文献速递细胞病理与分子病理泌尿与男性生殖病理

人工智能是否重新定义高级别尿路上皮癌诊断的核浆比阈值?

Does artificial intelligence redefine nuclear-to-cytoplasmic ratio threshold for diagnosing high-grade urothelial carcinoma?
PubMed 文献 · Cancer Cytopathol · 2025-01-01

本研究使用AI模型AIxURO对106例尿液细胞学全切片图像进行核浆比和核面积定量分析,病例包括非典型尿路上皮细胞、可疑高级别尿路上皮癌(SHGUC)和高级别尿路上皮癌(HGUC),均经活检证实为HGUC或原位癌(CIS)。结果显示可疑细胞核浆比高于非典型细胞(0.66 vs. 0.58,p < .001),且核面积更大(102.3 vs. 85.7 µm2,p < .001);上尿路与下尿路病例的核浆比无显著差异,但CIS的核面积大于HGUC。结论提示AIxURO可客观量化核浆比和核面积,SHGUC/HGUC的核浆比截断值0.66可能比TPS阈值>0.7更合适。

要点

  • AIxURO量化显示可疑细胞核浆比0.66,低于TPS阈值0.7。
  • 可疑细胞核浆比和核面积均显著高于非典型细胞。
  • 上尿路与下尿路病例的核浆比无显著差异,支持统一标准。

核心结论

  • AIxURO可客观量化核浆比和核面积,细化TPS标准以区分可疑与非典型细胞。
  • SHGUC/HGUC的核浆比截断值0.66可能比TPS阈值>0.7更合适。
  • 上尿路与下尿路病例可采用一致的核浆比标准。

研究设计与样本

  • 回顾性分析106例尿液细胞学全切片图像,来自46例下尿路和60例上尿路癌症病例。
  • 病例诊断分布:非典型尿路上皮细胞15.1%,SHGUC 23.6%,HGUC 61.3%,均经活检证实为HGUC或CIS。
  • 使用AIxURO模型量化可疑细胞、非典型细胞、核浆比和核面积,统计差异采用Kruskal-Wallis检验。

主要发现

  • AIxURO识别的可疑细胞数量少于非典型细胞(20.5 vs. 242.0,p < .001)。
  • 可疑细胞的核浆比高于非典型细胞(0.66 vs. 0.58,p < .001),核面积更大(102.3 vs. 85.7 µm2,p < .001)。
  • 上尿路与下尿路病例的核浆比无显著差异,但异常细胞核面积不同(CIS: 101.5 µm2;HGUC: 83.5 µm2)。
  • 在HGUC细胞学病例中,CIS类别的可疑细胞核面积大于HGUC(116.3 vs. 100.4 µm2),非典型细胞亦然(101.5 vs. 82.2 µm2)。

关键数值与推荐

  • SHGUC/HGUC的核浆比截断值0.66可能优于TPS阈值>0.7。
  • 可疑细胞核浆比0.66,非典型细胞0.58(p < .001)。
  • 可疑细胞核面积102.3 µm2,非典型细胞85.7 µm2(p < .001)。

临床怎么用

  • AIxURO可辅助客观测量核浆比和核面积,减少TPS标准的主观性。
  • 在区分可疑与非典型细胞时,可考虑采用较低的核浆比截断值0.66。
  • 上尿路和下尿路尿液细胞学可应用统一的核浆比标准。

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: The Paris System (TPS) introduced standardized nuclear-to-cytoplasmic (N/C) ratio thresholds for urine cytology to improve high-grade urothelial carcinoma (HGUC) detection, but these criteria remain subjective. This study used AIxURO, an artificial intelligence-based model, to measure N/C ratio and nuclear area to identify abnormal cells in whole slide images (WSIs). METHODS: A total of 106 urine cytology slides from 46 lower urinary tract (LUT) and 60 upper urinary tract (UUT) cancer cases, diagnosed as atypical urothelial cell (15.1%), suspicious for high-grade urothelial carcinoma (SHGUC) (23.6%), and HGUC (61.3%), with biopsy-confirmed HGUC or carcinoma in situ (CIS), were digitized and analyzed by AIxURO. The model quantified suspicious and atypical cells, N/C ratios, and nuclear areas, with statistical differences assessed using Kruskal-Wallis tests. RESULTS: AIxURO identified fewer suspicious cells than atypical cells (20.5 vs. 242.0, p < .001). Suspicious cells had higher N/C ratios (0.66 vs. 0.58, p < .001) and larger nuclear areas (102.3 vs. 85.7 µm2, p < .001). Although N/C ratios did not differ significantly between UUT and LUT cases, nuclear areas varied among abnormal cells (CIS: 101.5 µm2; HGUC: 83.5 µm2). In HGUC cytology cases, the CIS category had larger nuclear areas than HGUC for both suspicious (116.3 vs. 100.4 µm2) and atypical cells (101.5 vs. 82.2 µm2). CONCLUSIONS: AIxURO provides objective quantification of N/C ratios and nuclear areas, refining TPS criteria for distinguishing suspicious from atypical cells. A lower N/C ratio cutoff (0.66) for SHGUC/HGUC may be more appropriate than the TPS threshold (>0.7). Findings support using consistent N/C ratio criteria across UUT and LUT cases.

来源:Cancer Cytopathol,查看原文。版权归原作者所有。

引用

  1. Yang WL, Crothers BA, Liu TJ, et al. Does artificial intelligence redefine nuclear-to-cytoplasmic ratio threshold for diagnosing high-grade urothelial carcinoma? Cancer Cytopathol. 2025. PMID: 40317981. doi:10.1002/cncy.70017

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。