MCA-Net: A Lightweight Multi-order Context Aggregation Network for Low Dose CT Denoising

被引:0
作者
Li, Jianfang [1 ,2 ]
Wang, Li [1 ,2 ,3 ]
Wang, ShengXiang [1 ,2 ]
Yu, Zitong [4 ]
Li, Yakang [1 ,2 ,3 ]
Qi, Fazhi [1 ,2 ,3 ]
机构
[1] Spallat Neutron Source Sci Ctr, Dongguan, Peoples R China
[2] Chinese Acad Sci, Inst High Energy Phys, Beijing, Peoples R China
[3] Univ Chinese Acad Sci, Beijing, Peoples R China
[4] Great Bay Univ, Sch Comp & Informat Technol, Dongguan, Peoples R China
来源
ADVANCED INTELLIGENT COMPUTING TECHNOLOGY AND APPLICATIONS, PT VI, ICIC 2024 | 2024年 / 14880卷
基金
中国国家自然科学基金;
关键词
Low dose CT; Denoising; Multi-order context aggregation; Edge enhancement;
D O I
10.1007/978-981-97-5678-0_38
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Low-dose computed tomography (LDCT) is widely utilized to reduce patient radiation exposure but often results in elevated noise levels. While deep learning models for LDCT denoising have made significant strides, they continue to struggle with effectively capturing discriminative features from high-resolution feature maps. This work proposes a lightweight network based on multi-order context aggregation for LDCT denoising, called MCA-Net. The proposed method enables an enhanced discriminative feature representation through stacking multiple multi-order context aggregation blocks, which are consisted of effective convolutions and gated aggregation. Furthermore, MCA-Netmitigates the loss of spatial detail information by incorporating prior edge-enhanced information and preserving high-resolution feature maps. Experiments conducted on two public datasets demonstrate superior performance compared to state-of-the-art models. Additionally, our method exhibits high competitiveness concerning parameter counts and computational efficiency. The code and pre-trained models will be released on https://code.ihep.ac.cn/lijf/MCANet.
引用
收藏
页码:447 / 458
页数:12
相关论文
共 50 条
[31]   Enhancement based convolutional dictionary network with adaptive window for low-dose CT denoising [J].
Liu, Yi ;
Yan, Rongbiao ;
Liu, Yuhang ;
Zhang, Pengcheng ;
Chen, Yang ;
Gui, Zhiguo .
JOURNAL OF X-RAY SCIENCE AND TECHNOLOGY, 2023, 31 (06) :1165-1187
[32]   Scale-Sensitive Generative Adversarial Network for Low-Dose CT Image Denoising [J].
Wang, Yanling ;
Han, Zefang ;
Zhang, Xiong ;
Shangguan, Hong ;
Zhang, Pengcheng ;
Li, Jie ;
Xiao, Ning .
IEEE ACCESS, 2024, 12 :98693-98706
[33]   LOW-DOSE CT DENOISING USING A STRUCTURE-PRESERVING KERNEL PREDICTION NETWORK [J].
Xu, Lu ;
Zhang, Yuwei ;
Liu, Ying ;
Wang, Daoye ;
Zhou, Mu ;
Ren, Jimmy ;
Wei, Jingwei ;
Ye, Zhaoxiang .
2021 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP), 2021, :1639-1643
[34]   Low-Dose CT Image Denoising Using a Generative Adversarial Network With a Hybrid Loss Function for Noise Learning [J].
Ma, Yinjin ;
Wei, Biao ;
Feng, Peng ;
He, Peng ;
Guo, Xiaodong ;
Wang, Ge .
IEEE ACCESS, 2020, 8 (08) :67519-67529
[35]   Low dose X-ray CT image denoising via U-net in projection domain [J].
Song, Xiaofu ;
Zhu, Linlin ;
Xi, Xiaoqi ;
Han, Yu ;
Li, Lei ;
Feng, Zhiwei ;
Zhu, Mingwan ;
Kang, Guanyu ;
Yan, Bin .
AOPC 2020: DISPLAY TECHNOLOGY; PHOTONIC MEMS, THZ MEMS, AND METAMATERIALS; AND AI IN OPTICS AND PHOTONICS, 2020, 11565
[36]   MLF-IOSC: Multi-Level Fusion Network With Independent Operation Search Cell for Low-Dose CT Denoising [J].
Shen, Jinbo ;
Luo, Mengting ;
Liu, Han ;
Liao, Peixi ;
Chen, Hu ;
Zhang, Yi .
IEEE TRANSACTIONS ON MEDICAL IMAGING, 2023, 42 (04) :1145-1158
[37]   SACNN: Self-Attention Convolutional Neural Network for Low-Dose CT Denoising With Self-Supervised Perceptual Loss Network [J].
Li, Meng ;
Hsu, William ;
Xie, Xiaodong ;
Cong, Jason ;
Gao, Wen .
IEEE TRANSACTIONS ON MEDICAL IMAGING, 2020, 39 (07) :2289-2301
[38]   Multi-scale perceptual modulation network for low-dose computed tomography denoising [J].
Huang, Jiexing ;
Zhong, Anni ;
Liu, Yujian .
QUANTITATIVE IMAGING IN MEDICINE AND SURGERY, 2024, 14 (12) :9290-9305
[39]   High-Frequency Sensitive Generative Adversarial Network for Low-Dose CT Image Denoising [J].
Yang, Linlin ;
Hong Shangguan ;
Xiong Zhang ;
Wang, Anhong ;
Han, Zefang .
IEEE ACCESS, 2020, 8 :930-943
[40]   Dual-domain fusion deep convolutional neural network for low-dose CT denoising [J].
Li, Zhiyuan ;
Liu, Yi ;
Chen, Yang ;
Shu, Huazhong ;
Lu, Jing ;
Gui, Zhiguo .
JOURNAL OF X-RAY SCIENCE AND TECHNOLOGY, 2023, 31 (04) :757-775