Nodule-DETR: A Novel DETR Architecture with Frequency-Channel Attention for Ultrasound Thyroid Nodule Detection
This work addresses thyroid cancer diagnosis for clinicians by improving detection accuracy in ultrasound, though it is incremental as it builds on existing DETR architectures.
The paper tackled the problem of detecting thyroid nodules in ultrasound images, which is challenging due to low contrast and blurred boundaries, and proposed Nodule-DETR, achieving state-of-the-art performance with a 0.149 improvement in mAP@0.5:0.95 over the baseline.
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.