Speckle Noise Reduction Techniques Research Articles

Unsupervised speckle noise reduction technique for clinical ultrasound imaging.

Deep learning-based image enhancement has significant potential in the field of ultrasound image processing, as it can accurately model complicated nonlinear artifacts and noise, such as ultrasonic speckle patterns. However, training deep learning networks to acquire reference images that are clean and free of noise presents significant challenges. This study introduces an unsupervised deep learning framework, termed speckle-to-speckle (S2S), designed for speckle and noise suppression. This framework can complete its training without the need for clean (speckle-free) reference images. The proposed network leverages statistical reasoning for the mutual training of two in vivo images, each with distinct speckle patterns and noise. It then infers speckle- and noise-free images without needing clean reference images. This approach significantly reduces the time, cost, and effort experts need to invest in annotating reference images manually. The experimental results demonstrated that the proposed approach outperformed existing techniques in terms of the signal-to-noise ratio, contrast-to-noise ratio, structural similarity index, edge preservation index, and processing time (up to 86 times faster). It also performed excellently on images obtained from ultrasound scanners other than the ones used in this work. S2S demonstrates the potential of employing an unsupervised learning-based technique in medical imaging applications, where acquiring a ground truth reference is challenging.

Optical coherence tomography image despeckling based on tensor singular value decomposition and fractional edge detection

Optical coherence tomography (OCT) imaging is a technique that is frequently used to diagnose medical conditions. However, coherent noise, sometimes referred to as speckle noise, can dramatically reduce the quality of OCT images, which has an adverse effect on how OCT images are used. In order to enhance the quality of OCT images, a speckle noise reduction technique is developed, and this method is modelled as a low-rank tensor approximation issue. The grouped 3D tensors are first transformed into the transform domain using tensor singular value decomposition (t-SVD). Then, to cut down on speckle noise, transform coefficients are thresholded. Finally, the inverse transform can be used to produce images with speckle suppression. To further enhance the despeckling results, a feature-guided thresholding approach based on fractional edge detection and an adaptive backward projection technique are also presented. Experimental results indicate that the presented algorithm outperforms several comparison methods in relation to speckle suppression, objective metrics, and edge preservation.

Discrimination between normal and cancer white blood cells using holographic projection technique.

White blood cells (WBCs) play a vital role in the diagnosis of many blood diseases. Such diagnosis is based on the morphological analysis of blood microscopic images which is performed manually by skilled hematologist. However, this method has many drawbacks, such as the dependence on the hematologist’s skill, slow performance, and varying accuracy. Therefore, in the current study, a new optical method for discrimination between normal and cancer WBCs of peripheral blood film (PBF) images is presented. This method is based on holographic projection technique which is able to provide an accurate and fast optical reconstruction method of WBCs floating in the air. Besides, it can provide a 3D visualization map of one WBC with its characterization parameters from only a single 2D hologram. To achieve that, at first, WBCs are accurately segmented from the microscopic PBF images using a developed in-house MATLAB code. Then, their associated phase computer-generated holograms (CGHs) are calculated using the well-known iterative Fourier transform algorithm (IFTA). Within the utilized algorithm, a speckle noise reduction technique, based on temporal multiplexing of spatial frequencies, is applied to minimize the speckle noise across the reconstruction plane. Additionally, a special hologram modulation is added to the calculated holograms to provide a 3D visualization map of one WBC, and discriminate normal and cancer WBCs. Finally, the calculated phase-holograms are uploaded on a phase-only spatial light modulator (SLM) for optical reconstruction. The optical reconstruction of such phase-holograms yields precise representation of normal and cancer WBCs. Moreover, a 3D visualization map of one WBC with its characterization parameters is provided. Therefore, the proposed technique can be used as a valuable tool for interpretation and analysis of WBCs, this in turn could provide an improvement in diagnosis and prognosis of blood diseases.

