Strength of ensemble learning in automatic sleep stages classification using single-channel EEG and ECG signals.

Healthy sleep plays an essential role in human daily life. Classification of sleep stages is a crucial tool for assisting physicians in diagnosing and treating sleep disorders. In this study, a strong ensemble learning model is proposed to enhance the ability of classification models in accurate sleep staging, particularly in multi-class classification. We asserted that high-accuracy sleep classification is achievable using only single-channel electroencephalogram (EEG) and electrocardiogram (ECG) by combining their best-extractable features in the time and frequency domains we recommended. More importantly, the superiority of the recommended method, which is the simultaneous use of stacking and bagging, over conventional machine learning classifiers in sleep staging was demonstrated, using the MIT-BIH Polysomnographic and Sleep-EDF expanded databases. Finally, K-fold cross-validation was used to fairly estimate these models. The best mean test accuracy rates for distinguishing between two classes of "sleep vs. wake," "rapid vs. non-rapid eye movement," and "deep vs. light sleep," were obtained 99.93%, 99.64%, and 99.69%, respectively. Furthermore, our proposed method achieved accuracies of 97.14%, 95.18%, 92.7%, and 85.64% for separating three, four, five, and six sleep classes, respectively. Compared to recent studies, our method outperforms other sleep stage classification schemes, especially in multi-class staging.

Frame rate improvement in ultrafast coherent plane wave compounding.

Coherent plane wave compounding (CPWC), as an ultrafast ultrasound imaging technique, makes a significant breakthrough in frame rate enhancement. However, there exists a compromise between the quality of the final image and the frame rate in CPWC. In this paper, we propose an efficient method to minimize the number of required emissions, and consequently, improve the frame rate, while maintaining the image quality. To this end, we down-sample the angle interval using two specific sampling factors. More precisely, we construct two different subsets, each of which consists of a few numbers of emissions. The optimal values of the angle intervals are achieved based on the beampattern that corresponds to the reference case (that is, the case where all plane waves are used). Finally, in order to keep the image quality comparable with the reference case, we apply some modifications to the image reconstruction procedure. In the proposed algorithm, the Delay-and-Sum beamformed images of two considered subsets are convolved to achieve the final reconstructed image. The obtained results confirm the efficiency of the proposed method in terms of frame rate improvement compared to the reference case. In particular, by using the proposed method, the required emissions in PICMUS data reduce to 16, which is 4.6 times smaller compared to the reference case. Also, the gCNR values of the proposed method and the reference case are obtained as 0.98 and 0.97, respectively, for in-vivo dataset. This demonstrates that the proposed method successfully preserves the quality of the reconstructed image by using much fewer emissions.

Ultrafast Plane Wave Imaging Using Tensor Completion-Based Minimum Variance Algorithm.

OBJECTIVE: Coherent plane wave compounding (CPWC) imaging is an efficient technique in high-frame-rate ultrasound imaging. To improve the image quality obtained from the CPWC, the adaptive minimum variance (MV) algorithm can be used. However, the high computational complexity of this algorithm negatively affects the frame rate. In other words, achieving a high frame rate and high-quality features simultaneously remains a challenge in medical ultrasound imaging. The aim of the work described here was to develop an algorithm to tackle this challenge and improve the frame rate while preserving the good quality of the resulting image. METHODS: A tensor completion (TC)-based MV algorithm is proposed to simultaneously improve the frame rate and image quality in CPWC. In the proposed method, the MV algorithm is applied to a limited number of pixels in the beamforming grid. Then, the appropriate values are assigned to the remaining unprocessed pixels by using the TC algorithm. The proposed algorithm speeds up the beamforming process, and consequently, improves the frame rate. RESULTS: The computational complexity of the proposed TC-based MV algorithm is reduced compared with that of the conventional MV algorithm while the good quality of this algorithm is preserved. The results indicate that, in particular, by processing 40% of the beamforming grid using the MV beamformer followed by the TC algorithm, a reconstructed image comparable to that in the case in which the MV algorithm is performed on the full beamforming grid is obtained; the difference between the contrast-to-noise ratio evaluation metric between these two cases is about 0.16 dB for the experimental-resolution phantom. Also, the resulting images obtained from the MV algorithm and the TC-based MV method have the same resolution, indicating that the TC-based MV algorithm can successfully achieve the quality of the MV algorithm with a lower computational complexity. CONCLUSION: The TC-based MV algorithm is proposed in CPWC with the goal of improving frame rate and image quality. Qualitative and quantitative results reveal that by use of the proposed algorithm, the quality of the reconstructed image will be comparable to that of the conventional MV algorithm, and the frame rate will be improved.

