Positron emission tomography image enhancement using magnetic resonance images and U-net structure

被引：4

作者：

Garehdaghi, Farnaz ^{[1
]}

Meshgini, Saeed ^{[1
]}

Afrouzian, Reza ^{[2
]}

机构：

[1] Univ Tabriz, Fac Elect & Comp Engn, Dept Biomed Engn, Tabriz, Iran

[2] Univ Tabriz, Miyaneh Fac Engn, Miyaneh, Iran

来源：

COMPUTERS & ELECTRICAL ENGINEERING | 2021年 / 90卷

关键词：

Positron Emission Tomography; Convolutional Neural Networks; Residual Blocks; Perceptual Loss; Structural Similarity Index; SUPERRESOLUTION; BRAIN; MRI;

D O I：

10.1016/j.compeleceng.2021.106973

中图分类号：

TP3 [计算技术、计算机技术];

学科分类号：

0812 ;

摘要：

Positron Emission Tomography (PET) has become an important tool for diagnosing abnormalities, but it suffers from low spatial resolution and a high-level noise. In this article, a Convolutional Neural Network (CNN)-based Single Image Super-resolution (SISR) method is used to produce a PET image with a desired quality. The T1-Weighted Magnetic Resonance (MR) images are used to enrich the information applied to the network. A network based on U-Net structure is used and residual blocks are inserted into the network to improve system performance. This article also evaluates the impact of various loss functions, such as Mean Squared Error (MSE) and its combination with a perceptual loss on the efficiency of the proposed method. Peak Signal to Noise Ratio (PSNR) and Structural Similarity Index (SSIM) on two various databases (simulated and clinical data) are 36.78, 0.9927, and 37.36, 0.9714, respectively, indicating good performance of the proposed method compared to previous works.

引用

页数：12

共 25 条

[1]

[Anonymous], 2016, P EUR C COMPUT VIS

[2]

Cocosco C. A., 1997, NeuroImage, DOI DOI 10.1016/S1053-8119(97)80018-3

[3] Image Super-Resolution Using Deep Convolutional Networks [J].

Dong, Chao ;

Loy, Chen Change ;

He, Kaiming ;

Tang, Xiaoou .

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2016, 38 (02) :295-307

[4]

HE K, 2016, P C COMP VIS PATT RE, DOI [DOI 10.1109/CVPR.2016.90, DOI 10.1007/978-3-319-46493-0_38, 10.1007/978-3-319-46493-0_38]

[5] Enhancing the Image Quality via Transferred Deep Residual Learning of Coarse PET Sinograms [J].

Hong, Xiang ;

Zan, Yunlong ;

Weng, Fenghua ;

Tao, Weijie ;

Peng, Qiyu ;

Huang, Qiu .

IEEE TRANSACTIONS ON MEDICAL IMAGING, 2018, 37 (10) :2322-2332

[6] Enabling Linearly Homomorphic Signatures in Network Coding-based Named Data Networking [J].

Hu, Xiaoyan ;

Zheng, Shaoqi ;

Gong, Jian ;

Cheng, Guang ;

Zhang, Guoqiang ;

Li, Ruidong .

PROCEEDINGS OF THE 14TH INTERNATIONAL CONFERENCE ON FUTURE INTERNET TECHNOLOGIES (CFI'19), 2019,

[7]

Ioffe S., 2015, PMLR, P448, DOI DOI 10.48550/ARXIV.1502.03167

[8]

Jr Jack R. C, 2008, J MAGN RESON IMAGING, V27, P685

[9] Prediction of standard-dose brain PET image by using MRI and low-dose brain [18F]FDG PET images [J].

Kang, Jiayin ;

Gao, Yaozong ;

Shi, Feng ;

Lalush, David S. ;

Lin, Weili ;

Shen, Dinggang .

MEDICAL PHYSICS, 2015, 42 (09) :5301-5309

[10] Super-resolution in PET imaging [J].

Kennedy, JA ;

Israel, O ;

Frenkel, A ;

Bar-Shalom, R ;

Azhari, H .

IEEE TRANSACTIONS ON MEDICAL IMAGING, 2006, 25 (02) :137-147

← 1 2 3 →