Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Bridging the gap in OA therapeutics: Bioengineered strategies to target osteoclast-chondrocyte crosstalk.

Bioengineering & translational medicine·2026
Same author

A Noachian hydrosphere component in the 4.1-Ga Martian meteorite Teghaza 001.

Science advances·2026
Same author

Dexmedetomidine may alleviate severe acute pancreatitis-associated lung injury by targeting the AIM2 inflammasome in endothelial cells.

BMC anesthesiology·2026
Same author

Determination of HU override for gold fiducial markers in proton therapy.

Journal of applied clinical medical physics·2026
Same author

A Rare Case of Lower Gastrointestinal Bleeding: Appendiceal Dieulafoy's Lesion.

Digestive diseases and sciences·2026
Same author

CELF family of RNA-binding proteins: roles in disease biology and potential for therapeutic intervention.

Cell communication and signaling : CCS·2026

Related Experiment Video

Updated: Sep 14, 2025

Label-Free Identification of Lymphocyte Subtypes Using Three-Dimensional Quantitative Phase Imaging and Machine Learning
08:58

Label-Free Identification of Lymphocyte Subtypes Using Three-Dimensional Quantitative Phase Imaging and Machine Learning

Published on: November 19, 2018

12.7K

An Improved Diagnostic Deep Learning Model for Cervical Lymphadenopathy Characterization.

Wushuang Gong1, Minglei Li2, Shuhan Wang1

  • 1Department of In-Patient Ultrasound, The Second Affiliated Hospital of Harbin Medical University, Harbin, Heilongjiang, China.

Ultrasound in Medicine & Biology
|July 22, 2025
PubMed
Summary

A deep learning model using B-mode ultrasound shows promise for diagnosing cervical lymphadenopathy (CLP). This AI tool achieved higher accuracy than traditional methods, aiding in distinguishing benign from malignant cases.

Keywords:
Cervical lymphadenopathyConventional ultrasoundDeep learningDiagnostic performance

More Related Videos

Author Spotlight: A 3D Digital Model for the Diagnosis and Treatment of Pulmonary Nodules
10:26

Author Spotlight: A 3D Digital Model for the Diagnosis and Treatment of Pulmonary Nodules

Published on: May 19, 2023

2.1K
Comparison of Predictive Performance of Three Lymph Node Staging Systems in Colorectal Signet Ring Cell Carcinoma Based on Machine Learning Model
07:13

Comparison of Predictive Performance of Three Lymph Node Staging Systems in Colorectal Signet Ring Cell Carcinoma Based on Machine Learning Model

Published on: April 18, 2025

199

Related Experiment Videos

Last Updated: Sep 14, 2025

Label-Free Identification of Lymphocyte Subtypes Using Three-Dimensional Quantitative Phase Imaging and Machine Learning
08:58

Label-Free Identification of Lymphocyte Subtypes Using Three-Dimensional Quantitative Phase Imaging and Machine Learning

Published on: November 19, 2018

12.7K
Author Spotlight: A 3D Digital Model for the Diagnosis and Treatment of Pulmonary Nodules
10:26

Author Spotlight: A 3D Digital Model for the Diagnosis and Treatment of Pulmonary Nodules

Published on: May 19, 2023

2.1K
Comparison of Predictive Performance of Three Lymph Node Staging Systems in Colorectal Signet Ring Cell Carcinoma Based on Machine Learning Model
07:13

Comparison of Predictive Performance of Three Lymph Node Staging Systems in Colorectal Signet Ring Cell Carcinoma Based on Machine Learning Model

Published on: April 18, 2025

199

Area of Science:

  • Medical Imaging
  • Artificial Intelligence in Medicine
  • Oncology

Background:

  • Cervical lymphadenopathy (CLP) diagnosis relies on imaging and pathology.
  • Distinguishing benign from malignant CLP can be challenging with conventional B-mode ultrasound.
  • Deep learning (DL) offers potential for improved diagnostic accuracy.

Purpose of the Study:

  • To validate a B-mode ultrasound-based deep learning (DL) model for differentiating benign and malignant cervical lymphadenopathy (CLP).
  • To compare the diagnostic performance of the DL model against traditional ultrasound features and logistic regression models.

Main Methods:

  • A retrospective study included 210 CLPs with pathological results, split into training (n=169) and testing (n=41) cohorts.
  • A DL model was developed using convolutional neural networks, deformable convolution networks, and attention mechanisms.
  • Three models were compared: Model I (ultrasound features), Model II (logistic regression risk score), and Model III (DL output). Diagnostic utility was assessed using Area Under the Curve (AUC), sensitivity, and specificity.

Main Results:

  • In the training cohort, DL positive results were the strongest predictor of malignancy (OR = 39.05, p < 0.001).
  • In the test cohort, the DL model achieved a significantly higher AUC (0.871) compared to Model I (0.681, p=0.04) and Model II (0.679, p=0.03).
  • Model III (DL) demonstrated significantly higher specificity (93.3%) than Model I (40.0%, p=0.002) and Model II (60.0%, p=0.03).

Conclusions:

  • B-mode ultrasound-based deep learning is a potentially robust tool for the differential diagnosis of benign and malignant cervical lymphadenopathy.
  • The DL model significantly outperformed traditional methods in distinguishing malignant CLP.
  • This AI approach shows promise for improving diagnostic accuracy in cervical lymphadenopathy evaluation.