文献速递甲状腺疾病

基于卷积神经网络的超声计算机辅助诊断桥本甲状腺炎

Convolutional Neural Network-Based Computer-Assisted Diagnosis of Hashimoto's Thyroiditis on Ultrasound.
PubMed 文献 · J Clin Endocrinol Metab · 2022-01-01

本研究回顾性收集中国2家医院2008年9月至2018年2月21 118例患者的39 280张超声图像,按80%训练集和20%验证集划分,集成9个卷积神经网络构建CAD-HT模型用于桥本甲状腺炎分类。模型准确率0.892、敏感度0.890、特异度0.895,两院间性能无显著差异,较资深放射科医师准确率提高近9%(P<0.001),在甲状腺功能亢进、减退及正常三个亚组中准确率范围0.87-0.894。

要点

  • CAD-HT模型诊断桥本甲状腺炎的准确率0.892、敏感度0.890、特异度0.895。
  • CAD-HT较资深放射科医师准确率提高近9%(P<0.001)。
  • 两院间性能无显著差异,不同甲状腺激素水平亚组准确率范围0.87-0.894。

核心结论

  • 基于卷积神经网络的CAD-HT策略显著提高了放射科医师对桥本甲状腺炎的诊断准确率。
  • 该模型在不同医院和不同甲状腺激素水平下均表现出良好性能和稳健性。

研究设计与样本

  • 回顾性收集中国2家医院2008年9月至2018年2月确诊和未确诊桥本甲状腺炎患者的超声图像。
  • 图像按80%为训练集、20%为验证集划分,集成9个卷积神经网络作为最终分类模型CAD-HT。
  • 模型在2家医院验证集上验证并与资深/初级放射科医师比较准确率,同时按甲状腺功能亢进、减退和正常三个亚组分析性能。

主要发现

  • 共纳入21 118例患者的39 280张超声图像。
  • CAD-HT模型的准确率、敏感度和特异度分别为0.892、0.890和0.895。
  • 两院间CAD-HT性能无显著差异。
  • CAD-HT模型性能高于资深放射科医师(P<0.001),准确率提高近9%。
  • 基于甲状腺激素水平的三个亚组中,CAD-HT准确率范围0.87-0.894,表现几乎相似。

关键数值与推荐

  • CAD-HT诊断桥本甲状腺炎的准确率0.892、敏感度0.890、特异度0.895。
  • CAD-HT与资深放射科医师比较P<0.001,准确率提高近9%。
  • 甲状腺功能亢进、减退和正常三个亚组的CAD-HT准确率范围0.87-0.894。

临床怎么用

  • 原文未据此给出推荐。

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)。

原文

PURPOSE: This study investigates the efficiency of deep learning models in the automated diagnosis of Hashimoto's thyroiditis (HT) using real-world ultrasound data from ultrasound examinations by computer-assisted diagnosis (CAD) with artificial intelligence. METHODS: We retrospectively collected ultrasound images from patients with and without HT from 2 hospitals in China between September 2008 and February 2018. Images were divided into a training set (80%) and a validation set (20%). We ensembled 9 convolutional neural networks (CNNs) as the final model (CAD-HT) for HT classification. The model's diagnostic performance was validated and compared to 2 hospital validation sets. We also compared the accuracy of CAD-HT against seniors/junior radiologists. Subgroup analysis of CAD-HT performance for different thyroid hormone levels (hyperthyroidism, hypothyroidism, and euthyroidism) was also evaluated. RESULTS: 39 280 ultrasound images from 21 118 patients were included in this study. The accuracy, sensitivity, and specificity of the HT-CAD model were 0.892, 0.890, and 0.895, respectively. HT-CAD performance between 2 hospitals was not significantly different. The HT-CAD model achieved a higher performance (P < 0.001) when compared to senior radiologists, with a nearly 9% accuracy improvement. HT-CAD had almost similar accuracy (range 0.87-0.894) for the 3 subgroups based on thyroid hormone level. CONCLUSION: The HT-CAD strategy based on CNN significantly improved the radiologists' diagnostic accuracy of HT. Our model demonstrates good performance and robustness in different hospitals and for different thyroid hormone levels.

来源:J Clin Endocrinol Metab,查看原文。版权归原作者所有。

引用

  1. Zhao W, Kang Q, Qian F, et al. Convolutional Neural Network-Based Computer-Assisted Diagnosis of Hashimoto's Thyroiditis on Ultrasound. J Clin Endocrinol Metab. 2022. PMID: 34907442. doi:10.1210/clinem/dgab870

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。