scholarly journals COVID-19 Patient Detection Based on Fusion of Transfer Learning and Fuzzy Ensemble Models Using CXR Images

2021 ◽  
Vol 11 (23) ◽  
pp. 11423
Author(s):  
Chandrakanta Mahanty ◽  
Raghvendra Kumar ◽  
Panagiotis G. Asteris ◽  
Amir H. Gandomi
Keyword(s):  
Transfer Learning ◽  
Ensemble Methods ◽  
Cost Effective ◽  
Majority Voting ◽  
Learning Models ◽  
Medical Practitioners ◽  
Healthcare Facilities ◽  
Ensemble Techniques ◽  
Effective Manner ◽  
Detection Strategies

The COVID-19 pandemic has claimed the lives of millions of people and put a significant strain on healthcare facilities. To combat this disease, it is necessary to monitor affected patients in a timely and cost-effective manner. In this work, CXR images were used to identify COVID-19 patients. We compiled a CXR dataset with equal number of 2313 COVID positive, pneumonia and normal CXR images and utilized various transfer learning models as base classifiers, including VGG16, GoogleNet, and Xception. The proposed methodology combines fuzzy ensemble techniques, such as Majority Voting, Sugeno Integral, and Choquet Fuzzy, and adaptively combines the decision scores of the transfer learning models to identify coronavirus infection from CXR images. The proposed fuzzy ensemble methods outperformed each individual transfer learning technique and several state-of-the-art ensemble techniques in terms of accuracy and prediction. Specifically, VGG16 + Choquet Fuzzy, GoogleNet + Choquet Fuzzy, and Xception + Choquet Fuzzy achieved accuracies of 97.04%, 98.48%, and 99.57%, respectively. The results of this work are intended to help medical practitioners achieve an earlier detection of coronavirus compared to other detection strategies, which can further save millions of lives and advantageously influence society.

scholarly journals A Novel Approach of Ensembling the Transfer Learning Methods for Rice Plant Disease Detection and Classification

Webology ◽  
2021 ◽  
Vol 18 (2) ◽  
pp. 439-448
Author(s):  
Parameswar Kanuparthi ◽  
Vaibhav Bejgam ◽  
V. Madhu Viswanatham
Keyword(s):  
Transfer Learning ◽  
Rice Plant ◽  
Machine Learning Algorithms ◽  
Majority Voting ◽  
Brown Spot ◽  
Generalization Error ◽  
Learning Models ◽  
The People ◽  
Novel Approach ◽  
Crop Type

Agriculture, the primary sector of Indian economy. It contributes around 18 percent of overall GDP (Gross Domestic Product). More than fifty percent of Indians belong to an agricultural background. There is a necessary to rapidly increase the agriculture production in India due to the vast increasing of population. The significant crop type for most of the people in India is rice but it was one of the crops that has been mostly affected by the cause of diseases in majority of the cases. This results in reduced yield that lead to loss for farmers. The major challenges faced while cultivating the rice crops is getting infected by the diseases due to the various effects that include environmental conditions, pesticides used and natural disasters. Early detection of rice diseases will eventually help farmers to get out from disasters and help in better yield. In this paper, we are proposing a new method of ensembling the transfer learning models to detect the rice plant and classify the diseases using images. Using this model, the three most common rice crop diseases are detected such as Brown spot, Leaf smut and Bacterial leaf blight. Generally, transfer learning uses pre-trained models and gives better accuracy for the image datasets. Also, ensembling of machine learning algorithms (combining two or more ML algorithms) will help in reducing the generalization error and also makes the model more robust. Ensemble learning is becoming trendier as it reduces generalization error as well as makes the model more robust. The ensembling technique that was used in the paper is majority voting. Here we are proposing a novel model that ensembles three transfer learning models which are InceptionV3, MobileNetV2 and DenseNet121 with an accuracy of 96.42%.

scholarly journals Deep Learning Models for Poorly Differentiated Colorectal Adenocarcinoma Classification in Whole Slide Images Using Transfer Learning

