scholarly journals Novel image enhancement approaches for despeckling in ultrasound images for fibroid detection in human uterus

2021 ◽  
Vol 11 (1) ◽  
pp. 399-410
Author(s):  
Kaitheri Thacharedath Dilna ◽  
Duraisamy Jude Hemanth
Keyword(s):  
Image Processing ◽  
Signal To Noise Ratio ◽  
Ultrasound Image ◽  
Speckle Noise ◽  
Speckle Reduction ◽  
Ultrasound Images ◽  
Signal To Noise ◽  
Statistical Measures ◽  
Noise Ratio ◽  
Scanned Images

Abstract Ultrasonography is an extensively used medical imaging technique for multiple reasons. It works on the basic theory of echoes from the tissues under consideration. However, the occurrence of signal dependent noise such as speckle destroys utility of ultrasound images. Speckle noise is subject to the composition of image tissue and parameters of image. It reduces the effectiveness of many image processing steps and decreases human perception of fine details form ultrasound images. In many medical image processing methods, despeckling is used as the preprocessing step before segmentation and feature extraction. Many speckle reduction filters are proposed but while combining many techniques some speckle diagnostic information should be preserved. Removal of speckle noise from ultrasound image by preserving edges and added features is a great challenging task in ultrasound image restoration. This paper aims at a comprehensive description and comparison of reduction of speckle noise of ultrasound fibroid image. Many filters are applied on ultrasound scanned images and the performance is marked in terms of some statistical measures. Even though several despeckling filters are there for speckle reduction, all are not good for ultrasound scanned images. A comparison of quality measures such as mean square error, peak signal-to-noise ratio, and signal-to-noise ratio is done in ultrasound images in despeckling.

Comparative Study on Filter Methods of Medical Ultrasound Images

2011 ◽  
Vol 341-342 ◽  
pp. 467-471
Author(s):  
Run Xia Ma ◽  
Xu Ming Zhang ◽  
Ming Yue Ding ◽  
Qi Liu
Keyword(s):  
Comparative Study ◽  
Gabor Filter ◽  
Signal To Noise Ratio ◽  
Median Filter ◽  
Minimum Mean Square Error ◽  
Ultrasound Image ◽  
Ultrasound Images ◽  
Signal To Noise ◽  
Protection Factor ◽  
Noise Ratio

This paper presents a comparative study on six despeckling methods such as modified hybrid median filter, gabor filter, speckle reducing anisotropic diffusion, homomorphic filter, non-local mean filter and squeeze box filter. We select eight objective evaluation parameters, such as signal-to-ratio, contrast signal–to–noise ratio, figure of merit, least absolute error, peak signal-to-noise ratio, edge protection factor, quantitative parameters of despeckling, signal-to-minimum mean square error ratio, to quantify the performance of these filters. The comparative study will provide a good guidance for selecting a suitable filter in the ultrasound image processing.

scholarly journals Performance Analysis of Various Filters for De-Speckling of Thyroid Ultrasound Images

2019 ◽  
Vol 9 (2) ◽  
pp. 910-917
Keyword(s):  
Mean Square Error ◽  
Image Quality Assessment ◽  
Signal To Noise Ratio ◽  
Similarity Index ◽  
Structural Similarity ◽  
Speckle Noise ◽  
Ultrasound Images ◽  
Mean Square ◽  
Signal To Noise ◽  
Noise Ratio

Thyroid ultrasonography is the most common and extremely useful, safe, and cost effective way to image the thyroid gland and its pathology. However, an inherent characteristic of Ultrasound (US) imaging is the presence of multiplicative speckle noise. Speckle noise reduces the ability of an observer to distinguish fine details, make diagnosis more difficult. It limits the effective implementation of image analysis steps such as edge detection, segmentation and classification. The main objective of this study is to compare the performance of various spatial and frequency domain filters so as to identify efficient and optimum filter for de-speckling Thyroid US images. The performance of these filters is evaluated using the image quality assessment parameters Signal to Noise Ratio (SNR), Peak Signal to Noise Ratio (PSNR), Structural Similarity Index (SSIM), Mean Square Error (MSE) and Root Mean Square Error (RMSE) for different speckle variance. Experimental work revealed that kuan filter resulted in higher PSNR, SNR, SSIM and least MSE, RMSE values compared to other filters

A Proposed Approach to De-speckle an Ultrasound Image using Anisotropic Filter by Generating Diffusion Tensor

