Automatic annotation of cervical vertebrae in videofluoroscopy images via deep learning
Open accessAbstract
Judging swallowing kinematic impairments via videofluoroscopy represents the gold standard for the detection and evaluation of swallowing disorders. However, the efficiency and accuracy of such a biomechanical kinematic analysis vary significantly among human judges affected mainly by their training and experience. Here, we showed that a novel machine learning algorithm can with high accuracy automatically detect key anatomical points needed for a routine swallowing assessment in real-time. We trained a novel two-stage convolutional neural network to localize and measure the vertebral bodies using 1518 swallowing videofluoroscopies from 265 patients. Our network model yielded high accuracy as the mean distance between predicted points and annotations was 4.20 ± 5.54 pixels. In comparison, human inter-rater error was 4.35 ± 3.12 pixels. Furthermore, 93% of predicted points were less than five pixels from annotated pixels when tested on an independent dataset from 70 subjects. Our model offers more choices for speech language pathologists in their routine clinical swallowing assessments as it provides an efficient and accurate method for anatomic landmark localization in real-time, a task previously accomplished using an off-line time-sinking procedure.
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
Deep learning models such as U-Net and CNNs achieved F1 scores exceeding 0.9 and accuracy rates of 97.8% in detecting swallowing events and anatomical structures.
“deep learning models like U-Net and CNNs have achieved performance metrics such as F1 scores exceeding 0.9 and accuracy rates of 97.8%, indicating their robustness in detecting swallowing events and anatomical structures.”
From Artificial intelligence in the diagnosis and management of dysphagia: a scoping review (2025) · cites this paper as [75]
The Abstract (page unavailable) reports that a two-stage convolutional neural network localized cervical vertebral landmarks in swallowing videos, supporting the anatomical-structure portion of the claim. It reports 93% of predicted points within five pixels of annotations, not an F1 score above 0.9 or 97.8% accuracy. The paper does not report U-Net performance or its model detecting swallowing events. (LLM, conf=0.88)
Experimental — accuracy not yet measuredAI-driven tools have potential to improve diagnostic accuracy for dysphagia.
“These findings emphasize the potential of AI-driven tools in improving diagnostic accuracy for dysphagia(51,68,69,75).”
From Artificial intelligence in the diagnosis and management of dysphagia: a scoping review (2025) · cites this paper as [75]
Support vector machines (SVM) and Mask-RCNN demonstrated high accuracy in classifying swallowing events, with sensitivity and specificity reaching over 90%.
“Other methods, including support vector machines (SVM) and Mask-RCNN, have demonstrated high accuracy in classifying swallowing events, with metrics like sensitivity and specificity reaching over 90%.”
From Artificial intelligence in the diagnosis and management of dysphagia: a scoping review (2025) · cites this paper as [75]
The Abstract and Results describe a two-stage convolutional network that localizes cervical vertebrae in swallowing videos; the reported measures concern landmark location, not sensitivity or specificity for classifying swallowing events. Searches for SVM, Mask-RCNN, and sensitivity and specificity over 90% found no passage addressing that claim in our copy. (LLM, conf=0.76)
Experimental — accuracy not yet measured
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Cites
Proceedings of IEEE Conference on Computer Vision and Pattern Recognition
(1993) · doi:10.1109/cvpr.1993 · Cited by 17,989 · see citing works
A survey on deep learning in medical image analysis
