Showing papers in "Biomedical Signal Processing and Control in 2018"

TL;DR: The literature on ECG analysis, mostly from the last decade, is comprehensively reviewed based on all of the major aspects mentioned above.

TL;DR: A deep convolutional neural network is introduced on raw EEG samples for supervised learning of 5-class sleep stage prediction and a method for visualizing class-wise patterns learned by the network is presented.

TL;DR: A new model which is fully specified for automated seizure onset detection and seizure onset prediction based on electroencephalography (EEG) measurements is proposed which could outperform the state-of-the art models.

TL;DR: The current trends in segmentation and classification relevant to tumor infected human brain MR images with a target on gliomas which include astrocytoma are retrospected.

TL;DR: A brief introduction about CT imaging, the characteristics of noise in CT images and the popular methods of CT image denoising are presented and the merits and drawbacks of CT Image Denoising methods are discussed.

TL;DR: A review of the state of art techniques used in computer-aided diagnostic systems for dermoscopy, by giving the domain aspects of melanoma followed by the prominent Techniques used in each of the steps, and presents cognizance to judge the consequentiality of every methodology utilized in the literature.

TL;DR: Qualitative and quantitative study and analysis indicate that the proposed technique can be used as an effective tool for denoising of ECG signals and hence can serve for better diagnostic in computer-based automated medical system.

TL;DR: The results show that the features extracted from multichannel surface EMG signals using DBN method proposed in this paper outperform principal components analysis (PCA), and the root mean square error (RMSE) between the estimated joint angles and calculated ones during human walking is reduced by about 50%.

TL;DR: A novel Multiple-Feature-Branch Convolutional Neural Network (MFB-CNN) is proposed for automated MI detection and localization using ECG, based on deep learning framework, which can achieve a good performance in MI diagnosis.

TL;DR: This topical review divided symmetry measures into four subgroups: symmetry indices, complete gait cycle symmetry measures, statistically-based measures and approaches, and nonlinear measures and raised new questions and recommendations about their development and clinical use.

TL;DR: A minimalistic approach is focused on, in which four gestures are tried to classify with only 2 EMG channels installed on the flexor and extensor muscles of the forearm, showing that misclassification of other gestures as the unlocking never happened for expert users.

TL;DR: The objective of this study is to give the reader a bird's eye view of the biomedical signal processing world with a zoomed-in perspective of feature extraction methodologies which form the basis of machine learning and hence, artificial intelligence.

TL;DR: This paper investigates the use of deep learning network (DLN) to remove OAs in EEG signals and compared the proposed method with the classic independent component analysis (ICA), kurtosis-ICA (K-ICA), Second-order blind identification (SOBI) and a shallow network method.

TL;DR: The bag of visual word approach is used to improve the effectiveness of texture based features, such as gray level co-occurrence matrix (GLCM), scale invariant feature transform, local binary pattern and histogram of gradient in Alzheimer's disease brain images.

TL;DR: Simulation results show that the proposed method provides a better solution to the class imbalance problem in heartbeat classification.

TL;DR: The result suggests that playing the disliked music elicits neither negative emotion nor positive emotion as the changes were noted only at lateral frontal locations and there was an increase in the theta band energy of the frontal midline only for liked music and increased beta component energy was observed only at frontal electrode locations while listening to disliked music.

TL;DR: The promising results demonstrate the excellent performance of the proposed CNNs in simultaneously detecting the centers of both the fovea and OD without human intervention or handcrafted features.

TL;DR: Two feature extraction methods are proposed that have good performance compared to previous methods such as Filter banks and Wavelet transform and the performance of the second method is significantly better than the first.

TL;DR: Various segmentation approaches used by different researchers for optic disc followed by the optic cup and its classification for diagnosis of glaucoma are analyzed to address various research gaps and challenges.

TL;DR: Simulation results validate the better performance of the proposed method for baseline wander (BW) and power line interference (PLI) removal from electrocardiogram (ECG) signals than compared methods at different noise levels.

TL;DR: A novel multi-modality medical image fusion algorithm exploiting a moving frame based decomposition framework (MFDF) and the nonsubsampled shearlet transform (NSST) achieves better performance than other compared state-of-art methods in both visual effects and objective criteria.

TL;DR: Empirical results established that superior performance of the DDS to other related methods the findings of the achieved results can assist dental clinicians in their professional work.

TL;DR: Experimental results show fDistEn can measure the complexity of signals and the scheme is qualified to detect seizure automatically with not less than 98.338% accuracy in all cases and it indicates the effectiveness of the proposed seizure detection scheme.

TL;DR: A method for detecting vessel regions in angiography images is proposed which is based on deep learning approach using convolutional neural networks (CNN) and results show its superiority in extraction of vessels regions in comparison to state of the art methods.

TL;DR: The comparison results of the extensive experiments on clinical X-ray cardiovascular angiogram images further illustrate that the proposed SAID method can yield clearer cardiovascular images which can provide more useful vascular information for clinicians to analyze and diagnose the cardiovascular diseases.

TL;DR: A complete classification system with excellent generalization ability for ECG analysis and the results show that this proposal is a promising alternative and superior to most of the state-of-the-art methods.

TL;DR: This paper proposed the image watermarking algorithm in wavelet transformation (IDWT) using the singular value decomposition (SVD) and particle swarm optimization (PSO) and showed improved performance in terms of imperceptibility and robustness.

TL;DR: A systematic depiction of both feature engineering- and deep learning-based CADe schemes, including the categories of pulmonary nodules, modalities of chest medical imaging, commonly used datasets with nodule annotations, and related publications in recent years are provided.

TL;DR: In this article, a fully computer-aided detection system for speckle reduction and segmentation of nodules from thyroid ultrasound images is presented, which can facilitate the endocrinologists by providing second opinion to improve diagnosis of nodule as benign or malignant.

TL;DR: Relying on depth map images and employing Open CV library, the present research outperformed similar works where color images or such devices as accelerometers were used, attaining sensitivity and specificity of 100% and 97.5%, respectively.