Chest Computed Tomography Images in Neonatal Bronchial Pneumonia under the Adaptive Statistical Iterative...

Area of Science:

• Radiology
• Pediatrics
• Medical Imaging

Background:

• Neonatal bronchial pneumonia (NBP) diagnosis relies on imaging and biomarkers.
• Optimizing computed tomography (CT) image reconstruction is crucial for accurate diagnosis.

Purpose of the Study:

• To evaluate the diagnostic value of artificial intelligence (AI) algorithms in processing chest CT images for NBP.
• To compare the diagnostic efficiency of CT, C-reactive protein (CRP), erythrocyte sedimentation rate (ESR), and their combinations for NBP.

Main Methods:

• Chest CT images of 85 neonates with NBP were analyzed using the AI adaptive statistical iterative reconstruction (ASiR) algorithm.
• Peripheral blood levels of CRP and ESR were measured in neonates.
• Diagnostic accuracy of different methods was compared.

Main Results:

• The ASiR algorithm with a 50% preweight value yielded optimal CT image quality.
• Ground-glass features were observed in 92.9% of NBP cases post-treatment.
• Combined CRP, ESR, and CT examination achieved a 98.6% diagnostic accuracy for NBP.

Conclusions:

• AI-enhanced CT imaging offers high clinical value for NBP diagnosis.
• AI algorithms can optimize CT image reconstruction for improved diagnostic accuracy.
• Combined biomarker and AI-based CT analysis provides superior diagnostic performance for NBP.