Hybrid Pattern Extraction with Deep Learning-Based Heart Disease Diagnosis Using Echocardiogram Images

Echocardiography represents a noninvasive diagnostic approach that offers information concerning hemodynamics and cardiac function. It is a familiar cardiovascular diagnostic test apart from chest X-ray and echocardiography. The medical knowledge is enhanced by the Artificial Intelligence (AI) approaches like deep learning and machine learning because of the increase in the complexity as well as the volume of the data that in turn unlocks the clinically significant information. Similarly, the usage of developing information as well as communication technologies is becoming important for generating a persistent healthcare service via which the chronic disease and elderly patients get their medical facility at their home that in turn enhances the life quality and avoids hospitalizations. The main intention of this paper is to design and develop a novel heart disease diagnosis using speckle-noise reduction and deep learning-based feature learning and classification. The datasets gathered from the hospital are composed of both the images and the video frames. Since echocardiogram images suffer from speckle noise, the initial process is the speckle-noise reduction technique. Then, the pattern extraction is performed by combining the Local Binary Pattern (LBP), and Weber Local Descriptor (WLD) referred to as the hybrid pattern extraction. The deep feature learning is conducted by the optimized Convolutional Neural Network (CNN), in which the features are extracted from the max-pooling layer, and the fully connected layer is replaced by the optimized Recurrent Neural Network (RNN) for handling the diagnosis of heart disease, thus proposed model is termed as CRNN. The novel Adaptive Electric Fish Optimization (A-EFO) is used for performing feature learning and classification. In the final step, the best accuracy is achieved with the introduced model, while a comparative analysis is accomplished over the traditional models. From the experimental analysis, FDR of A-EFO-CRNN at 75% learning percentage is 21.05%, 15%, 48.89%, and 71.95% progressed than CRNN, CNN, RNN, and NN, respectively. Thus, the performance of the A-EFO-CRNN is enriched than the existing heuristic-oriented and classifiers in terms of the image dataset.

Principal Component Analysis Based Hybrid Speckle Noise Reduction Technique for Medical Ultrasound Imaging

Ultrasound imaging is the safest and most widely used medical imaging technique available today. The main disadvantage of ultrasound imaging is the presence of speckle noise in its images that may obscure pathological changes in the body and makes diagnosis more challenging. Therefore, many techniques were proposed to reduce speckle and improve image quality. Unfortunately, variations of their performance with different scan parameters and due to their methodologies make it hard to choose which one to adopt in clinical practice. In this work, we consider the problem of combining the information from multiple speckle filters and propose the use of principal component analysis to find the optimal set of weights that would retain the most information and hence would better represent the data in the final image. The new technique is implemented to process ultrasound images collected from a research system and the outcomes are compared to the individual techniques and their average using quantitative image quality metrics. The proposed technique has potential for utilization in clinical settings to provide consistently better-quality combined images that may help improve diagnostic accuracy.

A Review on Speckle Noise Reduction Techniques in Ultrasound Medical images based on Spatial Domain, Transform Domain and CNN Methods

Ultrasonography is non-invasive and painless. In Ultrasonography the images are often affected with Speckle noise. It is a multiplicative noise. To help the doctors to identify the abnormalities properly there are several methods to diagnose as speckle is a major problem. This paper gives details about popular spatial domain, transform domain, CNN techniques for despeckling in ultrasound images. Transform domain methods like Wavelet methods, Curvelet methods, Bayes Shrink methods are prominent among many researches. Deep learning based methods are evolving like DnCNN, ECNDNet etc. for efficient despeckling. An overview of the methods is given here with certain measurement parameters like PSNR, MSE.

Despeckling Techniques for Ultrasound Images

Biomedical imaging shows a substantial role in the era for diagnosis of cancer. Ultrasound (US) imaging modality is widely used in comparison to other modalities for disease diagnosis because it not being or involve in invasive medical procedure. US is a real-time imaging modality, economically, reliable and not uses harmful radiation during the diagnosis. The noise present in US, reduces the visuality and quality of US images is called speckle noise. It degrades the fine details of US image which causes difficulty in effective feature calculation, analysis and edge detection. Speckle noise effects image interpretation and causes misdiagnosis due to bed quality of the images. Many speckle noise reduction techniques have been investigated by various researchers for noise free images. In this paper, a detailed overview about different despeckling filters is presented with different evaluation parameters. This study will help the researchers to select efficient despeckling technique for preprocessing of US images.

