Automatic Hyoid Bone Tracking in Real-Time Ultrasound Swallowing Videos Using Deep Learning Based and Correlation Filter Based Trackers
| Autor: | Cheuk Ning Tang, Kwok Yan Ng, Shurui Feng, Elaine Kwong, Yongping Zheng, Queenie Tsung Kwan Shea |
|---|---|
| Rok vydání: | 2021 |
| Předmět: |
Computer science
dysphagia SiamFC real-time 02 engineering and technology TP1-1185 Biochemistry Article 030218 nuclear medicine & medical imaging Analytical Chemistry 03 medical and health sciences 0302 clinical medicine Swallowing stomatognathic system 0202 electrical engineering electronic engineering information engineering medicine Humans Computer vision Electrical and Electronic Engineering correlation filters Instrumentation Pixel ultrasound videos business.industry hyoid bone Deep learning Chemical technology Hyoid bone Frame (networking) Ultrasound deep learning tracking Frame rate Dysphagia Atomic and Molecular Physics and Optics Deglutition Fluoroscopy 020201 artificial intelligence & image processing Artificial intelligence medicine.symptom business Deglutition Disorders swallowing |
| Zdroj: | Sensors (Basel, Switzerland) Sensors, Vol 21, Iss 3712, p 3712 (2021) Sensors Volume 21 Issue 11 |
| ISSN: | 1424-8220 |
| Popis: | (1) Background: Ultrasound provides a radiation-free and portable method for assessing swallowing. Hyoid bone locations and displacements are often used as important indicators for the evaluation of swallowing disorders. However, this requires clinicians to spend a great deal of time reviewing the ultrasound images. (2) Methods: In this study, we applied tracking algorithms based on deep learning and correlation filters to detect hyoid locations in ultrasound videos collected during swallowing. Fifty videos were collected from 10 young, healthy subjects for training, evaluation, and testing of the trackers. (3) Results: The best performing deep learning algorithm, Fully-Convolutional Siamese Networks (SiamFC), proved to have reliable performance in getting accurate hyoid bone locations from each frame of the swallowing ultrasound videos. While having a real-time frame rate (175 fps) when running on an RTX 2060, SiamFC also achieved a precision of 98.9% at the threshold of 10 pixels (3.25 mm) and 80.5% at the threshold of 5 pixels (1.63 mm). The tracker’s root-mean-square error and average error were 3.9 pixels (1.27 mm) and 3.3 pixels (1.07 mm), respectively. (4) Conclusions: Our results pave the way for real-time automatic tracking of the hyoid bone in ultrasound videos for swallowing assessment. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|