Efficient Denoising Framework for Mammogram Images with a New Impulse Detector and Non-Local Means

Rajaguru, Harikumar; Chakravarthy, S. R. Sannasi

doi:10.31557/apjcp.2020.21.1.179

Cited by 7 publications

(3 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The classification process is used to classify the filtered images based on their features. SVM is a kind of supervised ML model that assists in categorization or regression issues [15][16][17]. The main aim of the SVM model is to discover the best edges among the probable results.…”

Section: Proposed Methodologymentioning

confidence: 99%

Speckle Noise Removal from Biomedical MRI Images and Classification by Multi-Support Vector Machine

Hemalatha,

Karthik,

Krishna Reddy

2024

EAI Endorsed Trans Perv Health Tech

View full text Add to dashboard Cite

INTRODUCTION: Image Processing (IP) methods play a vital role in medical images for diagnosing and predicting illness, as well as monitoring the patient's progress. The IP methods are utilized in many applications for example in the field of medicine. OBJECTIVES: The images that are obtained by the MRI magnetic Resonance imaging and x rays are analyzed with the help of image processing. METHODS: This application is very costly to the patient. Because of the several non-idealities in the image process, medical images are frequently tainted by impulsive, multiplicative, and addictive noise. RESULTS: By replacing some of the original image's pixels with new ones that have luminance values which are less than the allowed dynamic luminance range, noise frequently affects medical images. CONCLUSION: In this research work, the Speckle type noises are eliminated with the help of Mean Filter (MF) and classify the images using Multi-SVM classifier. The entire system developed using python programming.

show abstract

Section: Proposed Methodologymentioning

confidence: 99%

Speckle Noise Removal from Biomedical MRI Images and Classification by Multi-Support Vector Machine

Hemalatha,

Karthik,

Krishna Reddy

2024

EAI Endorsed Trans Perv Health Tech

View full text Add to dashboard Cite

show abstract

“…In this category, we point out on well-known Non Local Mean Filter (NLM filter). The advantage of NLM filter is the fact that all the surrounding pixels may affect the representative pixels, without restriction of the weighting function [ 33 , 34 ]. This type of the filtering incorporates two features: besides the intensity information NLM filter works with the distance function between representative pixel and others [ 35 , 36 , 37 , 38 ].…”

Section: Recent Workmentioning

confidence: 99%

Towards to Optimal Wavelet Denoising Scheme—A Novel Spatial and Volumetric Mapping of Wavelet-Based Biomedical Data Smoothing

Stanke

Kubíček

Vilímek

et al. 2020

Sensors

View full text Add to dashboard Cite

Wavelet transformation is one of the most frequent procedures for data denoising, smoothing, decomposition, features extraction, and further related tasks. In order to perform such tasks, we need to select appropriate wavelet settings, including particular wavelet, decomposition level and other parameters, which form the wavelet transformation outputs. Selection of such parameters is a challenging area due to absence of versatile recommendation tools for suitable wavelet settings. In this paper, we propose a versatile recommendation system for prediction of suitable wavelet selection for data smoothing. The proposed system is aimed to generate spatial response matrix for selected wavelets and the decomposition levels. Such response enables the mapping of selected evaluation parameters, determining the efficacy of wavelet settings. The proposed system also enables tracking the dynamical noise influence in the context of Wavelet efficacy by using volumetric response. We provide testing on computed tomography (CT) and magnetic resonance (MR) image data and EMG signals mostly of musculoskeletal system to objectivise system usability for clinical data processing. The experimental testing is done by using evaluation parameters such is MSE (Mean Squared Error), ED (Euclidean distance) and Corr (Correlation index). We also provide the statistical analysis of the results based on Mann-Whitney test, which points out on statistically significant differences for individual Wavelets for the data corrupted with Salt and Pepper and Gaussian noise.

show abstract

“…However, the use of low-exposure protocols has led to low contrast performance of mammogram images, especially when detecting the MCCs. During image acquisition, impulse noise can distort mammogram images (Rajaguru et al, 2020). Consequently, numerous image enhancement techniques have been evolved and introduced in digital mammograms.…”

Section: Introductionmentioning

confidence: 99%

Enhancing Detection of Microcalcifications using FADHECAL for Early Stage Breast Cancer

Suradi,

Abdullah,

Mat Isa

2023

MJST

View full text Add to dashboard Cite

Microcalcifications (MCCs) are reliable early signs of breast cancer. However, the small size of calcifications and low radiation factors used in digital mammograms cause low and poor quality mammogram images in detecting MCCs. This paper presents an image enhancement technique called Fuzzy Anisotropic Diffusion Histogram Equalization Contrast Adaptive Limited (FADHECAL) to enhance the details of MCCs in mammogram images by reducing the image noise while conserving contrast and brightness. A total of 23 mammogram images with MCCs were retrieved from the Mammographic Image Analysis Society’s database. The enhancement performance of FADHECAL was compared with Recursive Mean-Separate Histogram Equalization, Histogram Equalization and Fuzzy Clipped Contrast-Limited Adaptive Histogram Equalization. Image quality measurement tools of absolute mean brightness error (AMBE), structural similarity index measure (SSIM) and peak signal-to-noise ratio (PSNR) were used. The results showed that FADHECAL had the most superior results among other enhancement techniques, with 6.302 of AMBE, 20.453 of PSNR and 0.851 of SSIM. The proposed FADHECAL exhibited a high accuracy of 91.30% for the detection of MCCs. Hence, FADHECAL can be used as an ideal tool for identifying MCCs in early-stage breast cancer.

show abstract

Efficient Denoising Framework for Mammogram Images with a New Impulse Detector and Non-Local Means

Cited by 7 publications

References 19 publications

Speckle Noise Removal from Biomedical MRI Images and Classification by Multi-Support Vector Machine

Speckle Noise Removal from Biomedical MRI Images and Classification by Multi-Support Vector Machine

Towards to Optimal Wavelet Denoising Scheme—A Novel Spatial and Volumetric Mapping of Wavelet-Based Biomedical Data Smoothing

Enhancing Detection of Microcalcifications using FADHECAL for Early Stage Breast Cancer

Contact Info

Product

Resources

About