Texture-preserving low dose CT image denoising using Pearson divergence

模式识别(心理学) 人工智能 图像去噪 皮尔逊积矩相关系数 数学 降噪 分歧(语言学) 纹理(宇宙学) 计算机科学 计算机视觉 图像(数学) 核医学 医学 统计 语言学 哲学
作者
Jieun Oh,Dufan Wu,Boohwi Hong,Dongheon Lee,Min‐Woong Kang,Quanzheng Li,Kyungsang Kim
出处
期刊:Physics in Medicine and Biology [IOP Publishing]
卷期号:69 (11): 115021-115021 被引量:1
标识
DOI:10.1088/1361-6560/ad45a4
摘要

Abstract Objective. The mean squared error (MSE), also known as L 2 loss, has been widely used as a loss function to optimize image denoising models due to its strong performance as a mean estimator of the Gaussian noise model. Recently, various low-dose computed tomography (LDCT) image denoising methods using deep learning combined with the MSE loss have been developed; however, this approach has been observed to suffer from the regression-to-the-mean problem, leading to over-smoothed edges and degradation of texture in the image. Approach. To overcome this issue, we propose a stochastic function in the loss function to improve the texture of the denoised CT images, rather than relying on complicated networks or feature space losses. The proposed loss function includes the MSE loss to learn the mean distribution and the Pearson divergence loss to learn feature textures. Specifically, the Pearson divergence loss is computed in an image space to measure the distance between two intensity measures of denoised low-dose and normal-dose CT images. The evaluation of the proposed model employs a novel approach of multi-metric quantitative analysis utilizing relative texture feature distance. Results. Our experimental results show that the proposed Pearson divergence loss leads to a significant improvement in texture compared to the conventional MSE loss and generative adversarial network (GAN), both qualitatively and quantitatively. Significance. Achieving consistent texture preservation in LDCT is a challenge in conventional GAN-type methods due to adversarial aspects aimed at minimizing noise while preserving texture. By incorporating the Pearson regularizer in the loss function, we can easily achieve a balance between two conflicting properties. Consistent high-quality CT images can significantly help clinicians in diagnoses and supporting researchers in the development of AI-diagnostic models.
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
PDF的下载单位、IP信息已删除 (2025-6-4)

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
卡皮巴拉完成签到,获得积分10
刚刚
miaoww完成签到,获得积分10
1秒前
孤独寻云发布了新的文献求助30
1秒前
luckyshao完成签到,获得积分20
1秒前
2秒前
2秒前
3秒前
Majiko完成签到,获得积分10
3秒前
易安发布了新的文献求助10
4秒前
5秒前
咕噜噜完成签到,获得积分10
5秒前
6秒前
6秒前
星辰大海应助Majiko采纳,获得10
7秒前
7秒前
茶蛋完成签到 ,获得积分10
7秒前
7秒前
8秒前
夏铖铄完成签到,获得积分10
8秒前
8秒前
kelly发布了新的文献求助10
9秒前
you发布了新的文献求助30
10秒前
Dream123关注了科研通微信公众号
10秒前
momm852完成签到,获得积分10
10秒前
哈尼发布了新的文献求助10
10秒前
科研通AI2S应助孟双采纳,获得10
10秒前
shary发布了新的文献求助10
11秒前
11秒前
tomorrow9发布了新的文献求助10
11秒前
千寻发布了新的文献求助10
12秒前
12秒前
12秒前
12秒前
铺盖卷儿完成签到 ,获得积分10
13秒前
momm852发布了新的文献求助10
13秒前
轻轻发布了新的文献求助10
13秒前
蘸糖冰美式完成签到,获得积分10
13秒前
强小蝶发布了新的文献求助30
14秒前
Jacey79完成签到 ,获得积分10
14秒前
14秒前
高分求助中
A new approach to the extrapolation of accelerated life test data 1000
ACSM’s Guidelines for Exercise Testing and Prescription, 12th edition 500
Picture Books with Same-sex Parented Families: Unintentional Censorship 500
Nucleophilic substitution in azasydnone-modified dinitroanisoles 500
不知道标题是什么 500
A Preliminary Study on Correlation Between Independent Components of Facial Thermal Images and Subjective Assessment of Chronic Stress 500
Phylogenetic study of the order Polydesmida (Myriapoda: Diplopoda) 360
热门求助领域 (近24小时)
化学 材料科学 医学 生物 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 遗传学 基因 物理化学 催化作用 冶金 细胞生物学 免疫学
热门帖子
关注 科研通微信公众号,转发送积分 3971091
求助须知:如何正确求助?哪些是违规求助? 3515797
关于积分的说明 11179488
捐赠科研通 3250872
什么是DOI,文献DOI怎么找? 1795536
邀请新用户注册赠送积分活动 875891
科研通“疑难数据库(出版商)”最低求助积分说明 805207