Relevance of deep learning to facilitate the diagnosis of HER2 status in breast cancer

• Published in: Scientific reports Vol. 7; no. 1; p. 45938
• Main Authors: Vandenberghe, Michel E., Scott, Marietta L. J., Scorer, Paul W., Söderberg, Magnus, Balcerzak, Denis, Barker, Craig
• Format: Journal Article
• Language: English
• Published: London Nature Publishing Group UK 05-04-2017; Nature Publishing Group
• Subjects: 639/705/117; 692/4028/67/1347; 692/53/2421; Antineoplastic Agents, Immunological - therapeutic use; Artificial intelligence; Biomarkers, Tumor - antagonists & inhibitors; Biomarkers, Tumor - metabolism; Breast cancer; Breast Neoplasms - diagnosis; Breast Neoplasms - drug therapy; Breast Neoplasms - metabolism; Cohort Studies; Computer applications; Decision making; Diagnosis, Computer-Assisted - methods; Discordance; ErbB-2 protein; Female; Heterogeneity; Humanities and Social Sciences; Humans; Immunohistochemistry; Machine Learning; multidisciplinary; Receptor, ErbB-2 - antagonists & inhibitors; Receptor, ErbB-2 - metabolism; Reproducibility of Results; Science; Trastuzumab - therapeutic use; Tumors
• ISSN: 2045-2322; 2045-2322
• DOI: 10.1038/srep45938

Tissue biomarker scoring by pathologists is central to defining the appropriate therapy for patients with cancer. Yet, inter-pathologist variability in the interpretation of ambiguous cases can affect diagnostic accuracy. Modern artificial intelligence methods such as deep learning have the potential to supplement pathologist expertise to ensure constant diagnostic accuracy. We developed a computational approach based on deep learning that automatically scores HER2, a biomarker that defines patient eligibility for anti-HER2 targeted therapies in breast cancer. In a cohort of 71 breast tumour resection samples, automated scoring showed a concordance of 83% with a pathologist. The twelve discordant cases were then independently reviewed, leading to a modification of diagnosis from initial pathologist assessment for eight cases. Diagnostic discordance was found to be largely caused by perceptual differences in assessing HER2 expression due to high HER2 staining heterogeneity. This study provides evidence that deep learning aided diagnosis can facilitate clinical decision making in breast cancer by identifying cases at high risk of misdiagnosis.