A Supporting Platform for Semi-Automatic Hyoid Bone Tracking and Parameter Extraction from Videofluoroscopic Images for the Diagnosis of Dysphagia Patients
- 521 Downloads
Conventional kinematic analysis of videofluoroscopic (VF) swallowing image, most popular for dysphagia diagnosis, requires time-consuming and repetitive manual extraction of diagnostic information from multiple images representing one swallowing period, which results in a heavy work load for clinicians and excessive hospital visits for patients to receive counseling and prescriptions. In this study, a software platform was developed that can assist in the VF diagnosis of dysphagia by automatically extracting a two-dimensional moving trajectory of the hyoid bone as well as 11 temporal and kinematic parameters. Fifty VF swallowing videos containing both non-mandible-overlapped and mandible-overlapped cases from eight patients with dysphagia of various etiologies and 19 videos from ten healthy controls were utilized for performance verification. Percent errors of hyoid bone tracking were 1.7 ± 2.1% for non-overlapped images and 4.2 ± 4.8% for overlapped images. Correlation coefficients between manually extracted and automatically extracted moving trajectories of the hyoid bone were 0.986 ± 0.017 (X-axis) and 0.992 ± 0.006 (Y-axis) for non-overlapped images, and 0.988 ± 0.009 (X-axis) and 0.991 ± 0.006 (Y-axis) for overlapped images. Based on the experimental results, we believe that the proposed platform has the potential to improve the satisfaction of both clinicians and patients with dysphagia.
KeywordsDysphagia Videofluoroscopic Hyoid bone Diagnosis Deglutition Deglutition disorders
This research was supported by the Basic Science Research Program through the National Research Foundation of Korea (NRF) funded by the Ministry of Science, ICT and Future Planning (NRF-2013R1A1A1004622 and NRF-2015R1D1A1A01058652).
Compliance with Ethical Standards
Conflict of interest
There are no conflict of interest to report.
Supplementary material 1 (AVI 22902 kb)
- 7.US Census 2010—US Census Bureau. Populations Projections Program. Department of Commerce, Population Division. Accessed https://www.census.gov/aian/census_2010/.
- 8.DJO Global. Who is Affected: dysphagia by the numbers. DJO Global. Accessed http://www.djoglobal.com/vitalstim/what-dysphagia/who-affected.
- 11.Smith NR, Klongtruagrok T, DeSouza GN, Shyu CR, Dietrich M, Page MP. Non-invasive ambulatory monitoring of complex sEMG patterns and its potential application in the detection of vocal dysfunctions. E-Health networking, applications and services (Healthcom), 2014 IEEE 16th international conference on. 2014: pp 447–452.Google Scholar
- 12.Imtiaz U, Yamamura K, Kong W, Sessa S, Lin Z, Bartolomeo L, Takanishi A. Application of wireless inertial measurement units and EMG sensors for studying deglutition—preliminary results. International Conference IEEE EMBC. 2014: pp 5381–5384.Google Scholar
- 27.Aboofazeli M, Moussavi Z. Analysis and classification of swallowing sounds using reconstructed phase space features. International Conference IEEE ICASSP’05. 2005: pp 421–424.Google Scholar
- 28.Spadotto AA, Gatto AR, Guido RC, Montagnoli AN, Cola PC, Pereira JC, Schelp AO. Classification of normal swallowing and oropharyngeal dysphagia using wavelet. Appl Math Comput. 2009;207:75–82.Google Scholar
- 31.Reddy NP, Thomas R, Canilang EP, Casterline J. Toward classification of dysphagic patients using biomechanical measurements. J Rehab Res Develop. 1994;31:335–44.Google Scholar