info@itechprosolutions.in | +91 9790176891

Matlab 2018

Category Archives

Geometry-Based Pectoral Muscle Segmentation From MLO Mammogram Views

Abstract:

Computer-aided diagnosis systems (CADx) play a major role in the early diagnosis of breast cancer. Extracting the breast region precisely from a mammogram is an essential component of CADx for mammography. The appearance of the pectoral muscle on medio-lateral oblique (MLO) views increases the false positive rate in CADx. Therefore, the pectoral muscle should be identified and removed from the breast region in an MLO image before further analysis. None of the previous pectoral muscle segmentation methods address all breast types based on the breast imaging-reporting and data system tissue density classes. In this paper, we deal with this deficiency by introducing a new simple yet effective method that combines geometric rules with a region growing algorithm to support the segmentation of all types of pectoral muscles (normal, convex, concave, and combinatorial). Experimental segmentation accuracy results were reported for four tissue density classes on 872 MLO images from three publicly available datasets. An average Jaccard index and Dice similarity coefficient of 0.972 ± 0.003 and 0.985 ± 0.001 were obtained, respectively. The mean Hausdorff distance between the contours detected by our method and the ground truth is below 5 mm for all datasets. An average acceptable segmentation rate of ~95% was achieved outperforming several state-of-the-art competing methods. Excellent results were obtained even for the most challenging class of extremely dense breasts.

A Quantitative Index for classification in plantar thermal changes in the diabetic foot

Abstract

One of the main complications caused by diabetes mellitus is the development of diabetic foot, which in turn, can lead to ulcerations. Because ulceration risks are linked to an increase in plantar temperatures, recent approaches analyze thermal changes. These approaches try to identify spatial patterns of temperature that could be characteristic of a diabetic group. However, this is a difficult task since thermal patterns have wide variations resulting on complex classification. Moreover, the measurement of contralateral plantar temperatures is important to determine whether there is an abnormal difference but, this only provides information when thermal changes are asymmetric and in absence of ulceration or amputation. Therefore, in this work is proposed a quantitative index for measuring the thermal change in the plantar region of participants diagnosed diabetes mellitus regards to a reliable reference (control) or regards to the contralateral foot (as usual). Also, a classification of the thermal changes based on a quantitative index is proposed. Such classification demonstrate the wide diversity of spatial distributions in the diabetic foot but also demonstrate that it is possible to identify common characteristics. An automatic process, based on the analysis of plantar angiosomes and image processing, is presented to quantify these thermal changes and to provide valuable information to the medical expert.


Automated Diagnosis of Glaucoma Using Empirical Wavelet Transform and Correntropy Features Extracted From Fundus Images

Abstract:

Glaucoma is an ocular disorder caused due to increased fluid pressure in the optic nerve. It damages the optic nerve and subsequently causes loss of vision. The available scanning methods are Heidelberg retinal tomography, scanning laser polarimetry, and optical coherence tomography. These methods are expensive and require experienced clinicians to use them. So, there is a need to diagnose glaucoma accurately with low cost. Hence, in this paper, we have presented a new methodology for an automated diagnosis of glaucoma using digital fundus images based on empirical wavelet transform (EWT). The EWT is used to decompose the image, and correntropy features are obtained from decomposed EWT components. These extracted features are ranked based on t value feature selection algorithm. Then, these features are used for the classification of normal and glaucoma images using least-squares support vector machine (LS-SVM) classifier. The LS-SVM is employed for classification with radial basis function, Morlet wavelet, and Mexican-hat wavelet kernels. The classification accuracy of the proposed method is 98.33% and 96.67% using threefold and tenfold cross validation, respectively.