Speckle Noise Reduction Technique for SAR Images Using Statistical Characteristics of Speckle Noise and Discrete Wavelet Transform

Synthetic aperture radar (SAR) images map Earth’s surface at high resolution, regardless of the weather conditions or sunshine phenomena. Therefore, SAR images have applications in various fields. Speckle noise, which has the characteristic of multiplicative noise, degrades the image quality of SAR images, which causes information loss. This study proposes a speckle noise reduction algorithm while using the speckle reducing anisotropic diffusion (SRAD) filter, discrete wavelet transform (DWT), soft threshold, improved guided filter (IGF), and guided filter (GF), with the aim of removing speckle noise. First, the SRAD filter is applied to the SAR images, and a logarithmic transform is used to convert multiplicative noise in the resulting SRAD image into additive noise. A two-level DWT is used to divide the resulting SRAD image into one low-frequency and six high-frequency sub-band images. To remove the additive noise and preserve edge information, horizontal and vertical sub-band images employ the soft threshold; the diagonal sub-band images employ the IGF; while, the low- frequency sub-band image removes additive noise using the GF. The experiments used both standard and real SAR images. The experimental results reveal that the proposed method, in comparison to state-of-the art methods, obtains excellent speckle noise removal, while preserving the edges and maintaining low computational complexity.

2D MEMS-based high-speed beam-shifting technique for speckle noise reduction and flow rate measurement in optical coherence tomography.

In this manuscript, a two-dimensional (2D) micro-electro-mechanical system (MEMS)-based, high-speed beam-shifting spectral domain optical coherence tomography (MHB-SDOCT) is proposed for speckle noise reduction and absolute flow rate measurement. By combining a zigzag scanning protocol, the frame rates of 45.2 Hz for speckle reduction and 25.6 Hz for flow rate measurement are achieved for in-vivo tissue imaging. Phantom experimental results have shown that by setting the incident beam angle to ϕ = 4.76° (between optical axis of objective lens and beam axis) and rotating the beam about the optical axis in 17 discrete angular positions, 91% of speckle noise in the structural images can be reduced. Furthermore, a precision of 0.0032 µl/s is achieved for flow rate measurement with the same beam angle, using three discrete angular positions around the optical axis. In-vivo experiments on human skin and chicken embryo were also implemented to further verify the performance of speckle noise reduction and flow rate measurement of MHB-SDOCT.

Speckle noise reduction technique for Lidar echo signal based on self-adaptive pulse-matching independent component analysis

Speckle noise has always been a particularly tricky problem in improving the ranging capability and accuracy of Lidar system especially in harsh environment. Currently, effective speckle de-noising techniques are extremely scarce and should be further developed. In this study, a speckle noise reduction technique has been proposed based on independent component analysis (ICA). Since normally few changes happen in the shape of laser pulse itself, the authors employed the laser source as a reference pulse and executed the ICA decomposition to find the optimal matching position. In order to achieve the self-adaptability of algorithm, local Mean Square Error (MSE) has been defined as an appropriate criterion for investigating the iteration results. The obtained experimental results demonstrated that the self-adaptive pulse-matching ICA (PM-ICA) method could effectively decrease the speckle noise and recover the useful Lidar echo signal component with high quality. Especially, the proposed method achieves 4 dB more improvement of signal-to-noise ratio (SNR) than a traditional homomorphic wavelet method.

Speckle Noise Reduction Techniques Employing Multi-Link Wavelet and Adaptive Sampling for Medical Ultrasound Imaging

Speckle Noise Reduction Techniques Employing Multi-Link Wavelet and Adaptive Sampling for Medical Ultrasound Imaging

Efficient Speckle Noise Reduction Techniques for Synthetic Aperture Radars in Remote Sensing Applications

This paper undertakes the Automatic region extracting system by reduction of speckle noise reduction and regions extracting by segmentation in (Synthetic Aperture Radar) SAR images. Multiplicative speckle noise is inherently affected the SAR images Due to the coherent in nature. Noise density has been removed by using a Lee filter, Kuan filter, Weiner filter and NLM filter. The desired filtered SAR image result has a significant reduction in its variance with preserving the mean value of noise image. We apply the efficient methodology to a set of SAR speckle corrupted images. The results are evaluated on local quality and global criteria that shows the excellent proposal potential.

