Related Experiment Video
Updated: Jul 14, 2026
10:02
High-frequency Ultrasound Imaging of Mouse Cervical Lymph Nodes
Published on: July 25, 2015
19.0K
Artificial intelligence performance in ultrasound-based lymph node diagnosis: a systematic review and meta-analysis
Xinyang Han1, Jingguo Qu1, Man-Lik Chui1
1The Department of Health Technology and Informatics, The Hong Kong Polytechnic University, Hong Kong, China.
BMC Cancer
|January 13, 2025
Summary
Artificial intelligence (AI) accurately distinguishes benign from malignant lymph nodes (LNs) using ultrasound. This AI integration shows promise for improving diagnostic accuracy in clinical practice.
Area of Science:
- Medical Imaging
- Artificial Intelligence
- Oncology
Background:
- Accurate lymphadenopathy classification is vital for treatment selection.
- Ultrasound offers a non-invasive alternative to biopsies for lymph node assessment.
- Advancements in AI enhance diagnostic efficiency for lymph node evaluation.
Purpose of the Study:
- To evaluate the performance of AI applications utilizing ultrasound for classifying benign versus malignant lymph nodes.
- To assess the diagnostic efficacy of AI-driven ultrasound in lymph node analysis.
Main Methods:
- A comprehensive literature search was performed across PubMed, EMBASE, and Cochrane Library databases.
- Study quality was assessed using the QUADAS-2 tool.
- Pooled sensitivity, specificity, and diagnostic odds ratio (DOR) were calculated for AI-based ultrasound classification.
Main Results:
- 19 studies comprising 2,354 cases were analyzed.
- Pooled sensitivity was 0.836 and specificity was 0.850 for AI in classifying lymph nodes.
- The diagnostic odds ratio (DOR) was 33.331, with no significant publication bias detected.
Conclusions:
- AI demonstrates high accuracy in differentiating benign from malignant lymph nodes via ultrasound.
- AI-based decision support systems hold significant potential for clinical integration to improve diagnostic accuracy in oncology.
