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

• URL: http://arxiv.org/abs/2601.01908v1
• Date: Mon, 05 Jan 2026 08:53:04 GMT
• Title: Nodule-DETR: A Novel DETR Architecture with Frequency-Channel Attention for Ultrasound Thyroid Nodule Detection
• Authors: Jingjing Wang, Qianglin Liu, Zhuo Xiao, Xinning Yao, Bo Liu, Lu Li, Lijuan Niu, Fugen Zhou,
• Abstract summary: Thyroid cancer is the most common endocrine malignancy, and its incidence is rising globally.<n>We propose Nodule-DETR, a novel detection transformer (DETR) architecture designed for robust thyroid nodule detection in ultrasound images.<n>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.
• Score: 11.368372526576879
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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.

Related papers

• Prior-Guided DETR for Ultrasound Nodule Detection [12.28367495765275]
  We propose a prior-guided DETR framework specifically designed for ultrasound detection.<n>Instead of relying on purely data-driven feature learning, the proposed framework progressively incorporates different prior knowledge at multiple stages of the network.<n> Experiments conducted on two clinically collected thyroid ultrasound datasets demonstrate that the proposed method achieves superior accuracy compared with 18 detection methods.
  arXiv  Detail & Related papers  (2026-01-05T15:32:58Z)
• Accurate Thyroid Cancer Classification using a Novel Binary Pattern Driven Local Discrete Cosine Transform Descriptor [3.663197678470621]
  We develop a new CAD system for accurate thyroid cancer classification with emphasis on feature extraction.<n>We term our novel descriptor as Binary Pattern Driven Local Discrete Cosine Transform (BPD-LDCT)
  arXiv  Detail & Related papers  (2025-09-19T19:54:04Z)
• STACT-Time: Spatio-Temporal Cross Attention for Cine Thyroid Ultrasound Time Series Classification [2.510842391292067]
  Thyroid cancer is among the most common cancers in the United States.<n>Recent deep learning approaches have sought to improve risk stratification, but they often fail to utilize the rich temporal and spatial context provided by US cine clips.<n>We propose the Spatio-Temporal Cross Attention for Cine Thyroid Ultrasound Time Series Classification (STACT-Time) model.
  arXiv  Detail & Related papers  (2025-06-22T21:14:04Z)
• Structure-Accurate Medical Image Translation via Dynamic Frequency Balance and Knowledge Guidance [60.33892654669606]
  Diffusion model is a powerful strategy to synthesize the required medical images.<n>Existing approaches still suffer from the problem of anatomical structure distortion due to the overfitting of high-frequency information.<n>We propose a novel method based on dynamic frequency balance and knowledge guidance.
  arXiv  Detail & Related papers  (2025-04-13T05:48:13Z)
• CathFlow: Self-Supervised Segmentation of Catheters in Interventional Ultrasound Using Optical Flow and Transformers [66.15847237150909]
  We introduce a self-supervised deep learning architecture to segment catheters in longitudinal ultrasound images. The network architecture builds upon AiAReSeg, a segmentation transformer built with the Attention in Attention mechanism. We validated our model on a test dataset, consisting of unseen synthetic data and images collected from silicon aorta phantoms.
  arXiv  Detail & Related papers  (2024-03-21T15:13:36Z)
• AI-Generated Content Enhanced Computer-Aided Diagnosis Model for Thyroid Nodules: A ChatGPT-Style Assistant [36.02145235227822]
  An artificial intelligence-generated computer-aided diagnosis (AIGC-CAD) model, designated as ThyGPT, has been developed. This model, inspired by the architecture of ChatGPT, could assist radiologists in assessing the risk of thyroid nodules through semantic-level human-machine interaction.
  arXiv  Detail & Related papers  (2024-02-04T08:24:13Z)
• AiAReSeg: Catheter Detection and Segmentation in Interventional Ultrasound using Transformers [75.20925220246689]
  endovascular surgeries are performed using the golden standard of Fluoroscopy, which uses ionising radiation to visualise catheters and vasculature. This work proposes a solution using an adaptation of a state-of-the-art machine learning transformer architecture to detect and segment catheters in axial interventional Ultrasound image sequences.
  arXiv  Detail & Related papers  (2023-09-25T19:34:12Z)
• The role of noise in denoising models for anomaly detection in medical images [62.0532151156057]
  Pathological brain lesions exhibit diverse appearance in brain images. Unsupervised anomaly detection approaches have been proposed using only normal data for training. We show that optimization of the spatial resolution and magnitude of the noise improves the performance of different model training regimes.
  arXiv  Detail & Related papers  (2023-01-19T21:39:38Z)
• Image Synthesis with Disentangled Attributes for Chest X-Ray Nodule Augmentation and Detection [52.93342510469636]
  Lung nodule detection in chest X-ray (CXR) images is common to early screening of lung cancers. Deep-learning-based Computer-Assisted Diagnosis (CAD) systems can support radiologists for nodule screening in CXR. To alleviate the limited availability of such datasets, lung nodule synthesis methods are proposed for the sake of data augmentation.
  arXiv  Detail & Related papers  (2022-07-19T16:38:48Z)
• Less is More: Adaptive Curriculum Learning for Thyroid Nodule Diagnosis [50.231954872304314]
  We propose an Adaptive Curriculum Learning framework, which adaptively discovers and discards the samples with inconsistent labels. We also contribute TNCD: a Thyroid Nodule Classification dataset.
  arXiv  Detail & Related papers  (2022-07-02T11:50:02Z)
• Key-frame Guided Network for Thyroid Nodule Recognition using Ultrasound Videos [13.765306481109988]
  This paper proposes a novel method for the automated recognition of thyroid nodules through an exploration of ultrasound videos and key-frames. We first propose a detection-localization framework to automatically identify the clinical key-frame with a typical nodule in each ultrasound video. Based on the localized key-frame, we develop a key-frame guided video classification model for thyroid recognition.
  arXiv  Detail & Related papers  (2022-06-27T14:03:26Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.