人工智能辅助技术在进展期胃癌原发灶不同区域HER-2评估及判断预后中的应用
作者:
通讯作者:
作者单位:

1.河北医科大学第四医院 外三科,河北 石家庄 050011;2.河北医科大学第四医院 病理科,河北 石家庄 050011

作者简介:

刘洋,河北医科大学第四医院主治医师,主要从事胃肿瘤基础与研究方面的研究。

基金项目:

政府资助临床医学优秀人才培养基金资助项目(冀财社[2019]139号);河北省胃癌精准诊断与综合治疗重点实验室基金资助项目(SZX2022014)。


Application of artificial intelligence-assisted technology in assessment of HER-2 expression in different regions of primary lesions of advanced gastric cancer and prognostic estimation
Author:
Affiliation:

1.The Third Department of General Surgery, the Fourth Hospital of Hebei Medical University, Shijiazhuang 050011, China;2.Department of Pathology, the Fourth Hospital of Hebei Medical University, Shijiazhuang 050011, China

Fund Project:

  • 摘要
  • |
  • 图/表
  • |
  • 访问统计
  • |
  • 参考文献
  • |
  • 相似文献
  • |
  • 引证文献
  • |
  • 资源附件
  • |
  • 音频文件
  • |
  • 视频文件
    摘要:

    背景与目的 胃癌中人类表皮生长因子受体2(HER-2)表达存在较高的异质性,全面地评估患者的HER-2状态有利于发现抗HER-2治疗的潜在受益者。人工智能(AI)辅助显微镜可以通过大量读片以综合判断HER-2的状态,并减少人为评估的视觉误差。本研究旨在探讨AI辅助显微镜在胃癌原发灶多区域HER-2评估中的实用性和可行性。方法 对264例进展期胃癌患者术后标本同一区域HER-2免疫组化染色切片,分别使用普通光学显微镜视觉评估、AI辅助显微镜两种方法进行评估,评价AI辅助显微镜在胃癌HER-2评估中的准确性;并使用AI辅助显微镜对上述胃癌患者原发灶的其他区域的HER-2表达进行评估,将两个区域HER-2评分较高者作为最终判读结果,并进一步分析HER-2过表达与进展期胃癌患者临床病理特征及术后生存的关系。结果 视觉评估、AI辅助显微镜与金标准三者之间HER-2评分总体差异无统计学意义(P>0.05),但AI辅助显微镜相较视觉评估与金标准具有更高的一致性(κ=0.86 vs. κ=0.81,P<0.05)。使用AI辅助显微镜对胃癌原发灶两个不同区域的HER-2评估结果显示,两个区域HER-2评分不一致者为55例,不一致率为20.8%。其中区域1 HER-2过表达率为29.9%,区域2 HER-2过表达率为31.0%,综合评估两个区域取较高评分的HER-2过表达率为35.2%。综合评估两个区域HER-2表达得出的HER-2过表达率高于单独判读一个区域,但差异无统计学意义(P>0.05);进一步分析发现,胃癌原发灶HER-2异质性表达与肿瘤分化程度及Lauren分型明显有关(均P<0.05)。生存分析显示,HER-2过表达进展期胃癌患者3年中位OS时间为23个月,3年OS率为33.4%;HER-2非过表达的进展期胃癌患者3年中位OS时间为29个月,3年OS率为44.6%,差异有统计学意义(P<0.05)。结论 AI辅助显微镜是一种用于胃癌原发灶不同区域HER-2评估实用可靠的工具,可以更为全面准确地评估胃癌的HER-2表达状态,提高HER-2过表达检出率。中低分化及Lauren分型为非肠型的胃癌患者更易出现HER-2异质性表达,HER-2过表达可能是可切除进展期胃癌患者预后不良的因素。

    Abstract:

    Background and Aims The expression of human epidermal growth factor receptor 2 (HER-2) in gastric cancer exhibits significant heterogeneity, and comprehensive evaluation of HER-2 status in patients is advantageous for identifying potential beneficiaries of anti-HER-2 therapy. Artificial intelligence (AI)-assisted microscopy can integrate judgments on HER-2 status through extensive slide readings and reduce visual errors in human assessments. This study was performed to evaluate the practicality and feasibility of AI in evaluating HER-2 status in multiple regions of primary gastric cancer lesions.Methods A total of 264 postoperative specimens from patients with advanced gastric cancer were evaluated for HER-2 expression in the same region using two methods: visual assessment with a conventional light microscope and AI-assisted microscopy. The accuracy of AI in HER-2 evaluation in gastric cancer was evaluated. Additionally, using AI-assisted microscopy, HER-2 expression in other regions of the primary lesion in the gastric cancer patients was assessed. The higher HER-2 score between the two regions was used as the final interpretation result. Furthermore, the associations of HER-2 overexpression with clinicopathological features and postoperative survival of advanced gastric cancer patients were analyzed.Results There was no statistically significant overall difference in HER-2 scores among visual assessment, AI-assisted microscopy, and the gold standard (P>0.05), but AI-assisted microscopy showed higher consistency compared to visual assessment with the gold standard (κ=0.86 vs. κ=0.81, P<0.05). The results of HER-2 evaluation in two different regions of the primary lesion in gastric cancer using AI showed inconsistency in 55 cases, with a discordance rate of 20.8%. The HER-2 overexpression rate was 29.9% in region 1 and 31.0% in region 2. The comprehensive evaluation of HER-2 overexpression rate, taking the higher score between the two regions, was 35.2%. The HER-2 overexpression rate based on comprehensive evaluation of HER-2 expression in the two regions was higher than that of single-region assessment, but the difference was not statistically significant (P>0.05). Further analysis revealed that HER-2 heterogeneity in primary gastric cancer lesions was significantly associated with tumor differentiation and Lauren classification (both P<0.05). Survival analysis showed that the median 3-year overall survival was 23 months with a 3-year survival rate of 33.4% in HER-2 overexpressing advanced gastric cancer patients, while it was 29 months with a 3-year survival rate of 44.6% in HER-2 non-overexpressing advanced gastric cancer patients, and the difference was statistically significant (P<0.05).Conclusion AI is a practical and reliable tool for evaluating HER-2 expression in different regions of primary gastric cancer, enabling a more comprehensive and accurate assessment of HER-2 status in gastric cancer and improving the detection rate of HER-2 overexpression. HER-2 heterogeneous expression is more likely to occur in gastric cancer patients with moderate to low differentiation and non-intestinal type Lauren classification, and HER-2 overexpression may be a poor prognostic factor in resectable advanced gastric cancer patients.

    表 2 AI辅助显微镜与金标准HER-2评分结果对比(n)Table 2 Comparison of HER-2 scoring results between AI-assisted microscopy and gold standard assessment (n)
    表 3 AI辅助显微镜评估胃癌原发灶两个不同区域HER-2表达分析[n(%)]Table 3 Analysis of HER-2 expression in two different regions of primary gastric cancer using AI assessment [n (%)]
    表 4 两个区域HER-2评分情况与临床病理参数关系[n(%)]Table 4 Relationship between HER-2 scoring in two regions and clinicopathologic parameters [n (%)]
    图1 AI辅助显微镜与计算机输出界面Fig.1 AI-assisted microscope with computer output interface
    图2 AI辅助显微镜使用流程Fig.2 Workflow for the use of AI-assisted microscope
    图3 AI综合5个典型视野得出HER-2最终建议评分Fig.3 Integration of scores from 5 typical fields of view to generate the final recommended HER-2 score by AI
    图4 不同HER-2表达水平进展期胃癌患者生存曲线Fig.4 Survival curves of advanced gastric cancer patients with different HER-2 expression levels
    表 1 264例胃癌患者原发灶同一区域HER-2不同评估方式的评分结果[n(%)]Table 1 The scoring results of HER-2 evaluation in the same region of primary lesions in 264 cases of gastric cancer patients using different assessment methods [n (%)]
    参考文献
    相似文献
    引证文献
引用本文

刘洋,郭子阳,刘月平,王心然,王子涵,杨家轩,丁平安,郑涛,田园,郭洪海,檀碧波,范立侨,李勇,赵群.人工智能辅助技术在进展期胃癌原发灶不同区域HER-2评估及判断预后中的应用[J].中国普通外科杂志,2023,32(4):566-574.
DOI:10.7659/j. issn.1005-6947.2023.04.011

复制
分享
文章指标
  • 点击次数:
  • 下载次数:
历史
  • 收稿日期:2022-06-02
  • 最后修改日期:2023-03-24
  • 录用日期:
  • 在线发布日期: 2023-04-28