Automatic Detection of Retinal Lesions for Screening of Diabetic Retinopathy

Abstract:

Objective: Diabetic retinopathy (DR) is characterized by the progressive deterioration of retina with the appearance of different types of lesions that include micro-aneurysms, hemorrhages, exudates, etc. Detection of these lesions plays a significant role for early diagnosis of DR. Methods: To this aim, this paper proposes a novel and automated lesion detection scheme, which consists of the four main steps: vessel extraction and optic disc removal, preprocessing, candidate lesion detection, and postprocessing. The optic disc and the blood vessels are suppressed first to facilitate further processing. Curvelet-based edge enhancement is done to separate out the dark lesions from the poorly illuminated retinal background, while the contrast between the bright lesions and the background is enhanced through an optimally designed wideband bandpass filter. The mutual information of the maximum matched filter response and the maximum Laplacian of Gaussian response are then jointly maximized. Differential evolution algorithm is used to determine the optimal values for the parameters of the fuzzy functions that determine the thresholds of segmenting the candidate regions. Morphology-based postprocessing is finally applied to exclude the falsely detected candidate pixels. Results and Conclusions: Extensive simulations on different publicly available databases highlight an improved performance over the existing methods with an average accuracy of 97.71 % and robustness in detecting the various types of DR lesions irrespective of their intrinsic properties.

Segmentation of Locally Varying Numbers of Outer Retinal Layers by a Model Selection Approach

Abstract:

Extraction of image-based biomarkers, such as the presence, visibility, or thickness of a certain layer, from 3-D optical coherence tomography data provides relevant clinical information. We present a method to simultaneously determine the number of visible layers in the outer retina and segment them. The method is based on a model selection approach with special attention given to the balance between the quality of a fit and model complexity. This will ensure that a more complex model is selected only if this is sufficiently supported by the data. The performance of the method was evaluated on healthy and retinitis pigmentosa (RP) affected eyes. In addition, the reproducibility of automatic method and manual annotations was evaluated on healthy eyes. Good agreement between the segmentation performed manually by a medical doctor and results obtained from the automatic segmentation was found. The mean unsigned deviation for all outer retinal layers in healthy and RP affected eyes varied between 2.6 and 4.9 μm. The reproducibility of the automatic method was similar to the reproducibility of the manual segmentation. Overall, the method provides a flexible and accurate solution for determining the visibility and location of outer retinal layers and could be used as an aid for the disease diagnosis and monitoring.

Classification of cell types in Acute Myeloid Leukemia (AML) of M4, M5 and M7 subtypes with support vector machine classifier

Abstract:

Acute Myeloid Leukemia (AML) is one of cancer type that attack white blood cells in myeloid descendants. On the clinical examination of leukemia, the number of each blast cell in the laboratory is calculated. However, in some subtype of AML like M4, M5 dan M7 are affected by the same type of precursor cells. The precursor cell of them are myeloblast, monoblast and megakaryoblast, which needs more detailed analysis to distinguish. This research tries to help overcome the problem by doing cell type automatic classification from cells images. Classification is performed on cell types of precursors cells derived from bone marrow preparations. The stages that have been completed are preprocessing, segmentation, extraction and feature selection, and classification. Features used as input of classification stage are area, nucleus ratio, circularity, perimeter, mean, and standard deviation. The results showed the success rate of cell segmentation reached 87.72% of total 1710 cells. The support vector machine classification results in the best performance test data are achieved by Linear kernel. The performance was obtained by combining six features for eight cell types from the maturation of the three precursor cells. These cell types are myeloblast, promyelocyte, granulocyte, monoblast, promonocyte, monocyte, megakaryoblast and support cell with sequential accuracy of 98.67%, 98.01%, 84.05% 99.67%, 95.35%, 89.70%, 99.34% and 98.01% respectively.

Automated detection of white blood cells cancer diseases

Abstract:

Automated diagnosis of white blood cells cancer diseases such as Leukemia and Myeloma is a challenging biomedical research topic. Our approach presents for the first time a new state of the art application that assists in diagnosing the white blood cells diseases. we divide these diseases into two categories, each category includes similar symptoms diseases that may confuse in diagnosing. Based on the doctor’s selection, one of two approaches is implemented. Each approach is applied on one of the two diseases category by computing different features. Finally, Random Forest classifier is applied for final decision. The proposed approach aims to early discovery of white blood cells cancer, reduce the misdiagnosis cases in addition to improve the system learning methodology. Moreover, allowing the experts only to have the final tuning on the result obtained from the system. The proposed approach achieved an accuracy of 93% in the first category and 95% in the second category.

