文献速递膀胱癌与上尿路尿路上皮癌

深度学习模型用于尿液细胞图像识别:自动化玻片评估系统

Urine cell image recognition using a deep-learning model for an automated slide evaluation system.
PubMed 文献 · BJU Int · 2021-07-05

本研究开发了基于卷积神经网络的尿液细胞学AI分类系统,将尿液细胞图像分为阴性(良性)和阳性(非典型或恶性)。使用195例组织学确诊尿路上皮癌患者的尿液细胞学玻片,选取4637个细胞图像(3128个良性、398个非典型、1111个恶性或可疑恶性)进行训练和测试。AI在二分类中AUC达0.99,准确率95%,敏感度97%,特异度95%,且诊断准确性超过细胞技术员的最高水平。

要点

  • AI模型对尿液细胞学二分类的AUC为0.99,准确率95%,敏感度97%,特异度95%。
  • AI诊断准确性超过细胞技术员最高水平(Pr(Y>X)=0.95)。
  • AI对所有细胞亚型分类准确率均>90%,亚组分析准确率89%-97%。

核心结论

  • 新型AI尿液细胞学分类系统成功分类所有细胞亚型,准确率>90%,恶性诊断准确性优于细胞技术员最高水平。

研究设计与样本

  • 回顾性收集2016年1月至2017年12月195例组织学确诊尿路上皮癌患者的尿液细胞学玻片。
  • 两名认证细胞技术员独立评估并标记,选取诊断一致的4637个细胞图像(3128良性、398非典型、1111恶性/可疑恶性)。
  • 使用EfficientNet B6和Arcface架构,80%数据用于训练和验证(4:1),20%用于测试,五折交叉验证。

主要发现

  • ROC曲线下面积0.99(95%CI 0.98-0.99),最高准确率95%(95%CI 94-97),敏感度97%(95%CI 95-99),特异度95%(95%CI 93-97)。
  • AI二分类准确性超过细胞技术员最高水平[Pr(Y>X)=0.95]。
  • AI对所有细胞亚型分类准确率>90%;基于患者临床病理特征亚组分析,准确率范围89%-97%。

临床怎么用

  • 该AI系统可用于尿液细胞学自动化玻片评估,辅助区分良性与非典型/恶性细胞。
  • AI诊断准确性高于细胞技术员,可能提高尿液细胞学筛查的效率和一致性。

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

OBJECTIVES: To develop a classification system for urine cytology with artificial intelligence (AI) using a convolutional neural network algorithm that classifies urine cell images as negative (benign) or positive (atypical or malignant). PATIENTS AND METHODS: We collected 195 urine cytology slides from consecutive patients with a histologically confirmed diagnosis of urothelial cancer (between January 2016 and December 2017). Two certified cytotechnologists independently evaluated and labelled each slide; 4637 cell images with concordant diagnoses were selected, including 3128 benign cells (negative), 398 atypical cells, and 1111 cells that were malignant or suspicious for malignancy (positive). This pathologically confirmed labelled dataset was used to represent the ground truth for AI training/validation/testing. Customized CutMix (CircleCut) and Refined Data Augmentation were used for image processing. The model architecture included EfficientNet B6 and Arcface. We used 80% of the data for training and validation (4:1 ratio) and 20% for testing. Model performance was evaluated with fivefold cross-validation. A receiver-operating characteristic (ROC) analysis was used to evaluate the binary classification model. Bayesian posterior probabilities for the AI performance measure (Y) and cytotechnologist performance measure (X) were compared. RESULTS: The area under the ROC curve was 0.99 (95% confidence interval [CI] 0.98-0.99), the highest accuracy was 95% (95% CI 94-97), sensitivity was 97% (95% CI 95-99), and specificity was 95% (95% CI 93-97). The accuracy of AI surpassed the highest level of cytotechnologists for the binary classification [Pr(Y > X) = 0.95]. AI achieved >90% accuracy for all cell subtypes. In the subgroup analysis based on the clinicopathological characteristics of patients who provided the test cells, the accuracy of AI ranged between 89% and 97%. CONCLUSION: Our novel AI classification system for urine cytology successfully classified all cell subtypes with an accuracy of higher than 90%, and achieved diagnostic accuracy of malignancy superior to the highest level achieved by cytotechnologists.

来源:BJU Int,查看原文。版权归原作者所有。

引用

  1. Kaneko M, Tsuji K, Masuda K, et al. Urine cell image recognition using a deep-learning model for an automated slide evaluation system. BJU Int. 2021. PMID: 34143569. doi:10.1111/bju.15518

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。