Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2022 Feb 14;37(6):e42.
doi: 10.3346/jkms.2022.37.e42.

Deep Learning Analysis to Automatically Detect the Presence of Penetration or Aspiration in Videofluoroscopic Swallowing Study

Jeoung Kun Kim  1 , Yoo Jin Choo  2 , Gyu Sang Choi  3 , Hyunkwang Shin  3 , Min Cheol Chang  4 , Donghwi Park  5
Affiliations

Deep Learning Analysis to Automatically Detect the Presence of Penetration or Aspiration in Videofluoroscopic Swallowing Study

Jeoung Kun Kim et al. J Korean Med Sci. .

Abstract

Background: Videofluoroscopic swallowing study (VFSS) is currently considered the gold standard to precisely diagnose and quantitatively investigate dysphagia. However, VFSS interpretation is complex and requires consideration of several factors. Therefore, considering the expected impact on dysphagia management, this study aimed to apply deep learning to detect the presence of penetration or aspiration in VFSS of patients with dysphagia automatically.

Methods: The VFSS data of 190 participants with dysphagia were collected. A total of 10 frame images from one swallowing process were selected (five high-peak images and five low-peak images) for the application of deep learning in a VFSS video of a patient with dysphagia. We applied a convolutional neural network (CNN) for deep learning using the Python programming language. For the classification of VFSS findings (normal swallowing, penetration, and aspiration), the classification was determined in both high-peak and low-peak images. Thereafter, the two classifications determined through high-peak and low-peak images were integrated into a final classification.

Results: The area under the curve (AUC) for the validation dataset of the VFSS image for the CNN model was 0.942 for normal findings, 0.878 for penetration, and 1.000 for aspiration. The macro average AUC was 0.940 and micro average AUC was 0.961.

Conclusion: This study demonstrated that deep learning algorithms, particularly the CNN, could be applied for detecting the presence of penetration and aspiration in VFSS of patients with dysphagia.

Keywords: Deep Learning; Deglutition; Swallowing Reflex; VFSS.

PubMed Disclaimer

Conflict of interest statement

The authors have no potential conflicts of interest to disclose.

Figures

Fig. 1
Fig. 1. The steps of the modeling process applied in this study.
VFSS = videofluoroscopic swallowing study.
Fig. 2
Fig. 2. ROC curve for the data validation models. The AUC of the validation dataset of the VFSS images for the convolutional neural network model was 0.942 for normal findings, 0.878 for penetration, and 1.000 for aspiration. For calculating the average AUC, both macro and micro average AUC was employed. Macro average AUC was 0.940 and micro average AUC was 0.961.
AUC = area under the curve, ROC = receiver operating characteristic, VFSS = videofluoroscopic swallowing study.
See this image and copyright information in PMC

References

    1. Steele CM, Miller AJ. Sensory input pathways and mechanisms in swallowing: a review. Dysphagia. 2010;25(4):323–333. - PMC - PubMed
    1. Ertekin C. Electrophysiological evaluation of oropharyngeal dysphagia in Parkinson's disease. J Mov Disord. 2014;7(2):31–56. - PMC - PubMed
    1. Park S, Cho JY, Lee BJ, Hwang JM, Lee M, Hwang SY, et al. Effect of the submandibular push exercise using visual feedback from pressure sensor: an electromyography study. Sci Rep. 2020;10(1):11772. - PMC - PubMed
    1. Shaker R, Geenen JE. Management of dysphagia in stroke patients. Gastroenterol Hepatol (N Y) 2011;7(5):308–332. - PMC - PubMed
    1. Finestone HM, Greene-Finestone LS. Rehabilitation medicine: 2. Diagnosis of dysphagia and its nutritional management for stroke patients. CMAJ. 2003;169(10):1041–1044. - PMC - PubMed