Despecking of Ultrasound Image Using LENet-based Nonlocal-Means Method

被引:1
作者
Yu Houqiang [1 ]
Li Ling [2 ]
Zheng Min [3 ]
Qiu Wu [4 ,5 ]
Ding Mingyue [4 ,6 ]
机构
[1] Hubei Univ Sci & Technol, Dept Math & Stat, Xianning 437100, Hubei, Peoples R China
[2] Hubei Univ Sci & Technol, Xianning Med Coll, Sch Biomed Engn & Imaging, Xianning 437100, Hubei, Peoples R China
[3] Hubei Univ Sci & Technol, Sch Elect & Informat Engn, Xianning 437100, Hubei, Peoples R China
[4] Huazhong Univ Sci & Technol, Educ Minist China, Image Proc & Intelligence Control Key Lab, Dept Biomed Engn,Coll Life Sci & Technol, Wuhan 430074, Hubei, Peoples R China
[5] Wuhan Seekmore Intelligent Imaging Inc, Wuhan, Peoples R China
[6] Hubei Yueming Technol Co Ltd, Wuhan, Peoples R China
来源
MEDICAL IMAGING 2024: ULTRASONIC IMAGING AND TOMOGRAPHY | 2024年 / 12932卷
基金
中国国家自然科学基金;
关键词
ultrasound image; nonlocal-means; Laplacian Eigenmaps network; despeckling; NOISE REMOVAL; SPECKLE; MODELS;
D O I
10.1117/12.3006341
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Speckle noise is an integral component in medical ultrasound imaging, which have a random granular pattern formation. This noise degrades the visual quality of ultrasound images and complicates image-based interpretation and diagnosis. The removal of interference-induced noise is a primary challenge as ultrasound image studies seek to achieve higher accuracy and characterize more subtle small and low-contrast lesions. In this study, a novel method, which combines the nonlocal-means (NLM) filter with a simple unsupervised deep model named Laplacian Eigenmaps network (LENet), has been proposed for ultrasonic speckle reduction. The proposed method exploits both the global features, redundancy information and self-similarity properties of noisy images, which first extract features from the noisy image by the Laplacian Eigenmaps algorithm, and then apply it to refine the image self-similarities weight for helping the NLM filter to provide better despeckling performance. Specifically, this is a two-stage approach that the first stage is to learn filter banks from a small quantity of training samples by LENet network and the following stage is to utilize the output eigenvectors as similarity metrics of pixels within the NLM filter. The performance of our approach is compared with related state-of-the-art methods on synthetic images, simulated image and real ultrasound images. The results show that our method can provide better noise removal ability over many previously despecking filters.
引用
收藏
页数:8
相关论文
共 15 条
[1]   A non-local algorithm for image denoising [J].
Buades, A ;
Coll, B ;
Morel, JM .
2005 IEEE COMPUTER SOCIETY CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, VOL 2, PROCEEDINGS, 2005, :60-65
[2]   Nonlocal Means-Based Speckle Filtering for Ultrasound Images [J].
Coupe, Pierrick ;
Hellier, Pierre ;
Kervrann, Charles ;
Barillot, Christian .
IEEE TRANSACTIONS ON IMAGE PROCESSING, 2009, 18 (10) :2221-2229
[3]   Nonlocal total variation models for multiplicative noise removal using split Bregman iteration [J].
Dong, Fangfang ;
Zhang, Haili ;
Kong, De-Xing .
MATHEMATICAL AND COMPUTER MODELLING, 2012, 55 (3-4) :939-954
[4]   A MODEL FOR RADAR IMAGES AND ITS APPLICATION TO ADAPTIVE DIGITAL FILTERING OF MULTIPLICATIVE NOISE [J].
FROST, VS ;
STILES, JA ;
SHANMUGAN, KS ;
HOLTZMAN, JC .
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 1982, 4 (02) :157-166
[5]   Wavelet denoising for quantum noise removal in chest digital tomosynthesis [J].
Gomi, Tsutomu ;
Nakajima, Masahiro ;
Umeda, Tokuo .
INTERNATIONAL JOURNAL OF COMPUTER ASSISTED RADIOLOGY AND SURGERY, 2015, 10 (01) :75-86
[6]   ADAPTIVE RESTORATION OF IMAGES WITH SPECKLE [J].
KUAN, DT ;
SAWCHUK, AA ;
STRAND, TC ;
CHAVEL, P .
IEEE TRANSACTIONS ON ACOUSTICS SPEECH AND SIGNAL PROCESSING, 1987, 35 (03) :373-383
[7]   AN ADAPTIVE WEIGHTED MEDIAN FILTER FOR SPECKLE SUPPRESSION IN MEDICAL ULTRASONIC IMAGES [J].
LOUPAS, T ;
MCDICKEN, WN ;
ALLAN, PL .
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS, 1989, 36 (01) :129-135
[8]  
Pal S K, 2021, 2021 INT C ADV COMP
[9]   A versatile wavelet domain noise filtration technique for medical imaging [J].
Pizurica, A ;
Philips, W ;
Lemahieu, I ;
Acheroy, M .
IEEE TRANSACTIONS ON MEDICAL IMAGING, 2003, 22 (03) :323-331
[10]  
Slabaugh G., 2006, Computer Vision and Pattern Recognition, 2006 IEEE Computer Society Conference on, P45