Litjens, G., Kooi, T., Bejnordi, B. E., Setio, A. A. A., Ciompi, F., Ghafoorian, M., van der Laak, J. A. W. M., van Ginneken, B., & Sánchez, C. I. (2017) · Medical Image Analysis · doi:10.1016/j.media.2017.07.005 · Cited by 15,332 · see citing works
Proceedings of IEEE International Conference on Computer Vision
(1995) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.1995.466933 · Cited by 13,117 · see citing works
Identity mappings in deep residual networks
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-46493-0_38 · Cited by 10,741 · see citing works
A Survey on Bias and Fairness in Machine Learning
Mehrabi, N., Morstatter, F., Saxena, N., Lerman, K., & Galstyan, A. (2022) · ACM Computing Surveys · doi:10.1145/3457607 · Cited by 5,812 · see citing works
Proceedings European Conference on Computer Vision 2002
Heyden, A., Sparr, G., Nielsen, M., & Johansen, P. (2002) · Lund University Publications (Lund University) · Cited by 5,153 · see citing works
Deep learning as a tool for increased accuracy and efficiency of histopathological diagnosis
Litjens, G., Sánchez, C. I., Timofeeva, N., Hermsen, M., Nagtegaal, I., Kovacs, I., Hulsbergen - van de Kaa, C., Bult, P., van Ginneken, B., & van der Laak, J. (2016) · Scientific Reports · doi:10.1038/srep26286 · Cited by 1,069 · see citing works
Microscopy cell counting and detection with fully convolutional regression networks
Xie, W., Noble, J. A., & Zisserman, A. (2016) · Computer Methods in Biomechanics and Biomedical Engineering Imaging & Visualization · doi:10.1080/21681163.2016.1149104 · Cited by 457 · see citing works
Dysphagia in acute stroke: incidence, burden and impact on clinical outcome
Arnold, M., Liesirova, K., Broeg-Morvay, A., Meisterernst, J., Schlager, M., Mono, M.-L., El-Koussy, M., Kägi, G., Jung, S., & Sarikaya, H. (2016) · PLOS ONE · doi:10.1371/journal.pone.0148424 · Cited by 398 · see citing works
Deep Learning and Data Labeling for Medical Applications
Cornebise, J., Cardoso, J. S., Lu, Z., Loog, M., Nascimento, J. C., Papa, J. P., Belagiannis, V., Tavares, J. M. R. S., Bradley, A. P., Peter, L., et al. (2016) · Lecture notes in computer science · doi:10.1007/978-3-319-46976-8 · Cited by 351 · see citing works
Data Augmentation for Brain-Tumor Segmentation: A Review
Nalepa, J., Marcinkiewicz, M., & Kawulok, M. (2019) · Frontiers in Computational Neuroscience · doi:10.3389/fncom.2019.00083 · Cited by 340 · see citing works
Ngo, T. A., Lu, Z., & Carneiro, G. (2016) · Medical Image Analysis · doi:10.1016/j.media.2016.05.009 · Cited by 334 · see citing works
Artificial intelligence and machine learning in spine research
Galbusera, F., Casaroli, G., & Bassani, T. (2019) · JOR Spine · doi:10.1002/jsp2.1044 · Cited by 324 · see citing works
Iterative fully convolutional neural networks for automatic vertebra segmentation and identification
Leßmann, N., van Ginneken, B., de Jong, P. A., & Išgum, I. (2019) · Medical Image Analysis · doi:10.1016/j.media.2019.02.005 · Cited by 284 · see citing works
Retinal vessel segmentation via deep learning network and fully-connected conditional random fields
Fu, H., Xu, Y., Wong, D. W. K., et al. (2016) · IEEE International Symposium on Biomedical Imaging (ISBI) · doi:10.1109/isbi.2016.7493362 · Cited by 283 · see citing works
Estimating CT Image from MRI Data Using 3D Fully Convolutional Networks
Nie, D., Cao, X., Gao, Y., Wang, L., & Shen, D. G. (2016) · Lecture notes in computer science · doi:10.1007/978-3-319-46976-8_18 · Cited by 255 · see citing works
Rethinking on Multi-Stage Networks for Human Pose EstimationPreprint
Li, W., Wang, Z., Yin, B., Peng, Q., Du, Y., Xiao, T., Yu, G., Lu, H., Wei, Y., & Sun, J. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1901.00148 · Cited by 254 · see citing works
Lv, J.-J., Shao, X., Xing, J., Cheng, C., & Zhou, X. (2017) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2017.393 · Cited by 244 · see citing works
