scholarly journals Deep Ensemble Model for Classification of Novel Coronavirus in Chest X-Ray Images

2021 ◽  
Vol 2021 ◽  
pp. 1-17
Author(s):  
Fareed Ahmad ◽  
Amjad Farooq ◽  
Muhammad Usman Ghani
Keyword(s):  
Ensemble Learning ◽  
High Capacity ◽  
Automatic Classification ◽  
Fine Tuning ◽  
Radiographic Examination ◽  
Correct Identification ◽  
Ensemble Model ◽  
X Rays ◽  
Expert Radiologist ◽  
Novel Coronavirus

The novel coronavirus, SARS-CoV-2, can be deadly to people, causing COVID-19. The ease of its propagation, coupled with its high capacity for illness and death in infected individuals, makes it a hazard to the community. Chest X-rays are one of the most common but most difficult to interpret radiographic examination for early diagnosis of coronavirus-related infections. They carry a considerable amount of anatomical and physiological information, but it is sometimes difficult even for the expert radiologist to derive the related information they contain. Automatic classification using deep learning models can help in better assessing these infections swiftly. Deep CNN models, namely, MobileNet, ResNet50, and InceptionV3, were applied with different variations, including training the model from the start, fine-tuning along with adjusting learned weights of all layers, and fine-tuning with learned weights along with augmentation. Fine-tuning with augmentation produced the best results in pretrained models. Out of these, two best-performing models (MobileNet and InceptionV3) selected for ensemble learning produced accuracy and FScore of 95.18% and 90.34%, and 95.75% and 91.47%, respectively. The proposed hybrid ensemble model generated with the merger of these deep models produced a classification accuracy and FScore of 96.49% and 92.97%. For test dataset, which was separately kept, the model generated accuracy and FScore of 94.19% and 88.64%. Automatic classification using deep ensemble learning can help radiologists in the correct identification of coronavirus-related infections in chest X-rays. Consequently, this swift and computer-aided diagnosis can help in saving precious human lives and minimizing the social and economic impact on society.

Deep learning model for Pathogen Classification using Feature fusion and Data augmentation

2020 ◽  
Vol 15 ◽  
Author(s):  
Fareed Ahmad ◽  
Amjad Farooq ◽  
Muhammad Usman Ghani Khan
Keyword(s):  
Deep Learning ◽  
Cross Validation ◽  
Data Augmentation ◽  
Feature Vector ◽  
Feature Fusion ◽  
High Capacity ◽  
Automatic Classification ◽  
Fine Tuning ◽  
Correct Identification ◽  
Learning Models

Background: Bacterial pathogens are deadly for animals and humans. The ease of their dissemination, coupled with their high capacity for ailment and death in infected individuals, makes them a threat to society. Objective: Due to high similarity among genera and species of pathogens, it is sometimes difficult for microbiologists to differentiate between them. Their automatic classification using deep-learning models can help in reliable, and accurate outcomes. Method: Deep-learning models, namely; AlexNet, GoogleNet, ResNet101, and InceptionV3 are used with numerous variations including training model from scratch, fine-tuning without pre-trained weights, fine-tuning along with freezing weights of initial layers, fine-tuning along with adjusting weights of all layers and augmenting the dataset by random translation and reflection. Moreover, as the dataset is small, fine-tuning and data augmentation strategies are applied to avoid overfitting and produce a generalized model. A merged feature vector is produced using two best-performing models and accuracy is calculated by xgboost algorithm on the feature vector by applying cross-validation. Results: Fine-tuned models where augmentation is applied produces the best results. Out of these, two-best-performing deep models i.e. (ResNet101, and InceptionV3) selected for feature fusion, produced a similar validation accuracy of 95.83 with a loss of 0.0213 and 0.1066, and a testing accuracy of 97.92 and 93.75, respectively. The proposed model used xgboost to attained a classification accuracy of 98.17% by using 35-folds cross-validation. Conclusion: The automatic classification using these models can help experts in the correct identification of pathogens. Consequently, they can help in controlling epidemics and thereby minimizing the socio-economic impact on the community.

