MyMedR

Displaying all 7 publications

Abstract:

Sort:

Fulltext ET-NET: an ensemble of transfer learning models for prediction of COVID-19 infection through chest CT-scan images

Kundu R, Singh PK, Ferrara M, Ahmadian A, Sarkar R

Multimed Tools Appl, 2022;81(1):31-50.
PMID: 34483709 DOI: 10.1007/s11042-021-11319-8

The COVID-19 virus has caused a worldwide pandemic, affecting numerous individuals and accounting for more than a million deaths. The countries of the world had to declare complete lockdown when the coronavirus led to community spread. Although the real-time Polymerase Chain Reaction (RT-PCR) test is the gold-standard test for COVID-19 screening, it is not satisfactorily accurate and sensitive. On the other hand, Computer Tomography (CT) scan images are much more sensitive and can be suitable for COVID-19 detection. To this end, in this paper, we develop a fully automated method for fast COVID-19 screening by using chest CT-scan images employing Deep Learning techniques. For this supervised image classification problem, a bootstrap aggregating or Bagging ensemble of three transfer learning models, namely, Inception v3, ResNet34 and DenseNet201, has been used to boost the performance of the individual models. The proposed framework, called ET-NET, has been evaluated on a publicly available dataset, achieving 97.81 ± 0.53 % accuracy, 97.77 ± 0.58 % precision, 97.81 ± 0.52 % sensitivity and 97.77 ± 0.57 % specificity on 5-fold cross-validation outperforming the state-of-the-art method on the same dataset by 1.56%. The relevant codes for the proposed approach are accessible in: https://github.com/Rohit-Kundu/ET-NET_Covid-Detection.
Fulltext Geographical distribution of soil transmitted helminths and the effects of community type in South Asia and South East Asia - A systematic review

Silver ZA, Kaliappan SP, Samuel P, Venugopal S, Kang G, Sarkar R, et al.

PLoS Negl Trop Dis, 2018 01;12(1):e0006153.
PMID: 29346440 DOI: 10.1371/journal.pntd.0006153

BACKGROUND: Soil-transmitted helminth (STH) infections are among the most prevalent neglected tropical diseases (NTD) worldwide. Since the publication of the WHO road map to combat NTD in 2012, there has been a renewed commitment to control STH. In this study, we analysed the geographical distribution and effect of community type on prevalence of hookworm, Trichuris and Ascaris in south Asia and south east Asia.
METHODOLOGY: We conducted a systematic review of open-access literature published in PubMed Central and the Global Atlas of Helminth Infection. A total of 4182 articles were available and after applying selection criteria, 174 studies from the region were retained for analysis.
PRINCIPAL FINDINGS: Ascaris was the commonest STH identified with an overall prevalence of 18% (95% CI, 14-23%) followed by Trichuris (14%, 9-19%) and hookworm (12%, 9-15%). Hookworm prevalence was highest in Laos, Vietnam and Cambodia. We found a geographical overlap in countries with high prevalence rates for Trichuris and Ascaris (Malaysia, Philippines, Myanmar, Vietnam and Bangladesh). When the effect of community type was examined, prevalence rates of hookworm was comparable in rural (19%, 14-24%) and tribal communities (14%, 10-19%). Tribal communities, however, showed higher prevalence of Trichuris (38%, 18-63%) and Ascaris (32%, 23-43%) than rural communities (13%, 9-20% and 14%, 9-20% respectively). Considerable between and within country heterogeneity in the distribution of STH (I2 >90%) was also noted. When available data from school aged children (SAC) were analysed, prevalence of Ascaris (25% 16-31%) and Trichuris (22%, 14-34%) were higher than among the general population while that of hookworm (10%, 7-16%) was comparable.
CONCLUSIONS/SIGNIFICANCE: Our analysis showed significant variation in prevalence rates between and within countries in the region. Highlighting the importance of community type in prevalence and species mix, we showed that tribal and rural communities had higher hookworm infections than urban communities and for ascariasis and trichuriasis, tribal populations had higher levels of infection than rural populations. We also found a higher prevalence of ascariasis and trichuriasis in SAC compared to the general population but comparable levels of hookworm infections. These key findings need to be taken into account in planning future MDA and other interventions.
Fulltext Retraction Note: GraphCovidNet: A graph neural network based model for detecting COVID-19 from CT scans and X-rays of chest

Saha P, Mukherjee D, Singh PK, Ahmadian A, Ferrara M, Sarkar R

Sci Rep, 2021 11 30;11(1):23451.
PMID: 34848779 DOI: 10.1038/s41598-021-02469-8
Fulltext MRFGRO: a hybrid meta-heuristic feature selection method for screening COVID-19 using deep features

Dey A, Chattopadhyay S, Singh PK, Ahmadian A, Ferrara M, Senu N, et al.