Fast Beamforming Method for Plane Wave Compounding Based on Beamspace Adaptive Beamformer and Delay-Multiply-and-Sum.

OBJECTIVE: Although the use of coherent plane wave compounding is a promising technique for enabling the attainment of very high frame rate imaging, it achieves relatively low image quality because of data-independent reconstruction. Adaptive beamformers rather than delay-and-sum (DAS) conventional techniques have been proposed to improve the imaging quality. The minimum variance (MV) and delay-multiply-and-sum (DMAS) beamformers have been validated as effective in improving image quality. The MV improves mainly the resolution of the image, while being computationally expensive and having little impact on contrast. The DMAS increases the contrast while over-suppressing the speckle region in the case of 2-D summation for multi-transmission applications. METHODS: In a new approach, a beamformer based on MV and DMAS is proposed to enhance both spatial resolution and contrast in plane wave imaging. Prior to estimating the weight vector of MV, the backscattered echoes are decorrelated without any spatial smoothing. This enhances the robustness of MV without compromising the improvement in resolution. With a shift from element space to beamspace, MV weights are calculated using the spatial statistics of a set of orthogonal beams, which allows the high-complexity algorithm to be run faster. After that, the MV weights are applied to the DMAS output vector beamformed over different transmissions. DISCUSSION AND CONCLUSION: The proposed method can result in better contrast resolution, thereby avoiding over-suppression. The complexity of the applied DMAS version is also similar to that of DAS. Imaging results reveal that the proposed method offers improvements over the traditional compounding method in terms of spatial and contrast resolution. It also can achieve a higher image quality compared with some existing adaptive methods applied in the literature.

Plane wave ultrasound imaging using compressive sensing and minimum variance beamforming.

Coherent plane-wave compounding (CPWC) is a widely used technique in medical ultrasound imaging due to its high frame rate property. It is well-known that increasing the plane waves leads to improving the image quality. However, the image quality still needs to be further improved in CPWC. In this regard, a variety of methods have been proposed. In this paper, a new compressive sensing (CS) based approach is introduced with the combination of the adaptive minimum variance (MV) algorithm to further improve the image quality in terms of resolution and contrast. In the proposed method, which is called the CS-based MV technique, the CS method is used in the receive direction to produce the beamformed data for each plane wave. Then, the MV algorithm is performed in the plane wave transmit angle direction to coherently compound the images and improve the resolution. Moreover, to deal with the high computational complexity and also, the needing for high memory space during the CS method implementation, an approximation is considered which results in considerably reduced computational burden and memory space. The results obtained from the simulated point targets show that the proposed method leads to resolution improvement for about 71%, 5.5%, and 37% respectively, compared to DAS, DAS+MV, and CS+DAS beamformers. Also, the quantitative results obtained from the experimental contrast phantom in plane wave imaging challenge in medical ultrasound (PICMUS) data show a 3.02 dB, 2.57 dB, and 2.24 dB improvement of the contrast ratio metric using the proposed method compared to DAS, DAS+MV, and double-MV methods, respectively, indicating the good performance of the proposed method in image quality improvement.

Heterogeneous Recurrence Analysis of Imaged-EEG for Spatio-Temporal Epileptic Seizure Detection.

Epilepsy is known as a heterogeneous neurological disorder affecting 1 to 3 percent of the worldwide population. Epileptic seizures occur when brain cells feature abnormal synchronized recurrent activities. In this study, the recurrence characteristics of multichannel scalp electroencephalography (EEG) signals are extracted using Heterogeneous Recurrence Analysis (HRA) to investigate seizure phenomena. For this aim, imaged-EEGs are made using time, frequency, and statistical elementary features extracted from 2-second epochs. Each recording's channel-set provides the ground rule for placing feature values in the imaged-EEGs. Applying HRA method to imaged-EEGs extracts temporal recurrent features from successive epochs among the neighboring channels. Despite existing methods using each individual channel's characteristics as features for each epoch, this method can provide spatial heterogeneous recurrence information for each region of the image, consequently regions of the brain. Our method was evaluated using two publicly available datasets recorded from pediatric patients at Boston Children's Hospital (CHB-MIT) and American university of Beirut Medical Center (ABMC). Considering only temporal detection of seizures, the averaged evaluation parameters are 99.6% accuracy, 99.7% sensitivity, 99.4% specificity on 24 patients of CHB-MIT dataset, and 98.5% accuracy, 97.9% sensitivity, and 98.5% specificity on 6 patients of ABMC. The results show that the accuracy and specificity of the proposed method are comparable to the best machine learning baseline methods while the sensitivity is better. Besides good classification results, HRA on imaged-EEGs can give us valuable information about the patient's brain lobe/s in which recurrent features are distinctive for seizure detection.

