Back to all papers

A novel cross-attentive network for classifying cervical metastatic lymph nodes on B- and D-mode ultrasound images in oral squamous cell carcinoma.

November 9, 2025pubmed logopapers

Authors

Kim YR,Han JY,Yang S,Kim JW,Huh KH,Heo MS,Lee SS,Yi WJ,Kim JE

Affiliations (3)

  • Department of Oral and Maxillofacial Radiology, Dental Research Institute, School of Dentistry, Seoul National University, 101 Daehak-ro, Jongno-gu, 03080, Seoul, Korea.
  • Interdisciplinary Program in Bioengineering, Graduate School of Engineering, Seoul National University, 1 Gwanak-ro, Gwanak-gu, 08826, Seoul, Korea.
  • Department of Oral and Maxillofacial Surgery, Houston Methodist Research Institute, Houston, 77030, Texas, USA.

Abstract

This study proposes a deep convolutional neural network model that integrates B-mode and D-mode ultrasound images to classify metastatic lymph nodes in patients with oral squamous cell carcinoma. A shared backbone network incorporating a cross-attention mechanism was employed to enhance feature-level interactions between dual-input ultrasound images. A total of six convolutional neural network architectures (VGG16, SqueezeNet, ResNet50, EfficientNet B3, ConvNext, DenseNet121) were implemented within a shared backbone framework to investigate optimal performance. For each network, diagnostic performance was compared between dual-input and single-input ultrasound. In addition, model performance was evaluated against human observers with different levels of experience. The model using DenseNet121 as a shared backbone with an integrated cross-attention layer (LNM-Net) achieved the highest classification accuracy (85.3%) when utilizing dual-input images, surpassing the diagnostic performance of residents. The cross-attention module improved feature fusion, reducing false positives by suppressing modality-specific noise. LNM-Net demonstrates strong potential as a clinical decision-support tool for preoperative lymph node metastasis assessment in oral squamous cell carcinoma. Despite current limitations such as dataset size and cross-institutional variability, the model offers a promising supplementary aid, particularly in settings with limited radiological expertise. This study develops a novel cross-attentive network using dual-input B- and D-mode ultrasound images to classify metastatic lymph nodes in oral squamous cell carcinoma.

Topics

Journal Article

Ready to Sharpen Your Edge?

Join hundreds of your peers who rely on RadAI Slice. Get the essential weekly briefing that empowers you to navigate the future of radiology.

We respect your privacy. Unsubscribe at any time.