2018 ◽  
Vol 8 (3) ◽  
Author(s):  
Poonam Chauhan ◽  
Vikas Kaushik
Keyword(s):  
Ultrasound Imaging ◽  
Diffusion Tensor ◽  
Signal To Noise Ratio ◽  
Ultrasound Image ◽  
Similarity Index ◽  
Speckle Noise ◽  
The Body ◽  
Invasive Technique ◽  
Signal To Noise ◽  
Noise Ratio

Ultrasound imaging is a technique that is used to diagnose the diseases in medical field using radiology. US (ultrasound) imaging is a non -invasive technique and used for imaging of internal structure of the body without any kind of penetration which helps to identify the diseases that have probability and tissues. Many kinds of noises present in US images but the presence of speckle noise is a big challenge since last few years in biomedical field. Sometimes speckle noise becomes the part of information and vice-versa. So it becomes hard to find the disease for doctors. There are many de-speckled filters available for de-noising. This paper gives a proposed approach to de-speckled the US image using anisotropic diffusion filter by calculating the different numerical values like SSIM (structural similarity index), SNR (signal to noise ratio), MSE (mean square error), PSNR (peak signal to noise ratio), which results in coherence enhancement The proposed technique provides better and improved edge and coherence enhancement in ultrasound image data.

scholarly journals Wavelet Transform Image Enhancement Algorithm-Based Evaluation of Lung Recruitment Effect and Nursing of Acute Respiratory Distress Syndrome by Ultrasound Image

2021 ◽  
Vol 2021 ◽  
pp. 1-9
Author(s):  
Wangyan Jin ◽  
Ling Dai ◽  
Liuyan Ge ◽  
Xuhua Huang ◽  
Guanhua Xu ◽  
...  
Keyword(s):  
Acute Respiratory Distress Syndrome ◽  
Distress Syndrome ◽  
Signal To Noise Ratio ◽  
Ultrasound Image ◽  
Ultrasound Images ◽  
Signal To Noise ◽  
Running Time ◽  
Before And After ◽  
Noise Ratio ◽  
Enhancement Algorithm

This study aimed to analyze the application of ultrasound images of lung recruitment (LR) nursing treatment guided by positive-end expiratory pressure (PEEP) in patients with acute respiratory distress syndrome (ARDS). An ultrasound image enhancement algorithm (UIEA) wavelet transform (WT) was constructed, and the soft threshold (ST) and adjacent region average (ARA) were introduced for simulation comparison. In addition, the signal-to-noise ratio (SNR), peak signal-to-noise ratio (PSNR), and running time were undertaken as the evaluation indexes. The WT algorithm was applied to the ultrasound images of 85 ARDS patients before and after PEEP recruitment. The mean artery pressure (MAP), heart rate (HR), and central venous pressure (CVP), peak inspiratory pressure (Ppeak), mean inspiratory pressure (Pmean), dynamic lung compliance (DLC), PCO2, and PaO2/FiO2 of the patients were recorded before and after the LR. The results showed that the signal-to-noise ratio (SNR) (19.67 ± 3.15 dB) and PSNR (23.08 ± 2.08 dB) of the images enhanced by the WT algorithm were much higher than those of ST (13.88 ± 2.74 dB and 14.62 ± 1.76 dB, respectively) and ARA (14.96 ± 3.06 dB and 15.11 ± 1.94 dB, respectively), while the running time was in adverse ( P < 0.05 ); the HR and CVP of patients after LR nursing treatment were increased greatly, while the MAP was in the opposite case ( P < 0.05 ); after LR nursing treatment, Ppeak, Pmean, DLC, PCO2, and PaO2/FiO2 of the patient were significantly greater than those before the LR, and the difference was statistically significant ( P < 0.05 ). In short, the WT algorithm not only enhanced the quality of ultrasound images but also shortened the running time and improved the processing efficiency. PEEP LR nursing treatment could effectively improve the vascular patency, cardiac ejection capacity, and DLC in patients with ARDS, thereby increasing the airway pressure and maintaining the unobstructed expiration.

