Nodule-DETR: A Novel DETR Architecture with Frequency-Channel Attention for Ultrasound Thyroid Nodule Detection

2026-01-05

arXiv.org

AI Summary

Thyroid nodules in ultrasound images are often challenging to detect accurately due to low contrast and indistinct boundaries. To address this issue, this work proposes a novel DETR-based detection Transformer architecture that innovatively integrates frequency-domain feature enhancement, multispectral channel attention, hierarchical multi-scale feature fusion, and deformable attention mechanisms. This integrated approach significantly improves the model’s ability to identify low-contrast and irregularly shaped small nodules. Evaluated on a real-world clinical ultrasound dataset, the proposed method achieves a state-of-the-art performance, yielding a 0.149 improvement in mAP@0.5:0.95 over existing approaches.

Technology Category

• Computer Vision: Multi-modal Vision
• Machine Learning: Feature Construction/Reformulation
• Natural Language Processing: Fact-Checking / Misinformation Detection (NLP Focus)

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

Thyroid cancer is the most common endocrine malignancy, and its incidence is rising globally. While ultrasound is the preferred imaging modality for detecting thyroid nodules, its diagnostic accuracy is often limited by challenges such as low image contrast and blurred nodule boundaries. To address these issues, we propose Nodule-DETR, a novel detection transformer (DETR) architecture designed for robust thyroid nodule detection in ultrasound images. Nodule-DETR introduces three key innovations: a Multi-Spectral Frequency-domain Channel Attention (MSFCA) module that leverages frequency analysis to enhance features of low-contrast nodules; a Hierarchical Feature Fusion (HFF) module for efficient multi-scale integration; and Multi-Scale Deformable Attention (MSDA) to flexibly capture small and irregularly shaped nodules. We conducted extensive experiments on a clinical dataset of real-world thyroid ultrasound images. The results demonstrate that Nodule-DETR achieves state-of-the-art performance, outperforming the baseline model by a significant margin of 0.149 in mAP@0.5:0.95. The superior accuracy of Nodule-DETR highlights its significant potential for clinical application as an effective tool in computer-aided thyroid diagnosis. The code of work is available at https://github.com/wjj1wjj/Nodule-DETR.

Problem

• thyroid nodule detection
• ultrasound imaging
• low image contrast
• blurred boundaries
• computer-aided diagnosis

Innovation

• Multi-Spectral Frequency-domain Channel Attention
• Hierarchical Feature Fusion
• Multi-Scale Deformable Attention
• Detection Transformer
• Thyroid Nodule Detection