Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
4.7
2.8
Journals
Computers
Special Issues
Advanced Methods for Information Extraction in Medicine and Space Biology
share announcement

Advanced Methods for Information Extraction in Medicine and Space Biology

A special issue of Computers (ISSN 2073-431X).

Deadline for manuscript submissions: closed (31 December 2021) | Viewed by 9465

Special Issue Editor

Dr. Vidya Manian

E-Mail Website
Guest Editor
Department of Electrical and Computer Engineering & Bioengineering, University of Puerto Rico, Mayaguez, PR 00680, USA
Interests: gene data mining; neuroimaging; EEG; fMRI signal processing; brain–machine interface system using machine learning and artificial intelligence; remote sensing; multisensor data and image analysis

Special Issue Information

Dear Colleagues,

In the past decades, each disease was considered individually, diagnosed, and treated as a separate entity. Omics data are now available from high-throughput biochemical assays that comprehensively and simultaneously measure molecules of the same type from a biological sample. These data include genomics which profiles DNA, transcriptomics which measures transcripts, proteomics, and metabolomics which quantifies proteins and metabolites. The ability to simultaneously process multiple omics big data has paved the way for advanced research in the field of disease diagnosis and drug discovery. There are computational tools available today for multi-omics data integration for the identification of new correlations in the data, leading to the generation of novel hypotheses. Emerging diseases such as COVID-19 have accelerated research in the field of multi-omics data integration. Advanced information extraction methods are being implemented for early diagnosis of diseases, identification of novel pathways for disease progress, treatment options, and rapid drug repurposing. In a way, the explosion of new information extraction methods and algorithms has benefitted medical research. The computational power of supercomputers is being exploited to mine big data, paving the way for the application of new intensive multilevel, multisensor data fusion, and information extraction techniques to prevalent and existing disease conditions, as well as comorbidities. 

This Special Issue will be a venue to publish big-data fusion, information extraction, and classification methods applied to a plethora of big data sets acquired from multi-omics technologies, neuroimaging, satellite remote sensing, and space biology experiments. We invite authors to publish genome to phenome analysis in molecular and space biology, and correlations of genetic findings with outputs from morphological image analysis methods applied to the biomedical field for diagnosis, treatment, and drug repurposing for major disorders such as diabetes, muscle atrophy, heart and lung diseases, and neurological disorders. Large amounts of data are being made available from space and terrestrial next-generation genome sequencing and genome-wide analysis systems, which provide breakthrough and cutting-edge research results to combat novel genetic variants of existing diseases. Radiation studies in low Earth orbit and deep space experiments and their correlations with disease conditions are gaining importance as space radiation studies open up new options for cancer treatment on the ground. New trends and applications of machine learning including very deep networks and artificial intelligence in various fields of research will be considered for publication in this Special Issue. Bayesian inferencing methods with uncertainty modeling, Markov and Monte Carlo methods, transfer and reinforcement learning, multiagent modeling, and hybrid modeling are some of the topics in which we encourage the research community to publish their manuscripts in this Special Issue.

Dr. Vidya Manian
Guest Editor

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Computers is an international peer-reviewed open access monthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 1800 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Keywords

  • Multiomics data integration/genomics/proteomics/metabolomics/transcriptomics
  • Computational models/network analysis/network similarity/community detection/disease networks/drug discovery/drug repurposing
  • Fundamental artificial intelligence based methods for large scale biological data analysis/reliable methods integrating prior knowledge and uncertainty
  • Epigenetics/genome to phenome analysis/viral load/miRNA/DNA methylation
  • Space biology/radiation/microgravity/muscle atrophy/myostatin/drug treatment/counter measures/space and ground experiments with mice and humans
  • Health/cancer treatment/human orthologs/DNA repair
  • Neuroimaging/EEG signal processing/fMRI/CT/PET/image segmentation/early detection of neurological disorders/brain connectivity/brain networks
  • Brain–machine interfaces/steady-state visual evoked potentials/motor imagery/event-related potentials/pathspeller brain–computer interfaces/multiagent systems/sensory motor rehabilitation/brain stimulation
  • Central nervous system/dementia/Alzheimer’s/epilepsy detection/emotional/psychological behavioral studies
  • Environment and health/satellite remote sensing/seasonal variation/climate change
  • Satellite image processing/air quality/water quality/atmospheric aerosols/temperatures/water stress/vegetation/land use and land cover/coral reef mapping

Published Papers (3 papers)

Download All Papers
Order results
Result details
Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:

Research

23 pages, 10070 KiB  
Article
Uncertainty-Aware Deep Learning-Based Cardiac Arrhythmias Classification Model of Electrocardiogram Signals
by Ahmad O. Aseeri
Computers 2021, 10(6), 82; https://doi.org/10.3390/computers10060082 - 17 Jun 2021
Cited by 14 | Viewed by 2817
Abstract
Deep Learning-based methods have emerged to be one of the most effective and practical solutions in a wide range of medical problems, including the diagnosis of cardiac arrhythmias. A critical step to a precocious diagnosis in many heart dysfunctions diseases starts with the [...] Read more.
Deep Learning-based methods have emerged to be one of the most effective and practical solutions in a wide range of medical problems, including the diagnosis of cardiac arrhythmias. A critical step to a precocious diagnosis in many heart dysfunctions diseases starts with the accurate detection and classification of cardiac arrhythmias, which can be achieved via electrocardiograms (ECGs). Motivated by the desire to enhance conventional clinical methods in diagnosing cardiac arrhythmias, we introduce an uncertainty-aware deep learning-based predictive model design for accurate large-scale classification of cardiac arrhythmias successfully trained and evaluated using three benchmark medical datasets. In addition, considering that the quantification of uncertainty estimates is vital for clinical decision-making, our method incorporates a probabilistic approach to capture the model’s uncertainty using a Bayesian-based approximation method without introducing additional parameters or significant changes to the network’s architecture. Although many arrhythmias classification solutions with various ECG feature engineering techniques have been reported in the literature, the introduced AI-based probabilistic-enabled method in this paper outperforms the results of existing methods in outstanding multiclass classification results that manifest F1 scores of 98.62% and 96.73% with (MIT-BIH) dataset of 20 annotations, and 99.23% and 96.94% with (INCART) dataset of eight annotations, and 97.25% and 96.73% with (BIDMC) dataset of six annotations, for the deep ensemble and probabilistic mode, respectively. We demonstrate our method’s high-performing and statistical reliability results in numerical experiments on the language modeling using the gating mechanism of Recurrent Neural Networks. Full article
(This article belongs to the Special Issue Advanced Methods for Information Extraction in Medicine and Space Biology)
►▼ Show Figures

Figure 1

17 pages, 5943 KiB  
Article
Spatial Low-Rank Tensor Factorization and Unmixing of Hyperspectral Images
by William Navas-Auger and Vidya Manian
Computers 2021, 10(6), 78; https://doi.org/10.3390/computers10060078 - 11 Jun 2021
Cited by 2 | Viewed by 2534
Abstract
This work presents a method for hyperspectral image unmixing based on non-negative tensor factorization. While traditional approaches may process spectral information without regard for spatial structures in the dataset, tensor factorization preserves the spectral-spatial relationship which we intend to exploit. We used a [...] Read more.
This work presents a method for hyperspectral image unmixing based on non-negative tensor factorization. While traditional approaches may process spectral information without regard for spatial structures in the dataset, tensor factorization preserves the spectral-spatial relationship which we intend to exploit. We used a rank-(L, L, 1) decomposition, which approximates the original tensor as a sum of R components. Each component is a tensor resulting from the multiplication of a low-rank spatial representation and a spectral vector. Our approach uses spatial factors to identify high abundance areas where pure pixels (endmembers) may lie. Unmixing is done by applying Fully Constrained Least Squares such that abundance maps are produced for each inferred endmember. The results of this method are compared against other approaches based on non-negative matrix and tensor factorization. We observed a significant reduction of spectral angle distance for extracted endmembers and equal or better RMSE for abundance maps as compared with existing benchmarks. Full article
(This article belongs to the Special Issue Advanced Methods for Information Extraction in Medicine and Space Biology)
►▼ Show Figures

Figure 1

26 pages, 3769 KiB  
Article
Network Analysis of Local Gene Regulators in Arabidopsis thaliana under Spaceflight Stress
by Vidya Manian, Harshini Gangapuram, Jairo Orozco, Heeralal Janwa and Carlos Agrinsoni
Computers 2021, 10(2), 18; https://doi.org/10.3390/computers10020018 - 28 Jan 2021
Cited by 4 | Viewed by 3515
Abstract
Spaceflight microgravity affects normal plant growth in several ways. The transcriptional dataset of the plant model organism Arabidopsis thaliana grown in the international space station is mined using graph-theoretic network analysis approaches to identify significant gene transcriptions in microgravity essential for the plant’s [...] Read more.
Spaceflight microgravity affects normal plant growth in several ways. The transcriptional dataset of the plant model organism Arabidopsis thaliana grown in the international space station is mined using graph-theoretic network analysis approaches to identify significant gene transcriptions in microgravity essential for the plant’s survival and growth in altered environments. The photosynthesis process is critical for the survival of the plants in spaceflight under different environmentally stressful conditions such as lower levels of gravity, lesser oxygen availability, low atmospheric pressure, and the presence of cosmic radiation. Lasso regression method is used for gene regulatory network inferencing from gene expressions of four different ecotypes of Arabidopsis in spaceflight microgravity related to the photosynthetic process. The individual behavior of hub-genes and stress response genes in the photosynthetic process and their impact on the whole network is analyzed. Logistic regression on centrality measures computed from the networks, including average shortest path, betweenness centrality, closeness centrality, and eccentricity, and the HITS algorithm is used to rank genes and identify interactor or target genes from the networks. Through the hub and authority gene interactions, several biological processes associated with photosynthesis and carbon fixation genes are identified. The altered conditions in spaceflight have made all the ecotypes of Arabidopsis sensitive to dehydration-and-salt stress. The oxidative and heat-shock stress-response genes regulate the photosynthesis genes that are involved in the oxidation-reduction process in spaceflight microgravity, enabling the plant to adapt successfully to the spaceflight environment. Full article
(This article belongs to the Special Issue Advanced Methods for Information Extraction in Medicine and Space Biology)
►▼ Show Figures

Figure 1

Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:
 
Displaying articles 1-3
Back to TopTop