CoChat

A preliminary deep learning study on automatic segmentation of contrast-enhanced bolus in videofluorography of swallowing

Open access

The DOI matches its Crossref record; the references it cites are not checked yet.

Abstract

Although videofluorography (VFG) is an effective tool for evaluating swallowing functions, its accurate evaluation requires considerable time and effort. This study aimed to create a deep learning model for automated bolus segmentation on VFG images of patients with healthy swallowing and dysphagia using the artificial intelligence deep learning segmentation method, and to assess the performance of the method. VFG images of 72 swallowing of 12 patients were continuously converted into 15 static images per second. In total, 3910 images were arbitrarily assigned to the training, validation, test 1, and test 2 datasets. In the training and validation datasets, images of colored bolus areas were prepared, along with original images. Using a U-Net neural network, a trained model was created after 500 epochs of training. The test datasets were applied to the trained model, and the performances of automatic segmentation (Jaccard index, Sørensen–Dice coefficient, and sensitivity) were calculated. All performance values for the segmentation of the test 1 and 2 datasets were high, exceeding 0.9. Using an artificial intelligence deep learning segmentation method, we automatically segmented the bolus areas on VFG images; our method exhibited high performance. This model also allowed assessment of aspiration and laryngeal invasion.

Overview

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1038/s41598-022-21530-8

Cites

Statistics

Figures

Figure 1 Examples of contrast bolus segmentation using deep learning (A) The contrast bolus was accurately predicted. (B) The contrast bolus was not accurately predicted. This may have been caused by false-positive detection of the metals and chin area. (C) The contrast bolus, including area showing aspiration swallowing, was accurately predicted. (D) The retention of contrast medium in the pyriform sinus was well-visualized.
Figure 1 Examples of contrast bolus segmentation using deep learning (A) The contrast bolus was accurately predicted. (B) The contrast bolus was not accurately predicted. This may have been caused by false-positive detection of the metals and chin area. (C) The contrast bolus, including area showing aspiration swallowing, was accurately predicted. (D) The retention of contrast medium in the pyriform sinus was well-visualized.CC BY · PubMed Central
Figure 2 Image preparation. (A) A static image converted from videofluorography video images. The image size is 720 × 480 pixels. (B) The image was standardized to a size of 256 × 256 pixels by cutting off extra space at the top and front of the original image, then converted to JPEG format.
Figure 2 Image preparation. (A) A static image converted from videofluorography video images. The image size is 720 × 480 pixels. (B) The image was standardized to a size of 256 × 256 pixels by cutting off extra space at the top and front of the original image, then converted to JPEG format.CC BY · PubMed Central
Figure 3 The U-Net neural network used for this study.
Figure 3 The U-Net neural network used for this study.CC BY · PubMed Central
Figure 4 Annotation using training and verification datasets. (A) Original image. (B) Image in which contrast-enhanced bolus areas were colored.
Figure 4 Annotation using training and verification datasets. (A) Original image. (B) Image in which contrast-enhanced bolus areas were colored.CC BY · PubMed Central
Figure 5 Training and inference processes. Following a 500-epoch training process using training and validation datasets paired with the original and colored images, a trained model was created. In the inference process, test dataset 1 or 2 was applied to the trained model and the model performance was evaluated.
Figure 5 Training and inference processes. Following a 500-epoch training process using training and validation datasets paired with the original and colored images, a trained model was created. In the inference process, test dataset 1 or 2 was applied to the trained model and the model performance was evaluated.CC BY · PubMed Central

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

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?

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

The citation lists are queued

They are fetched later and appear here then.

References 12 · Cited by 19

Metadata

Authors
Ariji, Y., Gotoh, M., Fukuda, M., Watanabe, S., Nagao, T., Katsumata, A., & Ariji, E.
Affiliations
  • Aichi Gakuin University (JP)
  • Asahi University (JP)
Corresponding author
Ariji, Eiichiro
Venue
Scientific Reports
Published
2022-11-05
Volume
12
Issue
1
Pages
18754-18754
ISSN
2045-2322 (ISSN-L)
OpenAlex
W4308262271
Cited by
19
References
12
Citations by year
2026: 4 · 2025: 6 · 2024: 4 · 2023: 5
FWCI
1.23
Type
journal article
Language
en
Open access
Licence
Locations
  • Scientific Reports (publishedVersion, cc-by)
  • PubMed Central (publishedVersion, cc-by)
  • PubMed (publishedVersion)
  • DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
Funders
Japan Society for the Promotion of Science (20K10194)
Topics
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Medical Image Segmentation Techniques
  • Health Sciences › Health Professions › Speech and Hearing › Dysphagia Assessment and Management
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
Keywords
videofluorography, swallowing, dysphagia, U-Net, deep learning segmentation, aspiration, laryngeal invasion
MeSH terms
Deep Learning, Artificial Intelligence, Deglutition, Humans, Image Processing, Computer-Assisted, 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

How to cite

Cite CoChat for the checks on this page, and the paper for its own findings.

This page
CoChat. (2026). Citation check: A preliminary deep learning study on automatic segmentation of contrast-enhanced bolus in videofluorography of swallowing. https://app.cochat.ai/papers/10.1038/s41598-022-21530-8
The paper
Ariji, Y., Gotoh, M., Fukuda, M., Watanabe, S., Nagao, T., Katsumata, A., & Ariji, E. (2022). A preliminary deep learning study on automatic segmentation of contrast-enhanced bolus in videofluorography of swallowing. Scientific Reports. https://doi.org/10.1038/s41598-022-21530-8

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.