Fiberoptic Endoscopic Evaluation of Dysphagia to Identify Silent Aspiration
Leder, S. B., Sasaki, C. T., & Burrell, M. I. (1998) · Dysphagia · doi:10.1007/pl00009544 · Cited by 236 · see citing works
Radiological images and machine learning: Trends, perspectives, and prospects
Zhang, Z., & Sejdić, E. (2019) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2019.02.017 · Cited by 236 · see citing works
Self-citationConvolutional Experts Constrained Local Model for 3D Facial Landmark Detection
Zadeh, A., Lim, Y. C., Baltrušaitis, T., & Morency, L. (2017) · IEEE International Conference on Computer Vision Workshops · doi:10.1109/iccvw.2017.296 · Cited by 211 · see citing works
The relationship between hyoid and laryngeal displacement and swallowing impairment
Steele, C. M., Bailey, G. L., Chau, T. T., et al. (2010) · Clinical Otolaryngology · doi:10.1111/j.1749-4486.2010.02219.x · Cited by 178 · see citing works
Chang, H., Han, J., Zhong, C., Snijders, A. M., & Mao, J. (2017) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2017.2656884 · Cited by 175 · see citing works
Health-Related Quality of Life and Oropharyngeal Dysphagia: A Systematic Review
Jones, E., Speyer, R., Kertscher, B., Denman, D., Swan, K., & Cordier, R. (2017) · Dysphagia · doi:10.1007/s00455-017-9844-9 · Cited by 144 · see citing works
Approaching human level facial landmark localization by deep learning
Fan, H., & Zhou, E. (2015) · Image and Vision Computing · doi:10.1016/j.imavis.2015.11.004 · Cited by 117 · see citing works
Forsberg, D., Sjöblom, E., & Sunshine, J. L. (2017) · Journal of Imaging Informatics in Medicine · doi:10.1007/s10278-017-9945-x · Cited by 109 · see citing works
Proceedings. 18th IEEE Symposium on Computer-Based Medical Systems
(2005) · Proceedings - IEEE Symposium on Computer-Based Medical Systems · doi:10.1109/cbms.2005.2 · Cited by 108 · see citing works
Cervical lordosis: the effect of age and gender
Been, E., Shefi, S., & Soudack, M. (2017) · The Spine Journal · doi:10.1016/j.spinee.2017.02.007 · Cited by 102 · see citing works
Molfenter, S. M., & Steele, C. M. (2014) · Journal of Speech Language and Hearing Research · doi:10.1044/2014_jslhr-s-13-0152 · Cited by 97 · see citing works
Dysphagia Revisited: Common and Unusual Causes
Carucci, L. R., & Turner, M. A. (2015) · Radiographics · doi:10.1148/rg.351130150 · Cited by 87 · see citing works
Cervical Auscultation Synchronized with Images from Endoscopy Swallow Evaluations
Leslie, P., Drinnan, M. J., Zammit-Maempel, I., Coyle, J. L., Ford, G. A., & Wilson, J. A. (2007) · Dysphagia · doi:10.1007/s00455-007-9084-5 · Cited by 76 · see citing works
Self-citationChen, Y., Gao, Y., Li, K., Zhao, L., & Zhao, J. (2019) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2019.2927289 · Cited by 69 · see citing works
Automatic hyoid bone detection in fluoroscopic images using deep learning
Zhang, Z., Coyle, J. L., & Sejdić, E. (2018) · Scientific Reports · doi:10.1038/s41598-018-30182-6 · Cited by 64 · see citing works
Self-citationSeo, H. G., Oh, B., & Han, T. R. (2015) · Dysphagia · doi:10.1007/s00455-015-9670-x · Cited by 56 · see citing works
Style Aggregated Network for Facial Landmark DetectionPreprint
Dong, X., Yan, Y., Ouyang, W., et al. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1803.04108 · Cited by 54 · see citing works
Steele, C. M., Mukherjee, R., Kortelainen, J. M., Pölönen, H., Jedwab, M. R., Brady, S. L., Theimer, K. B., Langmore, S. E., Riquelme, L. F., Swigert, N. B., et al. (2019) · Dysphagia · doi:10.1007/s00455-018-09974-5 · Cited by 52 · see citing works
Computer-Assisted Assessment of Hyoid Bone Motion from Videofluoroscopic Swallow Studies
Kellen, P. M., Becker, D., Reinhardt, J. M., & Daele, D. J. V. (2009) · Dysphagia · doi:10.1007/s00455-009-9261-9 · Cited by 48 · see citing works