Diagnostics ◽  
2021 ◽  
Vol 11 (11) ◽  
pp. 2074
Author(s):  
Masayuki Tsuneki ◽  
Fahdi Kanavati
Keyword(s):  
Deep Learning ◽  
Transfer Learning ◽  
Characteristic Curve ◽  
Cost Effective ◽  
Endoscopic Biopsy ◽  
Histopathological Diagnosis ◽  
Average Risk ◽  
Learning Models ◽  
Poorly Differentiated ◽  
Whole Slide Images

Colorectal poorly differentiated adenocarcinoma (ADC) is known to have a poor prognosis as compared with well to moderately differentiated ADC. The frequency of poorly differentiated ADC is relatively low (usually less than 5% among colorectal carcinomas). Histopathological diagnosis based on endoscopic biopsy specimens is currently the most cost effective method to perform as part of colonoscopic screening in average risk patients, and it is an area that could benefit from AI-based tools to aid pathologists in their clinical workflows. In this study, we trained deep learning models to classify poorly differentiated colorectal ADC from Whole Slide Images (WSIs) using a simple transfer learning method. We evaluated the models on a combination of test sets obtained from five distinct sources, achieving receiver operating characteristic curve (ROC) area under the curves (AUCs) up to 0.95 on 1799 test cases.

scholarly journals Ensemble of Deep Learning Models for Sleep Apnea Detection: An Experimental Study

Sensors ◽  
2021 ◽  
Vol 21 (16) ◽  
pp. 5425
Author(s):  
Debadyuti Mukherjee ◽  
Koustav Dhar ◽  
Friedhelm Schwenker ◽  
Ram Sarkar
Keyword(s):  
Experimental Study ◽  
Deep Learning ◽  
Sleep Apnea ◽  
Choquet Integral ◽  
The Body ◽  
Majority Voting ◽  
Detection Accuracy ◽  
Learning Models ◽  
Ensemble Techniques ◽  
Obstructive Sleep

Sleep Apnea is a breathing disorder occurring during sleep. Older people suffer most from this disease. In-time diagnosis of apnea is needed which can be observed by the application of a proper health monitoring system. In this work, we focus on Obstructive Sleep Apnea (OSA) detection from the Electrocardiogram (ECG) signals obtained through the body sensors. Our work mainly consists of an experimental study of different ensemble techniques applied on three deep learning models—two Convolutional Neural Network (CNN) based models, and a combination of CNN and Long Short-Term Memory (LSTM) models, which were previously proposed in the OSA detection domain. We have chosen four ensemble techniques—majority voting, sum rule and Choquet integral based fuzzy fusion and trainable ensemble using Multi-Layer Perceptron (MLP) for our case study. All the experiments are conducted on the benchmark PhysioNet Apnea-ECG Database. Finally, we have achieved highest OSA detection accuracy of 85.58% using the MLP based ensemble approach. Our best result is also able to surpass many of state-of-the-art methods.

scholarly journals Deep learning models for poorly differentiated colorectal adenocarcinoma classification in whole slide images using transfer learning

2021 ◽  
Author(s):  
Masayuki Tsuneki ◽  
Fahdi Kanavati
Keyword(s):  
Deep Learning ◽  
Transfer Learning ◽  
Cost Effective ◽  
Endoscopic Biopsy ◽  
Histopathological Diagnosis ◽  
Average Risk ◽  
Learning Models ◽  
Poorly Differentiated ◽  
Roc Area ◽  
Whole Slide Images

Colorectal poorly differentiated adenocarcinoma (ADC) is known to have a poor prognosis as compared with well to moderately differentiated ADC. The frequency of poorly differentiated ADC is relatively low (usually less than 5% among colorectal carcinomas). Histopathological diagnosis based on endoscopic biopsy specimens is currently the most cost effective method to perform as part of colonoscopic screening in average risk patients, and it is an area that could benefit from AI-based tools to aid pathologists in their clinical workflows. In this study, we trained deep learning models to classify poorly differentiated colorectal ADC from Whole Slide Images (WSIs) using a simply transfer learning method. We evaluated the models on a combination of test sets obtained from five distinct sources, achieving receiver operator curve (ROC) area under the curves (AUCs) in the range of 0.94-0.98.

