Ultrasound speckle reduction using adaptive wavelet thresholding

Ultrasound is the most widely used biomedical imaging modality for the purpose of diagnosis. It often comes with speckle that results in reduced quality of images by hiding fine details like edges and boundaries, as well as texture information. In this present study, a novel wavelet thresholding technique for despeckling of ultrasound images is proposed. For analysing performance of the method, it is first tested on synthetic (ground truth) images. Speckle noise with distinct noise levels (0.01–0.04) has been added to the synthetic images in order to examine its efficiency at different noise levels. The proposed technique is applied to various orthogonal and biorthogonal wavelet filters. It has been observed that Daubechies 1 gives the best results out of all wavelet filters. The proposed method is further applied on ultrasound images. Performance of the proposed technique has been validated by comparing it with some state-of-the-art techniques. The results have also been validated visually by the expert. Results reveal that the proposed technique outperforms other state-of-the-art techniques in terms of edge preservation and similarities in structures. Thus, the technique is effective in reducing speckle noise in addition to preserving texture information that can be used for further processing.

     

Despeckling of ultrasound images using novel adaptive wavelet thresholding function

Multidimensional Systems and Signal Processing - In the present work, a new thresholding function has been proposed for despeckling of ultrasound images. The main limitation of ultrasound images is...     

Statistical recursive minimum cross entropy for ultrasound image segmentation

Multimedia Tools and Applications - Ultrasound imaging is one of the most widely used biomedical imaging modality for diagnostic purposes. Ultrasound image segmentation is an important step in...     

Two-channel perfect reconstruction (PR) quadrature mirror filter (QMF) bank design using logarithmic window function and spline function

In this work, two-channel perfect reconstruction quadrature mirror filter (QMF) bank has been proposed based on the prototype filter using windowing method. A novel window function based on logarithmic function along with the spline function is utilized for the design of prototype filter. The proposed window has a variable parameter ‘\(\alpha \)’, which varies the peak side lobe level and rate of fall-off side lobe level which in turn affects the peak reconstruction error (PRE) and amplitude distortion (\(e_{am}\)) of the QMF bank . The transition width of the prototype is controlled by the spline function using the parameter ‘\(\mu \)’. The perfect reconstruction condition is satisfied by setting the cutoff frequency (\(\omega _{c}\)) of the prototype low-pass filter at ‘\(\pi /2\)’. The performance of the proposed design method has been evaluated in terms of mean square error in the pass band, mean square error in the stop band, first side lobe attenuation (\(A_{1}\)), peak reconstruction error (PRE) and amplitude error (\(e_{am}\)) for different values of ‘\(\alpha \)’ and ‘\(\mu \)’. The results are provided and compared with the existing methods.     

A novel local octa-pattern feature descriptor for image retrieval

The local tetra patterns (LTrPs) gives four-directional information and ignores the diagonal pixel information, thereby affecting the retrieved image efficiency. In the present work, a novel retrieval approach has been proposed using local octa-patterns (LOcPs) for content-based image indexing and retrieval. The proposed approach encodes the center pixel directional information with its eight adjacent neighbors, from the directions that are computed using the first-order derivatives. Also the nth-order LOcP is computed using \((n-1)\)th-order local direction variations. In addition, the performance of the developed method by combining it with the Gabor transform has been analyzed. The performance of the proposed technique has been compared to existing techniques like LBP, LTP, LDP, and LTrP on Corel-1000 database (DB1) and Describable Textures Dataset (DB2). The performance observed shows that the developed method improves the retrieval parameters from 75.9%/77.13% to 79.4%/81.5% in the form of average precision on DB1/DB2 databases.     

Inferior myocardial infarction detection using stationary wavelet transform and machine learning approach

Early and accurate detection of myocardial infarction is imperative for reducing the mortality rate due to heart attack. Present work proposes a novel technique aiming toward accurate and timely detection of inferior myocardial infarction (IMI). Stationary wavelet transform has been used to decompose the segmented multilead electrocardiogram (ECG) signal into different sub-bands. Sample entropy, normalized sub-band energy, log energy entropy, and median slope calculated over selected bands of multilead ECG are used as features. Support vector machine (SVM) and K-nearest neighbor (KNN) have been used to classify between subjects admitted for health control (HC) and patients suffering from IMI, using attributes selected on the basis of gain ratio. The full length ECG of lead II, III, and aVF of all the subjects having IMI or admitted for HC from Physikalisch-Technische Bundesanstalt Database (PTB-DB) has been used in the present work. The proposed technique has been scrutinized under both “class-oriented,” and more practical, “subject-oriented” approach. Under the class-oriented approach, data have been divided into training and test data irrespective of the patients, whereas in subject-oriented approach, data from one patient have been used for test and training has been done on the rest of the subjects. Under the class-oriented approach, area under the receiver operating characteristic curve (Roc), sensitivity (Se%), specificity (Sp%), positive predictivity (+P%), and accuracy (Ac%) is Roc \(=\) 0.9945, Se% \(=\) 98.67, Sp% \(=\) 98.72, +P% \(=\) 98.79, Ac% \(=\) 98.69 using KNN and Roc \(=\) 0.9994, Se% \(=\) 99.35, Sp% \(=\) 98.29, +P% \(=\) 98.41, Ac% \(=\) 98.84 using SVM. For the subject-oriented approach, an average Ac% \(=\) 81.71, Se% \(=\) 79.01, Sp% \(=\) 79.26, and +P% \(=\) 80.25 has been achieved. This shows the potential of the proposed technique to work for an unknown subject, on which it has not been trained.