Hookworm Detection in Wireless Capsule Endoscopy Images With Deep Learning

Abstract:

As one of the most common human helminths, hookworm is a leading cause of maternal and child morbidity, which seriously threatens human health. Recently, wireless capsule endoscopy (WCE) has been applied to automatic hookworm detection. Unfortunately, it remains a challenging task. In recent years, deep convolutional neural network (CNN) has demonstrated impressive performance in various image and video analysis tasks. In this paper, a novel deep hookworm detection framework is proposed for WCE images, which simultaneously models visual appearances and tubular patterns of hookworms. This is the first deep learning framework specifically designed for hookworm detection in WCE images. Two CNN networks, namely edge extraction network and hookworm classification network, are seamlessly integrated in the proposed framework, which avoid the edge feature caching and speed up the classification. Two edge pooling layers are introduced to integrate the tubular regions induced from edge extraction network and the feature maps from hookworm classification network, leading to enhanced feature maps emphasizing the tubular regions. Experiments have been conducted on one of the largest WCE datasets with 440K WCE images, which demonstrate the effectiveness of the proposed hookworm detection framework. It significantly outperforms the state-of-the-art approaches. The high sensitivity and accuracy of the proposed method in detecting hookworms shows its potential for clinical application.

Supervised Saliency Map Driven Segmentation of Lesions in Dermoscopic Images

Abstract:

Lesion segmentation is the first step in most automatic melanoma recognition systems. Deficiencies and difficulties in dermoscopic images such as color inconstancy, hair occlusion, dark corners and color charts make lesion segmentation an intricate task. In order to detect the lesion in the presence of these problems, we propose a supervised saliency detection method tailored for dermoscopic images based on the discriminative regional feature integration (DRFI). DRFI method incorporates multi-level segmentation, regional contrast, property, background descriptors, and a random forest regressor to create saliency scores for each region in the image. In our improved saliency detection method, mDRFI, we have added some new features to regional property descriptors. Also, in order to achieve more robust regional background descriptors, a thresholding algorithm is proposed to obtain a new pseudo-background region. Findings reveal that mDRFI is superior to DRFI in detecting the lesion as the salient object in dermoscopic images. The proposed overall lesion segmentation framework uses detected saliency map to construct an initial mask of the lesion through thresholding and post-processing operations. The initial mask is then evolving in a level set framework to fit better on the lesion’s boundaries. The results of evaluation tests on three public datasets show that our proposed segmentation method outperforms the other conventional state-of-the-art segmentation algorithms and its performance is comparable with most recent approaches that are based on deep convolutional neural networks.

A Multi-Anatomical Retinal Structure Segmentation System for Automatic Eye Screening Using Morphological Adaptive Fuzzy Thresholding

Abstract:

Eye exam can be as efficacious as physical one in determining health concerns. Retina screening can be the very first clue for detecting a variety of hidden health issues including pre-diabetes and diabetes. Through the process of clinical diagnosis and prognosis; ophthalmologists rely heavily on the binary segmented version of retina fundus image; where the accuracy of segmented vessels, optic disc, and abnormal lesions extremely affects the diagnosis accuracy which in turn affect the subsequent clinical treatment steps. This paper proposes an automated retinal fundus image segmentation system composed of three segmentation subsystems follow same core segmentation algorithm. Despite of broad difference in features and characteristics; retinal vessels, optic disc, and exudate lesions are extracted by each subsystem without the need for texture analysis or synthesis. For sake of compact diagnosis and complete clinical insight, our proposed system can detect these anatomical structures in one session with high accuracy even in pathological retina images. The proposed system uses a robust hybrid segmentation algorithm combines adaptive fuzzy thresholding and mathematical morphology. The proposed system is validated using four benchmark datasets: DRIVE and STARE (vessels), DRISHTI-GS (optic disc), and DIARETDB1 (exudates lesions). Competitive segmentation performance is achieved, outperforming a variety of up-to-date systems and demonstrating the capacity to deal with other heterogeneous anatomical structures.

Artificial fish swarm based power allocation algorithm for MIMO-OFDM relay underwater acoustic communication

Abstract:

This study investigates the application of artificial fish swarm algorithm (AFSA) in the power allocation for multiple-input and multiple-output orthogonal frequency-division multiplexing (MIMO-OFDM) relay underwater acoustic (UWA) communication systems. First, by using the singular value decomposition technique, the two-hop transmission links are converted into the virtual direct links in an single-input and single-output OFDM (SISO-OFDM) system. Then, a power allocation optimisation problem, together with the assignment of subcarriers and relay nodes, are formulated for the virtual SISO-OFDM system. Finally, the problem-solving algorithms are proposed in two parts. Computer simulation results show that the proposed AFSA scheme improves in both power consumptions and diversity gains compared with two existing schemes for UWA communication systems.

