2026-10-13T12:13:22Z https://www.scidb.cn/oai

10.57760/sciencedb.dmh.00330 2025-07-01T09:14:16Z

2025-07-01 A Study of Ultrasound Image Segmentation of Thyroid Nodules Based on Feature Adaptive Extraction and Gated Fusion Mechanisms doi:10.57760/sciencedb.dmh.00330 en Objective To address the problems of high heterogeneity of nodule regions, blurred boundaries and noise interference in thyroid ultrasound images, a deep learning network FAGF-Net based on feature adaptive extraction and gated fusion mechanism is proposed to improve the segmentation accuracy of thyroid nodules.Methods A feature coupling encoder is designed to integrate CNN and Transformer in parallel to capture local texture details and global structural semantics, respectively; a multi-scale feature spatial coupling module is proposed to enhance the capture of multi-scale geometric features of the nodule by using dynamic multi-scale convolutional kernel and the channel-spatial attention mechanism; and a contextual gating feature attention module is proposed to filter the multi-level redundant features through the gating mechanism, and enhance the cross-level redundancy with the self-attention mechanism; the FAGF-Net is designed to enhance the segmentation accuracy of thyroid nodule by using the self-attention mechanism. We use the context-gated feature attention module to filter multi-layer redundant features through the gating mechanism, and enhance cross-layer feature associations with the help of self-attention to suppress noise interference.Results The TN3K dataset is used in the study, and the results show that the accuracy of FAGF-Net reaches 95.59%, which is 3.77% higher than that of the baseline model UNet; the Dice coefficient is 90.60%, which is 3.55% higher. The ablation experiments show that FC-Encoder, MFSE-Module and CGFA-Module improve the Dice coefficient by 1.40%, 0.69% and 2.41%, respectively, which verifies the necessity of each module. The visualisation results show that FAGF-Net significantly outperforms the comparison models in terms of boundary fitting smoothness, accuracy of tiny lesion localisation, and effectively reduces the phenomena of under-segmentation and over-segmentation.Conclusion FAGF-Net significantly improves the segmentation performance of ultrasound images of thyroid nodules through the innovative design of feature coupling and gating mechanism, providing a new solution for clinical automated diagnosis. Attention mechanism; Medical image processing; Thyroid nodules; Intelligent diagnosis Chengzi.Yao Han.Guo Zhiqiang.Jia PUBLIC https://creativecommons.org/publicdomain/zero/1.0/ dataset Science Data Bank