Showing papers in "Biocybernetics and Biomedical Engineering in 2021"

TL;DR: In this article, the authors compared deep learning-based feature extraction frameworks for automatic COVID-19 classification, and found that the DenseNet121 feature extractor with Bagging tree classifier achieved the best performance with 99% classification accuracy.

TL;DR: It is suggested that intelligible machine learning models can enhance symptom-based referral of pneumonia in LRS and in community settings.

TL;DR: An epileptic seizure prediction method that predicts the preictal state before the seizure onset using electroencephalogram (EEG) monitoring of brain activity is proposed and results obtained have been compared with recent state-of-the-art epilepsy prediction methods.

TL;DR: Transfer Learning approach, based on VGG16 and ResNet50 architectures, has been used to develop an algorithm to detect COVID-19 from CT scan images consisting of Healthy (Normal), CO VID-19, and Pneumonia categories and results show that the proposed model achieves superior performance and can be used for automated detection ofCOVID- 19 from CT scans.

TL;DR: The investigated ensemble classification methods exhibited a promising performance for detecting a wide range of respiratory disease conditions and the data fusion approach provides a promising insight into an alternative and more suitable solution to reduce the effect of imbalanced data for clinical applications in general and respiratory sound analysis studies in specific.

TL;DR: An improved RR interval-based cardiac arrhythmia classification approach that is significantly better and more accurate than the other classifiers used in this method.

TL;DR: A feature, named energy direction features based on empirical mode decomposition (EDF-EMD), is proposed to show the different characteristics of voice signals between PD patients and healthy subjects, and shows the best average resulting accuracy.

TL;DR: In this article, a robust deep learning-based system is proposed to detect the COVID-19 using chest X-ray images, which can reduce the workload of radiologists by classifying thousands of images on a single click to generate a probabilistic report in real-time.

TL;DR: A review of the recent application of AI-based computer-aided diagnostic (CAD) systems on AD and its stages, with a particular focus on the use of structural MRI due to its cost effectiveness and lack of ionizing radiation can be found in this article.

TL;DR: The proposed algorithm provides a deep learning segmentation procedure that can segment tumors in BUS images effectively and efficiently.

TL;DR: In this paper, a novel FractalCovNet architecture using Fractal blocks and U-Net was developed for segmentation of chest CT-scan images to localize the lesion region.

TL;DR: An automated tunable Q wavelet transform (A-TQWT) is proposed for automatic decomposition of EEG signals to develop an automated model that effectively classify HC subjects from PD patients with and without medication.

TL;DR: An original and novel Automated Skin-Melanoma Detection (ASMD) system with Melanoma-Index (MI), which incorporates image pre-processing, Bi-dimensional Empirical Mode Decomposition (BEMD), image texture enhancement, entropy and energy feature mining, as well as binary classification.

TL;DR: The experimental results demonstrated that this exoskeleton has good potential to reduce physical workload and increase endurance time during industrial assembly tasks.

TL;DR: This paper attempts to give an extensive outline of the advancement in methodologies to eliminate one of the most common artifacts, i.e., ocular artifact, from EEG signal with a validated simulation model on the recorded EEG signal.

TL;DR: An automatic recognition algorithm to identify hand movements using sEMG signals using Fourier intrinsic band functions using the Fourier decomposition method based on Fourier theory, which makes it suitable for real-time implementation due to low computational complexity.

TL;DR: In this study, binary classification of brain tumors and normal brain tissue with pseudo-brain tumors is achieved via deep neural networks using MRS data and it is confirmed that the proposed LSTM-based stacked method is successful in detecting pseudo brain tumors using M RS signals.

TL;DR: Proposed ensemble of TL strategy of pre-trained CNN models based on WT images obtained from EEG signal can be used for antidepressants treatment outcome prediction with a high accuracy.

TL;DR: A novel approach is developed for the identification of glaucoma using a segmentation based approach on the optic disc and optic cup using a custom UNET++ model, able to achieve state-of-art results for Intersection over Union (IOU) scores and improvement in training time.

TL;DR: The outcomes of this study indicate that the proposed articulatory features of Hilbert cepstral coefficients are suitable and accurate for PD assessment.

TL;DR: This paper aims to summarise the applications of AI in the field of Emergency Medicine by reviewing recent developments in Emergency Department operations and in the clinical management of patients.

TL;DR: The paper proposes a generalised ECG framework and provides implementation challenges and open research directions that should be considered when developing such devices for proper management of CVDs.

TL;DR: In this article, a modified residual neural network-based method for breast cancer detection using histopathology images was proposed, which provides good performance over varying magnification factors of 40X, 100X, 200X and 400X.

TL;DR: A novel deep convolutional encoder-decoder network for microaneurysm detection is designed to locate the MAs by the differences between the skip connection in the network, and an activation function with a long tail is used to produce an accurate probability map for MA detection.

TL;DR: Experimental outcomes indicate that the optimal channel selected by the harmony search algorithm has biological inference related to the alcoholic subject.

TL;DR: Although deep learning has demonstrated potential for analyzing thyroid nodules’ ultrasound images, this review highlights several existing barriers that need to be addressed in future works such as dealing with data limitation, generating public and valid datasets, and determining standard evaluation metrics.

TL;DR: In this article, a deep learning methodology is proposed to address the challenge of the automatic characterisation of Solitary Pulmonary Nodules (SPN) detected in CT scans, which is based on Convolutional Neural Networks, which have proven to be excellent automatic feature extractors for medical images.

TL;DR: A novel method for the automated binary classification of heart sound signals using the Fano-factor constrained tunable quality wavelet transform (TQWT) technique, which can be used in digital stethoscopes to automatically detect abnormal heart sounds and aid the clinicians in their diagnosis.

TL;DR: Computer analysis of the image echogenicity of the median nerve presented confidence levels comparable to trusted evaluation techniques and is a promising tool for assessing the nerve’s status in CTS as approach of the CTS assessment free from subjectivity of examiner.

TL;DR: The proposed tensor decomposition deciphers the higher-order interrelations among the considered clinical covariates for early prediction of sepsis and the results obtained are on par with existing state-of-the-art performances.