The Role of Artificial Intelligence in Accurate Interpretation of HER2 Immunohistochemical Scores 0 and 1+ in Breast Cancer

Si Wu; Meng Yue; Jun Zhang; Xiaoxian Li; Zaibo Li; Huina Zhang; Xinran Wang; Xiao Han; Lijing Cai; Jiuyan Shang; Zhanli Jia; Xiaoxiao Wang; Jinze Li; Yueping Liu

doi:10.1016/j.modpat.2022.100054

The Role of Artificial Intelligence in Accurate Interpretation of HER2 Immunohistochemical Scores 0 and 1+ in Breast Cancer

Mod Pathol. 2023 Mar;36(3):100054. doi: 10.1016/j.modpat.2022.100054. Epub 2023 Jan 10.

Authors

Si Wu¹, Meng Yue¹, Jun Zhang², Xiaoxian Li³, Zaibo Li⁴, Huina Zhang⁵, Xinran Wang¹, Xiao Han², Lijing Cai¹, Jiuyan Shang¹, Zhanli Jia¹, Xiaoxiao Wang¹, Jinze Li¹, Yueping Liu⁶

Affiliations

¹ Department of Pathology, the Fourth Hospital of Hebei Medical University, Shijiazhuang, Hebei, China.
² Tencent AI Lab, Nanshan District, Tencent Binhai Building, Shenzhen, Guangdong, China.
³ Department of Pathology and Laboratory Medicine, The Emory University School of Medicine, Atlanta, Georgia.
⁴ Department of Pathology, The Ohio State University Wexner Medical Center, Columbus, Ohio.
⁵ Department of Pathology, University of Rochester Medical Center, Rochester, New York.
⁶ Department of Pathology, the Fourth Hospital of Hebei Medical University, Shijiazhuang, Hebei, China. Electronic address: annama@163.com.

PMID: 36788100
DOI: 10.1016/j.modpat.2022.100054

Abstract

The new human epidermal growth factor receptor (HER)2-targeting antibody-drug conjugate offers the opportunity to treat patients with HER2-low breast cancer. Distinguishing HER2 immunohistochemical (IHC) scores of 0 and 1+ is not only critical but also challenging owing to HER2 heterogeneity and variability of observers. In this study, we aimed to increase the interpretation accuracy and consistency of HER2 IHC 0 and 1+ evaluation through assistance from an artificial intelligence (AI) algorithm. In addition, we examined the value of our AI algorithm in evaluating HER2 IHC scores in tumors with heterogeneity. AI-assisted interpretation consisted of AI algorithms and an augmenting reality module with a microscope. Fifteen pathologists (5 junior, 5 midlevel, and 5 senior) participated in this multi-institutional 2-round ring study that included 246 infiltrating duct carcinoma cases that were not otherwise specified. In round 1, pathologists analyzed 246 HER2 IHC slides by microscope without AI assistance. After a 2-week washout period, the pathologists read the same slides with AI algorithm assistance and rendered the definitive results by adjusting to the AI algorithm. The accuracy of interpretation accuracy with AI assistance (0.93 vs 0.80), thereby the evaluation precision of HER2 0 and the recall of HER2 1+. In addition, the AI algorithm improved the total consistency (intraclass correlation coefficient = 0.542-0.812), especially in HER2 1+ cases. In cases with heterogeneity, accuracy improved significantly (0.68 to 0.89) and to a similar level as in cases without heterogeneity (accuracy, 0.97). Both accuracy and consistency improved more for junior pathologists than those for the midlevel and senior pathologists. To the best of our knowledge, this is the first study to show that the accuracy and consistency of HER2 IHC 0 and 1+ evaluation and the accuracy of HER2 IHC evaluation in breast cancers with heterogeneity can be significantly improved using AI-assisted interpretation.

Keywords: HER2-low; artificial intelligence; breast cancer; heterogeneity.

Publication types

Research Support, Non-U.S. Gov't

MeSH terms

Algorithms
Artificial Intelligence
Breast Neoplasms* / pathology
Carcinoma, Ductal*
Female
Humans
Oncogenes
Receptor, ErbB-2 / genetics

Substances

Receptor, ErbB-2