Please use this identifier to cite or link to this item:
http://localhost/handle/Hannan/716996
Title: | PET Image Denoising Using a Deep Neural Network Through Fine Tuning |
Other Titles: | IEEE Transactions on Radiation and Plasma Medical Sciences |
Authors: | Kuang Gong|Jiahui Guan|Chih-Chieh Liu|Jinyi Qi |
subject: | positron emission tomography (PET)|fine-tuning|perceptual loss|Convolutional neural network (CNN)|image denoising |
Year: | -1-Uns- -1 |
Abstract: | Positron emission tomography (PET) is a functional imaging modality widely used in clinical diagnosis. In this paper, we trained a deep convolutional neural network to improve PET image quality. Perceptual loss based on features derived from a pretrained VGG network, instead of the conventional mean squared error, was employed as the training loss function to preserve image details. As the number of real patient data set for training is limited, we propose to pretrain the network using simulation data and fine-tune the last few layers of the network using real data sets. Results from simulation, real brain, and lung data sets show that the proposed method is more effective in removing noise than the traditional Gaussian filtering method. |
URI: | http://localhost/handle/Hannan/716996 |
ISBN: | 2469-7311 |
volume: | Volume |
issue: | Issue |
Appears in Collections: | New Ieee 2019 |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
08502864.pdf | 1.72 MB | Adobe PDF | ![]() Preview File |
Title: | PET Image Denoising Using a Deep Neural Network Through Fine Tuning |
Other Titles: | IEEE Transactions on Radiation and Plasma Medical Sciences |
Authors: | Kuang Gong|Jiahui Guan|Chih-Chieh Liu|Jinyi Qi |
subject: | positron emission tomography (PET)|fine-tuning|perceptual loss|Convolutional neural network (CNN)|image denoising |
Year: | -1-Uns- -1 |
Abstract: | Positron emission tomography (PET) is a functional imaging modality widely used in clinical diagnosis. In this paper, we trained a deep convolutional neural network to improve PET image quality. Perceptual loss based on features derived from a pretrained VGG network, instead of the conventional mean squared error, was employed as the training loss function to preserve image details. As the number of real patient data set for training is limited, we propose to pretrain the network using simulation data and fine-tune the last few layers of the network using real data sets. Results from simulation, real brain, and lung data sets show that the proposed method is more effective in removing noise than the traditional Gaussian filtering method. |
URI: | http://localhost/handle/Hannan/716996 |
ISBN: | 2469-7311 |
volume: | Volume |
issue: | Issue |
Appears in Collections: | New Ieee 2019 |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
08502864.pdf | 1.72 MB | Adobe PDF | ![]() Preview File |
Title: | PET Image Denoising Using a Deep Neural Network Through Fine Tuning |
Other Titles: | IEEE Transactions on Radiation and Plasma Medical Sciences |
Authors: | Kuang Gong|Jiahui Guan|Chih-Chieh Liu|Jinyi Qi |
subject: | positron emission tomography (PET)|fine-tuning|perceptual loss|Convolutional neural network (CNN)|image denoising |
Year: | -1-Uns- -1 |
Abstract: | Positron emission tomography (PET) is a functional imaging modality widely used in clinical diagnosis. In this paper, we trained a deep convolutional neural network to improve PET image quality. Perceptual loss based on features derived from a pretrained VGG network, instead of the conventional mean squared error, was employed as the training loss function to preserve image details. As the number of real patient data set for training is limited, we propose to pretrain the network using simulation data and fine-tune the last few layers of the network using real data sets. Results from simulation, real brain, and lung data sets show that the proposed method is more effective in removing noise than the traditional Gaussian filtering method. |
URI: | http://localhost/handle/Hannan/716996 |
ISBN: | 2469-7311 |
volume: | Volume |
issue: | Issue |
Appears in Collections: | New Ieee 2019 |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
08502864.pdf | 1.72 MB | Adobe PDF | ![]() Preview File |