arXiv subjects

Md. Kamrul Hasan

Publications and source records attributed to Md. Kamrul Hasan.

47 records · Page 3Linked to original sources

arXiv2019

Emotion Recognition with Forearm-based Electromyography

Electromyography is an unexplored field of study when it comes to alternate input modality while interacting with a computer. However, to make computers understand human emotions is pivotal in the area of human-computer interaction and in assistive technology. Traditional input devices used currently have limitations and restrictions when it comes to express human emotions. The applications regarding computers and emotions are vast. In this paper we analyze EMG signals recorded from a low cost MyoSensor and classify them into two classes - Relaxed and Angry. In order to perform this classification we have created a dataset collected from 10 users, extracted 8 significant features and classified them using Support Vector Machine algorithm. We show uniquely that forearm-based EMG signal can express emotions. Experimental results show an accuracy of 88.1% after 300 iterations.This shows significant opportunities in various fields of computer science such as gaming and e-learning tools where EMG signals can be used to detect human emotions and make the system provide feedback based on it. We discuss further applications of the method that seeks to expand the range of human-computer interaction beyond the button box.

cs.HC↗

arXiv2019

Classification of Breast Lesions Using Quantitative Ultrasound Biomarkers

Quantitative ultrasound (QUS) based parameters like the effective scatterer diameter (ESD) and mean scatterer spacing (MSS) are gaining attention recently as non-invasive biomarkers for soft tissue characterization. In this work, we propose a multiple QUS parameter based technique that employs ESD and MSS, for binary classification of breast lesions. In order to produce improved ESD estimates, we propose a modified frequency domain technique for ESD estimation of breast tissues from the diffuse component of backscattered radio-frequency (RF) data. Ensemble empirical mode decomposition (EEMD) is performed to separate the diffuse component from the coherent component by decomposing the RF data into their intrinsic mode functions (IMFs). A non-parametric Kolmogorov-Smirnov (K-S) test is employed for automatic IMF selection along with a multi-step system effect minimization process. The ESD is estimated using a nearest neighborhood average regression line fitting algorithm. Furthermore, we use an ameliorated EEMD domain autoregressive (AR) spectral estimation technique for MSS estimation. On using the ESD for binary classification of 159 lesions, we obtain high sensitivity, specificity, accuracy values of 91.07%, 96.12%, and 94.34%, respectively, with an area under the receiver operating characteristics (ROC) curve of 0.94. On combining ESD with MSS we obtain even more improved sensitivity, specificity, and accuracy values of 96.43%, 95.15%, and 95.60%, respectively, with an area under the ROC of 0.96. Such a high classification performance highlights the potential of these QUS parameters to be used as non-invasive biomarkers for breast cancer detection.

eess.SP↗

arXiv2019

Automatic Mass Detection in Breast Using Deep Convolutional Neural Network and SVM Classifier

Mammography is the most widely used gold standard for screening breast cancer, where, mass detection is considered as the prominent step. Detecting mass in the breast is, however, an arduous problem as they usually have large variations between them in terms of shape, size, boundary, and texture. In this literature, the process of mass detection is automated with the use of transfer learning techniques of Deep Convolutional Neural Networks (DCNN). Pre-trained VGG19 network is used to extract features which are then followed by bagged decision tree for features selection and then a Support Vector Machine (SVM) classifier is trained and used for classifying between the mass and non-mass. Area Under ROC Curve (AUC) is chosen as the performance metric, which is then maximized during classifier selection and hyper-parameter tuning. The robustness of the two selected type of classifiers, C-SVM, and \u{psion}-SVM, are investigated with extensive experiments before selecting the best performing classifier. All experiments in this paper were conducted using the INbreast dataset. The best AUC obtained from the experimental results is 0.994 +/- 0.003 i.e. [0.991, 0.997]. Our results conclude that by using pre-trained VGG19 network, high-level distinctive features can be extracted from Mammograms which when used with the proposed SVM classifier is able to robustly distinguish between the mass and non-mass present in breast.

cs.CV↗

arXiv2019

Application of DenseNet in Camera Model Identification and Post-processing Detection

