scispace - formally typeset
Search or ask a question
Journal Article

Poisson Noise Removal in Biomedical Imagesusing Non-Linear Techniques

TL;DR: Two technique which combines Multi-Scale Variance Stabilizing Transform, Fast Discrete Curvelet Transform with Thresholding and MS-VST, FDCT with Null Hypothesis testing for effectively removing the Poisson Noise from the medical images are proposed.
Abstract: Medical images have always been an important factor in diagnosis of disease. Poisson Noise in those images has always been a problem with the image clarity. We propose two technique which combines Multi-Scale Variance Stabilizing Transform (MS-VST), Fast Discrete Curvelet Transform (FDCT) with Thresholding and MS-VST, FDCT with Null Hypothesis testing for effectively removing the Poisson Noise from the medical images. The effectiveness of using these techniques has been analyzed using Peak Signal to Noise Ratio and Universal Image Quality Index.

Content maybe subject to copyright    Report

Citations
More filters
Journal ArticleDOI
TL;DR: In this paper, modified Harris corner point detector was used to predict noisy pixels and responsive median filtering in spatial domain was proposed to solve the problem of X-ray image denoising.
Abstract: Medical imaging is perturbed with inherent noise such as speckle noise in ultrasound, Poisson noise in X-ray and Rician noise in MRI imaging. This paper focuses on X-ray image denoising problem. X-ray image quality could be improved by increasing dose value; however, this may result in cell death or similar kinds of issues. Therefore, image processing techniques are developed to minimise noise instead of increasing dose value for patient safety. In this paper, usage of modified Harris corner point detector to predict noisy pixels and responsive median filtering in spatial domain is proposed. Experimentation proved that the proposed work performs better than simple median filter and moving average (MA) filter. The results are very close to non-local means Poisson noise filter which is one of the current state-of-the-art methods. Benefits of the proposed work are simple noise prediction mechanism, good visual quality and less execution time.

30 citations


Cites background from "Poisson Noise Removal in Biomedical..."

  • ...Jisha and Suresh Kumar [9] proposed an algorithm for Poisson noise reduction in medical images....

    [...]

Journal ArticleDOI
TL;DR: The results verify that the proposed filter enhances physicians’ and dentists’ skill of diagnosing normal and pathological events in the teeth, jaws, temporomandibular joint (TMJ) regions and changeable anatomical panoramic landmarks related to osteoporosis progress in the mandible bone using noise removal and improving images quality.

5 citations

Proceedings ArticleDOI
11 May 2023
TL;DR: In this paper , the Absolute Difference and Mean Filter (ADMF) is used to replace the processed pixel with the mean of its nearest neighbors within a 5x5 frame when the absolute difference between them is minimal.
Abstract: When it comes to diagnosing patients’ illnesses, digital image modalities like X-ray, Ultrasound (US), Computer Tomography (CT), Magnetic resonance imaging (MRI), etc. play an essential part. Noise is a common problem in the pictures produced by these modalities, reducing image quality. An important factor in making correct diagnosis of illness is the quality of the medical pictures used. Poisson noise is a prevalent problem in X-ray pictures. Hairline fractures inside bones, chest coughs, and other similar conditions become more difficult to diagnose when this noise is present. These sounds need to be eliminated from the X-ray picture before it may be improved. In this study, we aimed to establish a method for effectively denoising X-ray pictures, hence reducing the amount of Poisson noise present in them. The suggested filter makes use of the Absolute Difference and Mean Filter (ADMF) to replace the processed pixel with the mean of its nearest neighbors within a 5x5 frame when the absolute difference between them is minimal. Using 75 X-rays of teeth from the Digital Dental X-ray Database, the proposed technique is compared to the state-of-the-art Region Classification and Response Median Filtering (RCRMF) method. Filter performance is measured by Peak Signal to Noise Ratio (PSNR) and Mean Square Error (MSE) scores; the suggested approach improves PSNR by 5.41 percentage points and reduces MSE by 33.44 percentage points.
References
More filters
Journal ArticleDOI
TL;DR: Although the new index is mathematically defined and no human visual system model is explicitly employed, experiments on various image distortion types indicate that it performs significantly better than the widely used distortion metric mean squared error.
Abstract: We propose a new universal objective image quality index, which is easy to calculate and applicable to various image processing applications. Instead of using traditional error summation methods, the proposed index is designed by modeling any image distortion as a combination of three factors: loss of correlation, luminance distortion, and contrast distortion. Although the new index is mathematically defined and no human visual system model is explicitly employed, our experiments on various image distortion types indicate that it performs significantly better than the widely used distortion metric mean squared error. Demonstrative images and an efficient MATLAB implementation of the algorithm are available online at http://anchovy.ece.utexas.edu//spl sim/zwang/research/quality_index/demo.html.

