基于深度DuS-KFCM的不确定性甲状腺结节自动分割与诊断准确性优化研究
DOI:
https://doi.org/10.70693/cjst.v1i3.1339Keywords:
不确定性甲状腺结节；超声图像分割；模糊聚类（FC）；混合神经模糊系统Abstract
超声影像中不确定性甲状腺结节的及时、精确分类与分割，对于提升诊断准确性和指导临床管理至关重要，是优化患者预后的关键环节。传统方法在处理此类结节回声不均、边界模糊和形态特征多变等挑战时存在明显局限。本研究旨在通过引入一种新型深度学习模型——双空间核化约束模糊C均值（Deep DuS-KFCM）聚类算法，彻底改变这一领域的现状。该混合神经模糊系统融合了神经网络与模糊逻辑的优势，能够实现高度精确和高效的结节区域识别。该方法采用由粗到细的双重分割策略：首先利用结合空间纹理特征增强的空间核化模糊C均值（SKFCM）算法进行初始分割，进而采用基于ResNet50架构的DeepLabv3+模型优化分割结果。通过在主流甲状腺影像数据集上的大量实验，我们所提出的Deep DuS-KFCM模型实现了87.95%的准确率和96.33%的特异度，性能优于当前主流分割方法。研究结果证明了该模型对影像噪声的鲁棒性及其卓越的分割能力，尤其在边界模糊结节的勾画方面表现突出，从而为甲状腺癌诊断中的医学图像处理带来了重大突破。
References
Lu H, Pan Y, Ruan Y, et al. High Throughput Enhanced Quantitative Plasma Proteomics for Discovery of Biomarker in Early Diagnosis of Papillary Thyroid Carcinoma[A]. 浙江省免疫学会. 浙江省免疫学会第十三次学术大会论文集[C]. 浙江省免疫学会: 浙江省科学技术协会, 2023: 2.
董明华, 孟 芳. 超声AI联合C-TIRADS在甲状腺结节良恶性鉴别中的效果分析[J]. 中国实验诊断学, 2025, 29(08): 910-915.
康 峰, 齐宏伟, 张杰慧等. 超声引导下甲状腺细针穿刺对甲状腺微小乳头状癌早期诊断的临床价值[J]. 中国医药指南, 2019, 17(34): 20-21.
孙玉华, 韦勇锋. 高频超声检查在甲状腺癌早期诊断中的应用价值[J]. 实用医学影像杂志, 2019, 20(04): 399-401.
耿雪娜, 耿昌婕, 陈星宇等. 甲状腺多形性肉瘤一例[J]. 临床外科杂志, 2024, 32(12): 1318-1319.
胡广柱, 朱大荣, 韩志江. 颈部CT扫描中定位片对甲状腺锁骨伪影的预测价值[J]. 中国临床医学影像杂志, 2018, 29(07): 471-474.
韩 娟, 张立文, 宋金岭等. 局灶性强回声超声征象在鉴别TI-RADS 4类甲状腺结节良恶性中的临床价值[J]. 临床超声医学杂志, 2023, 25(06): 456-459.
张孜玮, 林 宁, 李建卫. 甲状腺乳头状癌术后甲状腺窝低回声的超声诊断分析[J]. 福建医药杂志, 2016, 38(03): 108-112.
王 华, 李小鹏, 李安茂等. 超声造影对甲状腺部分切除术侧低回声结节的诊断价值[J]. 中国超声医学杂志, 2014, 30(04): 292-294.
胡凤楠, 高天舒, 滕卫平等. 甲状腺超声广泛低回声临床意义的探讨[J]. 中华内分泌代谢杂志, 2004(02): 22-25.
韩 普, 刘森嶺, 陈文祺. 基于多尺度注意力和图神经网络的多模态医学实体识别研究[J]. 数据采集与处理, 2025, 40(04): 922-933.
Chen J, Cai Z, Heidari A H, et al. Multi-threshold image segmentation based on an improved differential evolution: Case study of thyroid papillary carcinoma[J]. Biomedical Signal Processing and Control, 2023, 85.
Ju Y K, Soo J L, Sik S K, et al. Retrospective Analysis of Cytopathology using Gray Level Co-occurrence Matrix Algorithm for Thyroid Malignant Nodules in the Ultrasound Imaging[J]. Journal of Radiological Science and Technology, 2017, 40(2).
Kumar J K J S, Parthasarathi P, Masud M, et al. Butterfly Optimized Feature Selection with Fuzzy C-Means Classifier for Thyroid Prediction[J]. Intelligent Automation & Soft Computing, 2023, 35(3).
Kumar P M. Segmentation of White Blood Cells Using Fuzzy C Means Segmentation Algorithm[J]. IOSR Journal of Computer Engineering, 2014, 16(3).
Venkataramana B, Padmasree L, Srinivasa Rao M, et al. Comparative Study on performance of Fuzzy clustering algorithms on Liver and Thyroid Data[J]. Journal of Fuzzy Set Valued Analysis, 2018, 2018(1).
Chen Y, Zhang X, Li D, et al. Automatic segmentation of thyroid with the assistance of the devised boundary improvement based on multicomponent small dataset[J]. Applied Intelligence (Dordrecht, Netherlands), 2023, 53(16).
Gong H, Chen J, Chen G, et al. Thyroid region prior guided attention for ultrasound segmentation of thyroid nodules[J]. Computers in Biology and Medicine, 2023, 155.
陆岚岚, 王礼同. 多模态CT特征联合纹理分析及临床信息对甲状腺结节良恶性的研究[J].实用医学影像杂志, 2024, 25(06): 417-421.
Zhou L, Chang L, Li J, et al. Aided diagnosis of thyroid nodules based on an all-optical diffraction neural network[J]. Quantitative Imaging in Medicine and Surgery, 2023, 13(9).
Wei S, Hu Z, Tan L. Res-ECA-UNet++: an automatic segmentation model for ovarian tumor ultrasound images based on residual networks and channel attention mechanism[J]. Frontiers in Medicine, 2025, 12.
Guo L, Lv F. A Two-Stage Deep-Learning Framework for Industrial Anomaly Detection: Integrating Small-Sample Semantic Segmentation and Knowledge Distillation[J]. Machines, 2025, 13(8).
Zhang G, Lu Y, Chen G, et al. A Two-Stage Deep Learning Method with Novel Damage Sensitive Features for Structural Damage Identification[J]. International Journal of Computational Methods, 2025(prepublish).
Yang C, Ashraf A M, Riaz M, et al. Enhanced thyroid nodule detection and diagnosis: a mobile-optimized DeepLabV3+ approach for clinical deployments[J]. Frontiers in Physiology, 2025,16.
Xiao N, Kong D, Wang J. Ultrasound Thyroid Nodule Segmentation Algorithm Based on DeepLabV3+ with EfficientNet[J]. Journal of Imaging Informatics in Medicine, 2025(prepublish).
Sag A A, Kazaure S H, Perkins M J, et al. Clinical Image-Guided Ablation for Thyroid Malignancy with Proposed Thyroid Segmentation System[J]. Advances in Clinical Radiology, 2020, 2(prepublish).
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2025 刘贤贤, 康慷, 魏岸若, 何志容, 谭礼健, 陈宏, 杨杰
This work is licensed under a Creative Commons Attribution 4.0 International License.
