The role of artificial intelligence in accurate interpretation of HER2 IHC 0 and 1+ in breast cancers

Abstract

The new HER2-targeting antibody drug conjugate offers the opportunity to treat patients with HER2-low breast cancer. Distinguishing HER2 immunohistochemistry (IHC) scores of 0 and 1+, is critical but also challenging due to HER2 heterogeneity and variability of observers. In this study, we aimed to increase interpretation accuracy and consistency of HER2 IHC 0 and 1 + evaluations through assistance from artificial intelligence (AI) algorithm. In addition, we examined the value of AI algorithm in evaluating HER2 IHC scores in tumors with heterogeneity. The AI-assisted interpretation consisted of AI algorithms and an augmenting reality module with microscope. Fifteen pathologists (5 junior, 5 mid-level and 5 senior) participated this multi-institutional two-round ring study that included 246 infiltrating duct carcinoma not otherwise specified (NOS) cases. In round 1, pathologists analyzed 246 HER2 IHC slides by microscope without AI assistance. After 2 weeks of washout period, the pathologists read the same slides with AI algorithm assistance and rendered the final results by adjusting to the AI algorithm. The interpretation accuracy was significantly increased with AI assistance (Accuracy 0.93 vs 0.80), as well as the evaluation precision of HER2 0 and the recall of HER2 1+. The AI algorithm also improved the total consistency (ICC = 0.542 to 0.812), especially in HER2 1 + cases. In cases with heterogeneity, the accuracy was improved significantly (Accuracy 0.68 to 0.89) and to similar level as cases without heterogeneity (Accuracy 0.95). Both accuracy and the consistency of junior pathologists were better improved than the mid-level and senior pathologists. To the best of our knowledge, it is the first study to show that the accuracy and consistency of HER2 IHC 0 and 1 + evaluations and the accuracy of HER2 IHC evaluation in breast cancers with heterogeneity can be significantly improved using AI-assisted interpretation.

Targeting HER2-low in metastatic breast cancer: an evolving treatment paradigm

“…Regardless, standard IHC alone may be suboptimal to define the lower boundary of HER2 expression necessary to predict the clinical activity of some therapies. 38 While novel quantification methods 84 are evaluated (e.g., using DNA/ mRNA, protein-based assays, artificial intelligence 17,[85][86][87] ) and the minimum HER2 expression 35,[88][89][90] Although these events were typically of low or moderate grade, three patients (0.8%) had a fatal grade 5 event. Furthermore, the time to onset of ILD was variable, with a median of 129 days (range, 26-710 days).…”

“…34 Until more information is available, clinicians must be aware of treatment and patient characteristics that may increase the risk of ILD and pneumonitis, such as drug dose, baseline oxygen saturation, moderate/severe renal impairment, certain lung comorbidities, and time since diagnosis. 86,90 Proactive monitoring can successfully identify the symptoms of these AEs and should include regular imaging; active management should involve early administration of glucocorticoids (even among asymptomatic patients) and treatment interruption. 34,88 As noted by other groups, the optimal approach to ADC rechallenge after interruption is still unknown: rechallenge is presently only recommended for patients with grade 1 ILD/pneumonitis that resolves, as evidence is limited to those with grade 2+ events.…”