AI-Assisted HER2 Scoring in Breast Cancer: Diagnostic Agreement and Understanding Discordance
Journal Title
Laboratory Investigation
Publication Type
Online publication before print
Abstract
PURPOSE: With trastuzumab deruxtecan demonstrating clinical benefit in HER2-low and ultralow breast cancer, precise discrimination at the lowest end of the HER2 immunohistochemistry (IHC) spectrum has become essential. In this 1-year retrospective study, we evaluated whether a commercially available, in vitro diagnostic (CE-IVD)-approved artificial intelligence (AI) system could improve the consistency of HER2 IHC scoring tested on all breast cancers from a single center. MATERIALS AND METHODS: In total, 853 HER2 IHC whole-slide images from 581 patients were analyzed and independently scored according to American Society of Clinical Oncology/College of American Pathologists (ASCO/CAP) guidelines by three expert pathologists and one non-expert reader, both without and with AI assistance. The AI provided categorical HER2 scores (0-3+) and quantitative cell-level staining metrics. Interobserver agreement was assessed using overall percent agreement (OPA), Conger's kappa, and pairwise Cohen's kappa. Logistic regression models were used to investigate factors associated with discrepancies between pathologists and the AI system. RESULTS: Before AI assistance, overall multi-rater agreement among human readers was substantial (OPA = 79.8%, 95% CI 77.9-81.7; Conger's κ = 0.72, 95% CI 0.69-0.74) and increased to near-perfect levels following AI assistance (OPA = 88.6%, 95 % CI 86.9-90.1; κ = 0.84, 95% CI 0.82-0.86). Most discordances clustered around the 10% ASCO/CAP cutoff and were driven mainly by undercalling of 2+ cases. Discordance was also associated with lower tumor cell counts, biopsy samples, and heterogeneous staining patterns. Among AI-classified HER2-0 tumors, true HER2-null cases without any detectable positive staining were rare, supporting a biological continuum of HER2 expression. CONCLUSIONS: AI-assisted HER2 IHC scoring significantly improves interobserver consistency and provides quantitative support that helps address key limitations of conventional categorical HER2 assessment.
Keywords
HER2-low; breast cancer; concordance; digital image analysis; human epidermal growth factor 2; immunohistochemistry
Department(s)
Laboratory Research
Terms of Use/Rights Notice
Refer to copyright notice on published article.


Creation Date: 2026-07-07 01:21:41
Last Modified: 2026-07-07 01:21:45
An error has occurred. This application may no longer respond until reloaded. Reload 🗙