Hybrid spread spectrum orthogonal waveforms for MIMO radar

Abstract:

In multiple input multiple output (MIMO) radar systems, choosing a proper orthogonal waveform is a critical task. A new hybrid spread spectrum (HSS) technique is proposed to maintain orthogonality at the transmit and receive ends. The HSS technique is a combination of direct-sequence spreading and frequency hopping schemes. In the context of MIMO radar, the transmitted signals are first spread using Hadamard-Walsh orthogonal codes and in every pulse repetition period, each signal hops to a different center frequency. The transmitted HSS signals are orthogonal in frequency and code domains. Simulation results show that the proposed HSS technique can achieve sharper auto ambiguity response and lower sidelobe cross ambiguity response with a gain of over 10 dB and better probability of detection in comparison with frequency orthogonality technique. The proposed HSS technique has the potential to resolve closely spaced targets and provide better immunity against narrowband interferences.

Hybrid beamforming for interference mitigation in MIMO radar

Abstract:

Hybrid beamforming for multiple input multiple output (MIMO) radar systems in a jamming environment is investigated. A new hybrid beamforming (HB) technique is proposed to reduce the dimensionality of the covariance matrix and to have a better jamming and interference mitigation capability. HB consists of two stages. The first stage decodes, phase shifts the received signals and adds signals decoded by the same code from different antenna elements. The second stage exploits digital beamforming techniques such as Minimum Variance Distortionless Response (MVDR) or convex optimization beamforming to determine the complex weights using N × N covariance matrix where N is the number of transmitting antennas. Simulation results show that the proposed HB technique can achieve better interference and jamming suppression results in comparison with other radar configurations. In addition, the HB technique has the potential to reduce the complexity of MIMO radar signal processing such as space-time adaptive processing.

Suppression Approach to Main-Beam Deceptive Jamming in FDA-MIMO Radar Using Nonhomogeneous Sample Detection

Abstract:

Suppressing the main-beam deceptive jamming in traditional radar systems is challenging. Furthermore, the observations corrupted by false targets generated by smart deceptive jammers, which are not independent and identically distributed because of the pseudo-random time delay. This in turn complicates the task of jamming suppression. In this paper, a new main-beam deceptive jamming suppression approach is proposed, using nonhomogeneous sample detection in the frequency diverse array-multiple-input and multiple-output radar with non-perfectly orthogonal waveforms. First, according to the time delay or range difference, the true and false targets are discriminated in the joint transmit–receive spatial frequency domain. Subsequently, due to the range mismatch, the false targets are suppressed through a transmit–receive 2-D matched filter. In particular, in order to obtain the jamming-plus-noise covariance matrix with high accuracy, a nonhomogeneous sample detection method is developed. Simulation results are provided to demonstrate the detection performance of the proposed approach.

Computationally effective spectral MUSIC algorithm for monostatic MIMO radar using real polynomial rooting

Abstract:

A computationally effective real-valued variant of multiple signal classification (MUSIC) algorithm for monostatic multiple-input multiple-output (MIMO) radar is presented. Reduced-dimension transformation is utilized to reduce the dimension of the received data matrix at first, and then the unitary transformation is employed to transform the complex covariance matrix of the received data into a real-valued one. To further reduce the computational complexity, a real polynomial rooting technique is presented to determine the local maxima of the MUSIC spectrum that corresponding to the DOAs of the targets instead of the computationally-expensive spectrum search. Simulations results demonstrate that the presented algorithm can greatly reduce the computational complexity without sacrificing the estimation accuracy.

