文献速递甲状腺与浅表头颈技术与安全US

通过深度学习实现超声图像中甲状腺结节的分割与风险分层

Localization and Risk Stratification of Thyroid Nodules in Ultrasound Images Through Deep Learning.
PubMed 文献 · Ultrasound Med Biol · 2024-03-16

研究收集两个独立站点304幅TI-RADS 4甲状腺结节超声图像,构建结合TI-RADS与Mask R-CNN的集成系统,同时分割结节并对TI-RADS 4亚类分层。独立测试集总体分层准确率90.79%,平均精度0.8579,平均DSC 0.83;4a、4b、4c分层准确率分别为95.83%、84.21%、77.78%。

要点

  • 集成系统在独立测试集对TI-RADS 4结节总体分层准确率90.79%。
  • 4a、4b、4c亚类分层准确率分别为95.83%、84.21%、77.78%。
  • 分割平均DSC 0.83,平均精度0.8579。

核心结论

  • 结合TI-RADS与深度学习模型的集成系统可同时提供TI-RADS诊断辅助和甲状腺结节精确分割,提高系统在临床实践中的适用性。

研究设计与样本

  • 研究论文;收集两个独立站点共304幅TI-RADS 4甲状腺结节超声图像,采用边缘连接与Criminisi算法去除人工标记,构建基于TI-RADS和Mask R-CNN的集成系统进行亚类分层与结节分割。

诊断标准与关键数值

  • 独立测试集TI-RADS 4结节总体分层准确率为90.79%。
  • 独立测试集平均平均精度为0.8579,平均DSC为0.83。
  • TI-RADS 4a、4b、4c结节分层准确率分别为95.83%、84.21%、77.78%。

临床应用与阅片要点

  • 系统可同时输出TI-RADS风险分层与结节分割轮廓,供临床诊断辅助使用。
  • 分割性能以Mask R-CNN分割与放射科医生勾画轮廓之间的DSC评估。

局限性

  • 原文未报告局限性。

以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。

英文原文(摘要)· 点击展开

OBJECTIVE: Deep learning algorithms have commonly been used for the differential diagnosis between benign and malignant thyroid nodules. The aim of the study described here was to develop an integrated system that combines a deep learning model and a clinical standard Thyroid Imaging Reporting and Data System (TI-RADS) for the simultaneous segmentation and risk stratification of thyroid nodules.

METHODS: Three hundred four ultrasound images from two independent sites with TI-RADS 4 thyroid nodules were collected. The edge connection and Criminisi algorithm were used to remove manually induced markers in ultrasound images. An integrated system based on TI-RADS and a mask region-based convolution neural network (Mask R-CNN) was proposed to stratify subclasses of TI-RADS 4 thyroid nodules and to segment thyroid nodules in the ultrasound images. Accuracy and the precision-recall curve were used to evaluate stratification performance, and the Dice similarity coefficient (DSC) between the segmentation of Mask R-CNN and the radiologist's contour was used to evaluate the segmentation performance of the model.

RESULTS: The combined approach could significantly enhance the performance of the proposed integrated system. Overall stratification accuracy of TI-RADS 4 thyroid nodules, mean average precision and mean DSC of the proposed model in the independent test set was 90.79%, 0.8579 and 0.83, respectively. Specifically, stratification accuracy values for TI-RADS 4a, 4b and 4c thyroid nodules were 95.83%, 84.21% and 77.78%, respectively.

CONCLUSION: An integrated system combining TI-RADS and a deep learning model was developed. The system can provide clinicians with not only diagnostic assistance from TI-RADS but also accurate segmentation of thyroid nodules, which improves the applicability of the system in clinical practice.

来源:Ultrasound Med Biol,查看原文。版权归原作者所有。

引用

  1. Wang Z, Wang X, Wang T, et al. Localization and Risk Stratification of Thyroid Nodules in Ultrasound Images Through Deep Learning. Ultrasound Med Biol. 2024. PMID: 38494413. doi:10.1016/j.ultrasmedbio.2024.02.013

供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。