A new data covariance matrix estimation for improving minimum variance brain source localization.

Data with finite samples results in accuracy and robustness reduction of data covariance matrix estimation, which in turn results in performance reduction of minimum variance beamformer (MVB) for brain source localization (BSL). General linear combination (GLC) and convex combination (CC) are methods of interest for data covariance matrix estimation and increasing its accuracy and robustness because their scalar coefficients are obtained automatically and adaptively. However, based on our best knowledge, the applicability of GLC and CC algorithms has not been investigated for BSL to inform us about their performance. In this paper, we have two goals: 1) Investigation of GLC and CC covariance matrices applications for BSL is carried out using various simulated MEG scenarios and real MEG and clinical epilepsy data; 2) Modified GLC and CC are developed for more accurate and robust estimation of data covariance matrix when data with finite samples is available. In the modified versions, the scalar coefficients are replaced by diagonal matrix form coefficients. These matrix form coefficients are computed using the Hadamard product and mean square error concept. The evaluations show that the CC and modified CC based MVBs are not robust for BSL due to very small values of coefficients. Based on the simulated, real, and clinical data results, it can be stated that the modified GLC is significantly superior to conventional GLC in terms of localization error, spatial resolution (all z < -2; all p-values < 0.001), and offering reliable results. Also, the proposed GLC offers fewer missed sources and less sensitivity to the depth biasing problem, particularly in a high signal-to-noise ratio. In conclusion, it can be said that the covariance matrix of modified GLC which is user-free and robust against the finite data samples can improve the MVB performance for BSL in terms of localization error and spatial resolution.

Automatic detection of epileptic seizures using Riemannian geometry from scalp EEG recordings.

This paper proposes a new framework for epileptic seizure detection using non-invasive scalp electroencephalogram (sEEG) signals. The major innovation of the current study is using the Riemannian geometry for transforming the covariance matrices estimated from the EEG channels into a feature vector. The spatial covariance matrices are considered as features in order to extract the spatial information of the sEEG signals without applying any spatial filtering. Since these matrices are symmetric and positive definite (SPD), they belong to a special manifold called the Riemannian manifold. Furthermore, a kernel based on Riemannian geometry is proposed. This kernel maps the SPD matrices onto the Riemannian tangent space. The SPD matrices, obtained from all channels of the segmented sEEG signals, have high dimensions and extra information. For these reasons, the sequential forward feature selection method is applied to select the best features and reduce the computational burden in the classification step. The selected features are fed into a support vector machine (SVM) with an RBF kernel to classify the feature vectors into seizure and non-seizure classes. The performance of the proposed method is evaluated using two long-term scalp EEG (CHB-MIT benchmark and private) databases. Experimental results on all 23 subjects of the CHB-MIT database reveal an accuracy of 99.87%, a sensitivity of 99.91%, and a specificity of 99.82%. In addition, the introduced algorithm is tested on the private sEEG signals recorded from 20 patients, having 1380 seizures. The proposed approach achieves an accuracy, a sensitivity, and a specificity of 98.14%, 98.16%, and 98.12%, respectively. The experimental results on both sEEG databases demonstrate the effectiveness of the proposed method for automated epileptic seizure detection, especially for the private database which has noisier signals in comparison to the CHB-MIT database. Graphical Abstract Block diagram of the proposed epileptic seizure detection algorithm.

User Parameter-Free Minimum Variance Beamformer in Medical Ultrasound Imaging.