scholarly journals Comparison of Classification Models Based on Deep learning on COVID-19 Chest X-Rays

2022 ◽  
Vol 2161 (1) ◽  
pp. 012078
Author(s):  
Pallavi R Mane ◽  
Rajat Shenoy ◽  
Ghanashyama Prabhu
Keyword(s):  
Deep Learning ◽  
Transfer Learning ◽  
State Of The Art ◽  
Cost Effective ◽  
X Rays ◽  
The Novel ◽  
Learning Models ◽  
X Ray ◽  
Chest X Ray ◽  
Fine Tune

Abstract COVID -19, is a deadly, dangerous and contagious disease caused by the novel corona virus. It is very important to detect COVID-19 infection accurately as quickly as possible to avoid the spreading. Deep learning methods can significantly improve the efficiency and accuracy of reading Chest X-Rays (CXRs). The existing Deep learning models with further fine tune provide cost effective, rapid, and better classification results. This paper tries to deploy well studied AI tools with modification on X-ray images to classify COVID 19. This research performs five experiments to classify COVID-19 CXRs from Normal and Viral Pneumonia CXRs using Convolutional Neural Networks (CNN). Four experiments were performed on state-of-the-art pre-trained models using transfer learning and one experiment was performed using a CNN designed from scratch. Dataset used for the experiments consists of chest X-Ray images from the Kaggle dataset and other publicly accessible sources. The data was split into three parts while 90% retained for training the models, 5% each was used in validation and testing of the constructed models. The four transfer learning models used were Inception, Xception, ResNet, and VGG19, that resulted in the test accuracies of 93.07%, 94.8%, 67.5%, and 91.1% respectively and our CNN model resulted in 94.6%.

Strategic planning in grassland farming: Principles andapplications

1997 ◽  
pp. 191-197
Author(s):  
W.J. Parker ◽  
N.M. Shadbolt ◽  
D.I. Gray
Keyword(s):  
Strategic Planning ◽  
Performance Indicators ◽  
Cost Effective ◽  
Key Performance Indicators ◽  
Strategic Plans ◽  
Effective Manner ◽  
Farm Business ◽  
Pastoral Farming ◽  
Financial Environment

Three levels of planning can be distinguished in grassland farming: strategic, tactical and operational. The purpose of strategic planning is to achieve a sustainable long-term fit of the farm business with its physical, social and financial environment. In pastoral farming, this essentially means developing plans that maximise and best match pasture growth with animal demand, while generating sufficient income to maintain or enhance farm resources and improvements, and attain personal and financial goals. Strategic plans relate to the whole farm business and are focused on the means to achieve future needs. They should be routinely (at least annually) reviewed and monitored for effectiveness through key performance indicators (e.g., Economic Farm Surplus) that enable progress toward goals to be measured in a timely and cost-effective manner. Failure to link strategy with control is likely to result in unfulfilled plans. Keywords: management, performance

scholarly journals Novel Regeneration Approach for Creating Reusable FO-SPR Probes with NTA Surface Chemistry

Nanomaterials ◽  
2021 ◽  
Vol 11 (1) ◽  
pp. 186
Author(s):  
Jia-Huan Qu ◽  
Karen Leirs ◽  
Remei Escudero ◽  
Žiga Strmšek ◽  
Roman Jerala ◽  
...  
Keyword(s):  
Surface Chemistry ◽  
Fluorescent Protein ◽  
Cost Effective ◽  
Nitrilotriacetic Acid ◽  
Antibody Fragments ◽  
Rapid Screening ◽  
Red Fluorescent Protein ◽  
Effective Manner ◽  
Surface Regeneration ◽  
Sensitivity Specificity

