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

TL;DR

Nodule-DETR is a new transformer-based model for thyroid nodule detection in ultrasound images, incorporating frequency-channel attention and multi-scale features to improve accuracy in challenging low-contrast conditions.

Contribution

It introduces a novel DETR architecture with frequency-channel attention, hierarchical feature fusion, and deformable attention modules for enhanced ultrasound thyroid nodule detection.

Findings

Achieves state-of-the-art detection performance with a 0.149 mAP improvement.

Effectively handles low-contrast and irregularly shaped nodules.

Demonstrates potential for clinical application in thyroid diagnosis.

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.