He, Q., Perera, S., Khalifa, Y., Zhang, Z., Mahoney, A. S., Sabry, A., Donohue, C., Coyle, J. L., & Sejdić, E. (2019) · IEEE Transactions on Neural Systems and Rehabilitation Engineering · doi:10.1109/tnsre.2019.2935302 · Cited by 39 · see citing works
Self-citationThe Prediction of Risk of Penetration–Aspiration Via Hyoid Bone Displacement Features
Zhang, Z., Perera, S., Donohue, C., Kurosu, A., Mahoney, A. S., Coyle, J. L., & Sejdić, E. (2019) · Dysphagia · doi:10.1007/s00455-019-10000-5 · Cited by 31 · see citing works
Self-citationAssessment of swallowing and its disorders—A dynamic MRI study
Kumar, K. V., Shankar, V., & Santosham, R. (2012) · European Journal of Radiology · doi:10.1016/j.ejrad.2012.09.010 · Cited by 22 · see citing works
Automatic Classification System for Lumbar Spine X-ray Images
Koompairojn, S., Hua, K. A., & Bhadrakom, C. (2006) · Proceedings - IEEE Symposium on Computer-Based Medical Systems · doi:10.1109/cbms.2006.54 · Cited by 22 · see citing works
Lee, J. C., Nam, K. W., Jang, D. P., Paik, N., Ryu, J. S., & Kim, I. Y. (2016) · Dysphagia · doi:10.1007/s00455-016-9759-x · Cited by 19 · see citing works
Semi-automatic assessment of hyoid bone motion in digital videofluoroscopic images
Hossain, I., Roberts-South, A., Jog, M., & El-Sakka, M. R. (2014) · Comput. methods Biomech. Biomed. Eng. Imaging Vis. · doi:10.1080/21681163.2013.833859 · Cited by 17 · see citing works
Lee, J. T., & Park, E. (2018) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-00919-9_38 · Cited by 7 · see citing works
A Deep Learning Approach to Detect Hyoid Bone in Ultrasound Exam
Lopes, M. R., Santos, A. S., Silva, C., et al. (2019) · Brazilian Conference on Intelligent Systems · doi:10.1109/bracis.2019.00102 · Cited by 4 · see citing works
Landmark localization approach for facial computing
Angulu, R., Adewumi, A. O., & Tapamo, J. (2017) · doi:10.1109/ictas.2017.7920664 · Cited by 3 · see citing works
Flagged first, then by citations
Cited by
Sorted by citations
Artificial Intelligence in Videofluoroscopy Swallow Study Analysis: A Comprehensive Review
Sanjeevi, G., Gopalakrishnan, U., Pathinarupothi, R. K., & Iyer, K. S. (2025) · Dysphagia · doi:10.1007/s00455-025-10812-8 · Cited by 12 · see citing works
Artificial intelligence in the diagnosis and management of dysphagia: a scoping review
Silva, R. D. D., Almeida, S. B., Gonçalves, F. M., Zeigelboim, B. S., Stechman-Neto, J., Schroder, A. G. D., Nascimento, W. V., Santos, R. S., & Araujo, C. M. D. (2025) · CoDAS · doi:10.1590/2317-1782/e20240305en · Cited by 6 · see citing works
- Authors
- Zhang, Z., Mao, S., Coyle, J., & Sejdić, E.
- Affiliations
- University of Pittsburgh (US)
- University of Toronto (CA)
- Corresponding author
- Sejdić, Ervin
- Venue
- Medical Image Analysis
- Publisher
- Elsevier BV
- Published
- 2021-12
- Volume
- 74
- Pages
- 102218
- ISSN
- 1361-8415 (ISSN-L)
- PMC
- PMC8560570
- OpenAlex
- W3195607837
- Cited by
- 18
- References
- 47
- Citations by year
- 2026: 2 · 2025: 7 · 2024: 5 · 2023: 2 · 2022: 2
- FWCI
- 0.68
- Type
- journal article
- Language
- en
- Open access
- green
- www.ncbi.nlm.nih.gov
- Licence
- Locations
- Medical Image Analysis (publishedVersion)
- PubMed (publishedVersion)
- PubMed Central (acceptedVersion)
- Funders
- National Institutes of Health (R01HD074819, R01HD092239)
- Eunice Kennedy Shriver National Institute of Child Health and Human Development
- Topics
- Physical Sciences › Engineering › Biomedical Engineering › Medical Imaging and Analysis
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Medical Image Segmentation Techniques
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
- Keywords
- cervical vertebrae, videofluoroscopy, dysphagia, two-stage convolutional neural network, interobserver variability, real-time image analysis, speech-language pathology
- MeSH terms
- Machine Learning, Deep Learning, Algorithms, Cervical Vertebrae, Humans, Neural Networks, Computer
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