SARS n-CoV2-19 detection from chest x-ray images using deep neural networks

2020 ◽  
Vol 16 (5) ◽  
pp. 419-427 ◽  
Author(s):  
Mohammad Khalid Pandit ◽  
Shoaib Amin Banday
Keyword(s):  
Health Care Professionals ◽  
Low Cost ◽  
Fine Tuning ◽  
Medical Community ◽  
X Rays ◽  
Data Set ◽  
Content Type ◽  
X Ray ◽  
Chest X Ray ◽  
Novel Coronavirus

Purpose Novel coronavirus is fast spreading pathogen worldwide and is threatening billions of lives. SARS n-CoV2 is known to affect the lungs of the COVID-19 positive patients. Chest x-rays are the most widely used imaging technique for clinical diagnosis due to fast imaging time and low cost. The purpose of this study is to use deep learning technique for automatic detection of COVID-19 using chest x-rays. Design/methodology/approach The authors used a data set containing confirmed COVID-19 positive, common bacterial pneumonia and healthy cases (no infection). A collection of 1,428 x-ray images is used in this study. The authors used a pre-trained VGG-16 model for the classification task. Transfer learning with fine-tuning was used in this study to effectively train the network on a relatively small chest x-ray data set. Initial experiments show that the model achieves promising results and can be greatly used to expedite COVID-19 detection. Findings The authors achieved an accuracy of 96% and 92.5% in two and three output class cases, respectively. Based on these findings, the medical community can access using x-ray images as possible diagnostic tool for faster COVID-19 detection to complement the already testing and diagnosis methods. Originality/value The proposed method can be used as initial screening which can help health-care professionals to better treat the COVID patients by timely detecting and screening the presence of disease.

scholarly journals 458. Molecular SARS-CoV-2 Testing During the COVID-19 Outbreak: Experiences of a Hospital in Southeast Michigan, USA

2020 ◽  
Vol 7 (Supplement_1) ◽  
pp. S296-S297
Author(s):  
Trini A Mathew ◽  
Jonathan Hopkins ◽  
Diane Kamerer ◽  
Shagufta N Ali ◽  
Daniel Ortiz ◽  
...  
Keyword(s):  
Clinical Features ◽  
Diagnostic Testing ◽  
Beaumont Hospital ◽  
High Capacity ◽  
Turnaround Time ◽  
Molecular Diagnostic ◽  
The Novel ◽  
Repeat Testing ◽  
Asymptomatic Patients ◽  
Novel Coronavirus

Abstract Background The novel Coronavirus SARS CoV-2 (COVID-19) outbreak was complicated by the lack of diagnostic testing kits. In early March 2020, leadership at Beaumont Hospital, Royal Oak Michigan (Beaumont) identified the need to develop high capacity testing modalities with appropriate sensitivity and specificity and rapid turnaround time. We describe the molecular diagnostic testing experience since initial rollout on March 16, 2020 at Beaumont, and results of repeat testing during the peak of the COVID-19 pandemic in MI. Methods Beaumont is an 1100 bed hospital in Southeast MI. In March, testing was initially performed with the EUA Luminex NxTAG CoV Extended Panel until March 28, 2020 when testing was converted to the EUA Cepheid Xpert Xpress SARS-CoV-2 for quicker turnaround times. Each assay was validated with a combination of patient samples and contrived specimens. Results During the initial week of testing there was > 20 % specimen positivity. As the prevalence grew the positivity rate reached 68% by the end of March (Figure 1). Many state and hospital initiatives were implemented during the outbreak, including social distancing and screening of asymptomatic patients to increase case-finding and prevent transmission. We also adopted a process for clinical review of symptomatic patients who initially tested negative for SARS-CoV-2 by a group of infectious disease physicians (Figure 2). This process was expanded to include other trained clinicians who were redeployed from other departments in the hospital. Repeat testing was performed to allow consideration of discontinuation of isolation precautions. During the surge of community cases from March 16 to April 30, 2020, we identified patients with negative PCR tests who subsequently had repeat testing based on clinical evaluation, with 7.1% (39/551) returning positive for SARS- CoV2. Of the patients who expired due to COVID-19 during this period, 4.3% (9/206) initially tested negative before ultimately testing positive. Figure 1 BH RO testing Epicurve Figure 2: Screening tool for repeat COVID19 testing and precautions Conclusion Many state and hospital initiatives helped us flatten the curve for COVID-19. Our hospital testing experience indicate that repeat testing may be warranted for those patients with clinical features suggestive of COVID-19. We will further analyze these cases and clinical features that prompted repeat testing. Disclosures All Authors: No reported disclosures

scholarly journals Automated classification of clinical trial eligibility criteria text based on ensemble learning and metric learning

2021 ◽  
Vol 21 (S2) ◽  
Author(s):  
Kun Zeng ◽  
Yibin Xu ◽  
Ge Lin ◽  
Likeng Liang ◽  
Tianyong Hao
Keyword(s):  
Clinical Trial ◽  
Ensemble Learning ◽  
Metric Learning ◽  
Classification Performance ◽  
Ensemble Model ◽  
Automated Classification ◽  
Eligibility Criteria ◽  
Data Imbalance ◽  
The Impact

