We use cookies to understand how you use our site and to improve your experience. This includes personalizing content and advertising. To learn more, click here. By continuing to use our site, you accept our use of cookies. Cookie Policy.

Features Partner Sites Information LinkXpress
Sign In
Advertise with Us

Download Mobile App

AI System Confirms Tracheal Tube Position on Chest X-Rays

By MedImaging International staff writers
Posted on 15 Sep 2023
Print article
Image: The AI system identifies improperly positioned endotracheal tube on chest radiographs (Photo courtesy of Lunit)
Image: The AI system identifies improperly positioned endotracheal tube on chest radiographs (Photo courtesy of Lunit)

Timely and accurate evaluation of chest X-rays to check the placement of endotracheal tubes (ETTs) is crucial for making immediate adjustments if required. A deep learning (DL)-powered artificial intelligence (AI) system has been found to be effective in detecting incorrectly positioned ETTs from chest X-rays taken right after the ETT was inserted or after admission to the ICU.

Researchers at Seoul National University Hospital (Seoul, Korea) conducted a study to evaluate the performance of a commercial DL-based AI system from Lunit (Seoul, Korea) for assessing the presence and placement of ETTs on chest X-rays. They examined three separate patient samples from two different medical centers. The first sample comprised 539 chest X-rays from 505 patients (293 males and 212 females, average age 63) taken immediately after ETT placement between January and March 2020 at institution A. The second sample involved 637 X-rays from 304 ICU patients (158 males and 147 females, average age 63) at the same institution, taken from January 1 to January 3, 2020. The third sample consisted of 546 X-rays from 83 ICU patients (54 males and 29 females, average age 70) at institution B, taken from January 1 to January 20, 2020.

Lunit’s commercial DL-based AI system was used to both detect the presence of the ETT and measure the distance from the tip of the ETT to the carina (TCD). Human readers set the standard for proper ETT placement as a TCD between 3 cm and 7 cm. A "critical" ETT placement was separately categorized as either an ETT tip located below the carina or a TCD equal to or less than 1 cm. Remarkably, the AI system exhibited a sensitivity range of 99.2–100% in identifying ETT presence and a specificity range of 94.5–98.7% across all three patient samples from the two institutions. For improper ETT positioning, it showed a sensitivity of 72.5–83.7% and specificity of 92.0–100%. For detecting critical ETT positioning, the system achieved 100% sensitivity in all samples and a specificity range of 96.7–100%.

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

Related Links:
Seoul National University Hospital

Gold Member
Solid State Kv/Dose Multi-Sensor
Breast Imaging Workstation
Silver Member
Mobile X-Ray Barrier
Lead Acrylic Mobile X-Ray Barriers
DR Flat Panel Detector

Print article



view channel
Image: The emerging role of MRI alongside PSA testing is redefining prostate cancer diagnostics (Photo courtesy of 123RF)

Combining MRI with PSA Testing Improves Clinical Outcomes for Prostate Cancer Patients

Prostate cancer is a leading health concern globally, consistently being one of the most common types of cancer among men and a major cause of cancer-related deaths. In the United States, it is the most... Read more

Nuclear Medicine

view channel
Image: The new SPECT/CT technique demonstrated impressive biomarker identification (Journal of Nuclear Medicine: doi.org/10.2967/jnumed.123.267189)

New SPECT/CT Technique Could Change Imaging Practices and Increase Patient Access

The development of lead-212 (212Pb)-PSMA–based targeted alpha therapy (TAT) is garnering significant interest in treating patients with metastatic castration-resistant prostate cancer. The imaging of 212Pb,... Read more

General/Advanced Imaging

view channel
Image: The Tyche machine-learning model could help capture crucial information. (Photo courtesy of 123RF)

New AI Method Captures Uncertainty in Medical Images

In the field of biomedicine, segmentation is the process of annotating pixels from an important structure in medical images, such as organs or cells. Artificial Intelligence (AI) models are utilized to... Read more

Imaging IT

view channel
Image: The new Medical Imaging Suite makes healthcare imaging data more accessible, interoperable and useful (Photo courtesy of Google Cloud)

New Google Cloud Medical Imaging Suite Makes Imaging Healthcare Data More Accessible

Medical imaging is a critical tool used to diagnose patients, and there are billions of medical images scanned globally each year. Imaging data accounts for about 90% of all healthcare data1 and, until... Read more
Copyright © 2000-2024 Globetech Media. All rights reserved.