A Deep Learning Based Method for Low Dose Lung CT Noise Reduction

被引：1

作者：

Ma, Yinjin ^{[1
,2
]}

Feng, Peng ^{[1
]}

He, Peng ^{[1
]}

Long, Zourong ^{[1
]}

Wei, Biao ^{[1
]}

机构：

[1] Chongqing Univ, Coll Optoelect Engn, Chongqing 400044, Peoples R China

[2] Tongren Univ, Sch Data Sci, Tongren 554300, Guizhou, Peoples R China

来源：

PROCEEDINGS OF 2019 CHINESE INTELLIGENT SYSTEMS CONFERENCE, VOL I | 2020年 / 592卷

基金：

中国国家自然科学基金;

关键词：

Low dose CT; Convolutional neural network; Residual learning; Noise reduction; X-RAY; RECONSTRUCTION;

D O I：

10.1007/978-981-32-9682-4_68

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

A method based on convolutional neural network auto encoder-decoder for low dose lung CT image noise reduction is presented. This method integrated convolutional neural network, auto encoder-decoder, residual learning, parametric rectified linear unit (PReLU). Particularly, the term of structural similarity index (SSIM) added to the loss function. After training patch by patch, the model attains a promising performance compared to state of the art traditional and deep learning methods in visual effects and quantitative measurements.

引用

页码：649 / 657

页数：9

共 12 条

[1] Ray Contribution Masks for Structure Adaptive Sinogram Filtering [J].

Balda, Michael ;

Hornegger, Joachim ;

Heismann, Bjoern .

IEEE TRANSACTIONS ON MEDICAL IMAGING, 2012, 31 (06) :1228-1239

[2] Low-Dose CT With a Residual Encoder-Decoder Convolutional Neural Network [J].

Chen, Hu ;

Zhang, Yi ;

Kalra, Mannudeep K. ;

Lin, Feng ;

Chen, Yang ;

Liao, Peixi ;

Zhou, Jiliu ;

Wang, Ge .

IEEE TRANSACTIONS ON MEDICAL IMAGING, 2017, 36 (12) :2524-2535

[3] Low-dose CT via convolutional neural network [J].

Chen, Hu ;

Zhang, Yi ;

Zhang, Weihua ;

Liao, Peixi ;

Li, Ke ;

Zhou, Jiliu ;

Wang, Ge .

BIOMEDICAL OPTICS EXPRESS, 2017, 8 (02) :679-694

[4] Deep Residual Learning for Image Recognition [J].

He, Kaiming ;

Zhang, Xiangyu ;

Ren, Shaoqing ;

Sun, Jian .

2016 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2016, :770-778

[5] Image Denoising of Low-radiation Dose Coronary CT Angiography by an Adaptive Block-Matching 3D Algorithm [J].

Kang, Dongwoo ;

Slomka, Piotr ;

Nakazato, Ryo ;

Woo, Jonghye ;

Berman, Daniel S. ;

Kuo, C. -C. Jay ;

Dey, Damini .

MEDICAL IMAGING 2013: IMAGE PROCESSING, 2013, 8669

[6] A deep convolutional neural network using directional wavelets for low-dose X-ray CT reconstruction [J].

Kang, Eunhee ;

Min, Junhong ;

Ye, Jong Chul .

MEDICAL PHYSICS, 2017, 44 (10) :e360-e375

[7] Adaptive nonlocal means filtering based on local noise level for CT denoising [J].

Li, Zhoubo ;

Yu, Lifeng ;

Trzasko, Joshua D. ;

Lake, David S. ;

Blezek, Daniel J. ;

Fletcher, Joel G. ;

McCollough, Cynthia H. ;

Manduca, Armando .

MEDICAL PHYSICS, 2014, 41 (01)

[8] DIAGNOSTIC-X-RAY AND ULTRASOUND EXPOSURE AND RISK OF CHILDHOOD-CANCER [J].

SHU, XO ;

JIN, F ;

LINET, MS ;

ZHENG, W ;

CLEMENS, J ;

MILLS, J ;

GAO, YT .

BRITISH JOURNAL OF CANCER, 1994, 70 (03) :531-536

[9] Image reconstruction in circular cone-beam computed tomography by constrained, total-variation minimization [J].

Sidky, Emil Y. ;

Pan, Xiaochuan .

PHYSICS IN MEDICINE AND BIOLOGY, 2008, 53 (17) :4777-4807

[10] An outlook on x-ray CT research and development [J].

Wang, Ge ;

Yu, Hengyong ;

De Man, Bruno .

MEDICAL PHYSICS, 2008, 35 (03) :1051-1064

← 1 2 →