Noise removal techniques have become an essential practice in medical imaging application for the study of anatomical structure and image processing of MRI medical images. To report these issues many de-noising algorithm has been developed like Weiner filter, Gaussian filter, median filter etc. In this research work is done with only three of the above filters which are already mentioned were successfully used in medical imaging. The most commonly affected noises in medical MRI image are Salt and Pepper, Speckle, Gaussian and Poisson noise. The medical images taken for comparison include MRI images, in gray scale and RGB. The performances of these algorithms are examined for various noise types which are salt-and-pepper, Poisson, speckle, blurred and Gaussian Noise. The evaluation of these algorithms is done by the measures of the image file size, histogram and clarity scale of the images. The median filter performs better for removing salt-and-pepper noise and Poisson Noise for images in gray scale, and Weiner filter performs better for removing Speckle and Gaussian Noise and Gaussian filter for the Blurred Noise as suggested in the experimental results.

/pdf/noise-removal-and-filtering-techniques-used-in-medical-3z26dsalwg.pdf

Noise Removal and Filtering Techniques Used in Medical Images

Intravascular optical coherence tomography (IV-OCT) allows evaluation of atherosclerotic plaques; however, plaque characterization is performed by visual assessment and requires a trained expert for interpretation of the large data sets. Here, we present a novel computational method for automated IV-OCT plaque characterization. This method is based on the modeling of each A-line of an IV-OCT data set as a linear combination of a number of depth profiles. After estimating these depth profiles by means of an alternating least square optimization strategy, they are automatically classified to predefined tissue types based on their morphological characteristics. The performance of our proposed method was evaluated with IV-OCT scans of cadaveric human coronary arteries and corresponding tissue histopathology. Our results suggest that this methodology allows automated identification of fibrotic and lipid-containing plaques. Moreover, this novel computational method has the potential to enable high throughput atherosclerotic plaque characterization.

Automatic classification of atherosclerotic plaques imaged with intravascular OCT

Medical Imaging is the most significant technique that constitutes information needed to diagnose and make the right decisions for treatment. These images suffer from inadequate contrast and noise that occurs during image acquisition. Thus, denoising and contrast enhancement is crucial in increasing the visual quality of the images for obtaining quantitative measures. In this research, an innovative and improvised denoising technique is implemented that applies a sparse aware with convolution neural network (SA_CNN) for investigating various medical modalities. To evaluate and validate, the convolution neural network utilizes patch creation and dictionary methods for obtaining information. The proposed framework is predominant to other current approaches by employing image assessment quantitative measures like peak signal to noise ratio (PSNR), structural similarity index (SSIM), and mean squared error (MSE). The study also optimizes the computational time to achieve increased efficiency and better visual quality of the image. Furthermore, the widespread use of the Internet of Healthcare Things (IoHT) helps to provide security with vault and challenge schemes between IoT devices and servers.

/pdf/security-assured-cnn-based-model-for-reconstruction-of-3itxyjxj6r.pdf

Security Assured CNN-Based Model for Reconstruction of Medical Images on the Internet of Healthcare Things

Noise in digital images is the major cause of severe artifacts. Filter design for denoising applications can also be addressed with optimization techniques as conventional filters incur in this. Exploration and Exploitation capability features of the Meta Heuristic Optimization Techniques make them applicable to noise reduction in digital images. An increasing number of Meta Heuristic Optimization algorithms make it suitable for designing FIR filters. In the proposed method, Particle Swarm Optimization, a global optimizer algorithm was used in calculating the appropriate coefficients for 2D FIR Filter. The proposed filter was applied to standard test images for testing its noise suppression capability. Indicators of performance, such as Peak signal to noise ratio (PSNR) values and Structural Content (SC) were used in accessing the efficiency of the proposed method and to the adaptability of the method for removing different noise types. Thus a brief comparison for noise suppression in digital images with both multiplicative and additive noise types using PSO optimized 2D FIR filter is addressed in this paper.

Analysis of Particle Swarm Optimization Based 2D FIR Filter for Reduction of Additive and Multiplicative Noise in Images

The dominant degrading factor of quality in ultrasound images is mainly due to the occurrence of speckle noise that in turn leads to false ameliorative decisions, restricts auto diagnosis and telemedicine practices. In medical image analysis speckle reduction is contemplated to be the pre-processing task that sustains decisive information and exclude speckle noise. Meta-heuristics optimization algorithm were used now a days for speckle reduction problems. Our contribution in this paper analyses the use of optimization technique in determining the best noise removing filter coefficients that removes the speckle content contributively. The proposed method comprises the use of Finite Impulse Response filter receiving the filter coefficients from Tree Seed optimization algorithm. Evaluation of noise removal with standard metrics such as Peak Signal to Noise Ratio, Correlation coefficient and Structural Similarity Index shows that the proposed method gives optimal speckle reduction score when compared with conventional filters and its superiority in despeckling medical ultrasound images. Assessment of the proposed methodology with advanced evaluation metrics ensures the ability of it in terms of preserving edges and textural features.