Abstract Background Eligibility criteria are the primary strategy for screening the target participants of a clinical trial. Automated classification of clinical trial eligibility criteria text by using machine learning methods improves recruitment efficiency to reduce the cost of clinical research. However, existing methods suffer from poor classification performance due to the complexity and imbalance of eligibility criteria text data. Methods An ensemble learning-based model with metric learning is proposed for eligibility criteria classification. The model integrates a set of pre-trained models including Bidirectional Encoder Representations from Transformers (BERT), A Robustly Optimized BERT Pretraining Approach (RoBERTa), XLNet, Pre-training Text Encoders as Discriminators Rather Than Generators (ELECTRA), and Enhanced Representation through Knowledge Integration (ERNIE). Focal Loss is used as a loss function to address the data imbalance problem. Metric learning is employed to train the embedding of each base model for feature distinguish. Soft Voting is applied to achieve final classification of the ensemble model. The dataset is from the standard evaluation task 3 of 5th China Health Information Processing Conference containing 38,341 eligibility criteria text in 44 categories. Results Our ensemble method had an accuracy of 0.8497, a precision of 0.8229, and a recall of 0.8216 on the dataset. The macro F1-score was 0.8169, outperforming state-of-the-art baseline methods by 0.84% improvement on average. In addition, the performance improvement had a p-value of 2.152e-07 with a standard t-test, indicating that our model achieved a significant improvement. Conclusions A model for classifying eligibility criteria text of clinical trials based on multi-model ensemble learning and metric learning was proposed. The experiments demonstrated that the classification performance was improved by our ensemble model significantly. In addition, metric learning was able to improve word embedding representation and the focal loss reduced the impact of data imbalance to model performance.

scholarly journals Particulate bioglass in the regeneration of alveolar bone in dogs: clinical, surgical and radiographic evaluations

Revista CERES ◽  
2011 ◽  
Vol 58 (2) ◽  
pp. 149-154
Author(s):  
Alexandre Couto Tsiomis ◽  
Andréa Pacheco Batista Borges ◽  
Ana Paula Falci Daibert ◽  
Tatiana Schmitz Duarte ◽  
Emily Correna Carlo Reis ◽  
...  
Keyword(s):  
Wound Healing ◽  
Bone Substitute ◽  
Alveolar Bone ◽  
Gradual Increase ◽  
Treated Group ◽  
Radiographic Examination ◽  
Control Group ◽  
X Rays ◽  
Clinical Evaluations ◽  
Radiological Analysis

Bone loss, either by trauma or other diseases, generates an increasing need for substitutes of this tissue. This study evaluated Bioglass as a bone substitute in the regeneration of the alveolar bone in mandibles of dogs by clinical, surgical and radiological analysis. Twenty-eight adult dogs were randomly separated into two equal groups. In each animal, a bone defect was created on the vestibular surface of the alveolar bone between the roots of the fourth right premolar tooth. In the treated group, the defect was immediately filled with bioglass, while in the control, it remained unfilled. Clinical evaluations were performed daily for a week, as well as x-rays immediately after surgery and at 8, 14, 21, 42, 60, 90 and 120 days post-operative. Most animals in both groups showed no signs of inflammation and wound healing was similar. Radiographic examination revealed a gradual increase of radiopacity in the region of the defect in the control group. In the treated group, initial radiopacity was higher than that of adjacent bone, decreasing until 21 days after surgery. Then it gradually increased until 120 days after surgery, when the defect became undetectable. The results showed that Bioglass integrates into bone tissue, is biocompatible and reduced the period for complete bone regeneration.

scholarly journals Detection of novel coronavirus from chest X-rays using deep convolutional neural networks

2021 ◽  
Author(s):  
Shashwat Sanket ◽  
M. Vergin Raja Sarobin ◽  
L. Jani Anbarasi ◽  
Jayraj Thakor ◽  
Urmila Singh ◽  
...  
Keyword(s):  
Neural Networks ◽  
Convolutional Neural Networks ◽  
X Rays ◽  
Deep Convolutional Neural Networks ◽  
Novel Coronavirus

scholarly journals Deep Learning of COVID-19 Chest X-Rays: New Models or Fine Tuning?

