Multiclass COVID-19 detection by utilizing ESN: Extreme Smart Network without MeanDropout feature space.

Multiclass COVID-19 detection by utilizing ESN: Extreme Smart Network without MeanDropout feature space.

<p>Multiclass COVID-19 detection by utilizing ESN: Extreme Smart Network without MeanDropout feature space.</p>

Saved in:

Bibliographic Details
Main Author:	Saghir Ahmed (4416544) (author)
Other Authors:	Basit Raza (20175794) (author), Lal Hussain (14100502) (author), Touseef Sadiq (20175797) (author), Ashit Kumar Dutta (11547381) (author)
Published:	2024
Subjects:	Cancer Space Science Biological Sciences not elsewhere classified Information Systems not elsewhere classified publicly available sources promising significant advancements portable chest x novel approach called large dataset containing extreme smart network 000 cxr images model &# 8217 images encompass covid enhancing multiclass covid enhancing covid prediction mdfs model achieved 16 model 19 prediction trained vgg superior ability study explores study aimed research proposes optimize performance normal conditions normal cases meticulously addressed mdfs ). hyperparameter tuning fold cross findings demonstrate enhance multi data imbalance cxrs ). bacterial pneumonia
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Confusion Matrix to distinguish Multiclass COVID-19 detection by utilizing ESN: Extreme Smart Network without MeanDropout feature space.
by: Saghir Ahmed (4416544)
Published: (2024)

Multiclass COVID-19 detection by utilizing ESN-MDFS: Extreme Smart Network using mean dropout feature selection technique.
by: Saghir Ahmed (4416544)
Published: (2024)

Confusion matrix to distinguish multiclass COVID-19 detection by utilizing ESN-MDFS: Extreme Smart Network using mean dropout feature selection technique.
by: Saghir Ahmed (4416544)
Published: (2024)

Comparison of Multiclass COVID-19 detection by utilizing ESN-MDFS with existing Lightweight models.
by: Saghir Ahmed (4416544)
Published: (2024)

Area under the receiver operating characteristic curve (AUC) to distinguish Multiclass COVID-19 detection by utilizing ESN-MDFS.
by: Saghir Ahmed (4416544)
Published: (2024)

Fold vs accuracy curve to distinguish multi-class using ESN-MDFS.
by: Saghir Ahmed (4416544)
Published: (2024)

Data Augmentation techniques on multiclass.
by: Saghir Ahmed (4416544)
Published: (2024)

Comparison of AI-assisted recent studies for COVID-19 lung infection.
by: Saghir Ahmed (4416544)
Published: (2024)

Hyperparameters optimization of XGBoost algorithm.
by: Saghir Ahmed (4416544)
Published: (2024)

Fig 6 -
by: Saghir Ahmed (4416544)
Published: (2024)

Fig 5 -
by: Saghir Ahmed (4416544)
Published: (2024)

General architecture of XGBoost algorithm.
by: Saghir Ahmed (4416544)
Published: (2024)

Image pre-processing steps.
by: Saghir Ahmed (4416544)
Published: (2024)

Fig 1 -
by: Saghir Ahmed (4416544)
Published: (2024)

(A) Agreement of CAD software with radiologists, at manufacturer suggested thresholds for normal vs. abnormal CXRs.
by: Sam Linsen (20606266)
Published: (2025)

Software performance at a set radiologist observed sensitivity and specificity.
by: Sam Linsen (20606266)
Published: (2025)

Radiologist accuracy in identifying COVID-19 on CXR in comparison to laboratory test results.
by: Sam Linsen (20606266)
Published: (2025)

Radiologist interpretation of CXRs in comparison to laboratory testing results.
by: Sam Linsen (20606266)
Published: (2025)

Demographic and clinical characteristics from included participants PCR: Sars CoV-2 polymerase chain reaction testing, Antigen: Sars CoV-2 Antigen test.
by: Sam Linsen (20606266)
Published: (2025)

Fig 5 -
by: Sam Linsen (20606266)
Published: (2025)

Software and radiologist performance at diagnosing COVID-19 before and after the shift to Omicron being the dominant variant.
by: Sam Linsen (20606266)
Published: (2025)

Performance of radiologist and software CAD1 and CAD2 at identifying Covid-19 in comparison to baseline molecular testing.
by: Sam Linsen (20606266)
Published: (2025)