Efficient polar coded spatial multiplexing

Abstract:

This paper explores the design of efficient capacity achieving polar codes for multiple input multiple output (MIMO) channels and schemes for polar coded spatial multiplexing (PCSM). For polar code construction, the singular value decomposition (SVD) of a given MIMO channel into multiple independent single input single output (SISO) channels is considered as the first step of natural polarization. Firstly, we propose a basic PCSM scheme by constructing a polar code for each independent SISO channel. Then, we extend the scheme by using compound polar codes to construct a unified PCSM scheme for MIMO channels. Further, we present a novel approach for constructing an optimal compound polar codes which minimize block error rate (BLER) for a given NR× NTMIMO channel. Simulation results reveal that the extended schemes achieve at least 1.5 dB gain in terms of BLER with lesser computational complexity as compared to the basic scheme.

A Joint Rate and Buffer Control Scheme for Video Transmission over LTE Wireless Networks

Abstract:

In wireless communication systems, the quality of time-varying wireless channels and limited resources, make video transmission very challenging. In order to play video frequently, this paper proposes a novel method of QoE (Quality of Experience)-aware video transmission optimization algorithm over LTE networks by jointly controlling the transmission rate and playback buffer management to reduce the probability of video playback interruptions and adapt to constantly changing network status effectively. In order to calculate QoE more accurately and meet user’s requirements, this paper also proposes an improved QoE calculation model based on ITU-TP.1201, which considers video bitrate, playback interruption duration, number of playback interruptions, buffer overflow duration, and number of buffer overflows. The experimental results demonstrate that the proposed method can reduce the probability of video playback interruptions and video frame skipping under the finite resource constraints and varying network status more effectively compared with an existing algorithm, thus improving the QoE of video streaming.

Performance analysis of PDSCH downlink & inter-cell interferece parameters in LTE network

Abstract:

The expanding interest for mobile information activity brings new difficulties on cell networks as far as expanded information throughput. With this advances in the cell systems, which presents Long Term Evolution (LTE), the rearranged design utilizes a less number of nodes in the client plane. LTE Downlink transmission is dissected by LTE transceiver. Simulation is introduced in Physical Downlink Shared Channel (PDSCH). Estimations of Simulation result throughput for various numbers of edges and SNR values are calculated. Compelling use of dense spectrum reuse may increment Inter cell interference, which thus extremely restricts limit of clients in framework. It can confine general framework execution as far as throughput, particularly for the clients situated at the cell edge territory. Consequently, cautious administration of inter cell interference noticeably pivotal to enhance LTE performance.

Estimation of transmit-antenna number with different space–frequency transmission schemes for MIMO-OFDM systems

Abstract:

A hypothesis testing based algorithm is proposed to estimate the transmit-antenna number with different space-frequency transmission schemes for multiple-input multiple-output orthogonal frequency division multiplexing (MIMO-OFDM) systems. The ranks of received sample covariance matrices composed by every two adjacent subcarriers can be estimated by utilising the statistical property of the largest noise eigenvalue. With a series of the estimated values of the ranks, the number of transmit antennas is determined by a decision mechanism, which is designed based on the frequencies of the rank values. Simulations demonstrate that the proposed algorithm performs well without the prior knowledge of the space-frequency transmission scheme.

Large random matrix-based channel estimation for massive MIMO-OFDM uplink

Abstract:

This study investigates the benefits offered by random matrix theory (RMT) towards the design of reliable channel estimation algorithms for a multi-user massive multiple-input multiple-out (MIMO)-orthogonal frequency-division multiplexing uplink. Assuming no a priori knowledge of channel statistics (KCS) at the massive base station, the authors propose RMT-aided minimum mean square estimation (MMSE) and RMT-aided sparse Bayesian learning (SBL) approaches for massive channel estimation. These approaches render efficient channel estimates, as illustrated through mean square error (MSE) performance, extracted via Monte-Carlo simulations. The results also show that with increasing antennas at the base station, MSE from the RMT-aided MMSE approach decreases, suggesting its aptness to massive MIMO systems. To further enhance the MSE performance, the MMSE and SBL estimated channel impulse responses are pruned using threshold computed from RMT analysis. The authors characterise MSE degradation due to the randomness in the threshold, with the help of the Marcenko-Pastur law-based non-asymptotic framework and concentration inequalities. Analysis results show that, for channels with approximate sparse common support, this MSE degradation is quite insignificant. Altogether, the study demonstrates that RMT analysis is competent in improving channel estimation at a massive MIMO system, when a priori KCS is completely unavailable.