Camera model identification has earned paramount importance in the field of image forensics with an upsurge of digitally altered images which are constantly being shared through websites, media, and social applications. But, the task of identification becomes quite challenging if metadata are absent from the image and/or if the image has been post-processed. In this paper, we present a DenseNet pipeline to solve the problem of identifying the source camera-model of an image. Our approach is to extract patches of 256*256 from a labeled image dataset and apply augmentations, i.e., Empirical Mode Decomposition (EMD). We use this extended dataset to train a Neural Network with the DenseNet-201 architecture. We concatenate the output features for 3 different sizes (64*64, 128*128, 256*256) and pass them to a secondary network to make the final prediction. This strategy proves to be very robust for identifying the source camera model, even when the original image is post-processed. Our model has been trained and tested on the Forensic Camera-Model Identification Dataset provided for the IEEE Signal Processing (SP) Cup 2018. During testing we achieved an overall accuracy of 98.37%, which is the current state-of-the-art on this dataset using a single model. We used transfer learning and tested our model on the Dresden Database for Camera Model Identification, with an overall test accuracy of over 99% for 19 models. In addition, we demonstrate that the proposed pipeline is suitable for other image-forensic classification tasks, such as, detecting the type of post-processing applied to an image with an accuracy of 96.66% -- which indicates the generality of our approach.

eess.IV↗

arXiv2019

Comparative Analysis of Automatic Skin Lesion Segmentation with Two Different Implementations

Lesion segmentation from the surrounding skin is the first task for developing automatic Computer-Aided Diagnosis of skin cancer. Variant features of lesion like uneven distribution of color, irregular shape, border and texture make this task challenging. The contribution of this paper is to present and compare two different approaches to skin lesion segmentation. The first approach uses watershed, while the second approach uses mean-shift. Pre-processing steps were performed in both approaches for removing hair and dark borders of microscopic images. The Evaluation of the proposed approaches was performed using Jaccard Index (Intersection over Union or IoU). An additional contribution of this paper is to present pipelines for performing pre-processing and segmentation applying existing segmentation and morphological algorithms which led to promising results. On average, the first approach showed better performance than the second one with average Jaccard Index over 200 ISIC-2017 challenge images are 89.16% and 76.94% respectively.

cs.CV↗

arXiv2019

Brain Tissue Segmentation Using NeuroNet With Different Pre-processing Techniques

Automatic segmentation of brain Magnetic Resonance Imaging (MRI) images is one of the vital steps for quantitative analysis of brain for further inspection. In this paper, NeuroNet has been adopted to segment the brain tissues (white matter (WM), grey matter (GM) and cerebrospinal fluid (CSF)) which uses Residual Network (ResNet) in encoder and Fully Convolution Network (FCN) in the decoder. To achieve the best performance, various hyper-parameters have been tuned, while, network parameters (kernel and bias) were initialized using the NeuroNet pre-trained model. Different pre-processing pipelines have also been introduced to get a robust trained model. The model has been trained and tested on IBSR18 data-set. To validate the research outcome, performance was measured quantitatively using Dice Similarity Coefficient (DSC) and is reported on average as 0.84 for CSF, 0.94 for GM, and 0.94 for WM. The outcome of the research indicates that for the IBSR18 data-set, pre-processing and proper tuning of hyper-parameters for NeuroNet model have improvement in DSC for the brain tissue segmentation.

cs.CV↗

arXiv2019

SHEAR-net: An End-to-End Deep Learning Approach for Single Push Ultrasound Shear Wave Elasticity Imaging

Ultrasound Shear Wave Elastography (USWE) with conventional B-mode imaging demonstrates better performance in lesion segmentation and classification problems. In this article, we propose SHEAR-net, an end-to-end deep neural network, to reconstruct USWE images from tracked tissue displacement data at different time instants induced by a single acoustic radiation force (ARF) with 100% or 50% of the energy in conventional use. The SHEAR-net consists of a localizer called the S-net to first localize the lesion location and then uses recurrent layers to extract temporal correlations from wave patterns using different time frames, and finally, with an estimator, it reconstructs the shear modulus image from the concatenated outputs of S-net and recurrent layers. The network is trained with 800 simulation and a limited number of CIRS tissue mimicking phantom data and is optimized using a multi-task learning loss function where the tasks are: inclusion localization and modulus estimation. The efficacy of the proposed SHEAR-net is extensively evaluated both qualitatively and quantitatively on 125 test set of motion data obtained from simulation and CIRS phantoms. We show that the proposed approach consistently outperforms the current state-of-the-art method and achieves overall 4-5 dB improvement in PSNR and SNR. In addition, an average gain of 0.15 in DSC and SSIM values indicate that the SHEAR-net has a better inclusion coverage area and structural similarity of the two approaches. The proposed real-time deep learning based technique can accurately estimate shear modulus for a minimum tissue displacement of 0.5$μ$m and image multiple inclusions with a single push ARF.

eess.IV↗

arXiv2018

Cuffless Blood Pressure Estimation from Electrocardiogram and Photoplethysmogram Using Waveform Based ANN-LSTM Network

