CMCNet: Aligning Ultrasound Image Embeddings with Textual TI-RADS Representations for Fine-Grained Thyroid Classification

Researchers introduced CMCNet, a model that aligns ultrasound image embeddings with textual TI-RADS representations for fine-grained thyroid classification, achieving superior performance over InfoNCE, center loss, multitask learning, and a VQA-style model, especially in imbalanced settings. The study also presents the STN dataset of 600 thyroid nodules with paired images and complete TI-RADS feature labels, available at doi: 10.5281/zenodo.19125693.

arXiv:2608.13939v1 Announce Type: new Abstract: Ultrasound is the primary imaging modality for assessing thyroid nodules, and the ACR TI-RADS framework standardizes diagnosis through five ultrasound feature categories that are aggregated into five risk levels TR1-TR5 . Although widely adopted in clinical practice, most deep learning approaches focus on binary malignancy classification, while multi-class prediction and explicit utilization of feature-level supervision remain underexplored, largely due to limited annotated data. In this study, we introduce the STN dataset of 600 thyroid nodules with paired transverse and longitudinal ultrasound images, bounding box annotations, and complete labels for all five TI-RADS feature categories. Following the clinical decision process, we investigate how structured feature information can guide representation learning during training while requiring only images at inference. We demonstrate that text embeddings derived from standardized feature descriptions form a stable surrogate representation for TI-RADS risk levels. Based on this observation, we propose CMCNet, which aligns image embeddings to fixed textual embeddings via a Center-Margin Contrastive Loss that simultaneously promotes intra-class compactness and inter-class separation. Experimental results show that this embedding alignment strategy is more data-efficient and robust than direct multitask learning, and consistently outperforms InfoNCE, center loss, a strong multitask baseline, and a VQA-style multimodal model, particularly in imbalanced settings. The dataset is freely available at doi: 10.5281/zenodo.19125693 and the source code is available at: https://www.healthinformaticslab.org/supp/.