Student or educator? Sign up with your school email and get 6 months of Pro free.
CoChat

The DOI matches its Crossref record; 40 of the 40 references it cites were found in a registry or an index.

Artificial intelligence-aided method to detect uterine fibroids in ultrasound images: a retrospective study

Open access

Published version of a preprint

Abstract

We explored a new artificial intelligence-assisted method to assist junior ultrasonographers in improving the diagnostic performance of uterine fibroids and further compared it with senior ultrasonographers to confirm the effectiveness and feasibility of the artificial intelligence method. In this retrospective study, we collected a total of 3870 ultrasound images from 667 patients with a mean age of 42.45 years ± 6.23 [SD] for those who received a pathologically confirmed diagnosis of uterine fibroids and 570 women with a mean age of 39.24 years ± 5.32 [SD] without uterine lesions from Shunde Hospital of Southern Medical University between 2015 and 2020. The DCNN model was trained and developed on the training dataset (2706 images) and internal validation dataset (676 images). To evaluate the performance of the model on the external validation dataset (488 images), we assessed the diagnostic performance of the DCNN with ultrasonographers possessing different levels of seniority. The DCNN model aided the junior ultrasonographers (Averaged) in diagnosing uterine fibroids with higher accuracy (94.72% vs. 86.63%, P < 0.001), sensitivity (92.82% vs. 83.21%, P = 0.001), specificity (97.05% vs. 90.80%, P = 0.009), positive predictive value (97.45% vs. 91.68%, P = 0.007), and negative predictive value (91.73% vs. 81.61%, P = 0.001) than they achieved alone. Their ability was comparable to that of senior ultrasonographers (Averaged) in terms of accuracy (94.72% vs. 95.24%, P = 0.66), sensitivity (92.82% vs. 93.66%, P = 0.73), specificity (97.05% vs. 97.16%, P = 0.79), positive predictive value (97.45% vs. 97.57%, P = 0.77), and negative predictive value (91.73% vs. 92.63%, P = 0.75). The DCNN-assisted strategy can considerably improve the uterine fibroid diagnosis performance of junior ultrasonographers to make them more comparable to senior ultrasonographers.

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/s41598-022-26771-1

Cites

40 of 40 references verified0 citation errors · 0 not checkable

Statistics

Figures

Figure 1 Flowchart of the procedures used in the development and evaluation of the DCNN model for automated uterine fibroid diagnosis. DCNN deep convolutional neural network.
Figure 1 Flowchart of the procedures used in the development and evaluation of the DCNN model for automated uterine fibroid diagnosis. DCNN deep convolutional neural network.CC BY · PubMed Central
Figure 2 Examples of original ultrasound data and sample data after labeling. (A) Training sample of ultrasound image with two uterine fibroids. (B) Training sample of ultrasound image with one fibroid. (C) Labeled training sample of ultrasound image with two uterine fibroids. (D) Labeled training sample of an ultrasound image with only one fibroid. The yellow box shows the extent of fibroids marked by the ultrasonographers.
Figure 2 Examples of original ultrasound data and sample data after labeling. (A) Training sample of ultrasound image with two uterine fibroids. (B) Training sample of ultrasound image with one fibroid. (C) Labeled training sample of ultrasound image with two uterine fibroids. (D) Labeled training sample of an ultrasound image with only one fibroid. The yellow box shows the extent of fibroids marked by the ultrasonographers.CC BY · PubMed Central
Figure 3 Outline of the DCNN for uterine fibroid detection. Schematic representation of the DCNN network architecture for uterine fibroid detection from ultrasound images. The CBL in front of each Res module acts as a downsampling. Con-cat = tensor concatenation, which expands the dimensionality of two tensors. Add: tensor summing, no dimensionality expansion. Convs Convolutional layers, CBL Minimum component in the structure of the YOLOv3 network united by the Conv + Bn + leaky-ReLU activation function. Res-Unit Residual structure, Res-X Large component in Yolov3 consisting of a CBL and X Res-Units.
Figure 3 Outline of the DCNN for uterine fibroid detection. Schematic representation of the DCNN network architecture for uterine fibroid detection from ultrasound images. The CBL in front of each Res module acts as a downsampling. Con-cat = tensor concatenation, which expands the dimensionality of two tensors. Add: tensor summing, no dimensionality expansion. Convs Convolutional layers, CBL Minimum component in the structure of the YOLOv3 network united by the Conv + Bn + leaky-ReLU activation function. Res-Unit Residual structure, Res-X Large component in Yolov3 consisting of a CBL and X Res-Units.CC BY · PubMed Central
Figure 4 Uterine fibroid detection results. (A) Target detection results of multiple uterine fibroids in a single ultrasound image. (B) Target detection results of a single uterine fibroid in a single ultrasound image. (C) Target detection results of single uterine fibroids in patients with double ultrasound images. (D) Target detection results of multiple uterine fibroids in patients with double ultrasound images. Green boxes are the GT boxes annotated by our invited radiologists, and blue boxes are the boxes predicted by the trained model. The number marked in the upper left corner is the model detection confidence score.
Figure 4 Uterine fibroid detection results. (A) Target detection results of multiple uterine fibroids in a single ultrasound image. (B) Target detection results of a single uterine fibroid in a single ultrasound image. (C) Target detection results of single uterine fibroids in patients with double ultrasound images. (D) Target detection results of multiple uterine fibroids in patients with double ultrasound images. Green boxes are the GT boxes annotated by our invited radiologists, and blue boxes are the boxes predicted by the trained model. The number marked in the upper left corner is the model detection confidence score.CC BY · PubMed Central
Figure 5 Receiver operating characteristic curves (ROC) show the diagnostic performance in uterine fibroids of the DCNN model, ultrasonographers with different seniority levels and junior ultrasonographers assisted by the DCNN model in the external validation dataset. The ROC curves for Junior ultrasonographers (Averaged) (blue), Senior ultrasonographers (Averaged) (orange), the DCNN model (green), and the DCNN + Junior ultrasonographers (Averaged) (red) provide corresponding AUCs of 0.87 (95% CI 0.84–0.91), 0.95 (95% CI 0.84–0.91), 0.95 (95% CI 0.92–0.97) and 0.95 (95% CI 0.93–0.97).
Figure 5 Receiver operating characteristic curves (ROC) show the diagnostic performance in uterine fibroids of the DCNN model, ultrasonographers with different seniority levels and junior ultrasonographers assisted by the DCNN model in the external validation dataset. The ROC curves for Junior ultrasonographers (Averaged) (blue), Senior ultrasonographers (Averaged) (orange), the DCNN model (green), and the DCNN + Junior ultrasonographers (Averaged) (red) provide corresponding AUCs of 0.87 (95% CI 0.84–0.91), 0.95 (95% CI 0.84–0.91), 0.95 (95% CI 0.92–0.97) and 0.95 (95% CI 0.93–0.97).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

