A. Ghaffari, M. R. Homaeinezhad, M. Akraminia,
Volume 6, Issue 1 (3-2010)
Abstract
The aim of this study is to address a new feature extraction method in the area of the heart arrhythmia classification based on a metric with simple mathematical calculation called Curve-Length Method (CLM). In the presented method, curve length of the under study excerpted segment of signal is considered as an informative feature in which the effect of important geometric parameters of the original signal can be found. To show merits of the presented method, first the original electrocardiogram (ECG) in lead I is pre-processed by removing its baseline wander then by scaling it in the [-1,1] interval. In the next step, using a trous method, discrete wavelet scales 23 and 24 and smoothing function scale 22 are extracted. Afterwards, segments including samples of the QRS complex, P and T waves are estimated via an approximation criterion and CLM is implemented to extract corresponding features from aforementioned scales, smoothing function and also from each original segment. The resulted feature vector (including 12 components) is used to tune an Adaptive Network Fuzzy Inference System (ANFIS) classifier. The presented strategy is applied to classify four categories found in the MIT-BIH Arrhythmia Database namely as Atrial Premature Beat (APB), Left Bundle Branch Block (LBBB), Right Bundle Branch Block (RBBB) and Premature Ventricular Contraction (PVC) and average values of Se = 99.81%, P+ = 99.80%, Sp = 99.81% and Acc = 99.72% are obtained for sensitivity, positive predictivity, specifity and accuracy respectively showing marginal improvement of the heart arrhythmia classification performance.
M. Petrov,
Volume 17, Issue 1 (3-2021)
Abstract
The noise in reconstructed slices of X-ray Computed Tomography (CT) is of unknown distribution, non-stationary, oriented and difficult to distinguish from main structural information. This requires the development of special post-processing methods based on the local statistical evaluation of the noise component. This paper presents an adaptive method of reducing noise in CT images employing the shearlet domain in order to obtain such an estimate. The algorithm for statistical noise assessment takes into account the distribution of signal energy in different scales and directions. The method efficiently uses the strong targeted sensitivity of shearlet systems in order to reflect more accurately the anisotropic information in the image. Because of the complex characteristics of the noise in these images, the threshold constant is determined by means of the relative entropy change criterion. The comparative analysis, which has been conducted, shows that the proposed method achieves higher values for the Peak Signal-to-Noise Ratio (PSNR), as well as lower values for the Mean Squared Error (MSE), in comparison with the other methods considered. For the MATLAB’S Shepp Logan Phantom test image, the numerical value of this superiority is on average more than 23% for the first quantitative measure, and 37% for the second. Its efficiency, which is greater than that of the wavelet-based method, is confirmed by the results obtained – the edges have been preserved during noise reduction in real CT images.
S. A. Karimi, S. Mirzakuchaki,
Volume 17, Issue 4 (12-2021)
Abstract
Various methods have been proposed to detect the attention and perception of an operator during tasks such as radar monitoring. Due to the high accuracy of electroencephalographic signals, it is utilized for systems based on brain signal. The event-related potential (ERP) technique has been widely used for testing theories of perception and attention. Brain-computer Interface (BCI) provides the communication link between the human’s brain and an external device. In this article, we propose a method to investigate the attention of operators of very sensitive monitoring devices, in particular, the operators of navy ships’ radars in detecting fighter aircrafts. Using a Visual Stimuli, which was shown to the subjects prior to the test, the protocol utilized in this paper yielded a very high accuracy (up to 87%), which makes it a robust method to use in such conditions. Linear LDA and non-linear SVM classifiers were utilized in processing the output signal. Although several P300 systems have been used to detect attention using pattern recognition techniques, the novelty of this study is that attention detection is used for the first time for a radar operator which resulted in acceptable accuracy.
S. Fouladifard, H. Behnam, P. Gifani, M. Shojaeifard,
Volume 18, Issue 2 (6-2022)
Abstract
A semi-automatic method for the segmentation of the Left Ventricle in echocardiography images is presented. The manual segmentation of the left ventricle in all image sequences takes a lot of time. The proposed method is based on sparse representation and the design of overcomplete dictionaries based on prior knowledge of the intensity variation time curves (IVTC). We used the sparse recovery algorithm of orthogonal matching pursuit (OMP) to find the sparse coefficients of the IVTC signals. We obtained the histogram of non-zero sparse coefficients for all images. The binary images from successive frames were constructed via thresholding. In addition, we defined one image representing all the frames, dividing all the points of the heart into three groups. One group involved the points located inside the cavities in all frames. The second group included the points that belonged to the tissue in all frames. Points that in some frames are located inside the cavities and in some other frames are located inside the tissue. The results on 2D echocardiographic images acquired from both healthy and patient subjects showed good agreement with manual tracing and took a short time for the contour, including the whole left ventricle. According to the cardiology specialist, the value of ejection fraction is correctly calculated, and the error percentages were 0.83 and 2.33 for two healthy data samples. The proposed method can be applied to 3D echocardiography images to obtain the left ventricular volume. This approach also can be used for other types of medical images.
O. Mahmoudi Mehr, M. R. Mohammadi, M. Soryani,
Volume 19, Issue 3 (9-2023)
Abstract
Speckle noise is an inherent artifact appearing in medical images that significantly lowers the quality and accuracy of diagnosis and treatment. Therefore, speckle reduction is considered as an essential step before processing and analyzing the ultrasound images. In this paper, we propose an ultrasound speckle reduction method based on speckle noise model estimation using a deep learning architecture called “speckle noise-based inception convolutional denoising neural network" (SNICDNN). Regarding the complicated nature of speckle noise, an inception module is added to the first layer to boost the power of feature extraction. Reconstruction of the despeckled image is performed by introducing a mathematical method based on solving a quadratic equation and applying an image-based inception convolutional denoising autoencoder (IICDAE). The results of various quantitative and qualitative evaluations on real ultrasound images demonstrate that SNICDNN outperforms the state-of-the-art methods for ultrasound despeckling. SNICDNN achieves 0.4579 dB and 0.0100 additional gains on average for PSNR and SSIM, respectively, compared to other methods. Denoising ultrasound based on its noise model estimation is not only a novel approach in comparison to traditional denoising autoencoder models but also due to the fact that it uses mathematical solutions to recover denoised images, SNICDNN shows a greater power in ultrasound despeckling.
V. Esmaeili, M. Mohassel Feghhi,
Volume 19, Issue 3 (9-2023)
Abstract
The coronavirus disease or COVID-19, as a global disease, is an unprecedented health care crisis due to increasing mortality and its high rate of infection. Patients usually show significant complications in the respiratory system. This disease is caused by SARS-CoV-2. Decreasing the time of diagnosis is essential for reducing deaths and low spreading of the virus. Also, using the optimal tool in the pediatric setting and Intensive care unit (ICU) is required. Therefore, using lung ultrasound is recommended. It does not have any radiation and it has a lower cost. However, it makes noisy and low-quality data. In this paper, we propose a novel approach called Uniform Local Binary Pattern on Five intersecting Planes and convolutional neural Network (ULBPFP-Net) that overcomes the said limitation. We extract worthwhile features from five planes for feeding a network. Our experiments confirm the success of the ULBPFP-Net in COVID-19 diagnosis compared to the previous approaches.
Neda Gorji Kandi, Hamid Behnam, Ali Hosseinsabet,
Volume 20, Issue 2 (6-2024)
Abstract