To date, surface plasmon resonance (SPR) biosensors have been exploited in numerous different contexts while continuously pushing boundaries in terms of improved sensitivity, specificity, portability and reusability. The latter has attracted attention as a viable alternative to disposable biosensors, also offering prospects for rapid screening of biomolecules or biomolecular interactions. In this context here, we developed an approach to successfully regenerate a fiber-optic (FO)-SPR surface when utilizing cobalt (II)-nitrilotriacetic acid (NTA) surface chemistry. To achieve this, we tested multiple regeneration conditions that can disrupt the NTA chelate on a surface fully saturated with His6-tagged antibody fragments (scFv-33H1F7) over ten regeneration cycles. The best surface regeneration was obtained when combining 100 mM EDTA, 500 mM imidazole and 0.5% SDS at pH 8.0 for 1 min with shaking at 150 rpm followed by washing with 0.5 M NaOH for 3 min. The true versatility of the established approach was proven by regenerating the NTA surface for ten cycles with three other model system bioreceptors, different in their size and structure: His6-tagged SARS-CoV-2 spike fragment (receptor binding domain, RBD), a red fluorescent protein (RFP) and protein origami carrying 4 RFPs (Tet12SN-RRRR). Enabling the removal of His6-tagged bioreceptors from NTA surfaces in a fast and cost-effective manner can have broad applications, spanning from the development of biosensors and various biopharmaceutical analyses to the synthesis of novel biomaterials.

scholarly journals Risk Estimate of Duodenoscope-Associated Infections in The Netherlands

2020 ◽  
Vol 41 (S1) ◽  
pp. s436-s437
Author(s):  
M. Vos ◽  
Judith Kwakman ◽  
Marco Bruno
Keyword(s):  
The Netherlands ◽  
Multidrug Resistant ◽  
National Database ◽  
Clinical Infection ◽  
Minimum Risk ◽  
Medical Practitioners ◽  
Healthcare Facilities ◽  
Calculated Risk ◽  
Original Calculation ◽  
Bare Minimum

Background: The likelihood of endoscopy-associated infections (EAIs) is often referenced from a paper published in 1993 by Kimmery et al1 in which a risk of 1 exogenous infection for every 1.8 million endoscopies (0.00006%) is proclaimed. Even though Ofstead et al2 pointed out in 2013 that this was at least an underestimation by 6-fold because of erroneous assumptions and mathematical errors, the original calculation is still often referred to. In the past decade, multiple outbreaks of multidrug-resistant microorganisms (MDROs) related to contaminated duodenoscopes have been reported worldwide. This leads to the assumption that the former risk calculation is indeed incorrect. Objective: We calculated the duodenoscope-associated infection (DAI) risk for the Dutch ERCP practice. Methods: We searched and consolidated all Dutch patients reported in the literature to have suffered from a clinical infection linked to a contaminated duodenoscope between 2008 and 2018. From a national database, the number of ERCPs performed per year in The Netherlands were retrieved. Actual numbers were available from 2012 to 2018. Numbers from 2008 to 2011 were estimated and assumed to be equal to 2012. Results: In 2008–2018, 3 MDRO outbreaks in Dutch hospitals were reported in the literature, with 21 patients suffering from a clinical infection based on a microorganism proven to be transmitted by a duodenoscope. In that period, ∼203,500 ERCP procedures were performed. Hence, for every 9,690 procedures, 1 patient developed a clinically relevant infection (DAI risk, 0.010%). Conclusions: The risk of developing a DAI is at least 30–180 times higher than the risks that were previously reported for all types of endoscopy-associated infections. Importantly, the current calculated risk of 0.010% constitutes a bare minimum risk of DAI because endoscope-related infections are underreported. Apart from DAI risk, a patient is also at risk of becoming colonized with a microorganism through contaminated endoscopes but without developing symptoms of clinical infection. These data call for consorted action of medical practitioners, industry, and government agencies to minimize and ultimately eliminate the risk of exogenous endoscope-associated infections and contamination. As a first step, the FDA recently recommended that healthcare facilities and manufacturers begin transitioning to duodenoscopes with disposable components.3Funding: NoneDisclosures: None

Sign in / Sign up

Export Citation Format

Share Document