Sci Rep, 2021 Dec 15;11(1):24065.
PMID: 34911977 DOI: 10.1038/s41598-021-02731-z

COVID-19 is a respiratory disease that causes infection in both lungs and the upper respiratory tract. The World Health Organization (WHO) has declared it a global pandemic because of its rapid spread across the globe. The most common way for COVID-19 diagnosis is real-time reverse transcription-polymerase chain reaction (RT-PCR) which takes a significant amount of time to get the result. Computer based medical image analysis is more beneficial for the diagnosis of such disease as it can give better results in less time. Computed Tomography (CT) scans are used to monitor lung diseases including COVID-19. In this work, a hybrid model for COVID-19 detection has developed which has two key stages. In the first stage, we have fine-tuned the parameters of the pre-trained convolutional neural networks (CNNs) to extract some features from the COVID-19 affected lungs. As pre-trained CNNs, we have used two standard CNNs namely, GoogleNet and ResNet18. Then, we have proposed a hybrid meta-heuristic feature selection (FS) algorithm, named as Manta Ray Foraging based Golden Ratio Optimizer (MRFGRO) to select the most significant feature subset. The proposed model is implemented over three publicly available datasets, namely, COVID-CT dataset, SARS-COV-2 dataset, and MOSMED dataset, and attains state-of-the-art classification accuracies of 99.15%, 99.42% and 95.57% respectively. Obtained results confirm that the proposed approach is quite efficient when compared to the local texture descriptors used for COVID-19 detection from chest CT-scan images.
Fulltext Fuzzy rank-based fusion of CNN models using Gompertz function for screening COVID-19 CT-scans

Kundu R, Basak H, Singh PK, Ahmadian A, Ferrara M, Sarkar R

Sci Rep, 2021 Jul 08;11(1):14133.
PMID: 34238992 DOI: 10.1038/s41598-021-93658-y

COVID-19 has crippled the world's healthcare systems, setting back the economy and taking the lives of several people. Although potential vaccines are being tested and supplied around the world, it will take a long time to reach every human being, more so with new variants of the virus emerging, enforcing a lockdown-like situation on parts of the world. Thus, there is a dire need for early and accurate detection of COVID-19 to prevent the spread of the disease, even more. The current gold-standard RT-PCR test is only 71% sensitive and is a laborious test to perform, leading to the incapability of conducting the population-wide screening. To this end, in this paper, we propose an automated COVID-19 detection system that uses CT-scan images of the lungs for classifying the same into COVID and Non-COVID cases. The proposed method applies an ensemble strategy that generates fuzzy ranks of the base classification models using the Gompertz function and fuses the decision scores of the base models adaptively to make the final predictions on the test cases. Three transfer learning-based convolutional neural network models are used, namely VGG-11, Wide ResNet-50-2, and Inception v3, to generate the decision scores to be fused by the proposed ensemble model. The framework has been evaluated on two publicly available chest CT scan datasets achieving state-of-the-art performance, justifying the reliability of the model. The relevant source codes related to the present work is available in: GitHub.
Fulltext GraphCovidNet: A graph neural network based model for detecting COVID-19 from CT scans and X-rays of chest

Saha P, Mukherjee D, Singh PK, Ahmadian A, Ferrara M, Sarkar R

Sci Rep, 2021 04 15;11(1):8304.
PMID: 33859222 DOI: 10.1038/s41598-021-87523-1

COVID-19, a viral infection originated from Wuhan, China has spread across the world and it has currently affected over 115 million people. Although vaccination process has already started, reaching sufficient availability will take time. Considering the impact of this widespread disease, many research attempts have been made by the computer scientists to screen the COVID-19 from Chest X-Rays (CXRs) or Computed Tomography (CT) scans. To this end, we have proposed GraphCovidNet, a Graph Isomorphic Network (GIN) based model which is used to detect COVID-19 from CT-scans and CXRs of the affected patients. Our proposed model only accepts input data in the form of graph as we follow a GIN based architecture. Initially, pre-processing is performed to convert an image data into an undirected graph to consider only the edges instead of the whole image. Our proposed GraphCovidNet model is evaluated on four standard datasets: SARS-COV-2 Ct-Scan dataset, COVID-CT dataset, combination of covid-chestxray-dataset, Chest X-Ray Images (Pneumonia) dataset and CMSC-678-ML-Project dataset. The model shows an impressive accuracy of 99% for all the datasets and its prediction capability becomes 100% accurate for the binary classification problem of detecting COVID-19 scans. Source code of this work can be found at GitHub-link .
Fulltext 5' isomiR variation is of functional and evolutionary importance

Tan GC, Chan E, Molnar A, Sarkar R, Alexieva D, Isa IM, et al.

Nucleic Acids Res, 2014 Aug;42(14):9424-35.
PMID: 25056318 DOI: 10.1093/nar/gku656

We have sequenced miRNA libraries from human embryonic, neural and foetal mesenchymal stem cells. We report that the majority of miRNA genes encode mature isomers that vary in size by one or more bases at the 3' and/or 5' end of the miRNA. Northern blotting for individual miRNAs showed that the proportions of isomiRs expressed by a single miRNA gene often differ between cell and tissue types. IsomiRs were readily co-immunoprecipitated with Argonaute proteins in vivo and were active in luciferase assays, indicating that they are functional. Bioinformatics analysis predicts substantial differences in targeting between miRNAs with minor 5' differences and in support of this we report that a 5' isomiR-9-1 gained the ability to inhibit the expression of DNMT3B and NCAM2 but lost the ability to inhibit CDH1 in vitro. This result was confirmed by the use of isomiR-specific sponges. Our analysis of the miRGator database indicates that a small percentage of human miRNA genes express isomiRs as the dominant transcript in certain cell types and analysis of miRBase shows that 5' isomiRs have replaced canonical miRNAs many times during evolution. This strongly indicates that isomiRs are of functional importance and have contributed to the evolution of miRNA genes.