Low‐dose CT denoising with a high‐level feature refinement and dynamic convolution network

特征(语言学) 计算机科学 降噪 卷积(计算机科学) 人工智能 核(代数) 噪音(视频) 模式识别(心理学) 投影(关系代数) 医学影像学 计算机视觉 算法 图像(数学) 人工神经网络 数学 哲学 语言学 组合数学
作者
Sihan Yang,Qiang Pu,Chunting Lei,Qiao Zhang,Seunggil Jeon,Xiaomin Yang
出处
期刊:Medical Physics [Wiley]
卷期号:50 (6): 3597-3611 被引量:2
标识
DOI:10.1002/mp.16175
摘要

Since the potential health risks of the radiation generated by computer tomography (CT), concerns have been expressed on reducing the radiation dose. However, low-dose CT (LDCT) images contain complex noise and artifacts, bringing uncertainty to medical diagnosis.Existing deep learning (DL)-based denoising methods are difficult to fully exploit hierarchical features of different levels, limiting the effect of denoising. Moreover, the standard convolution kernel is parameter sharing and cannot be adjusted dynamically with input change. This paper proposes an LDCT denoising network using high-level feature refinement and multiscale dynamic convolution to mitigate these problems.The dual network structure proposed in this paper consists of the feature refinement network (FRN) and the dynamic perception network (DPN). The FDN extracts features of different levels through residual dense connections. The high-level hierarchical information is transmitted to DPN to improve the low-level representations. In DPN, the two networks' features are fused by local channel attention (LCA) to assign weights in different regions and handle CT images' delicate tissues better. Then, the dynamic dilated convolution (DDC) with multibranch and multiscale receptive fields is proposed to enhance the expression and processing ability of the denoising network. The experiments were trained and tested on the dataset "NIH-AAPM-Mayo Clinic Low-Dose CT Grand Challenge," consisting of 10 anonymous patients with normal-dose abdominal CT and LDCT at 25% dose. In addition, external validation was performed on the dataset "Low Dose CT Image and Projection Data," which included 300 chest CT images at 10% dose and 300 head CT images at 25% dose.Proposed method compared with seven mainstream LDCT denoising algorithms. On the Mayo dataset, achieved peak signal-to-noise ratio (PSNR): 46.3526 dB (95% CI: 46.0121-46.6931 dB) and structural similarity (SSIM): 0.9844 (95% CI: 0.9834-0.9854). Compared with LDCT, the average increase was 3.4159 dB and 0.0239, respectively. The results are relatively optimal and statistically significant compared with other methods. In external verification, our algorithm can cope well with ultra-low-dose chest CT images at 10% dose and obtain PSNR: 28.6130 (95% CI: 28.1680-29.0580 dB) and SSIM: 0.7201 (95% CI: 0.7101-0.7301). Compared with LDCT, PSNR/SSIM is increased by 3.6536dB and 0.2132, respectively. In addition, the quality of LDCT can also be improved in head CT denoising.This paper proposes a DL-based LDCT denoising algorithm, which utilizes high-level features and multiscale dynamic convolution to optimize the network's denoising effect. This method can realize speedy denoising and performs well in noise suppression and detail preservation, which can be helpful for the diagnosis of LDCT.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
更新
大幅提高文件上传限制,最高150M (2024-4-1)

科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
Ivan完成签到 ,获得积分10
1秒前
不吃了完成签到 ,获得积分10
4秒前
xiaohong完成签到 ,获得积分0
5秒前
迅速的巧曼完成签到 ,获得积分10
6秒前
6秒前
7秒前
kl完成签到 ,获得积分10
8秒前
sihaibo完成签到,获得积分10
10秒前
TOUHOUU发布了新的文献求助10
13秒前
14秒前
yfy完成签到 ,获得积分10
17秒前
生动听筠完成签到 ,获得积分10
29秒前
wangxc完成签到 ,获得积分10
30秒前
如沐完成签到 ,获得积分20
30秒前
30秒前
H-kevin.完成签到,获得积分10
32秒前
婉莹完成签到 ,获得积分0
33秒前
cripple发布了新的文献求助10
34秒前
丰盛的煎饼应助zyjsunye采纳,获得10
35秒前
TOUHOUU完成签到,获得积分10
35秒前
沉沉完成签到 ,获得积分0
36秒前
黑球发布了新的文献求助10
36秒前
今宵 别梦寒完成签到 ,获得积分10
38秒前
39秒前
Krim完成签到 ,获得积分10
40秒前
隔壁的镇长完成签到,获得积分10
42秒前
yys发布了新的文献求助10
43秒前
浮生若梦完成签到,获得积分10
44秒前
黑球完成签到,获得积分10
44秒前
燕晓啸完成签到 ,获得积分0
44秒前
epmoct完成签到 ,获得积分10
45秒前
一叶舟完成签到,获得积分10
47秒前
李健应助黑球采纳,获得10
48秒前
伴夏完成签到 ,获得积分10
53秒前
徐悦完成签到,获得积分10
58秒前
58秒前
cripple完成签到,获得积分10
1分钟前
wowser发布了新的文献求助10
1分钟前
整齐的大开完成签到 ,获得积分10
1分钟前
涨芝士完成签到 ,获得积分10
1分钟前
高分求助中
좌파는 어떻게 좌파가 됐나:한국 급진노동운동의 형성과 궤적 2500
Sustainability in Tides Chemistry 1500
TM 5-855-1(Fundamentals of protective design for conventional weapons) 1000
Cognitive linguistics critical concepts in linguistics 800
Threaded Harmony: A Sustainable Approach to Fashion 799
Livre et militantisme : La Cité éditeur 1958-1967 500
氟盐冷却高温堆非能动余热排出性能及安全分析研究 500
热门求助领域 (近24小时)
化学 医学 生物 材料科学 工程类 有机化学 生物化学 物理 内科学 纳米技术 计算机科学 化学工程 复合材料 基因 遗传学 催化作用 物理化学 免疫学 量子力学 细胞生物学
热门帖子
关注 科研通微信公众号,转发送积分 3052652
求助须知:如何正确求助?哪些是违规求助? 2709874
关于积分的说明 7418298
捐赠科研通 2354492
什么是DOI,文献DOI怎么找? 1246104
科研通“疑难数据库(出版商)”最低求助积分说明 605951
版权声明 595921