The minimum variance beamformer (MVB) is a well-known adaptive beamformer in medical ultrasound imaging. Accurate estimation of the covariance matrix has a great effect on the performance of the MVB. In adaptive ultrasound imaging, parameters such as the subarray length, the number of samples used for temporal averaging, and the value of diagonal loading (DL) have the main role in the true estimation of the covariance matrix. The optimal values for these parameters are different from one scenario to another one. Thus, the MVB is not a parameter-free method, and its behavior is scenario-dependent. In the field of telecommunications and radar, the shrinkage method was proposed to determine the DL factor, but no method has been provided yet to determine other parameters. In this article, an adaptive approach is developed to determine the MVB parameters, which is completely independent of the user. The minimum variance variable loading along with the modified shrinkage (MVVL-MSh) algorithm is introduced to adaptively calculate the optimal DL. Also, two methods based on the coherence factor (CF) are proposed to determine the subarray length in the spatial smoothing and the number of samples required for temporal averaging. The performance of the proposed methods is evaluated using simulated and experimental RF data. It is shown that the methods preserve the contrast and improve the resolution by about 35% and 38% compared to the MV having a fix loading coefficient and the MV-Sh algorithm.

Automatic seizure detection using orthogonal matching pursuit, discrete wavelet transform, and entropy based features of EEG signals.

BACKGROUND AND OBJECTIVE: Epilepsy is a prevalent disorder that affects the central nervous system, causing seizures. In the current study, a novel algorithm is developed using electroencephalographic (EEG) signals for automatic seizure detection from the continuous EEG monitoring data. METHODS: In the proposed methods, the discrete wavelet transform (DWT) and orthogonal matching pursuit (OMP) techniques are used to extract different coefficients from the EEG signals. Then, some non-linear features, such as fuzzy/approximate/sample/alphabet and correct conditional entropy, along with some statistical features are calculated using the DWT and OMP coefficients. Three widely-used EEG datasets were utilized to assess the performance of the proposed techniques. RESULTS: The proposed OMP-based technique along with the support vector machine classifier yielded an average specificity of 96.58%, an average accuracy of 97%, and an average sensitivity of 97.08% for different types of classification tasks. Moreover, the proposed DWT-based technique provided an average sensitivity of 99.39%, an average accuracy of 99.63%, and an average specificity of 99.72%. CONCLUSIONS: The experimental findings indicated that the proposed algorithms outperformed other existing techniques. Therefore, these algorithms can be implemented in relevant hardware to help neurologists with seizure detection.

Seizure onset detection based on detection of changes in brain activity quantified by evolutionary game theory model.

BACKGROUND AND OBJECTIVE: Epilepsy is one of the most common diseases of the nervous system, affecting about 1% of the world's population. The unpredictable nature of the epilepsy seizures deprives the patients and those around them of living a normal life. Therefore, the development of new methods that can help these patients will increase the life quality of these people and can bring a lot of economic savings in the health sector. METHODS: In this study, we introduced a new framework for seizure onset detection. Our framework provides a new modelling for brain activity using evolutionary game theory and Kalman filter. If the patterns in the electroencephalogram (EEG) signal violate the predicted patterns by the proposed model, using a novel detection algorithm that has been also introduced in this paper, it can be determined whether the observed violation is the result of the onset of an epileptic seizure or not. RESULTS: The proposed approach was able to detect the onset of all the seizures in CHB-MIT dataset with an average delay of -0.8 s and a false alarm of 0.39 per hour. Also, our proposed approach is about 20 times faster compared to recent studies. CONCLUSIONS: The experimental results of applying the proposed framework on the CHB-MIT dataset show that our framework not only performed well with respect to the sensitivity, delay, and false alarm metrics but also performed much better in terms of run time compared to recent studies. This appropriate run time, along with other suitable metrics, makes it possible to use this framework in many cases where processing power or energy is limited and to think about creating new and inexpensive solutions for the treatment and care of people diagnosed with epilepsy.

Minimum Variance Combined With Modified Delay Multiply-and-Sum Beamforming for Plane-Wave Compounding.