Goal: Although photoplethysmogram (PPG) and electrocardiogram (ECG) signals can be used to estimate blood pressure (BP) by extracting various features, the changes in morphological contours of both PPG and ECG signals due to various diseases of circulatory system and interaction of other physiological systems make the extraction of such features very difficult. Methods: In this work, we propose a waveform-based hierarchical Artificial Neural Network - Long Short Term Memory (ANN-LSTM) model for BP estimation. The model consists of two hierarchy levels, where the lower hierarchy level uses ANNs to extract necessary morphological features from ECG and PPG waveforms and the upper hierarchy level uses LSTM layers to account for the time domain variation of the features extracted by lower hierarchy level. Results: The proposed model is evaluated on 39 subjects using the Association for the Advancement of Medical Instrumentations (AAMI) standard and the British Hypertension Society (BHS) standard. The method satisfies both the standards in the estimation of systolic blood pressure (SBP) and diastolic blood pressure (DBP). For the proposed network, the mean absolute error (MAE) and the root mean square error (RMSE) for SBP estimation are 1.10 and 1.56 mmHg, respectively, and for DBP estimation are 0.58 and 0.85 mmHg, respectively. Conclusion: The performance of the proposed hierarchical ANN-LSTM model is found to be better than the other feature engineering-based networks. It is shown that the proposed model is able to automatically extract the necessary features and their time domain variations to estimate BP reliably in a noninvasive continuous manner. Significance: The method is expected to greatly facilitate the presently available mobile health-care gadgets in continuous BP estimation.

eess.SP↗

arXiv2018

Quantification of Trabeculae Inside the Heart from MRI Using Fractal Analysis

Left ventricular non-compaction (LVNC) is a rare cardiomyopathy (CMP) that should be considered as a possible diagnosis because of its potential complications which are heart failure, ventricular arrhythmias, and embolic events. For analysis cardiac functionality, extracting information from the Left ventricular (LV) is already a broad field of Medical Imaging. Different algorithms and strategies ranging that is semiautomated or automated has already been developed to get useful information from such a critical structure of heart. Trabeculae in the heart undergoes difference changes like solid from spongy. Due to failure of this process left ventricle non-compaction occurred. In this project, we will demonstrate the fractal dimension (FD) and manual segmentation of the Magnetic Resonance Imaging (MRI) of the heart that quantify amount of trabeculae inside the heart. The greater the value of fractal dimension inside the heart indicates the greater complex pattern of the trabeculae in the heart.

q-bio.QM↗

arXiv2017

Ultrasonic Tissue Reflectivity Function Estimation Using Correlation Constrained Multichannel FLMS Algorithm with Missing RF Data

Poor resolution of ultrasound images due to convolution of the tissue reflectivity function (TRF) with the system point spread function (PSF) is a major issue in medical ultrasound imaging. In this paper, we propose a correlation constrained missing-data estimation based blind multichannel frequency- domain least-mean-squares (md-bMCFLMS) algorithm to undo the effect of PSF on the ultrasound radio-frequency (RF) data. In the first step, a block-based MCFLMS (bMCFLMS) algorithm is proposed to estimate the TRFs and the PSF which are used in the second step to estimate the missing data. This missing data is used in the md-bMCFLMS algorithm to construct a modified cost function for further improvement of the image resolution. To account for the nonstationarity of the PSF, unlike the blocking approach described in the literature, we introduce a time-efficient blocking method in this paper. The blocking approach described here uses a block position independent fixed size matrix and can be implemented parallely. The bMCFLMS algorithm, however, shows misconvergence due to both channel noise and propagation of TRF estimation error from the previous blocks. This phe- nomenon is more intense in the case of md-bMCFLMS algorithm because of increased estimation error. To address this problem, a novel constraint based on the correlation between the measured RF data and estimated TRF is proposed in this paper. The efficacy of our proposed blind deconvolution algorithm is measured using simulation phantom, experimental phantom and in-vivo data.

eess.SP↗

arXiv2013

An Improved ACS Algorithm for the Solutions of Larger TSP Problems

Solving large traveling salesman problem (TSP) in an efficient way is a challenging area for the researchers of computer science. This paper presents a modified version of the ant colony system (ACS) algorithm called Red-Black Ant Colony System (RB-ACS) for the solutions of TSP which is the most prominent member of the combinatorial optimization problem. RB-ACS uses the concept of ant colony system together with the parallel search of genetic algorithm for obtaining the optimal solutions quickly. In this paper, it is shown that the proposed RB-ACS algorithm yields significantly better performance than the existing best-known algorithms.

cs.AI↗