Beltrami-Regularized Denoising Filter Based on Tree Seed Optimization Algorithm: An Ultrasound Image Application

Noise refers to the random variation of intensity of a pixel, which modifies the actual information of the image. As a result, pixels which appear in the image are not the actual pixels. Addition of extraneous values to the image causes the occurrence of noise. Noise is categorized into impulse (salt-and-pepper) noise, uniform noise, Gaussian noise, exponential noise, Erlang (gamma) noise, photon noise, speckle noise, etc. Speckle noise is the noise that arises due to the effect of environmental conditions on the imaging sensor during image acquisition. Speckle noise is mostly detected in case of medical images, active Radar images and Synthetic Aperture Radar (SAR) images. Various researchers have performed experiments to overcome this kind of noise using different filtering techniques based on soft computing approaches, such as Fuzzy Filter, Genetic Algorithm, Particle Swarm Optimization, Artificial Bee Colony Optimization, Neural Networks, etc. In this paper, we present a brief analysis of different techniques used for speckle noise reduction, along with their advantages and disadvantages, in a comparative manner.

A Comparative Study on Approaches to Speckle Noise Reduction in Images

/pdf/a-review-on-multi-lingual-sentiment-analysis-by-machine-5gijap4rf8.pdf

A Review on Multi-Lingual Sentiment Analysis by Machine Learning Methods

A summary is the shorter version of the existing long text which elaborates the whole idea of the document. The most conventional and easy version of summarization is extractive text summarization. Extractive approach selects sentences from the original text based on some features. In automatic text summarization (ATS), it is a difficult task to select such sentences with high accuracy to meet the optimum meaning of the full text as compared to manual approaches. In this paper, author tries to represent extractive summary as an optimization problem where the objective is to cover maximum topics of the document and simultaneously minimize the redundancies between the sentences of the summary. Bat algorithm (BA) is used as an optimization technique which provides efficient result in creating an extractive summary.

Extractive Summary: An Optimization Approach Using Bat Algorithm

India’s heritage texts have had a long history of being mined for knowledge of language and culture by Christian missionaries to India, colonial officers of the East Indian Company and the British Raj, German, European and American Indologists and later by native scholars driven by nationalist sentiments. It was during their investigative exercises that a vast body of India’s heritage texts was recovered and made the subject of rigorous study. A large number of editions in English translation as well as in modern Indian vernacular languages started appearing on the scene. The focus then was primarily on patthoddhar [retrieval of the ‘ur’-text] or making shuddhasanskarana [correct edition]. The exercise was purely manual and time-consuming and concentrated on a limited number of texts. But there still lies a vast treasure of ancient knowledge in India’s palm leaf manuscripts, waiting to be discovered, deciphered and interpreted for contemporary readers and scholars. It is impossible to ignore the ubiquitousness of Information Technology based tools and the scope that they offer for large-scale data mining. Of late, a large body of historical texts is being made available digitally

/pdf/engaging-with-an-indian-epic-a-digital-approach-3p5exl4psu.pdf

Engaging with an Indian Epic: A Digital Approach

Automatic text summarization (ATS) is a widely used approach. Through the years, various techniques have been implemented to produce the summary. An extractive summary is a traditional mechanism for information extraction, where important sentences are selected which refers to the basic concepts of the article. In this paper, extractive summarization has been considered as a classification problem. Machine learning techniques have been implemented for classification problems in various domains. To solve the summarization problem in this paper, machine learning is taken into consideration, and KNN, random forest, support vector machine, multilayer perceptron, decision tree and logistic regression algorithm have been implemented on Newsroom dataset.

Anshuman Pattanaik

Papers

A Comparative Study on Approaches to Speckle Noise Reduction in Images

A Review on Multi-Lingual Sentiment Analysis by Machine Learning Methods

Extractive Summary: An Optimization Approach Using Bat Algorithm

Engaging with an Indian Epic: A Digital Approach

A Comparative Study of Classifiers for Extractive Text Summarization