Accuracy of Fully Automated and Human-assisted Artificial Intelligence–based CT Quantification of Pleural Effusion Changes after Thoracentesis

2025/01/01 by Eui Jin Hwang, Hyunsook Hong, S. Ko +4 · 1 voice
Engineering · Medicine · #COVID-19 diagnosis using AI #Medical Imaging and Analysis #Radiomics and Machine Learning in Medical Imaging

paper · doi:10.1148/ryai.240215

openalex publication_date 2025/01/01 · openalex created_date 2025/01/16 · openalex updated_date 2026/07/30

Abstract

Fully automated and human-assisted artificial intelligence–based measurements of pleural effusion changes on CT scans after thoracentesis underestimated the volume of drained pleural fluid, indicating the need for careful interpretation before implementing CT quantification in practice.

Citations

• Measuring agreement in method comparison studies
• Management of a malignant pleural effusion: British Thoracic Society pleural disease guideline 2010

Discussions

• Accuracy of Fully Automated and Human-assisted AI-based CT Quantification of Pleural Effusion Changes after Thoracentesis https://doi.org/10.1148/ryai.240215 @rsnasky.bsky.social #ChestRad #PleuralEff [bsky, 3 points, 0 comments]

Related

• AI-Assisted Pleural Effusion Volume Estimation from Contrast-Enhanced CT Images
• minoHealth.ai: A Clinical Evaluation Of Deep Learning Systems For the Diagnosis of Pleural Effusion and Cardiomegaly In Ghana, Vietnam and the United States of America
• Deep Learning-based Segmentation of Pleural Effusion From Ultrasound Using Coordinate Convolutions
• Clinical Implementation of AI for Pulmonary Embolism Detection in over 30 000 CT Pulmonary Angiography Examinations
• Commercial AI Model Diagnostic Accuracy for Intracranial Large- and Medium-Vessel Occlusion at Emergency CT Angiography