Application of Independent Component Analysis techniques in speckle noise reduction of retinal OCT images

Optical Coherence Tomography (OCT) is an emerging technique in the field of biomedical imaging, with applications in ophthalmology, dermatology, coronary imaging, etc. OCT images usually suffer from a granular pattern, called speckle noise, which restricts the process of interpretation. Therefore the need for speckle noise reduction techniques is of high importance. To the best of our knowledge, use of Independent Component Analysis (ICA) techniques has never been explored for speckle reduction of OCT images. Here, a comparative study of several ICA techniques (InfoMax, JADE, FastICA and SOBI) is provided for noise reduction of retinal OCT images. Having multiple B-scans of the same location, the eye movements are compensated using a rigid registration technique. Then, different ICA techniques are applied to the aggregated set of B-scans for extracting the noise-free image. Signal-to-Noise-Ratio (SNR), Contrast-to-Noise-Ratio (CNR) and Equivalent-Number-of-Looks (ENL), as well as analysis on the computational complexity of the methods, are considered as metrics for comparison. The results show that use of ICA can be beneficial, especially in case of having fewer number of B-scans.

Speckle reduction based on Wiener filter in ultrasound images.

In this manuscript, a technique for speckle noise reduction in ultrasound images is presented. The method exploits Wiener filter and is able to take into account spatial correlation among noise samples. With respect to classical Wiener filter approach developed in independence hypothesis, the methodology is able to sensibly improve filtering performances, at the cost of no computational time increase. Results on realistic simulated datasets are reported, showing the effectiveness of the approach.

Subspace-Based Technique for Speckle Noise Reduction in SAR Images

Image-subspace-based approach for speckle noise removal from synthetic aperture radar (SAR) images is proposed. The underlying principle is to apply homomorphic framework in order to convert multiplicative speckle noise into additive and then to decompose the vector space of the noisy image into signal and noise subspaces. Enhancement is performed by nulling the noise subspace and estimating the clean image from the remaining signal subspace. Linear estimator minimizing image distortion while maintaining the residual noise energy below some given threshold is used to estimate the clean image. Experiments are carried out using synthetically generated data set with controlled statistics and real SAR image of Selangor area in Malaysia. The performance of the proposed technique is compared with Lee and homomorphic wavelet in terms of noise variance reduction and preservation of radiometric edges. The results indicate moderate noise reduction by the proposed filter in comparison to Lee but with a significantly less blurry effect and a comparable performance in terms of noise reduction to wavelet but with less artifacts. The results also show better preservation of edges, texture, and point targets by the proposed filter than both Lee and wavelet and less required computational time.

Subspace-based technique for speckle noise reduction in ultrasound images.

Background and purposeUltrasound imaging is a very essential technique in medical diagnosis due to its being safe, economical and non-invasive nature. Despite its popularity, the US images, however, are corrupted with speckle noise, which reduces US images qualities, hampering image interpretation and processing stage. Hence, there are many efforts made by researches to formulate various despeckling methods for speckle reduction in US images.MethodsIn this paper, a subspace-based speckle reduction technique in ultrasound images is proposed. The fundamental principle of subspace-based despeckling technique is to convert multiplicative speckle noise into additive via logarithmic transformation, then to decompose the vector space of the noisy image into signal and noise subspaces. Image enhancement is achieved by nulling the noise subspace and estimating the clean image from the remaining signal subspace. Linear estimation of the clean image is derived by minimizing image distortion while maintaining the residual noise energy below some given threshold. The real US data for validation purposes were acquired under the IRB protocol (200210851-7) at the University of California Davis, which is also consistent with NIH requirements.ResultsExperiments are carried out using a synthetically generated B-mode ultrasound image, a computer generated cyst image and real ultrasound images. The performance of the proposed technique is compared with Lee, homomorphic wavelet and squeeze box filter (SBF) in terms of noise variance reduction, mean preservation, texture preservation and ultrasound despeckling assessment index (USDSAI). The results indicate better noise reduction capability with the simulated images by the SDC than Lee, Wavelet and SBF in addition to less blurry effect. With the real case scenario, the SDC, Lee, Wavelet and SBF are tested with images obtained from raw radio frequency (RF) data. Results generated using real US data indicate that, in addition to good contrast enhancement, the autocorrelation results shows better preservation of image texture by SDC than Lee, Wavelet and SBF.ConclusionIn general, the performance of the SDC filter is better than Lee, Wavelet and SBF in terms of noise reduction, improvement in image contrast and preservation of the autocorrelation profiles. Furthermore, the filter required less computational time compared to Lee, Wavelet and SBF, which indicates its suitability for real time application.