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

Cites

Show all 40 references

Research works printed but not linked: 2

  1. Redmon, J., & Farhadi, A. Yolov3: An incremental improvement. https:://arXiv:1804.02767 (2018).
  2. Sundar, S. & Sumathy, S. Transfer learning approach in deep neural networks for uterine fibroid detection. Int. J. Comput. Sci. Eng. 25, 52–63 (2022).

Cited by

See all 38

Metadata

Authors
Huo, T., Li, L., Chen, X., Wang, Z., Zhang, X., Liu, S., Huang, J., Zhang, J., Yang, Q., Wu, W., Xie, Y., Wang, H., Ye, Z., & Deng, K.
Affiliations
  • Wuhan Union Hospital (CN)
  • The First People's Hospital of Shunde (CN)
  • Huazhong University of Science and Technology (CN)
Corresponding author
  • Ye, Zhewei
  • Deng, Kaixian
Venue
Scientific Reports
Published
2023-03-06
Volume
13
Issue
1
Pages
3714-3714
ISSN
2045-2322 (ISSN-L)
OpenAlex
W4323313484
Cited by
38
References
40
Citations by year
2026: 9 · 2025: 14 · 2024: 11 · 2023: 4
FWCI
1.52
Type
journal article
Language
en
Open access
Licence
Locations
  • Scientific Reports (publishedVersion, cc-by)
  • Research Square (acceptedVersion, cc-by)
  • PubMed Central (publishedVersion, cc-by)
  • PubMed (publishedVersion)
  • DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
Funders
  • National Natural Science Foundation of China (82172524, 81974355)
  • Guangdong Medical Research Foundation (A2020527)
  • Medical Research Project of Foshan Health Bureau (20230068)
Topics
  • Health Sciences › Medicine › Health Informatics › Artificial Intelligence in Healthcare and Education
  • Health Sciences › Medicine › Obstetrics and Gynecology › Uterine Myomas and Treatments
  • Physical Sciences › Computer Science › Artificial Intelligence › AI in cancer detection
Keywords
uterine fibroids, artificial intelligence, deep convolutional neural networks, ultrasound image analysis, diagnostic accuracy, computer-aided diagnosis, external validation, sensitivity and specificity, radiology workflow efficiency, quality of life
MeSH terms
Adult, Allied Health Personnel, Artificial Intelligence, Female, Humans, Hydrolases, Leiomyoma, Retrospective Studies, Ultrasonography

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: Artificial intelligence-aided method to detect uterine fibroids in ultrasound images: a retrospective study. https://app.cochat.ai/papers/10.1038/s41598-022-26771-1
The paper
Huo, T., Li, L., Chen, X., Wang, Z., Zhang, X., Liu, S., Huang, J., Zhang, J., Yang, Q., Wu, W., Xie, Y., Wang, H., Ye, Z., & Deng, K. (2023). Artificial intelligence-aided method to detect uterine fibroids in ultrasound images: a retrospective study. Scientific Reports. https://doi.org/10.1038/s41598-022-26771-1

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.