Plane-wave compounding is an active topic of research in ultrasound imaging because it is a promising technique for ultrafast ultrasound imaging. Unfortunately, due to the data-independent nature of the traditional compounding method, it imposes a fundamental limit on image quality. To address this issue, adaptive beamformers have been implemented in the compounding procedure. In this article, a new adaptive beamformer for the 2-D data set obtained from multiple plane-wave transmissions is investigated. In the proposed scheme, the minimum variance (MV) weights are applied to the backscattered echoes. Then, the final image is obtained by employing a modified version of the delay multiply-and-sum (DMAS) beamformer in the coherent compounding. The results demonstrate that the presented MV-DMAS scheme outperforms the conventional coherent compounding in both terms of resolution and contrast. It also offers improvements over the 2-D-DMAS and some MV-based methods presented in the literature, such that it achieves at least 20.9% enhancement in sidelobe reduction compared with the best result of MV-based methods. Also, by the proposed method, the in vivo study shows an improved generalized contrast-to-noise ratio (GCNR) that implies a higher probability of lesion detection.

Adaptive transverse blood velocity estimation in medical ultrasound: A simulation study.

Undoubtedly, highly valuable information about vascular anomalies is attained by the examination of the blood flow profile. The chief drawback of the conventional medical ultrasound in preparation of the blood periodogram is the measurement system shortcoming at the beam to flow angles near 90°. Recently, a method based on transverse oscillation (TO) approach, known as "Fourth-order estimation", has been developed to directly estimate the transverse power spectral density (PSD) of the fully transverse blood flow. One of the basic requirements to accomplish acceptable PSDs by this technique is the sufficiently large observation window. In this paper, two adaptive approaches for efficient estimation of the velocity spectrum of a fully transverse flow by a limited observation window length are described. The first proposed adaptive approach is based on the minimum variance adaptive spectral estimation in combination with the well-known TO technique (TO-MV). Then, by exploiting the eigenspace separation of the observed data to eliminate the contribution of the undesired components, the second technique (TO-EIBMV) is developed. The approaches are validated using Field II simulations for pulsating flow. The proposed methods are tested and compared to the conventional TO transverse spectral estimator by metrics of relative standard deviation (RSD) and relative bias (RB). One of the main achievements is the decrement of the required data samples for spectrogram estimation, which leads to a better temporal resolution. Moreover, for the analyzed adaptive techniques, the robustness of the estimation results for the beam to flow angles of 60-90° and vessel depths ranging from 20 mm to 60 mm are investigated.

High Resolution Minimum Variance Beamformer With Low Complexity in Medical Ultrasound Imaging.

Although the minimum variance beamformer (MVB) shows a significant improvement in resolution and contrast in medical ultrasound imaging, its high computational complexity is a major problem in a real-time imaging system. Therefore, it seems necessary to propose a new method with a lower computational complexity that preserves the advantages of the MVB. In this paper, the MVB was implemented with a partial generalized sidelobe canceler (GSC) with a blocking matrix based on our previous study, which projected the incoming signals to a lower dimensional space. The partial GSC separated the weight vector into one fixed and one adaptive weight, whereby the optimization could be performed with lower complexity on the adaptive part. In addition, this dimension reduction allowed us to increase the length of the subarray when using a spatial smoothing method, which was used to decorrelate the incoming signals. The subarray length was limited to half the length of the full array size in the ordinary MVB, while the proposed beamformer could cross over this limitation. The results demonstrated that the point spread function of the proposed beamformer was about 6.3 times narrower than the classic MVB, while the contrast was almost saved. These results were achieved with linear computational complexity by the proposed method, while it was cubic for the MVB. For a sample scenario, the proposed method needed only 1.8% of the required ops of the MVB.

Minimum variance based fusion of fundamental and second harmonic ultrasound imaging: Simulation and experimental study.

Harmonic imaging is widely used in clinical ultrasound due to its higher resolution in comparison with fundamental mode. However, the low amplitude of harmonic components in this imaging method is a crucial problem, resulting in a high sensitivity to noise, while the fundamental imaging is more robust against noise. To exploit the benefits of both the fundamental and harmonic imaging, we propose a minimum variance (MV)-based adaptive combination of fundamental and harmonic images. The performance of the proposed mixing-together MV (MTMV) beamformer is evaluated on simulated and experimental RF data. The results of the simulated point targets show that in the regions near of point targets, where the desire signals exist, the proposed MTMV beamformer mostly follows the MV-beamformed harmonic image to retain a better resolution. In the regions far from the point targets, where there is just noise, it follows the MV-beamformed fundamental image to benefit from more robustness. Also, the results of the simulated and experimental cyst phantoms indicate that MTMV reduces the background noise level and improves the contrast without compromising the high resolution of the MV-beamformed harmonic image. In the simulated cyst phantom, in comparison to DAS (fundamental), DAS (harmonic), MV (fundamental), MV (harmonic), and wavelet fusion, the image contrast ratio (CR) is increased, in average, about 5.2 dB, 3.5 dB, 1.5 dB, 3.6 dB, and 2.8 dB, respectively. The contrast-to-noise ratio (CNR) is significantly improved; about 59%, 53%, 41%, 37%, and 24%, respectively. In the experimental cyst phantom, these relative improvements are about 6.6 dB, 3.5 dB, 4.2 dB, 2.1 dB, and 3.8 dB for CR, and about 64%, 52%, 25%, 33%, and 33%, for CNR, respectively.

