文献速递甲状腺疾病

人工智能技术提高甲状腺细针穿刺细胞学诊断准确性

Improved Diagnostic Accuracy of Thyroid Fine-Needle Aspiration Cytology with Artificial Intelligence Technology.
PubMed 文献 · Thyroid · 2024-01-01

该多中心回顾性诊断准确性研究基于开放人工智能数据集项目,使用来自3所大学医院和215家韩国机构的甲状腺细针穿刺全切片图像构建人工智能模型。Inception ResNet v2模型在测试集准确率达94.9%,优于专家细胞病理医师平均准确率88.91%,且专家参考人工智能结果后诊断准确率和一致性提高。

要点

  • 人工智能模型在测试集准确率94.9%、敏感度100%、特异度90.4%。
  • 人工智能准确率99.71% vs 专家平均88.91%,超出两个标准差。
  • 专家参考人工智能结果后诊断一致性从0.64升至0.84。

核心结论

  • 人工智能技术应用于甲状腺细针穿刺细胞学可能提高诊断准确性并改善病理医师的观察者内和观察者间变异,需进一步验证性研究。

研究设计与样本

  • 多中心回顾性诊断准确性研究,使用开放人工智能数据集项目中来自3所大学医院和215家韩国机构的甲状腺细针穿刺数字化图像。
  • 训练集来自306例甲状腺细针穿刺的10,332个图像块,包括78例恶性(甲状腺乳头状癌)和228例良性,来自86家机构。
  • 使用三种不同扫描仪采集多个z层图像,经焦点融合和颜色归一化后提取图像块并调整尺寸。
  • 预测试六种人工智能模型,使用数据子集确定Inception ResNet v2为最佳模型,随后用全数据集测试最终模型。
  • 使用随机选取的1031个图像块比较人工智能与细胞病理医师的表现,并在参考人工智能结果后重新评估细胞病理医师的表现。

主要发现

  • Inception ResNet v2在训练集、验证集和测试集的准确率分别为99.7%、97.7%和94.9%。
  • 训练集敏感度99.9%、特异度99.6%;验证集敏感度99.6%、特异度96.4%;测试集敏感度100%、特异度90.4%。
  • 人工智能模型准确率99.71%(95%CI 99.38-100.00%)vs 专家细胞病理医师平均88.91%(95%CI 86.99-90.83%),超出两个标准差。
  • 人工智能敏感度99.81%(95%CI 99.54-100.00%)vs 专家平均87.26%(95%CI 85.22-89.30%)。
  • 人工智能特异度99.61%(95%CI 99.23-99.99%)vs 专家平均90.58%(95%CI 88.80-92.36%)。

临床怎么用

  • 原文未据此给出推荐。

局限性

  • 原文结论指出需进一步验证性研究。

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

Background: Artificial intelligence (AI) is increasingly being applied in pathology and cytology, showing promising results. We collected a large dataset of whole slide images (WSIs) of thyroid fine-needle aspiration cytology (FNA), incorporating z-stacking, from institutions across the nation to develop an AI model. Methods: We conducted a multicenter retrospective diagnostic accuracy study using thyroid FNA dataset from the Open AI Dataset Project that consists of digitalized images samples collected from 3 university hospitals and 215 Korean institutions through extensive quality check during the case selection, scanning, labeling, and reviewing process. Multiple z-layer images were captured using three different scanners and image patches were extracted from WSIs and resized after focus fusion and color normalization. We pretested six AI models, determining Inception ResNet v2 as the best model using a subset of dataset, and subsequently tested the final model with total datasets. Additionally, we compared the performance of AI and cytopathologists using randomly selected 1031 image patches and reevaluated the cytopathologists' performance after reference to AI results. Results: A total of 10,332 image patches from 306 thyroid FNAs, comprising 78 malignant (papillary thyroid carcinoma) and 228 benign from 86 institutions were used for the AI training. Inception ResNet v2 achieved highest accuracy of 99.7%, 97.7%, and 94.9% for training, validation, and test dataset, respectively (sensitivity 99.9%, 99.6%, and 100% and specificity 99.6%, 96.4%, and 90.4% for training, validation, and test dataset, respectively). In the comparison between AI and human, AI model showed higher accuracy and specificity than the average expert cytopathologists beyond the two-standard deviation (accuracy 99.71% [95% confidence interval (CI), 99.38-100.00%] vs. 88.91% [95% CI, 86.99-90.83%], sensitivity 99.81% [95% CI, 99.54-100.00%] vs. 87.26% [95% CI, 85.22-89.30%], and specificity 99.61% [95% CI, 99.23-99.99%] vs. 90.58% [95% CI, 88.80-92.36%]). Moreover, after referring to the AI results, the performance of all the experts (accuracy 96%, 95%, and 96%, respectively) and the diagnostic agreement (from 0.64 to 0.84) increased. Conclusions: These results suggest that the application of AI technology to thyroid FNA cytology may improve the diagnostic accuracy as well as intra- and inter-observer variability among pathologists. Further confirmatory research is needed.

来源:Thyroid,查看原文。版权归原作者所有。

引用

  1. Lee Y, Alam MR, Park H, et al. Improved Diagnostic Accuracy of Thyroid Fine-Needle Aspiration Cytology with Artificial Intelligence Technology. Thyroid. 2024. PMID: 38874262. doi:10.1089/thy.2023.0384

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。