TY - JOUR
T1 - Fully Automated Artificial Intelligence Solution for Human Epidermal Growth Factor Receptor 2 Immunohistochemistry Scoring in Breast Cancer
T2 - A Multireader Study
AU - Krishnamurthy, Savitri
AU - Schnitt, Stuart J.
AU - Vincent-Salomon, Anne
AU - Canas-Marques, Rita
AU - Colon, Eugenia
AU - Kantekure, Kanchan
AU - Maklakovski, Marina
AU - Finck, Wilfrid
AU - Thomassin, Jeanne
AU - Globerson, Yuval
AU - Bien, Lilach
AU - Mallel, Giuseppe
AU - Grinwald, Maya
AU - Linhart, Chaim
AU - Sandbank, Judith
AU - Vecsler, Manuela
N1 - Publisher Copyright:
© 2024 by American Society of Clinical Oncology.
PY - 2024/10/1
Y1 - 2024/10/1
N2 - PURPOSE The proven efficacy of human epidermal growth factor receptor 2 (HER2) antibody-drug conjugate therapy for treating HER2-low breast cancers necessitates more accurate and reproducible HER2 immunohistochemistry (IHC) scoring. We aimed to validate performance and utility of a fully automated artificial intelligence (AI) solution for interpreting HER2 IHC in breast carcinoma. MATERIALS A two-arm multireader study of 120 HER2 IHC whole-slide images from four AND METHODS sites assessed HER2 scoring by four surgical pathologists without and with the aid of an AI HER2 solution. Both arms were compared with high-confidence ground truth (GT) established by agreement of at least four of five breast pathology subspecialists according to ASCO/College of American Pathologists (CAP) 2018/2023 guidelines. RESULTS The mean interobserver agreement among GT pathologists across all HER2 scores was 72.4% (N 5 120). The AI solution demonstrated high accuracy for HER2 scoring, with 92.1% agreement on slides with high confidence GT (n 5 92). The use of the AI tool led to improved performance by readers, interobserver agreement increased from 75.0% for digital manual read to 83.7% for AI-assisted review, and scoring accuracy improved from 85.3% to 88.0%. For the distinction of HER2 0 from 11 cases (n 5 58), pathologists supported by AI showed significantly higher interobserver agreement (69.8% without AI v 87.4% with AI) and accuracy (81.9% without AI v 88.8% with AI). CONCLUSION This study demonstrated utility of a fully automated AI solution to aid in scoring HER2 IHC accurately according to ASCO/CAP 2018/2023 guidelines. Pathologists supported by AI showed improvements in HER2 IHC scoring consistency and accuracy, especially for distinguishing HER2 0 from 11 cases. This AI solution could be used by pathologists as a decision support tool for enhancing reproducibility and consistency of HER2 scoring and particularly for identifying HER2-low breast cancers.
AB - PURPOSE The proven efficacy of human epidermal growth factor receptor 2 (HER2) antibody-drug conjugate therapy for treating HER2-low breast cancers necessitates more accurate and reproducible HER2 immunohistochemistry (IHC) scoring. We aimed to validate performance and utility of a fully automated artificial intelligence (AI) solution for interpreting HER2 IHC in breast carcinoma. MATERIALS A two-arm multireader study of 120 HER2 IHC whole-slide images from four AND METHODS sites assessed HER2 scoring by four surgical pathologists without and with the aid of an AI HER2 solution. Both arms were compared with high-confidence ground truth (GT) established by agreement of at least four of five breast pathology subspecialists according to ASCO/College of American Pathologists (CAP) 2018/2023 guidelines. RESULTS The mean interobserver agreement among GT pathologists across all HER2 scores was 72.4% (N 5 120). The AI solution demonstrated high accuracy for HER2 scoring, with 92.1% agreement on slides with high confidence GT (n 5 92). The use of the AI tool led to improved performance by readers, interobserver agreement increased from 75.0% for digital manual read to 83.7% for AI-assisted review, and scoring accuracy improved from 85.3% to 88.0%. For the distinction of HER2 0 from 11 cases (n 5 58), pathologists supported by AI showed significantly higher interobserver agreement (69.8% without AI v 87.4% with AI) and accuracy (81.9% without AI v 88.8% with AI). CONCLUSION This study demonstrated utility of a fully automated AI solution to aid in scoring HER2 IHC accurately according to ASCO/CAP 2018/2023 guidelines. Pathologists supported by AI showed improvements in HER2 IHC scoring consistency and accuracy, especially for distinguishing HER2 0 from 11 cases. This AI solution could be used by pathologists as a decision support tool for enhancing reproducibility and consistency of HER2 scoring and particularly for identifying HER2-low breast cancers.
UR - https://www.scopus.com/pages/publications/85207444091
U2 - 10.1200/PO.24.00353
DO - 10.1200/PO.24.00353
M3 - ???researchoutput.researchoutputtypes.contributiontojournal.article???
C2 - 39393036
AN - SCOPUS:85207444091
SN - 2473-4284
VL - 8
JO - JCO Precision Oncology
JF - JCO Precision Oncology
M1 - e2400353
ER -