Aggregate performance and 95% confidence intervals of radiologist and software CAD1 and CAD2 at identifying Covid-19 in comparison to baseline molecular testing. AUC: Area under Curve, RadRS: Radiologist reference standard for COVID-19.
by: Sam Linsen (20606266)
Published: (2025)

Fig 1 -
by: Sam Linsen (20606266)
Published: (2025)

Subgroup analysis of performance of radiologist and software CAD1 and CAD2 at identifying COVID-19 in comparison to baseline molecular testing grouped by HIV status.
by: Sam Linsen (20606266)
Published: (2025)

Subgroup analysis of performance of radiologist and software CAD1 and CAD2 at identifying COVID-19 in comparison to baseline molecular testing grouped by diabetes status.
by: Sam Linsen (20606266)
Published: (2025)

S2 Fig -
by: Sam Linsen (20606266)
Published: (2025)

Subgroup analysis of performance of radiologist and software CAD1 and CAD2 at identifying COVID-19 in comparison to baseline molecular testing grouped by age.
by: Sam Linsen (20606266)
Published: (2025)

Comparison of severity scoring performance across prior studies and the proposed severity scoring module. MAE: Mean Absolute Error.
by: Nastaran Enshaei (9405653)
Published: (2025)

Summary of reported AUC values from previous studies and the proposed model across different CXR-based pneumonia detection tasks. All studies had close collaboration with radiologists for data interpretation and validation.
by: Nastaran Enshaei (9405653)
Published: (2025)

Evaluation of the severity scoring model’s robustness to inter-observer variability. The model was trained using the average scores from four radiologists. During testing, one radiologist was excluded at a time, and performance was compared against the remaining consensus. Results include overall Pearson correlation and MAE, along with subgroup MAEs across three severity levels: Group 1 (SI ≤ 8), Group 2 (9 ≤ SI < 16), and Group 3 (SI ≥ 16). Pearson Co.: Pearson correlation. MAE: mean absolute error. SI: Severity score Index.
by: Nastaran Enshaei (9405653)
Published: (2025)

External validation results of the diagnostic model on the COVIDGR-1.0 dataset, compared with previously published models (COVIDNet-CXR and COVID-CAPS). Performance metrics include class-wise recall, precision, F1-score, and overall accuracy.
by: Nastaran Enshaei (9405653)
Published: (2025)

Ablation study in the second diagnosis scenario (including all 808 COVID-19 CXRs) over the five-fold cross-validation approach. In all experiments, the segmented thorax regions have been used as the model input.
by: Nastaran Enshaei (9405653)
Published: (2025)

Ablation study in the firs diagnosis scenario (excluding COVID-19 CXRs with no evidence of infection) over the five-fold cross-validation approach.
by: Nastaran Enshaei (9405653)
Published: (2025)

Design of experiments. TL: Transfer Learning.
by: Nastaran Enshaei (9405653)
Published: (2025)

Performance comparison across architectures for differentiating COVID-19 from other viral pneumonia and normal cases. The presented results are the Mean ± SD of the obtained results through a five-fold cross-validation process. The best results have been highlighted in bold. The results have been reported for the first diagnosis scenario.
by: Nastaran Enshaei (9405653)
Published: (2025)

COVID-19 sensitivity (%) of the proposed DL diagnostic model compared to four individual radiologists and their consensus, stratified by severity level. Severity was categorized based on radiographic severity scores: low (≤ 8), medium (8–16), and severe (> 16). Sensitivity is reported as mean ± standard deviation across eight randomized test splits.
by: Nastaran Enshaei (9405653)
Published: (2025)

The performance of individual radiologists, their consensus, and the DL model in the second diagnostic scenario (including all 808 COVID-19 cases).
by: Nastaran Enshaei (9405653)
Published: (2025)

F1-scores and accuracy (95% CI) for individual radiologists, consensus, and the DL model.
by: Nastaran Enshaei (9405653)
Published: (2025)

The performance of individual radiologists, their consensus, and the DL model in the first diagnostic scenario (excluding COVID-19 CXRs with a severity score of zero as assessed by at least three radiologists).
by: Nastaran Enshaei (9405653)
Published: (2025)

Cannot write session to /tmp/vufind_sessions/sess_205d6p55k8cc201g32sbkmhf67