Showing papers in "Computers in Biology and Medicine in 2022"

TL;DR: A comprehensive and systematic review and analysis of medical image augmentation work are carried out, and its research status and development prospects are reviewed in this paper , which mainly collected by ELSEVIER, IEEE Xplore, and Springer from 2018 to 2021.

TL;DR: A comprehensive review of the use of ML in the medical field highlighting standard technologies and how they affect medical diagnosis is provided in this article , where five major medical applications are deeply discussed, focusing on adapting the ML models to solve the problems in cancer, medical chemistry, brain, medical imaging, and wearable sensors.

TL;DR: Wang et al. as mentioned in this paper presented a new multilevel image segmentation method based on the swarm intelligence algorithm (SIA) to enhance the segmentation of COVID-19 X-rays.

TL;DR: Wang et al. as mentioned in this paper proposed a multilevel thresholding image segmentation (MTIS) method based on an enhanced multiverse optimizer (CCMVO), which has a more assertive global search ability and can jump out of the local optimum in optimization.

TL;DR: Zhang et al. as mentioned in this paper used neutrosophic theory to enhance the quality of specular reflections detection in the colonoscopy images, and introduced two level short connections into the saliency detection network, aiming to take advantage of the multi-level and multi-scale features extracted from different stages of the network.

TL;DR: In this article , the authors proposed an effective confidential management solution on the cloud, whose basic idea is to deploy a trusted local server between the untrusted cloud and each trusted client of a medical information management system, responsible for running an EMR cloud hierarchical storage model and an eMR cloud segmentation query model.

TL;DR: In this paper , the authors conducted a comprehensive bioinformatic analysis using public single-cell RNA sequencing datasets to understand the mechanism by which SARS-CoV-2 invades human cells and reveal organ-specific susceptible cell types for COVID-19.

TL;DR: Wang et al. as discussed by the authors proposed an enhanced whale optimization algorithm named E-WOA using a pooling mechanism and three effective search strategies named migrating, preferential selecting, and enriched encircling prey.

TL;DR: In this article , the currently available deep learning methods that are used to detect coronavirus infection in lung images are surveyed, including transfer learning and fine-tuning, novel architectures, and other approaches.

TL;DR: In this paper , the authors identify nine different interpretability methods that have been used for understanding deep learning models for medical image analysis applications based on the type of generated explanations and technical similarities.

TL;DR: In this article , a compendious review of different medical imaging modalities and evaluation of related multimodal databases along with the statistical results is provided, and the quality assessments fusion metrics are also encapsulated in this article.

TL;DR: In this paper , a classification method for computed tomography chest images in the COVID-19 Radiography Database using features extracted by popular Convolutional Neural Networks (CNN) models was presented, and the determination of hyperparameters of Machine Learning (ML) algorithms by Bayesian optimization, and ANN-based image segmentation are the two main contributions.

TL;DR: Wang et al. as discussed by the authors proposed a texture-constrained multichannel progressive generative adversarial network (TMP-GAN), which uses joint training of multiple channels to avoid the typical shortcomings of the current generation methods.

TL;DR: Wang et al. as discussed by the authors proposed a weakly supervised segmentation neural network approach based on a dual branch soft erase module that expands the foreground response region while constraining the erroneous expansion of the foreground region by the enhancement of background features.

TL;DR: In this article , a stochastic epidemic model consisting of four human classes is reformulated and a unique positive solution to the proposed model is established, and a stationary distribution under several conditions is obtained by incorporating stochastically Lyapunov function.

TL;DR: Wang et al. as discussed by the authors constructed a new intelligent diagnostic rule that is accurate, fast, noninvasive, and cost-effective, distinguishing between complicated and uncomplicated appendicitis.

TL;DR: In this paper , a new parameter optimization strategy based on a disperse foraging sine cosine algorithm (DFSCA) is proposed, which is utilized to force some portions of search agents to explore other potential regions.

TL;DR: In this article , transfer learning and bottleneck feature extraction were used for detecting COVID-19 from audio recordings of cough, breath, and speech, and the results showed that a Resnet50 classifier trained by this transfer learning process delivered optimal or near-optimal performance across all datasets achieving areas under the receiver operating characteristic (ROC AUC) of 0.98, 0.94 and 0.92 respectively for all three sound classes: coughs, breaths and speech.

TL;DR: In this article , a number of significant research publications on the DL-based classification of COVID-19 through CXR and CT images are summarized and reviewed, and an outline of the current state-of-the-art advances and a critical discussion of open challenges are presented.

TL;DR: In this paper , a fractional order pandemic model was developed to examine the spread of COVID-19 and its relationship with diabetes, and the existence and uniqueness of solution were examined by using the fixed point theory.

TL;DR: In this article , a Bayesian optimization-based convolutional neural network (CNN) model was proposed for the recognition of chest X-ray images of COVID-19 artefacts in real world situations.

TL;DR: A comprehensive overview of studies conducted on the automated diagnosis of SZ using MRI modalities is presented in this article , where an AI-based computer aided-diagnosis system (CADS) for SZ diagnosis and its relevant sections are presented.

TL;DR: Wang et al. as discussed by the authors proposed a cross-stage partial network (CSPNet) for real-time and high-performance automatic polyp detection and applied the proposed methods on the recently published novel datasets, which are SUN polyp database and the PICCOLO database.

TL;DR: Wang et al. as mentioned in this paper proposed an improved ABC (CCABC) based on a horizontal search mechanism and a vertical search mechanism to improve the algorithm's performance and also presented a multilevel thresholding image segmentation (MTIS) method based on CCABC to enhance the effectiveness of the multi-level thresholding approach.

TL;DR: In this paper , a prediction framework that is based on an improved binary Harris hawk optimization (HHO) algorithm in combination with a kernel extreme learning machine is proposed in order to accurately determine the factors that play a decisive role in the early recognition and discrimination of COVID-19 severity.

TL;DR: Wang et al. as mentioned in this paper proposed a new pipeline called ECG-BiCoNet to investigate the potential of using ECG data for diagnosing COVID-19, which employs five deep learning models of distinct structural design.

TL;DR: In this article , a two-stage feature ensemble of deep convolutional neural networks (CNN) is proposed for precise and automatic classification of brain tumors, which achieved an average accuracy of 99.13%.

TL;DR: Wang et al. as discussed by the authors proposed a secure health monitoring system in healthcare 5.0 by utilizing a blockchain technology and Intrusion Detection System (IDS) to detect any malicious activity in a healthcare network and enable physicians to monitor patients through medical sensors and take necessary measures periodically by predicting diseases.

TL;DR: In this article , a two-step methodology for the robust classification of leukocytes for leukemia diagnosis by building a VGG16-adapted fine-tuned feature-extractor model, termed as "LeuFeatx", was presented.

TL;DR: Wang et al. as discussed by the authors proposed a novel transformer-based deep learning neural network, ECG DETR, which performs arrhythmia detection on continuous single-lead ECG segments simultaneously predicts the positions and categories of all the heartbeats within an ECG segment.