News | Artificial Intelligence | September 18, 2023

AI system by Lunit identified improperly positioned endotracheal tube on chest radiographs obtained after insertion, as well as on chest radiographs obtained from patients in the ICU at two institutions

AI system by Lunit identified improperly positioned endotracheal tube on chest radiographs obtained after insertion, as well as on chest radiographs obtained from patients in the ICU at two institutions

Left: Chest radiograph from 80-year-old patient in sample A. AI identified endotracheal tube (ETT) with probability score of 0.98, and properly localized tip of ETT (solid arrow). AI also identified tracheal carina with probability score of 0.99 and properly localized carina (open arrow). Based on pixel spacing information in DICOM data header, AI automatically measured absolute distance between ETT tip and tracheal carina (tip-to-carina distance, TCD) as 4.3 cm. AI also measured distance between ETT tip and carina along radiograph’s vertical axis of (y-axis tip-to-carina difference, TCDy) as 4.0 cm, indicating that ETT tip is located 4.0 cm above carina. ETT is in proper position based on TCD. Right: Chest radiograph from 77-year-old patient in sample A. ETT is in critical position, with tip located below tracheal carina. AI-derived TCD was 2.5 cm. AI-derived TCDy was -1.4 cm, indicating that ETT tip is located 1.4 cm below carina. Image courtesy of AJR 


September 18, 2023 — According to an accepted manuscript published in the American Journal of Roentgenology (AJR), an artificial intelligence (AI) system developed by Lunit (Seoul, Korea) identified improperly positioned endotracheal tube (ETTs) on chest radiographs obtained after ETT insertion, as well as on chest radiographs obtained from patients in the ICU at two institutions. 

“Automated AI identification of improper ETT position on chest radiograph may allow earlier repositioning and thereby reduce complications,” wrote corresponding author Eui Jin Hwang, MD, PhD, from the department of radiology at Korea’s Seoul National University Hospital

Hwang et al.’s retrospective AJR study included 539 chest radiographs obtained immediately after ETT insertion from January 1, 2020 to March 31, 2020 in 505 patients (293 men, 212 women; mean age, 63 years) from institution A (sample A); 637 chest radiographs obtained from January 1, 2020 to January 3, 2020 in 304 patients (158 men, 147 women; mean age, 63 years) in the ICU (with or without an ETT) from institution A (sample B); and 546 chest radiographs obtained from January 1, 2020 to January 20, 2020 in 83 patients (54 men, 29 women; mean age, 70 years) in the ICU (with or without an ETT) from institution B (sample C). Lunit’s commercial DL-based AI system was used to identify ETT presence and measure ETT tip-to-carina distance (TCD). Reference standard for proper ETT position was TCD between 3 cm and 7 cm, determined by human readers. Critical ETT position was separately defined as ETT tip below the carina or TCD less than or equal to 1 cm. 

Ultimately, in three patient samples from two different institutions, an AI system identified ETT presence with sensitivity of 99.2–100%; and specificity of 94.5–98.7%, improper ETT position with sensitivity of 72.5–83.7% and specificity of 92.0–100%, and critical ETT position with sensitivity of 100% in all samples and specificity of 96.7–100%. 

For more information: www.arrs.org


Related Content

News | Information Technology

September 29, 2023 — Fuse Oncology (Fuse) a trailblazing leader in radiation oncology software solutions, unveils their ...

Time September 29, 2023
arrow
News | Computed Tomography (CT)

September 29, 2023 —Nano-X Imaging, an innovative medical imaging technology company, today announced that HealthCCSng ...

Time September 29, 2023
arrow
News | Magnetic Resonance Imaging (MRI)

September 28, 2023 — Siemens Healthineers has announced the Food and Drug Administration (FDA) clearance of the Magnetom ...

Time September 28, 2023
arrow
News | Lung Imaging

September 26, 2023 — In a study of more than 2,000 chest X-rays, radiologists outperformed AI in accurately identifying ...

Time September 26, 2023
arrow
News | Point-of-Care Ultrasound (POCUS)

September 26, 2023 — Exo (pronounced “echo”), a medical imaging software and device company, today unveiled a category ...

Time September 26, 2023
arrow
News | Mammography

September 26, 2023 — Artificial intelligence(AI) and machine learning tools have received a lot of attention recently ...

Time September 26, 2023
arrow
News | Artificial Intelligence

September 25, 2023 — Viz.ai, a leader in AI-powered disease detection and intelligent care coordination, today announced ...

Time September 25, 2023
arrow
Feature | Magnetic Resonance Imaging (MRI) | By Robert L. Bard, MD, and Lennard M. Gettz, EdD

Since the advent of the magnetic resonance imaging (MRI) exam on human patients in the late 1970s, this innovation ...

Time September 25, 2023
arrow
News | Digital Pathology

September 22, 2023 — Lunit, a leading provider of AI-powered solutions for cancer diagnostics and therapeutics, today ...

Time September 22, 2023
arrow
News | Prostate Cancer

September 22, 2023 — According to an accepted manuscript published in the American Journal of Roentgenology (AJR) ...

Time September 22, 2023
arrow
Subscribe Now