Best Papers
 Few-Shot Anomaly Detection for Medical Ultrasound Images Using Metric Learning and Multimodal BiomedCLIP Embeddings 


Vol. 50,  No. 10, pp. 1505-1514, Oct.  2025
10.7840/kics.2025.50.10.1505


PDF Full-Text
  Abstract

Medical ultrasound imaging is extensively utilized in clinical practice due to its advantages of safety, cost-effectiveness, and real-time imaging capability. Nevertheless, inherent issues such as low signal-to-noise ratios, operator dependency, and speckle noise introduce significant challenges in automated anomaly detection. To overcome these limitations, we propose a novel few-shot anomaly detection framework specifically designed for medical ultrasound imaging. Our method employs BiomedCLIP, a multimodal model tailored for biomedical applications, to jointly encode ultrasound images and clinically relevant textual descriptions into semantically rich embeddings. Subsequently, these embeddings are refined through a projection network to create compact, discriminative representations optimized for anomaly classification. A prototype-based metric learning approach further enhances the separability of these embeddings by explicitly clustering normal and abnormal cases. Extensive evaluations conducted on representative ultrasound datasets demonstrate that our proposed method achieves superior anomaly detection performance compared to existing contrastive and multimodal learning frameworks, particularly in severely limited data scenarios. Our findings underscore the efficacy and clinical potential of combining multimodal embeddings and metric learning for robust and interpretable anomaly detection in medical ultrasound images.

  Statistics
Cumulative Counts from November, 2022
Multiple requests among the same browser session are counted as one view. If you mouse over a chart, the values of data points will be shown.


  Related Articles
  Cite this article

[IEEE Style]

H. Lee, K. Lee, J. Kim, "Few-Shot Anomaly Detection for Medical Ultrasound Images Using Metric Learning and Multimodal BiomedCLIP Embeddings," The Journal of Korean Institute of Communications and Information Sciences, vol. 50, no. 10, pp. 1505-1514, 2025. DOI: 10.7840/kics.2025.50.10.1505.

[ACM Style]

Haeyun Lee, Kyungsu Lee, and Jihun Kim. 2025. Few-Shot Anomaly Detection for Medical Ultrasound Images Using Metric Learning and Multimodal BiomedCLIP Embeddings. The Journal of Korean Institute of Communications and Information Sciences, 50, 10, (2025), 1505-1514. DOI: 10.7840/kics.2025.50.10.1505.

[KICS Style]

Haeyun Lee, Kyungsu Lee, Jihun Kim, "Few-Shot Anomaly Detection for Medical Ultrasound Images Using Metric Learning and Multimodal BiomedCLIP Embeddings," The Journal of Korean Institute of Communications and Information Sciences, vol. 50, no. 10, pp. 1505-1514, 10. 2025. (https://doi.org/10.7840/kics.2025.50.10.1505)
Vol. 50, No. 10 Index

Search
(IN TITLE, AUTHOR, ABSTRACT,KEYWORDS)

Advanced Search ▼

POPULAR KEYWORDS
(TOP 10 KEYWORDS)

Recent Publications
(LAST 3 YEARS)






pISSN : 1226 - 4717
eISSN : 2287 - 3880