2020 ◽  
Author(s):  
Tuan Pham
Keyword(s):  
Deep Learning ◽  
High Performance ◽  
Data Augmentation ◽  
Dominant Role ◽  
Care Center ◽  
Characteristic Curve ◽  
Fine Tuning ◽  
Urgent Care ◽  
X Rays ◽  
Training Time

Chest X-rays have been found to be very promising for assessing COVID-19 patients, especially for resolving emergency-department and urgent-care-center overcapacity. Deep-learning (DL) methods in artificial intelligence (AI) play a dominant role as high-performance classifiers in the detection of the disease using chest X-rays. While many new DL models have been being developed for this purpose, this study aimed to investigate the fine tuning of pretrained convolutional neural networks (CNNs) for the classification of COVID-19 using chest X-rays. Three pretrained CNNs, which are AlexNet, GoogleNet, and SqueezeNet, were selected and fine-tuned without data augmentation to carry out 2-class and 3-class classification tasks using 3 public chest X-ray databases. In comparison with other recently developed DL models, the 3 pretrained CNNs achieved very high classification results in terms of accuracy, sensitivity, specificity, precision, F1 score, and area under the receiver-operating-characteristic curve. AlexNet, GoogleNet, and SqueezeNet require the least training time among pretrained DL models, but with suitable selection of training parameters, excellent classification results can be achieved without data augmentation by these networks. The findings contribute to the urgent need for harnessing the pandemic by facilitating the deployment of AI tools that are fully automated and readily available in the public domain for rapid implementation.

scholarly journals DELPHI: accurate deep ensemble model for protein interaction sites prediction

2020 ◽  
Author(s):  
Yiwei Li ◽  
G Brian Golding ◽  
Lucian Ilie
Keyword(s):  
Deep Learning ◽  
Protein Interaction ◽  
Binding Sites ◽  
Web Server ◽  
Fine Tuning ◽  
Supplementary Information ◽  
Ensemble Model ◽  
Position Information ◽  
Interaction Sites ◽  
Protein Interaction Sites

Abstract Motivation Proteins usually perform their functions by interacting with other proteins, which is why accurately predicting protein–protein interaction (PPI) binding sites is a fundamental problem. Experimental methods are slow and expensive. Therefore, great efforts are being made towards increasing the performance of computational methods. Results We propose DEep Learning Prediction of Highly probable protein Interaction sites (DELPHI), a new sequence-based deep learning suite for PPI-binding sites prediction. DELPHI has an ensemble structure which combines a CNN and a RNN component with fine tuning technique. Three novel features, HSP, position information and ProtVec are used in addition to nine existing ones. We comprehensively compare DELPHI to nine state-of-the-art programmes on five datasets, and DELPHI outperforms the competing methods in all metrics even though its training dataset shares the least similarities with the testing datasets. In the most important metrics, AUPRC and MCC, it surpasses the second best programmes by as much as 18.5% and 27.7%, respectively. We also demonstrated that the improvement is essentially due to using the ensemble model and, especially, the three new features. Using DELPHI it is shown that there is a strong correlation with protein-binding residues (PBRs) and sites with strong evolutionary conservation. In addition, DELPHI’s predicted PBR sites closely match known data from Pfam. DELPHI is available as open-sourced standalone software and web server. Availability and implementation The DELPHI web server can be found at delphi.csd.uwo.ca/, with all datasets and results in this study. The trained models, the DELPHI standalone source code, and the feature computation pipeline are freely available at github.com/lucian-ilie/DELPHI. Supplementary information Supplementary data are available at Bioinformatics online.

scholarly journals Minimized lithium trapping by isovalent isomorphism for high initial Coulombic efficiency of silicon anodes

2019 ◽  
Vol 5 (11) ◽  
pp. eaax0651 ◽  
Author(s):  
Bin Zhu ◽  
Guoliang Liu ◽  
Guangxin Lv ◽  
Yu Mu ◽  
Yunlei Zhao ◽  
...  
Keyword(s):  
Large Scale ◽  
Coulombic Efficiency ◽  
Solid Electrolyte Interphase ◽  
High Capacity ◽  
Lithium Ion ◽  
Elemental Abundance ◽  
Fine Tuning ◽  
Electrochemical Behaviors ◽  
Battery Materials ◽  
Initial Coulombic Efficiency

Silicon demonstrates great potential as a next-generation lithium ion battery anode because of high capacity and elemental abundance. However, the issue of low initial Coulombic efficiency needs to be addressed to enable large-scale applications. There are mainly two mechanisms for this lithium loss in the first cycle: the formation of the solid electrolyte interphase and lithium trapping in the electrode. The former has been heavily investigated while the latter has been largely neglected. Here, through both theoretical calculation and experimental study, we demonstrate that by introducing Ge substitution in Si with fine compositional control, the energy barrier of lithium diffusion will be greatly reduced because of the lattice expansion. This effect of isovalent isomorphism significantly reduces the Li trapping by ~70% and improves the initial Coulombic efficiency to over 90%. We expect that various systems of battery materials can benefit from this mechanism for fine-tuning their electrochemical behaviors.

Sign in / Sign up

Export Citation Format

Share Document