Intelligent Diagnosis Using Dual-Branch Attention Network for Rare Thyroid Carcinoma Recognition with Ultrasound Imaging

2025/05/04 by Peiqi Li, Li, Peiqi, Gao, Yincheng +22
Computer Science · #AI in cancer detection #Classifier (UML) #Computer Vision and Pattern Recognition (cs.CV) #Deep learning #Extractor #FOS: Computer and information sciences #FOS: Electrical engineering #Feature (linguistics) #Feature extraction #Image and Video Processing (eess.IV) #Pattern recognition (psychology) #Residual #Thyroid carcinoma #electronic engineering #information engineering

paper · pdf · doi:10.48550/arxiv.2505.02211

published in arXiv (Cornell University) (Cornell University)

openalex publication_date 2025/05/04 · openalex created_date 2025/10/18 · openalex updated_date 2026/08/05

Abstract

Heterogeneous morphological features and data imbalance pose significant challenges in rare thyroid carcinoma classification using ultrasound imaging. To address this issue, we propose a novel multitask learning framework, Channel-Spatial Attention Synergy Network (CSASN), which integrates a dual-branch feature extractor - combining EfficientNet for local spatial encoding and ViT for global semantic modeling, with a cascaded channel-spatial attention refinement module. A residual multiscale classifier and dynamically weighted loss function further enhance classification stability and accuracy. Trained on a multicenter dataset comprising more than 2000 patients from four clinical institutions, our framework leverages a residual multiscale classifier and dynamically weighted loss function to enhance classification stability and accuracy. Extensive ablation studies demonstrate that each module contributes significantly to model performance, particularly in recognizing rare subtypes such as FTC and MTC carcinomas. Experimental results show that CSASN outperforms existing single-stream CNN or Transformer-based models, achieving a superior balance between precision and recall under class-imbalanced conditions. This framework provides a promising strategy for AI-assisted thyroid cancer diagnosis.

Citations

• Detection of Disease on Nasal Breath Sound by New Lightweight Architecture: Using COVID-19 as An Example
• Swin Transformer V2: Scaling Up Capacity and Resolution
• Residual Attention: A Simple but Effective Method for Multi-Label Recognition
• Transformer in Transformer
• Training data-efficient image transformers & distillation through attention
• An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
• EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks
• Selective Kernel Networks
• Dynamic Curriculum Learning for Imbalanced Data Classification
• Attention Gated Networks: Learning to Leverage Salient Regions in Medical Images
• CBAM: Convolutional Block Attention Module
• Auxiliary Tasks in Multi-task Learning
• Non-local Neural Networks
• Squeeze-and-Excitation Networks
• Deep Learning for Medical Image Analysis
• Attention Is All You Need
• Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semantics
• Densely Connected Convolutional Networks
• SGDR: Stochastic Gradient Descent with Warm Restarts
• Layer Normalization
• Deep Residual Learning for Image Recognition
• Compact Bilinear Pooling
• Revised American Thyroid Association Guidelines for the Management of Medullary Thyroid Carcinoma
• 2015 American Thyroid Association Management Guidelines for Adult Patients with Thyroid Nodules and Differentiated Thyroid Cancer: The American Thyroid Association Guidelines Task Force on Thyroid Nodules and Differentiated Thyroid Cancer

Related

• Multi-Attribute Attention Network for Interpretable Diagnosis of Thyroid Nodules in Ultrasound Images
• Multi-channel deep convolutional neural networks for multi-classifying thyroid disease
• UESA-Net: U-Shaped Embedded Multidirectional Shrinkage Attention Network for Ultrasound Nodule Segmentation
• STACT-Time: Spatio-Temporal Cross Attention for Cine Thyroid Ultrasound Time Series Classification
• Reducing Overtreatment of Indeterminate Thyroid Nodules Using a Multimodal Deep Learning Model