(A) Agreement of CAD software with radiologists, at manufacturer suggested thresholds for normal vs. abnormal CXRs.

(A) Agreement of CAD software with radiologists, at manufacturer suggested thresholds for normal vs. abnormal CXRs.

<p>CAD1: Computer Aided Detection software 1, CAD2: Computer Aided Detection software 2. Percentages group each radiologist assessment according to the corresponding CAD outcome. (B) Percentage agreement of CAD software with radiologists, at manufacturer suggested thresholds for normal vs. abn...

Full description

Saved in:

Bibliographic Details
Main Author:	Sam Linsen (20606266) (author)
Other Authors:	Aurélie Kamoun (13235082) (author), Andrews Gunda (5537063) (author), Tamara Mwenifumbo (20606269) (author), Chancy Chavula (17445772) (author), Lindiwe Nchimunya (20606272) (author), Yucheng Tsai (20606275) (author), Namwaka Mulenga (20606278) (author), Godfrey Kadewele (20606281) (author), Eunice Nahache Kajombo (20606284) (author), Veronica Sunkutu (846233) (author), Jane Shawa (20606287) (author), Rigveda Kadam (8374446) (author), Matthew Arentz (122414) (author)
Published:	2025
Subjects:	Medicine Neuroscience Cancer Biological Sciences not elsewhere classified Information Systems not elsewhere classified representative training data ongoing data collection maintain diagnostic accuracy high prevalent population effectiveness varies significantly 65 &# 8211 52 &# 8211 19 laboratory results 19 case finding cad show promise support effective triage settings regarding covid highly portable cxr showed inferior performance one cad software study evaluating cxrs 671 individuals evaluated 19 cad performance zambia </ p radiologists interpreted cxrs showed performance cad software evaluated performance study highlights optimize performance 19 cxr individuals evaluated cad ), abnormal cxrs sars cov retrospective cross little evidence key populations june 2022 january 2021 identifying covid future pandemics findings suggest expert radiologist distinguishing normal differentiating normal diagnosing covid current ai chest radiographs better prepare 75 )), 63 )). 2 infection
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Radiologist interpretation of CXRs in comparison to laboratory testing results.
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)

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)

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)

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)

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)

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)

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)

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

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

The distribution of severity scores in our COVID-19 CXRs based on the average evaluations of four radiologists.
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)

Frontal CXRs and corresponding Grad-CAM heatmaps for the two-stage DL diagnosis system.
by: Nastaran Enshaei (9405653)
Published: (2025)

Representative examples of COVID-19 CXRs at varying severity levels alongside corresponding model attention maps.
by: Nastaran Enshaei (9405653)
Published: (2025)

Comparison of AI-assisted recent studies for COVID-19 lung infection.
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)

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

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

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

Fold vs accuracy curve to distinguish multi-class using ESN-MDFS.
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)

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)

Confusion Matrix to distinguish Multiclass COVID-19 detection by utilizing ESN: Extreme Smart Network without MeanDropout feature space.
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)

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

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

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

External validation of DL severity scoring module on 86 COVID-19 CXRs from a publicly available dataset.
by: Nastaran Enshaei (9405653)
Published: (2025)

Examples of CXR severity score evaluations by two radiologists.
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)

DL-Predicted severity scores versus consensus radiologists’ severity scores.
by: Nastaran Enshaei (9405653)
Published: (2025)

Demographic characteristics of the study population across diagnostic groups, including the number of CXRs, mean patient age ± standard deviation, and percentage of female patients in each group.
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)

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)

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)

Cannot write session to /tmp/vufind_sessions/sess_dhl2fmfiqckngk22813ta04np8