AI-Based Assessment of Chest Diseases on Chest X-ray Imaging Using DenseNet-121 and a CheXpert-Trained Model
AI-Based Assessment of Chest Diseases on Chest X-ray Imaging Using DenseNet-121 and a CheXpert-Trained Model: A Comparative Diagnostic Accuracy Study
Chest X-rays are widely used to detect thoracic and lung conditions, but reviewing high volumes of radiographs can lead to workload strain and variation between interpreters. Artificial intelligence (AI), particularly deep learning neural networks like DenseNet-121, has shown strong potential to assist clinicians with automated image interpretation. However, AI models trained on large international datasets, such as CheXpert, may perform differently across distinct patient populations due to variations in imaging technique, patient demographics, and disease presentation.
The primary purpose of this study is to compare the diagnostic accuracy of a DenseNet-121 model trained or fine-tuned on local data against a DenseNet-121 model pretrained on the CheXpert dataset for identifying thoracic pathologies. Both models will evaluate de-identified frontal chest radiographs from adult patients. Model predictions will be compared against a reference standard established by expert radiologist consensus, with discordant findings resolved using chest computed tomography (CT). Findings will evaluate whether local model adaptation improves diagnostic precision and workflow efficiency in clinical settings.
Studie Overzicht
Toestand
Toestand
Conditie
Conditie
Studietype
Studietype
Inschrijving (Geschat)
Inschrijving
Deelname Criteria
Geschiktheidscriteria
Geschiktheidscriteria
Leeftijden die in aanmerking komen voor studie
Accepteert gezonde vrijwilligers
Geslachten die in aanmerking komen voor studie
Bemonsteringsmethode
Studie Bevolking
The study population comprises adult patients aged 18 years and older who undergo frontal chest radiography within institutional radiology departments. Eligible subjects have de-identified, diagnostic-quality frontal chest X-ray images with available reference diagnostic labels verified through expert radiologist consensus and chest CT adjudication. Pediatric cases, non-diagnostic images, incomplete metadata, and duplicate scans are excluded.
Beschrijving
Inclusion Criteria:
- Adult patients aged 18 years or older.
- Undergoing frontal chest radiography.
- Diagnostic-quality frontal chest radiographs.
- Availability of reference diagnostic labels (verified by expert radiologist consensus or chest CT).
Exclusion Criteria:
- Pediatric patients (under 18 years of age).
- Non-diagnostic or poor-quality chest radiographs.
- Incomplete clinical or imaging metadata.
- Duplicate radiographic images or repeat patient entries.
Studie plan
Hoe is de studie opgezet?
Ontwerpdetails
- Observatiemodellen: COHORT
- Tijdsperspectieven: CROSS_SECTIONAL
Aantal groepen / cohorten
Cohorten en interventies
Groep / CohortGroep / Cohort |
|---|
|
Adult Frontal Chest Radiography Cohort
This cohort includes adult patients aged 18 years and older who undergo diagnostic-quality frontal chest radiography with available reference diagnostic labels. De-identified chest radiographs from this group are evaluated by two deep learning architectures: a study-trained/fine-tuned DenseNet-121 convolutional neural network and a CheXpert-pretrained DenseNet-121 model. Model predictions are evaluated against reference standards derived from expert radiologist consensus, with discordant cases adjudicated via chest computed tomography (CT). |
Wat meet het onderzoek?
Primaire uitkomstmaten
Primaire uitkomstmaten
Uitkomstmaat |
Maatregel Beschrijving |
Tijdsspanne |
|---|---|---|
|
Area Under the Receiver Operating Characteristic Curve (AUROC)
Tijdsspanne: Baseline
|
AUROC will be calculated to assess and compare the diagnostic performance of the study-trained DenseNet-121 model versus the CheXpert-pretrained DenseNet-121 model in detecting thoracic pathologies on frontal chest radiographs. AI predictions will be compared against the reference standard of expert radiologist consensus, with discordant findings adjudicated by chest CT. AUROC values range from 0.5 (no discrimination) to 1.0 (perfect discrimination). |
Baseline
|
Medewerkers en onderzoekers
Sponsor
Sponsor
Studie record data
Bestudeer belangrijke data
Studie start (Geschat)
Studie start
Primaire voltooiing (Geschat)
Primaire voltooiing
Studie voltooiing (Geschat)
Studie voltooiing
Studieregistratiedata
Eerst ingediend
Eerst ingediend
Eerst ingediend dat voldeed aan de QC-criteria
Eerst ingediend dat voldeed aan de QC-criteria
Eerst geplaatst (Werkelijk)
Eerst geplaatst
Updates van studierecords
Laatste update geplaatst (Werkelijk)
Laatste update geplaatst
Laatste update ingediend die voldeed aan QC-criteria
Laatste update ingediend die voldeed aan QC-criteria
Laatst geverifieerd
Laatst geverifieerd
Meer informatie
Termen gerelateerd aan deze studie
Trefwoorden
Aanvullende relevante MeSH-voorwaarden
Andere studie-ID-nummers
Andere studie-ID-nummers
- AI Chest X-Ray Assessment
Deze informatie is zonder wijzigingen rechtstreeks van de website clinicaltrials.gov gehaald. Als u verzoeken heeft om uw onderzoeksgegevens te wijzigen, te verwijderen of bij te werken, neem dan contact op met register@clinicaltrials.gov. Zodra er een wijziging wordt doorgevoerd op clinicaltrials.gov, wordt deze ook automatisch bijgewerkt op onze website .