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.
View on arXiv@article{li2025_2505.02211,
title={ CSASN: A Multitask Attention-Based Framework for Heterogeneous Thyroid Carcinoma Classification in Ultrasound Images },
author={ Peiqi Li and Yincheng Gao and Renxing Li and Haojie Yang and Yunyun Liu and Boji Liu and Jiahui Ni and Ying Zhang and Yulu Wu and Xiaowei Fang and Lehang Guo and Liping Sun and Jiangang Chen },
journal={arXiv preprint arXiv:2505.02211},
year={ 2025 }
}