoral Science Foundation (No. 2021M692830).
Publisher Copyright:
© 2021 IEEE.
PY - 2021
Y1 - 2021
N2 - The structure of the deep neural network is constantly changing, and its performance is constantly breaking through. Recently, a new network, Nouveau variational auto-encoder (NVAE), has been proposed and gained great attention. In addition to the ability to generate high-quality images, the more important nature of NVAE is that it can generate a distribution that makes it possible to measure the uncertainty. In this work, we proposed to use NVAE for PET image denoising and estimate the uncertainty from both training data and model at the same time. 2.5D training based on 28 patients was performed and quantification based on 7 real patient data showed that NVAE has a good performance for PET denoising, which outperforms the Unet. The variance of 1000 sample output was calculated to show the uncertainty map.
AB - The structure of the deep neural network is constantly changing, and its performance is constantly breaking through. Recently, a new network, Nouveau variational auto-encoder (NVAE), has been proposed and gained great attention. In addition to the ability to generate high-quality images, the more important nature of NVAE is that it can generate a distribution that makes it possible to measure the uncertainty. In this work, we proposed to use NVAE for PET image denoising and estimate the uncertainty from both training data and model at the same time. 2.5D training based on 28 patients was performed and quantification based on 7 real patient data showed that NVAE has a good performance for PET denoising, which outperforms the Unet. The variance of 1000 sample output was calculated to show the uncertainty map.
UR - http://www.scopus.com/inward/record.url?scp=85139011487&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85139011487&partnerID=8YFLogxK
U2 - 10.1109/NSS/MIC44867.2021.9875487
DO - 10.1109/NSS/MIC44867.2021.9875487
M3 - Conference contribution
AN - SCOPUS:85139011487
T3 - 2021 IEEE Nuclear Science Symposium and Medical Imaging Conference Record, NSS/MIC 2021 and 28th International Symposium on Room-Temperature Semiconductor Detectors, RTSD 2022
BT - 2021 IEEE Nuclear Science Symposium and Medical Imaging Conference Record, NSS/MIC 2021 and 28th International Symposium on Room-Temperature Semiconductor Detectors, RTSD 2022
A2 - Tomita, Hideki
A2 - Nakamura, Tatsuya
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2021 IEEE Nuclear Science Symposium and Medical Imaging Conference, NSS/MIC 2021
Y2 - 16 October 2021 through 23 October 2021
ER -