LeqMod: Adaptable Lesion-Quantification-Consistent Modulation for Deep Learning Low-Count PET Image Denoising

人工智能 深度学习 计算机科学 降噪 分割 能见度 计算机视觉 模式识别(心理学) 噪音(视频) 正电子发射断层摄影术 调制(音乐) 图像分割 推论 采样(信号处理) 还原(数学) 图像质量 航程(航空) 迭代重建 信噪比(成像) 图像(数学) 对比度(视觉) 图像复原 图像处理 医学影像学 图像噪声 干扰(通信) 特征提取 增采样
作者
Menghua Xia,Huidong Xie,Qiong Liu,Bo Zhou,Hanzhong Wang,Biao Li,Axel Rominger,Quanzheng Li,Ramsey D. Badawi,Kuangyu Shi,Georges El Fakhri,Chi Liu
出处
期刊:IEEE Transactions on Medical Imaging [Institute of Electrical and Electronics Engineers]
卷期号:45 (3): 1115-1126 被引量:2
标识
DOI:10.1109/tmi.2025.3618247
摘要

Deep learning-based positron emission tomography (PET) image denoising offers the potential to reduce radiation exposure and scanning time by transforming low-count images into high-count equivalents. However, existing methods typically blur crucial details, leading to inaccurate lesion quantification. This paper proposes a lesion-perceived and quantification-consistent modulation (LeqMod) strategy for enhanced PET image denoising, via employing downstream lesion quantification analysis as auxiliary tools. The LeqMod is a plug-and-play design adaptable to a wide range of model architectures, modulating the sampling and optimization procedures of model training without adding any computational burden to the inference phase. Specifically, the LeqMod consists of two components, the lesion-perceived modulation (LeMod) and the multiscale quantification-consistent modulation (QuMod). The LeMod enhances lesion contrast and visibility by allocating higher sampling weights and stricter loss criteria to lesion-present samples determined by an auxiliary segmentation network than lesion-absent ones. The QuMod further emphasizes quantification accuracy for both the mean and maximum standardized uptake value ( ${\mathrm {SUV}}_{{\textit {mean}}}$ and ${\mathrm {SUV}}_{{\textit {max}}}$ ) across multiscale sub-regions throughout the entire image, thereby reducing biases of denoised results relative to high-count references. Experiments conducted on large PET datasets from multiple centers and vendors, and varying noise levels demonstrated the LeqMod efficacy across various denoising frameworks. Compared to frameworks without LeqMod, the integration of LeqMod reduces the lesion ${\mathrm {SUV}}_{{\textit {max}}}$ bias by 5.92% on average and increases the peak signal-to-noise ratio (PSNR) by 0.36 on average, when denoising images across participating sites. (Code is available at https://github.com/mhxiaaa/LeqMod_PET_denoising).
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
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
1秒前
Lemonhead的应助被小木屋采纳,获得30
1秒前
科研通AI6.3的应助被chuangLiu采纳,获得10
1秒前
2秒前
99完成签到,获得积分10
2秒前
Violet的应助被牧百川采纳,获得10
3秒前
4秒前
顾矜的应助被18781913856采纳,获得10
4秒前
在水一方的应助被不灵0采纳,获得10
5秒前
5秒前
6秒前
狗研究完成签到 ,获得积分10
7秒前
乐乐的应助被崔崔大王采纳,获得10
7秒前
8秒前
英吉利25发布了新的文献求助10
8秒前
rumeng完成签到,获得积分10
9秒前
lyj完成签到 ,获得积分10
10秒前
英俊的铭的应助被akare采纳,获得10
11秒前
我叫蜜柑发布了新的文献求助10
11秒前
12秒前
12秒前
慢慢完成签到,获得积分10
13秒前
科研通AI6.3的应助被积极从蕾采纳,获得10
13秒前
14秒前
研友_VZG7GZ的应助被蓝胖子采纳,获得10
15秒前
风筝与亭完成签到 ,获得积分10
15秒前
15秒前
务时完成签到,获得积分20
16秒前
CaiRL完成签到,获得积分10
16秒前
俏皮道之完成签到,获得积分10
16秒前
akare完成签到,获得积分10
17秒前
lmy的应助被茶壶喝茶采纳,获得10
17秒前
binbin完成签到,获得积分10
19秒前
why发布了新的文献求助10
19秒前
李健的应助被实验狗采纳,获得10
19秒前
20秒前
务时发布了新的文献求助10
21秒前
22秒前
小女子常戚戚完成签到,获得积分10
22秒前
深情安青的应助被牧百川采纳,获得10
23秒前
高分求助中
(应助此贴封号)【重要!!请各用户(尤其是新用户)详细阅读】【科研通的精品贴汇总】 10000
拉伸高分子熔体中缠结行为的模拟和小角中子散射研究 1700
The World Atlas of Wine 9th edition 1000
奈特基础组织学:配套组织病理学(第4版)(Netter's Essential Histology With Correlated Histopathology) 800
八旗制度の研究 600
Improving the wear resistance of vehicle gear oil by oil soluble LaF3 nanoparticles and typical additives of gear oil 500
Boundaries and Bodhisattvas 500
热门求助领域 (近24小时)
化学 材料科学 医学 生物 纳米技术 计算机科学 工程类 有机化学 化学工程 生物化学 物理 复合材料 内科学 催化作用 光电子学 人工智能 细胞生物学 无机化学 物理化学 数学
热门帖子
关注 科研通微信公众号,转发送积分 8183324
求助须知:如何正确求助?哪些是违规求助? 9572627
关于积分的说明 21826529
捐赠科研通 7780320
什么是DOI,文献DOI怎么找? 3433993
关于科研通互助平台的介绍 2558155
邀请新用户注册赠送积分活动 2480290