Automatic Detection of Obstructive Sleep Apnea Using Wavelet Transform and Entropy-Based Features From Single-Lead ECG Signal.

Obstructive sleep apnea (OSA) is a prevalent sleep disorder and highly affects the quality of human life. Currently, gold standard for OSA detection is polysomnogram. Since this method is time consuming and cost inefficient, practical systems focus on the usage of electrocardiogram (ECG) signals for OSA detection. In this paper, a novel automatic OSA detection method using a single-lead ECG signal has been proposed. A nonlinear feature extraction using wavelet transform (WT) coefficients obtained by an ECG signal decomposition is employed. In addition, different classification methods are investigated. ECG signals are decomposed into eight levels using a Symlet function as a mother Wavelet function with third order. Then, the entropy-based features including fuzzy/approximate/sample/correct conditional entropy as well as other nonlinear features including interquartile range, mean absolute deviation, variance, Poincare plot, and recurrence plot are extracted from WT coefficients. The best features are chosen using the automatic sequential forward feature selection algorithm. In order to assess the introduced method, 95 single-lead ECG recordings are used. The support vector machine classifier having a radial basis function kernel leads to an accuracy of 94.63% (sensitivity: 94.43% and specificity: 94.77%) and 95.71% (sensitivity: 95.83% and specificity: 95.66%) for minute-by-minute and subject-by-subject classifications, respectively. The results show that applying entropy-based features for extracting hidden information of the ECG signals outperforms other available automatic OSA detection methods. The results indicate that a highly accurate OSA detection is attained by just exploiting the single-lead ECG signals. Furthermore, due to the low computational load in the proposed method, it can easily be applied to the home monitoring systems.

Modified Dominant Mode Rejection Beamformer for Localizing Brain Activities When Data Covariance Matrix Is Rank Deficient.

OBJECTIVE: Minimum variance beamformer (MVB) and its extensions fail in localizing short time brain activities particularly evoked potentials because of rank deficiency or inaccurate estimation of a data covariance matrix. In this paper, the conventional dominant mode rejection (DMR) adaptive beamformer is modified to localize brain short time activities. METHODS: In the modified DMR, it is attempted to obtain a well-conditioned covariance matrix by dividing the eigenvalues of the data covariance matrix into dominant, medium, and small eigenvalues and then modifying medium and small parts. The performance of the proposed approach is compared with diagonal loading MVB (DL_MVB) and fast fully adaptive (FFA) beamformer by using simulated event-related potentials and real event-related field data. Eigenspace versions of DL_MVB and modified DMR are also implemented. RESULTS: In all simulations, the modified DMR obtains the least localization error (0-5 mm) and spread radius (0-8 mm) when the signal-to-noise ratio (SNR) varies from 0 to 10 dB with step 1 dB. In real data, the new approach in comparison to two other ones attains the most concentrated power spectrum. Eigenspace projection of DL_MVB presents better results than DL_MVB but worse results than the modified DMR. Applying eigenspace projection on the proposed method improves its performance at high SNR levels. CONCLUSION: Empirical results illustrate the superiority of the proposed DMR method to the DL_MVB and FFA in localizing brain short time activities. SIGNIFICANCE: The proposed method can be utilized in source localization of epilepsy for presurgical clinical evaluation purpose and also in applications dealing with the localization of evoked potentials and fields.

Melanoma recognition in dermoscopy images using lesion's peripheral region information.

