The role of the pathologist has remarkably evolved over the last two decades. In addition to their critical role in multidisciplinary team meetings, cancer datasets, teaching, education, quality assurance, trials and research, pathologists are currently more and more involved in molecular and genomic testing (1).
This talk will highlight the quintessential role of the pathologist, with emphasis on breast pathology, in molecular diagnostics, analysing predictive and prognostic markers, molecular classification of breast cancer, analysing companion diagnostics for specific therapies and redefining old tests in the current genomic era.
Molecular diagnostic tests can be used to confirm the morphological diagnosis of several rare breast cancers such as Tall Cell Carcinoma with Reversed Polarity (TCCRP), secretory carcinomas and adenoid cystic carcinoma. BRCA and PIK3CA gene status is currently used to direct therapy. PD-L1 testing in triple negative metastatic breast cancer has been implemented in routine practice to guide immunotherapy decisions (2). In addition, the value of old tests (such as HER2 testing) has been emphasised to allow selection of tumours with HER2-Low expression for ADC therapy. Digital and Artificial Intelligence (AI) algorithms further extend the possibilities for aiding the diagnosis and providing fast, accurate and quantitative assessment of biomarkers.
 

Precision oncology requires complex biomarkers which are often based on molecular and genetic tests of tumor tissue. For many of these tests, universal implementation in clinical practice is limited. However, for virtually every cancer patient, pathology tissue slides stained with hematoxylin and eosin (H&E) are available. Artificial intelligence (AI) can extract biomarkers for better treatment decisions from these images. This talk will summarize the state of the art of AI in oncology for precision oncology biomarkers. It will cover the technical foundations, emerging use cases and established applications which are already available for clinical use.