背景:尿液细胞学,虽然是一种有用的尿路上皮癌筛查方法,缺乏敏感性。作为一项新兴技术,人工智能(AI)显著提高了图像分析精度。
目的:开发一种完全自动化的AI系统,以协助病理学家从数字化尿细胞学切片中进行高级别尿路上皮癌(HGUC)的组织学预测。
方法:我们将535个连续的尿细胞学切片数字化用于AI。在这些幻灯片中,181个用于人工智能开发,39个作为AI测试数据,通过细胞水平分类识别HGUC,315个用作幻灯片水平分类的AI测试数据。
方法:在315张幻灯片中,在膀胱活检或经尿道膀胱肿瘤电切术之前立即收集了171例,然后将结果与手术标本中HGUC的组织学存在进行比较。主要目的是将HGUC组织学存在的AI预测与病理学家对HGUC的组织学诊断进行比较。次要目的是比较AI评估所需的时间以及AI的分类和病理学家的细胞学诊断之间的一致性。
结论:预测HGUC组织学存在的AI能力曲线下面积为0.78。将AI预测性能与病理学家的诊断进行比较,AI对组织学HGUC预测的敏感度为63%,优于病理学家的细胞学敏感度为46%(p=0.0037).相反,83%的AI特异性和89%的病理学家特异性之间没有显著差异(p=0.13),AI准确率为74%,病理学家准确率为68%(p=0.08)。AI评估所需的时间为139s。关于AI预测与病理学家的细胞学诊断之间的一致性,准确率为86%。与正面和负面结果的协议分别为92%和84%,分别。
结论:我们开发了一个完全自动化的AI系统,以协助病理学家使用数字化幻灯片进行HGUC的组织学诊断。该AI系统显示出比董事会认证的细胞病理学家明显更高的灵敏度,并且可以帮助病理学家进行尿液细胞学诊断。减少他们的工作量。
结果:在这项研究中,我们提出了一个基于深度学习的人工智能(AI)系统,根据巴黎系统对尿液细胞学切片进行分类。开发了自动AI系统,并使用535个连续的尿液细胞学载玻片进行了验证。AI预测来自数字化尿细胞学切片的组织学高级别尿路上皮癌,其敏感性优于病理学家。同时保持可比的特异性和准确性。
BACKGROUND: Urine cytology, although a useful screening method for urothelial carcinoma, lacks sensitivity. As an emerging technology, artificial intelligence (AI) improved image analysis accuracy significantly.
OBJECTIVE: To develop a fully automated AI system to assist pathologists in the histological prediction of high-grade urothelial carcinoma (HGUC) from digitized urine cytology slides.
METHODS: We digitized 535 consecutive urine cytology slides for AI use. Among these slides, 181 were used for AI development, 39 were used as AI test data to identify HGUC by cell-level classification, and 315 were used as AI test data for slide-level classification.
METHODS: Out of the 315 slides, 171 were collected immediately prior to bladder biopsy or transurethral resection of bladder tumor, and then outcomes were compared with the histological presence of HGUC in the surgical specimen. The primary aim was to compare AI prediction of the histological presence of HGUC with the pathologist\'s histological diagnosis of HGUC. Secondary aims were to compare the time required for AI evaluation and concordance between the AI\'s classification and pathologist\'s cytology diagnosis.
CONCLUSIONS: The AI capability for predicting the histological presence of HGUC was 0.78 for the area under the curve. Comparing the AI predictive performance with pathologists\' diagnosis, the AI sensitivity of 63% for histological HGUC prediction was superior to a pathologists\' cytology sensitivity of 46% (p = 0.0037). On the contrary, there was no significant difference between the AI specificity of 83% and pathologists\' specificity of 89% (p = 0.13), and AI accuracy of 74% and pathologists\' accuracy of 68% (p = 0.08). The time required for AI evaluation was 139 s. With respect to the concordance between the AI prediction and pathologist\'s cytology diagnosis, the accuracy was 86%. Agreements with positive and negative findings were 92% and 84%, respectively.
CONCLUSIONS: We developed a fully automated AI system to assist pathologists\' histological diagnosis of HGUC using digitized slides. This AI system showed significantly higher sensitivity than a board-certified cytopathologist and may assist pathologists in making urine cytology diagnoses, reducing their workload.
RESULTS: In this study, we present a deep learning-based artificial intelligence (AI) system that classifies urine cytology slides according to the Paris system. An automated AI system was developed and validated with 535 consecutive urine cytology slides. The AI predicted histological high-grade urothelial carcinoma from digitized urine cytology slides with superior sensitivity than pathologists, while maintaining comparable specificity and accuracy.