Retinal Digital Image Quality Improvement as A Diabetes Retinopatic Disease Detection Effort

2020 ◽  
Vol 4 (2) ◽  
pp. 53-60
Author(s):  
Latifah Listyalina ◽  
Yudianingsih Yudianingsih ◽  
Dhimas Arief Dharmawan
Keyword(s):  
Image Processing ◽  
Diabetic Retinopathy ◽  
Image Quality ◽  
Digital Image ◽  
Signal To Noise Ratio ◽  
Histogram Equalization ◽  
Vital Role ◽  
Retinal Images ◽  
Signal To Noise ◽  
Noise Ratio

Image processing is a technical term useful for modifying images in various ways. In medicine, image processing has a vital role. One example of images in the medical world, namely retinal images, can be obtained from a fundus camera. The retina image is useful in the detection of diabetic retinopathy. In general, direct observation of diabetic retinopathy is conducted by a doctor on the retinal image. The weakness of this method is the slow handling of the disease. For this reason, a computer system is required to help doctors detect diabetes retinopathy quickly and accurately. This system involves a series of digital image processing techniques that can process retinal images into good quality images. In this research, a method to improve the quality of retinal images was designed by comparing the methods for adjusting histogram equalization, contrast stretching, and increasing brightness. The performance of the three methods was evaluated using Mean Square Error (MSE), Peak Signal to Noise Ratio (PSNR), and Signal to Noise Ratio (SNR). Low MSE values and high PSNR and SNR values indicated that the image had good quality. The results of the study revealed that the image was the best to use, as evidenced by the lowest MSE values and the highest SNR and PSNR values compared to other techniques. It indicated that adaptive histogram equalization techniques could improve image quality while maintaining its information.

Measurement of signal-to-noise ratio in dysphonic voices by image processing of spectrograms

2014 ◽  
Vol 61-62 ◽  
pp. 17-32 ◽  
Author(s):  
Maurílio N. Vieira ◽  
João Pedro H. Sansão ◽  
Hani C. Yehia
Keyword(s):  
Image Processing ◽  
Signal To Noise Ratio ◽  
Signal To Noise ◽  
Noise Ratio

High-signal-to-noise-ratio image processing in low-signal-to-bias-ratio environments

1997 ◽  
Author(s):  
Hakan Urey ◽  
William T. Rhodes ◽  
H. John Caulfield ◽  
Zafer Urey
Keyword(s):  
Image Processing ◽  
Signal To Noise Ratio ◽  
High Signal ◽  
Signal To Noise ◽  
Ratio Image ◽  
Bias Ratio ◽  
Noise Ratio

scholarly journals Novel ultrasound transmission and reconstruction techniques for synthetic transmit aperture imaging

2021 ◽  
Author(s):  
Ping Gong
Keyword(s):  
Signal To Noise Ratio ◽  
Singular Values ◽  
Single Element ◽  
Ultrasound Images ◽  
Transmission Scheme ◽  
Signal To Noise ◽  
Spatial Compounding ◽  
Image Quality Enhancement ◽  
Noise Ratio ◽  
Value Decomposition

This dissertation describes ultrasound algorithms developed for synthetic transmit aperture (STA) imaging during the transmission and the image reconstruction stages. Images generated using these algorithms demonstrate image quality enhancement both theoretically and experimentally. The advanced algorithms also improve the application of STA imaging. Due to the single element transmission pattern, the low signal-to-noise ratio is a major limitation for STA imaging. A delay-encoded transmission scheme (DE-STA) was designed in this dissertation to encode all the transmissions. The decoded RF signals were equivalent to the standard STA signals, but with a higher SNR. Improved image qualities were observed under DE-STA transmission in terms of lateral resolution (+28%), peak-signal-to-noise ratio (PSNR, +7 dB) and target contrast-to-noise ratio (CNR, +360%) compared to those acquired with the standard STA mode. The stability of DE-STA was analyzed and verified under various noise levels by the special distribution of the singular values of the encoding matrix through singular value decomposition (SVD) (i.e. all the singular values were the same except for the first one and the last one). A more efficient decoding process was also derived based on pseudo-inversion (PI) and the computation complexity was reduced by 2/3. Speckle and undesired sidelobe signals can reduce the lesion CNR and detectability in ultrasound images. Typically, the CNR can be increased by spatial compounding (SC) or frequency compounding (FC) during reconstruction. We proposed methods to implement a 2-dimentional (2-D) aperture domain filter in the SC/FC processes, referred to as filtered spatial compounding (FSC) and filtered frequency compounding (FFC), for synthetic transmit aperture (STA) imaging. Both techniques reduced the sidelobe interference and provided improved lesion CNR. Consequently, the lesion signal-to-noise ratio (lSNR) in FSC and FFC increased (up to +130%), compared to that in the standard delay-and-sum (DAS) method. This dissertation investigates all these proposed advanced ultrasound algorithms, with the end goal of implementing these methods in STA imaging to extend its application in clinic.

Sign in / Sign up

Export Citation Format

Share Document