Article: Endotracheal tubes positioning detection in adult portable chest radiography for intensive care unit

Purpose: To present an automated method for detecting endotracheal (ET) tubes and marking their tips in portable chest radiography (CXR) for intensive care units (ICUs).

Methods: In this method, the lung region is first estimated and then the spine is detected between the right lung and the left lung. Because medical tubes are inserted into the body through the throat, the region of interest (ROI) is obtained across the spine. A seed point is determined in the cervical region of the ROI, and then the line path is selected from the seed point. In order to detect ET tubes, the ICU CXR image is preprocessed by contrast-limited adaptive histogram equalization. Then, a feature-based threshold method is applied to the line path to determine the tip location. A comparison to the method by use of Hough transform is also presented. The distance (error) between the detected locations and the locations annotated by a radiologist is used to evaluate the detection precision for the tip location.

Results: The proposed method is evaluated using 44 images with ET tubes and 43 images without ET tubes. The discriminant performance for detecting the existence of ET tubes in this study was 95 %, and the average of detection error for the tip location was approximately 2.5 mm.

Conclusions: The proposed method could be useful for detecting malpositioned ET tubes in ICU CXRs.

Citing Articles

Detection and position evaluation of chest percutaneous drainage catheter on chest radiographs using deep learning.

Kim D, Nam I, Kim D, Kim J, Hwang I, Lee J PLoS One. 2024; 19(8):e0305859.

PMID: 39133733 PMC: 11318879. DOI: 10.1371/journal.pone.0305859.

Assessment of the Endotracheal Tube Tip Position by Bedside Ultrasound in a Pediatric Intensive Care Unit: A Cross-sectional Study.

Subramani S, Parameswaran N, Ananthkrishnan R, Abraham S, Chidambaram M, Rameshkumar R Indian J Crit Care Med. 2023; 26(11):1218-1224.

PMID: 36873587 PMC: 9983650. DOI: 10.5005/jp-journals-10071-24355.

Position Classification of the Endotracheal Tube with Automatic Segmentation of the Trachea and the Tube on Plain Chest Radiography Using Deep Convolutional Neural Network.

Jung H, Kim C, Oh J, Kim T, Kim B, Lee J J Pers Med. 2022; 12(9).

PMID: 36143148 PMC: 9503144. DOI: 10.3390/jpm12091363.

Detecting Endotracheal Tube and Carina on Portable Supine Chest Radiographs Using One-Stage Detector with a Coarse-to-Fine Attention.

Mao L, Huang M, Lai C, Sun Y, Chen C Diagnostics (Basel). 2022; 12(8).

PMID: 36010263 PMC: 9406505. DOI: 10.3390/diagnostics12081913.

Automatic Detection and Classification of Multiple Catheters in Neonatal Radiographs with Deep Learning.

Henderson R, Yi X, Adams S, Babyn P J Digit Imaging. 2021; 34(4):888-897.

PMID: 34173089 PMC: 8455735. DOI: 10.1007/s10278-021-00473-y.

References

1.

Trotman-Dickenson B . Radiology in the intensive care unit (Part I). J Intensive Care Med. 2004; 18(4):198-210. DOI: 10.1177/0885066603251897. View

2.

Sheng C, Li L, Pei W . Automatic detection of supporting device positioning in intensive care unit radiography. Int J Med Robot. 2009; 5(3):332-40. DOI: 10.1002/rcs.265. View

3.

Saleh M, Eswaran C, Mueen A . An automated blood vessel segmentation algorithm using histogram equalization and automatic threshold selection. J Digit Imaging. 2010; 24(4):564-72. PMC: 3138933. DOI: 10.1007/s10278-010-9302-9. View

4.

Blayney M, Logan D . First thoracic vertebral body as reference for endotracheal tube placement. Arch Dis Child Fetal Neonatal Ed. 1994; 71(1):F32-5. PMC: 1061065. DOI: 10.1136/fn.71.1.f32. View

5.

Chaudhury K, Sage D, Unser M . Fast O1 bilateral filtering using trigonometric range kernels. IEEE Trans Image Process. 2011; 20(12):3376-82. DOI: 10.1109/TIP.2011.2159234. View

6.

Kao E, Jaw T, Li C, Chou M, Liu G . Automated detection of endotracheal tubes in paediatric chest radiographs. Comput Methods Programs Biomed. 2014; 118(1):1-10. DOI: 10.1016/j.cmpb.2014.10.009. View

7.

Staib L, Duncan J . Model-based deformable surface finding for medical images. IEEE Trans Med Imaging. 1996; 15(5):720-31. DOI: 10.1109/42.538949. View

8.

McInerney T, Terzopoulos D . Deformable models in medical image analysis: a survey. Med Image Anal. 1996; 1(2):91-108. DOI: 10.1016/s1361-8415(96)80007-7. View

9.

Sofka M, Wetzl J, Birkbeck N, Zhang J, Kohlberger T, Kaftan J . Multi-stage learning for robust lung segmentation in challenging CT volumes. Med Image Comput Comput Assist Interv. 2011; 14(Pt 3):667-74. DOI: 10.1007/978-3-642-23626-6_82. View

10.

Al-Haj A, Amer A . Secured telemedicine using region-based watermarking with tamper localization. J Digit Imaging. 2014; 27(6):737-50. PMC: 4391064. DOI: 10.1007/s10278-014-9709-9. View

11.

Black J, Skinner D . Confirmation of correct endotracheal tube placement. J Accid Emerg Med. 2000; 17(1):74-5. PMC: 1756275. DOI: 10.1136/emj.17.1.74-a. View

Endotracheal Tubes Positioning Detection in Adult Portable Chest Radiography for Intensive Care Unit