Novel computer-aided systems for interpreting immu- nohistochemistry (IHC) results in breast cancer based on deep learning algorithms: A systematic review
Abstract
Breast cancer is a prevalent disease worldwide and the accurate diagnosis and prog-nosis of breast cancer are essential for the development of effective treatment plans.Pathology remains the gold standard for diagnosis and prognosis but with limita-tions such as time-consuming manual scoring and some error-prone results. Re-cently, deep learning techniques, especially convolutional neural networks (CNN),have been proposed for the interpretation of immunohistochemistry (IHC) resultsin breast cancer. The objective of this systematic review is to critically assess the ex-isting literature on computer-aided systems for the interpretation of IHC results inbreast cancer based on deep learning algorithms. We included studies with modelsthat use novel approaches such as deep learning for quantitative measurements ofimmunohistochemically stained Ki-67, ER, PR, and HER2 images. We systematical-ly searched PubMed, Scopus, and web of science up to September 2022. 15 studies(seven HER2, seven Ki67, and one ER/PR scoring studies) met our inclusion criteria.Various AI-based assays have been developed for different applications in breast pa-thology, including diagnostic and prognostic applications, as well as predictive valuesand responses to treatment. These algorithms have shown promise in improving theaccuracy of breast cancer diagnosis and prognosis. It is essential to consider the dif-ferences in training and inter-observer variability while designing tools, and there isan urgent need to integrate the detection and analysis of various biomarkers at thesame place and time to facilitate the formation of patients’ reports and treatment.