RESULTS: We trained a DL model on a multicentric cohort of breast cancer cases with HER2-IHC scores (n = 299). The model was validated on two independent multicentric validation cohorts (n = 369 and n = 92), with all cases reviewed by three senior breast pathologists. All cases underwent a thorough review by three senior breast pathologists, with the ground truth determined by a majority consensus on the final HER2 score among the pathologists. In total, 760 breast cancer cases were utilized throughout the training and validation phases of the study. The model\'s concordance with the ground truth (ICC = 0.77 [0.68-0.83]; Fisher P = 1.32e-10) is higher than the average agreement among the three senior pathologists (ICC = 0.45 [0.17-0.65]; Fisher P = 2e-3). In the two validation cohorts, the DL model identifies 95% [93% - 98%] and 97% [91% - 100%] of HER2-low and HER2-positive tumours, respectively. Discordant results were characterized by morphological features such as extended fibrosis, a high number of tumour-infiltrating lymphocytes, and necrosis, whilst some artefacts such as nonspecific background cytoplasmic stain in the cytoplasm of tumour cells also cause discrepancy.
CONCLUSIONS: Deep learning can support pathologists\' interpretation of difficult HER2-low cases. Morphological variables and some specific artefacts can cause discrepant HER2-scores between the pathologist and the DL model.
结果:我们在具有HER2-IHC评分的乳腺癌患者的多中心队列中训练了DL模型(n=299)。该模型在两个独立的多中心验证队列(n=369和n=92)上进行了验证,所有病例均由三名资深乳腺病理学家审查。所有病例均由三名资深乳腺病理学家进行全面审查,根据病理学家对最终HER2评分的多数共识确定的基本事实。总的来说,在整个研究的训练和验证阶段使用了760例乳腺癌病例。模型与地面实况的一致性(ICC=0.77[0.68-0.83];FisherP=1.32e-10)高于三位高级病理学家的平均一致性(ICC=0.45[0.17-0.65];FisherP=2e-3)。在两个验证队列中,DL模型识别了95%[93%-98%]和97%[91%-100%]的HER2低和HER2阳性肿瘤,分别。不一致的结果以形态学特征为特征,如扩展的纤维化,大量的肿瘤浸润淋巴细胞,和坏死,而肿瘤细胞的细胞质中的一些伪像,例如非特异性背景细胞质染色也会引起差异。
结论:深度学习可以支持病理学家对困难的低HER2病例的解释。形态学变量和一些特定的伪影可能导致病理学家和DL模型之间的HER2评分不一致。