A Review on Speckle Noise Reduction Techniques

In medical image processing, Image denoising plays a very important role in diagnosis. Medical images are very much inconsistent. In medical imaging, Ultrasound is very popular due to its low cost, least harmful to human body, real time system and small in size. Besides itsadvantage,It suffers from a major problem i.e. speckle noise which reduces the diagnosis ability. Speckle noise is the result of diffuse scattering, which occurs when the sound waves (ultrasound) randomly interferes with a small particle or object on a scale comparable to small wavelength. Speckle Noise is an inherent property of SAR and ultrasound images. As Speckle noise is multiplicative in nature which is very much difficult to remove.So this paper presents a review on different spatial and transform methods such as spatial domain technique and wavelet domain techniques which are already proposed for filtering speckle noise in ultrasound images

Wavelet domain compounding for speckle reduction in optical coherence tomography

Visibility of optical coherence tomography (OCT) images can be severely degraded by speckle noise. A computationally efficient despeckling approach that strongly reduces the speckle noise is reported. It is based on discrete wavelet transform (DWT), but eliminates the conventional process of threshold estimation. By decomposing an image into different levels, a set of sub-band images are generated, where speckle noise is additive. These sub-band images can be compounded to suppress the additive speckle noise, as DWT coefficients resulting from speckle noise tend to be approximately decorrelated. The final despeckled image is reconstructed by taking the inverse wavelet transform of the new compounded sub-band images. The performance of speckle reduction and edge preservation is controlled by a single parameter: the level of wavelet decomposition. The proposed technique is applied to intravascular OCT imaging of porcine carotid arterial wall and ophthalmic OCT images. Results demonstrate the effectiveness of this technique for speckle noise reduction and simultaneous edge preservation. The presented method is fast and easy to implement and to improve the quality of OCT images.

Wavelet Denoising of SAR Images Corrupted by Speckle Noise Using Cycle Spinning

A novel and efficient speckle noise reduction algorithm based on wavelet transform by cycle spinning for removing speckle of unknown variance and minimizing the effect of pseudo-Gibbs phenomena from Synthetic Aperture Radar (SAR) images is proposed. Therefore, we show that the sub-band decompositions of logarithmically transformed SAR images. Then, we process and reconstruct multi-resolution wavelet coefficients by wavelet-threshold using cycle spinning, a technique estimating the true images as the linear average of individual estimates derived from wavelet thresholded translated versions of the noise images. Experimental results show that the proposed de-noising algorithm is possible to achieve an excellent balance between suppresses speckle effectively and weaken as many image Gibbs phenomena as possible. Quantitative and qualitative comparisons of the results obtained by the new method with the results achieved from the other speckle noise reduction techniques demonstrate its higher performance for speckle reduction in SAR images.

Application of RPCA in optical coherence tomography for speckle noise reduction

Optical coherence tomography (OCT) is a promising technology, which could be used in a variety of imaging applications. However, OCT images are usually degraded by speckle noise. Speckle noise reduction in OCT is particularly challenging because it is difficult to separate the noise and the information components in the speckle pattern. In this study, a novel speckle noise reduction technique, based on robust principal component analysis (RPCA), is presented and applied to OCT images for the first time. The proposed technique gives an optimal estimate of OCT image domain transformations such that the matrix of transformed OCT images can be decomposed as the sum of a sparse matrix of speckle noise and a low-rank matrix of the denoised image. The decomposition is a unique feature of the proposed method which can not only reduce the speckle noise, but also preserve the structural information about the imaged object. Applying the proposed technique to a number of OCT images showed significant improvement of image quality.