Novel automatic endotracheal position confirmation system: Mannequin model algorithm evaluation
- 76 Downloads
A novel endotracheal intubation accurate positioning confirmation system based on image classification algorithm is introduced and evaluated using a mannequin model.
The system comprises a miniature complementary metal oxide silicon sensor (CMOS) attached to the tip of a semi rigid stylet and connected to a digital signal processor (DSP) with an integrated video acquisition component. Video signals acquired and processed by an algorithm implemented on the processor. During mannequin intubations, video signals were continuously recorded. A total of 10 videos were recorded. From each video, 7 images of esophageal intubation and 8 images of endotracheal intubation (in which the carina could be clearly seen) were extracted, yielding a total of 150 images taken from arbitrary positions and angles which were processed by the confirmation algorithm.
The performance of the confirmation algorithm was evaluated using a leave-one-out method: in each iteration, 149 images were used to train the system and estimate the models, and the remaining image was used to test the system. This process was repeated 150 times such that each image participated once in testing. The system correctly identified 80 out of 80 endotracheal intubations and 70 out of 70 esophageal intubations.
This fully automatic image recognition system was used successfully to discriminate airway carina and non-carina endotracheal tube positioning. The system had a 100% success rate using a mannequin model and therefore further investigation including live tissue model and human research should follow.
Keywordsairway management endotracheal intubation confirmation esophageal intubation detection image classification carina pattern recognition Gaussian mixture model one-lung intubation
Unable to display preview. Download preview PDF.
- 2.Yap SJ, Morris RW, Pybus DA. Alterations in endotracheal tube position during general anesthesia. Anaesth Crit Care. 1994;22:586–588.Google Scholar
- 5.Timmermann A, Russo SG, Eich C, Roessler M, Braun U, Rosenblatt WH, Quintel M. The out-of-hospital esophageal and endobronchial intubations performed by emergency physicians. Crit Care Trauma. 2007;104(3):619–623.Google Scholar
- 9.Klepper ID, Webb RK, Walt JVD, Ludbrooks GL, Cockings J. The stethoscope: application and limitation- an analysis of 2000 incident reports. Anaesth Intens Care. 1993;21(5):575–578.Google Scholar
- 11.Gravenstein JS, Jaffe MB, Paulus DA, editors. Capnography clinical aspects. Cambridge: Cambridge University Press; 2004.Google Scholar
- 13.Bjoraker DG. Airway management in the operating room. In: Capnography clinical aspects, chapter. Cambrdige: Cambrdige University Press; 2004. p. 39–44.Google Scholar
- 14.Bhende SM, Thompson AE. Evaluation of an end-tidal CO2 detector during pediatric cardiopulmonary resuscitation. Pediat. 1995;95(3):395–399.Google Scholar
- 16.Webb RK, Walt JHVD, Runciman WB, Williamson JA, Cockings J, Russell WJ, Helps S. Which monitor? an analysis of 2000 incident reports. Anaesth Intens Care. 1993;21(5):529–542.Google Scholar
- 19.Lederman D. An energy ratio test for one lung intubation detection, in Proceedings of the 18th Biennial International EURASIP Conference, Brno, Czech Republic. 2006.Google Scholar
- 25.Haralick RM, Shapiro LG. Computer and robot vision. Boston: Addison-Wesley Longman Publishing Co., Inc; 1992.Google Scholar
- 27.Jensen JR. Introductory image processing: a remote sensing perspective. 3rd ed. Upper Saddle River: Pearson Prentice Hall; 2005.Google Scholar
- 29.Duda RO, Hart PE, Stork DG. Pattern classification. 2nd ed. New Jork: A Wiley-Interscience Publication; 2000.Google Scholar
- 30.Rose RC, Reynolds DA. Text-independent speaker identification using automatic acoustic segmentation. In IEEE Int Conf Acous Speech and Signal Proc 1990; 293–296.Google Scholar
- 31.Reynolds DA. A Gaussian mixture modeling approach to text-independent speaker identification, Ph.D. thesis, Georgia Institute of Technology, Atlanta. 1992.Google Scholar
- 32.Dempster AP, Laird NM, Rubin DB. Maximum likelihood from incomplete data via the EM algorithm. J Roy Stat Soc B. 1977;39:1–38.Google Scholar