5,285 citations

Journal ArticleDOI
TL;DR: A variance stabilizing transform (VST) is applied on a filtered discrete Poisson process, yielding a near Gaussian process with asymptotic constant variance, leading to multiscale VSTs (MS-VSTs) and nonlinear decomposition schemes.
Abstract: In order to denoise Poisson count data, we introduce a variance stabilizing transform (VST) applied on a filtered discrete Poisson process, yielding a near Gaussian process with asymptotic constant variance. This new transform, which can be deemed as an extension of the Anscombe transform to filtered data, is simple, fast, and efficient in (very) low-count situations. We combine this VST with the filter banks of wavelets, ridgelets and curvelets, leading to multiscale VSTs (MS-VSTs) and nonlinear decomposition schemes. By doing so, the noise-contaminated coefficients of these MS-VST-modified transforms are asymptotically normally distributed with known variances. A classical hypothesis-testing framework is adopted to detect the significant coefficients, and a sparsity-driven iterative scheme reconstructs properly the final estimate. A range of examples show the power of this MS-VST approach for recovering important structures of various morphologies in (very) low-count images. These results also demonstrate that the MS-VST approach is competitive relative to many existing denoising methods.

380 citations


"Poisson Noise Removal in Biomedical..." refers background or methods in this paper

  • ...It is effective in sparse representation of sharp edges and fine curves [5]....

    [...]

  • ...PERFORMANCE ANALYSIS To measure the performance of Thresholding and Null Hypothesis testing, Peak Signal to Noise Ratio and Universal Image Quality Index [5] are used....

    [...]

  • ...PSNR and Universal Image Quality Index were used to evaluate the performance of proposed methods....

    [...]

  • ...We have analysed the denoised images using two mathematically defined measures viz Peak Signal to Noise Ratio and Universal Image Quality Index [3] for measuring the effectiveness of using the techniques....

    [...]

  • ...Keywords: Multi-Scale Variance Stabilizing Transform, Fast Discrete Curvelet Transform, Thresholding, Null Hypothesis, Signal to Noise Ratio,Universal Image Quality Index....

    [...]

Journal ArticleDOI
TL;DR: A comparison with a similar algorithm based on Wavelet texture descriptors shows that using FDCT based texture features significantly improves the classification rate of liver tumours from CT scans.
Abstract: In this paper, a novel feature extraction scheme is proposed, based on multiresolution fast discrete curvelet transform for computer-aided diagnosis of liver diseases. The liver is segmented from CT images using adaptive threshold detection and morphological processing. The suspected tumour region is extracted from the segmented liver using FCM clustering. The textural information obtained from the extracted tumour using Fast Discrete Curvelet Transform (FDCT) is used to train and classify the liver tumour into hemangioma and hepatoma employing artificial neural network classifier. A comparison with a similar algorithm based on Wavelet texture descriptors shows that using FDCT based texture features significantly improves the classification rate of liver tumours from CT scans.

36 citations


"Poisson Noise Removal in Biomedical..." refers methods in this paper

  • ...There are two separate Discrete Curvelet Transform (DCT) algorithms [4]....

    [...]

Proceedings ArticleDOI
17 Mar 2011
TL;DR: The results show that the VST combined with the FDCT is a promising candidate for Poisson denoising, and a simple approach to achieve this is presented.
Abstract: We propose a strategy to combine the variance stabilizing transform (VST), used for Poisson image denoising, with the fast discrete Curvelet transform (FDCT). The VST transforms the Poisson image to approximately Gaussian distributed, and the subsequent denoising can be performed in the Gaussian domain. However, the performance of the VST degrades when the original image intensity is very low. On the other hand, the FDCT can sparsely represent the intrinsic features of images having discontinuities along smooth curves. Therefore, it is suitable for denoising applications. Combining the VST with the FDCT leads to good Poisson image denoising algorithms, even for low intensity images. We present a simple approach to achieve this and demonstrate some simulation results. The results show that the VST combined with the FDCT is a promising candidate for Poisson denoising.

7 citations


"Poisson Noise Removal in Biomedical..." refers background or methods in this paper

  • ...FDCT [1]-[2] is a second generation curvelet transform which is a multi resolution method....

    [...]

  • ...MS-VST [1] stabilizes the variance in Poisson Noise affected images and Gaussianize it to an extent....

    [...]

01 Jan 2013
TL;DR: Two methods of removing poisson noise from images using a bilateral filter and by Fast discrete Curvelet Transform (FDCT), which show that FDCT is more efficient for preserving image features, while bilateral filter is much faster and simple to implement.
Abstract: We analyse two methods of removing poisson noise from images using a bilateral filter and by Fast discrete Curvelet Transform (FDCT). The Variance stabilizing transform (VST) is the main feature of the noise removal as it converts the Poisson distribution to the Gaussian domain, which makes the noise removal process relatively simple. Once the Gaussian distribution is obtained, the bilateral filter (BF) can be used for removing noise. We can also use the FDCT instead of bilateral filter, as it is capable of sparse representation of image intrinsic features. We implement both the methods separately, compare them and demonstrate simulations for monitoring their effectiveness in poisson noise removal. The results show that FDCT is more efficient for preserving image features, while bilateral filter is much faster and simple to implement.

1 citations


"Poisson Noise Removal in Biomedical..." refers methods in this paper

  • ...FDCT [1]-[2] is a second generation curvelet transform which is a multi resolution method....

    [...]