TY - JOUR
T1 - Systematic review and meta-analysis of artificial intelligence in classifying HER2 status in breast cancer immunohistochemistry
AU - Navarro Albuquerque, Daniel Arruda
AU - Vianna, Matheus Trotta
AU - Fernandes Sampaio, Luana Alencar
AU - Vasiliu, Andrei
AU - Cunha Neves Filho, Eduardo Henrique
PY - 2025/1/27
Y1 - 2025/1/27
N2 - The DESTINY-Breast04 trial has recently demonstrated survival benefits of trastuzumab-deruxtecan (T-DXd) in metastatic breast cancer patients with low Human Epidermal Growth Factor Receptor 2 (HER2) expression. Accurate differentiation of HER2 scores has now become crucial. However, visual immunohistochemistry (IHC) scoring is labour-intensive and prone to high interobserver variability, and artificial intelligence (AI) has emerged as a promising tool in diagnostic medicine. We conducted a diagnostic meta-analysis to evaluate AI’s performance in classifying HER2 IHC scores, demonstrating high accuracy in predicting T-DXd eligibility, with a pooled sensitivity of 0.97 [95% CI 0.96 - 0.98] and specificity of 0.82 [95% CI 0.73 - 0.88]. Meta-regression revealed better performance with deep learning and patch-based analysis, while performance declined in externally validated and those utilising commercially available algorithms. Our findings indicate that AI holds promising potential in accurately identifying HER2-low patients and excels in distinguishing 2+ and 3+ scores.
AB - The DESTINY-Breast04 trial has recently demonstrated survival benefits of trastuzumab-deruxtecan (T-DXd) in metastatic breast cancer patients with low Human Epidermal Growth Factor Receptor 2 (HER2) expression. Accurate differentiation of HER2 scores has now become crucial. However, visual immunohistochemistry (IHC) scoring is labour-intensive and prone to high interobserver variability, and artificial intelligence (AI) has emerged as a promising tool in diagnostic medicine. We conducted a diagnostic meta-analysis to evaluate AI’s performance in classifying HER2 IHC scores, demonstrating high accuracy in predicting T-DXd eligibility, with a pooled sensitivity of 0.97 [95% CI 0.96 - 0.98] and specificity of 0.82 [95% CI 0.73 - 0.88]. Meta-regression revealed better performance with deep learning and patch-based analysis, while performance declined in externally validated and those utilising commercially available algorithms. Our findings indicate that AI holds promising potential in accurately identifying HER2-low patients and excels in distinguishing 2+ and 3+ scores.
KW - artificial intelligence
KW - breast cancer
KW - immunohistochemistry
KW - HER2
KW - HER2-low
M3 - Article
SN - 2398-6352
JO - n p j Digital Medicine
JF - n p j Digital Medicine
ER -