BACKGROUND AND OBJECTIVES: Melanoma is one of the most dangerous forms of skin cancer, but it has a high survival rate if diagnosed on time. The first diagnostic approach in melanoma recognition is to visually assess the lesion through dermoscopic images. Computer-aided diagnosis systems for melanoma recognition has attracted a lot of attention in the last decade and proved to be helpful in that area. Methods for skin lesions analysis usually involves three main steps: lesion segmentation, feature extraction, and features classification. Extracting highly discriminative features from the lesion has a great impact on the recognition task. In this paper, we are seeking a lesion recognition system that incorporates these highly discriminative features. METHODS: For segmentation step, we use contour propagation model with a novel two-component speed function. In the feature extraction step, a new set of features based on peripheral information of the lesion are introduced. For this end, the peripheral area of the lesion is mapped to log-polar space using the Daugman's transformation and then a set of texture features are extracted from it. Newly introduced features do not need further segmentation of dermoscopic structures and are robust against lesion's scale, orientation, location, and shape variation. We also design the other global texture features to describe only the information from the lesion area. In the classification step, we evaluated two different schemes to prove the distinction power of the new features, one comprises linear SVM to recognize melanoma vs. nevus and the other scheme uses RUSBoost classifier to recognize melanoma vs. nevus and atypical-nevus. Sequential feature selection algorithm has been utilized in each classification scheme to rank features based on their distinction power. RESULTS: Cross-validation experiments on the well-known PH2 dataset resulted in an average of 97% for sensitivity and 100% for specificity on melanoma vs. nevus recognition task using only four features. Also, in the second classification scheme, we achieved high sensitivity and specificity values of 95% for melanoma vs. nevus and atypical nevus recognition experiments. CONCLUSION: High values for evaluation metrics show that the proposed melanoma recognition system is superior to the other state-of-the-art algorithms, which proves the high distinction power of the newly introduced features.

Robust heartbeat detection using multimodal recordings and ECG quality assessment with signal amplitudes dispersion.

BACKGROUND AND OBJECTIVES: The electrocardiogram (ECG) is a bioelectric signal which represents heart's electrical activity graphically. This bioelectric signal is subject of lots of researches and so many algorithms are designed for extracting lots of clinically important parameters from it. Most of these parameters can be measured by detecting R peak of the QRS complex in ECG signal, but when ECG signal is corrupted by different kinds of noise and artifacts, such as electromyogram (EMG) from muscles, power line interference, motion artifacts and changes in electrode-skin interface, detection of R peaks becomes hard or impossible for algorithms which are designed for heart beat detection on ECG signal. In modern patient monitoring devices often not only one ECG signal is recorded but also so many other biological signals are simultaneously recorded from the patient which some of them, such as blood pressure (BP), are containing useful information about the heart activity which could be very helpful in making the heart beat detection more robust. METHODS: In this study, a new method is introduced for distinguishing noise free segments of ECG from noisy segments that uses samples amplitudes dispersion with an adaptive threshold for variance of samples amplitude and a method which uses compatibility of detected beats in ECG and some of other signals which are related to the heart activity such as BP, arterial pressure (ART) and pulmonary artery pressure (PAP). A prioritization is applied in other pulsatile signals based on the amplitude and clarity of peaks on them, and a fusion strategy is employed for segments on which ECG is noisy and other available signals in the data, which contain peaks corresponding to R peak of the ECG, are scored in a three steps scoring function. RESULTS: The final scores achieved by the proposed algorithm in terms of average sensitivity, positive predictive value, accuracy and F1 measure on the database which is freely available in Physionet Computing in Cardiology Challenge 2014 are respectively 95.47%, 96.03%, 93.11% and 95.62%. CONCLUSIONS: The results show the outperformance of the proposed method against other recently published works.

Iterative Minimum Variance Beamformer with Low Complexity for Medical Ultrasound Imaging.

Minimum variance beamformer (MVB) improves the resolution and contrast of medical ultrasound images compared with delay and sum (DAS) beamformer. The weight vector of this beamformer should be calculated for each imaging point independently, with a cost of increasing computational complexity. The large number of necessary calculations limits this beamformer to application in real-time systems. A beamformer is proposed based on the MVB with lower computational complexity while preserving its advantages. This beamformer avoids matrix inversion, which is the most complex part of the MVB, by solving the optimization problem iteratively. The received signals from two imaging points close together do not vary much in medical ultrasound imaging. Therefore, using the previously optimized weight vector for one point as initial weight vector for the new neighboring point can improve the convergence speed and decrease the computational complexity. The proposed method was applied on several data sets, and it has been shown that the method can regenerate the results obtained by the MVB while the order of complexity is decreased from O(L3) to O(L2).