背景:乳腺癌分子亚型的准确分类对于确定治疗策略和预测临床结果至关重要。这种分类很大程度上取决于人类表皮生长因子受体2(HER2)的评估,雌激素受体(ER),和孕激素受体(PR)状态。然而,病理学家之间解释的差异性对这种分类的准确性提出了挑战.这项研究评估了人工智能(AI)在增强这些评估一致性方面的作用。
方法:AI驱动的HER2和ER/PR分析仪,由细胞和组织模型组成,是使用1,259HER2,744ER开发的,和466乳腺癌PR染色的免疫组织化学(IHC)全片图像。外部验证队列包括HER2、ER、用这些人工智能分析仪分析了201例乳腺癌病例的PRIHC。三名董事会认证的病理学家独立评估了这些病例,没有AI注释。然后,病理学家和人工智能分析仪之间有不同解释的病例在人工智能的帮助下重新审视,与初始评估相比,重点评估AI辅助对病理学家之间一致性的影响。
结果:61(30.3%)需要重新评估,42(20.9%),和80(39.8%)的HER2,在15(7.5%),17(8.5%),和11个(5.5%)急诊室,在26(12.9%)中,24(11.9%),病理学家进行了28项(13.9%)PR评估,分别。与最初的解释相比,AI的协助导致三位病理学家对HER2状态的协议显着增加(从49.3%增加到74.1%,p<0.001),ER(从93.0到96.5%,p=0.096),和PR(从84.6%到91.5%,p=0.006)。这种改善在HER2+和1+的情况下尤其明显。其中一致性从46.2%显着增加到68.4%,从26.5%增加到70.7%,分别。因此,乳腺癌分子亚型分类的改进(从58.2%到78.6%,p<0.001)是在AI辅助下实现的。
结论:本研究强调了AI分析仪在提高病理学家对乳腺癌分子亚型分类的一致性方面的重要作用。
Accurate classification of breast cancer molecular subtypes is crucial in determining treatment strategies and predicting clinical outcomes. This classification largely depends on the assessment of human epidermal growth factor receptor 2 (HER2), estrogen receptor (ER), and progesterone receptor (PR) status. However, variability in interpretation among pathologists pose challenges to the accuracy of this classification. This study evaluates the role of artificial intelligence (AI) in enhancing the consistency of these evaluations.
AI-powered HER2 and ER/PR analyzers, consisting of cell and tissue models, were developed using 1,259 HER2, 744 ER, and 466 PR-stained immunohistochemistry (IHC) whole-slide images of breast cancer. External validation cohort comprising HER2, ER, and PR IHCs of 201 breast cancer cases were analyzed with these AI-powered analyzers. Three board-certified pathologists independently assessed these cases without AI annotation. Then, cases with differing interpretations between pathologists and the AI analyzer were revisited with AI assistance, focusing on evaluating the influence of AI assistance on the concordance among pathologists during the revised evaluation compared to the initial assessment.
Reevaluation was required in 61 (30.3%), 42 (20.9%), and 80 (39.8%) of HER2, in 15 (7.5%), 17 (8.5%), and 11 (5.5%) of ER, and in 26 (12.9%), 24 (11.9%), and 28 (13.9%) of PR evaluations by the pathologists, respectively. Compared to initial interpretations, the assistance of AI led to a notable increase in the agreement among three pathologists on the status of HER2 (from 49.3 to 74.1%, p < 0.001), ER (from 93.0 to 96.5%, p = 0.096), and PR (from 84.6 to 91.5%, p = 0.006). This improvement was especially evident in cases of HER2 2+ and 1+, where the concordance significantly increased from 46.2 to 68.4% and from 26.5 to 70.7%, respectively. Consequently, a refinement in the classification of breast cancer molecular subtypes (from 58.2 to 78.6%, p < 0.001) was achieved with AI assistance.
This study underscores the significant role of AI analyzers in improving pathologists\' concordance in the classification of breast cancer molecular subtypes.