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 Apr 9;19(8):4529.
doi: 10.3390/ijerph19084529.

A Basic Study for Predicting Dysphagia in Panoramic X-ray Images Using Artificial Intelligence (AI)-Part 1: Determining Evaluation Factors and Cutoff Levels

Yukiko Matsuda  1 , Emi Ito  1 , Migiwa Kuroda  1 , Kazuyuki Araki  1
Affiliations

A Basic Study for Predicting Dysphagia in Panoramic X-ray Images Using Artificial Intelligence (AI)-Part 1: Determining Evaluation Factors and Cutoff Levels

Yukiko Matsuda et al. Int J Environ Res Public Health. .

Abstract

Background: Dysphagia relates to quality of life; this disorder is related to the difficulties of dental treatment.

Purpose: To detect radiographic signs of dysphagia by using panoramic radiograph with an AI system.

Methods: Seventy-seven patients who underwent a panoramic radiograph and a videofluorographic swallowing study were analyzed. Age, gender, the number of remaining teeth, the distance between the tongue and the palate, the vertical and horizontal hyoid bone position, and the width of the tongue were analyzed. Logistic regression analysis was used. For the statistically significant factors, the cutoff level was determined. The cutoff level was determined by using analysis of the receiver operations characteristic (ROC) curve and the Youden Index.

Results: A significant relationship with presence of dysphagia was only observed for the vertical hyoid bone position. The area under the curve (AUC) was 0.72. The cutoff level decided for the hyoid bone was observed to be lower than the mandibular border line.

Conclusions: In cases where the hyoid bone is lower than the mandibular border line on a panoramic radiograph, it suggests the risk of dysphagia would be high. We will create an AI model for the detection of the risk of dysphagia by using the assessment of vertical hyoid bone position.

Keywords: dysphagia; panoramic radiograph; vertical hyoid bone position.

PubMed Disclaimer

Conflict of interest statement

The funders had no role in the design of the study; in the collection, analyses, or interpretation of data; in the writing of the manuscript; or in the decision to publish the results.

Figures

Figure 1
Figure 1
Vertical hyoid bone position. Mandibular border line was defined as a line that moves virtual line which is connecting the both side of mandibular angles, in parallel along the center line and attach to the lowest point of the mandibular inferior edge. An evaluation was conducted of the extent to which the hyoid body and greater horn appeared in the upper area from the mandibular border line.
Figure 2
Figure 2
Sample images of vertical hyoid bone position. Arrow shows the hyoid bone. On Type 0, hyoid bone is invisible.
Figure 3
Figure 3
Horizontal hyoid bone position. The horizontal hyoid bone position was graded by the position of the anterior point of the hyoid body.
Figure 4
Figure 4
Sample images of horizontal hyoid bone position. Arrow shows the anterior point of the hyoid body.
Figure 5
Figure 5
Measurement from the surface of the tongue to the palate on the midline (mm). Double sided arrow shows the measurement between the palate to tongue.
Figure 6
Figure 6
Width of the tongue. The location where the outer border of tongue overlapped the anatomical structure was assessed.
Figure 7
Figure 7
Sample images of width of tongue. Arrows show the outer border of the tongue.
Figure 8
Figure 8
Sample VF images. Left image shows the aspiration and right image shows penetration.
Figure 9
Figure 9
The ROC curve of the vertical hyoid bone position. The AUC was 0.715.
See this image and copyright information in PMC

References

    1. Tuzoff D.V., Tuzova L.N., Bornstein M.M., Krasnov A.S., Kharchenko M.A., Nikolenko S.I., Sveshnikov M.M., Bednenko G.B. Tooth detection and numbering in panoramic radiographs using convolutional neural networks. Dentomaxillofac. Radiol. 2019;48:4. doi: 10.1259/dmfr.20180051. - DOI - PMC - PubMed
    1. Ohashi Y., Ariji Y., Katsumata A., Fujita H., Nakayama M., Fukuda M., Nozawa M., Ariji E. Utilization of computer-aided detection system in diagnosing unilateral maxillary sinusitis on panoramic radiographs. Dentomaxillofac. Radiol. 2016;45:3. doi: 10.1259/dmfr.20150419. - DOI - PMC - PubMed
    1. Nurtanio I., Astuti E.R., Pumama I.K.E., Hariadi M., Purnomo M.H. Classifying cyst and tumor lesion using support vector machine based on dental panoramic images texture features. IAENG Int. J. Comput. Sci. 2013;40:29–37.
    1. Nakamoto T., Taguchi A., Ohtsuka M., Suei Y., Fujita M., Tsuda M., Sanada M., Kudo Y., Asano A., Tanimoto K. A computer-aided diagnosis system to screen for osteoporosis using dental panoramic radiographs. Dentomaxillofac. Radiol. 2008;37:274–281. doi: 10.1259/dmfr/68621207. - DOI - PubMed
    1. Sawagashira T., Hayashi T., Hara T., Katsumata A., Muramatsu C., Zhou X., Iida Y., Katagi K., Fujita H. An automatic detection method for carotid artery calcifications using top-hat filter on dental panoramic radiographs. IEICE Trans. Inf. Syst. 2013;96:1878–1881. doi: 10.1587/transinf.E96.D.1878. - DOI - PubMed

Publication types

LinkOut - more resources