Time domain cyclic selective mapping for PAPR reduction in MIMO-OFDM systems

Abstract:

Peak-to-average power ratio (PAPR) is one of the main impairments in multiple-input multiple-output (MIMO) orthogonal frequency-division multiplexing (OFDM) systems. Large PAPR causes inefficiency in the power amplifier (PA) so that the energy consumption of the devices increases. Selective mapping (SLM) has been commonly used as the favorable PAPR reduction technique. Conventional SLM technique has relatively high complexity due to the use of some inverse discrete Fourier transform (IDFT) operations. In addition, it requires to transmit side information (SI) to the receiver. In this paper, we examine the performance of the low complexity time domain cyclic SLM (TD-C-SLM) in MIMO-OFDM systems. TD-C-SLM generates the signal candidates by summing the original OFDM signal and its cyclically shifted version. The signal candidate with the lowest PAPR will be transmitted. This technique requires no SI transmission. Simulation results show that up to 2 dB PAPR reduction can be achieved without increasing the out-of-band (OOB) spectrum by using the TD-C-SLM.

Performance evaluations of software-defined acoustic MIMO-OFDM transmission

Abstract:

In recent years, the system using acoustic communication is increasing. However, because acoustic communication uses low frequency, transmission rate is lower than radio wave communication. In wireless communication, MIMO-OFDM is proposed for improvement quality and transmission rate. In this paper, we introduce a software-defined acoustic communication platform by using MATLAB and implement acoustic MIMO-OFDM transmission into the platform. Also, we evaluate BER characteristics in various experimental parameters in MATLAB simulation and real environment. Moreover, we evaluate image quality in actual acoustic image transmission by using the acoustic communication platform and we can successfully transmit the image via acoustic MIMO-OFDM.

Channel Estimation in MIMO – OFDM Systems based on a new adaptive greedy algorithm

Abstract:

Channel estimation methods based on Compressed Sensing (CS) can be used to obtain channel state information of MIMO-OFDM system effectively. This paper proposes a new adaptive matching pursuit (NAMP) algorithm and the evaluation prototype based on LTE-Advanced wireless channel model. First, NAMP does not need the priori-knowledge of the sparsity level. Second, the fixed step size is determined in order to improve the efficiency of signal reconstruction. Third, a Singular Entropy order determination mechanism is employed to prevent the less relevant atoms from being introduced. Finally, Simulation results are discussed in detail, which demonstrate that the proposed method expenses smaller computational complexity, especially achieves more stable performance.

Structured compressed sensing-based time-frequency joint channel estimation for MIMO-OFDM systems

Abstract:

This paper proposes a time-frequency joint channel estimation method based on structured compression sensing (SCS) for multi-input and multi-output orthogonal frequency division multiplexing (MIMO-OFDM) system, which is different from traditional channel estimation scheme. In the proposed method, the received time-domain training sequences (TSs) without interference cancellation are exploited to obtain the coarse MIMO channel estimation of the path delays. By utilizing structured compression sensing method, furthermore a priori information-assisted adaptive structured subspace pursuit (PA-ASSP) algorithm which adopts a small amount of frequency domain orthogonal pilots is proposed to reconstruct the channel impulse response (CIR) of the MIMO channel so that the accurate channel gains is obtained. The simulation results show that the proposed scheme can more accurately estimate the channel with fewer pilots, and its performance is closer to the least squares (LS) algorithm.

Compressive sensing based channel estimation for MIMO-OFDM systems

Abstract:

In this paper, an adaptive structured-generalized orthogonal matching pursuit (AS-gOMP) algorithm is proposed for time domain channel estimation by utilizing the characteristics of multiple-input multiple-output orthogonal frequency division multiplexing (MIMO-OFDM) system. This algorithm uses the properties of the PN sequence to obtain partial channel prior information firstly, then the remaining support sets are obtained by the improved generalized orthogonal matching pursuit (gOMP) algorithm in MIMO system. A good channel estimation result is achieved by exploiting the characteristics of PN sequence and the common sparsity in spatial and time domain. The simulation results show that the proposed method can reduce the bit error rate (BER) of channel estimation and improve the performance of the MIMO-OFDM system.

RECENT PAPERS