Artificial intelligence and digital pathology as drivers of precision oncology

Background: Digitalisation offers many opportunities to improve diagnosis and treatment in cancer, especially in the field of pathology. In addition to the molecular analysis of malignant tumours and protein analysis (immunohistochemistry), the digitalisation of pathology is a further evolutionary step that will profoundlymodernise and transform this field. Methods: This work is based on a selective literature search in the PubMed database on the topic of "digital pathology" and "AI algorithms". Results: The spectrum of digital transformation ranges from digitalisation and structuring of diagnostic reports for faster, more precise and reproducible diagnosis for oncological patients, to the introduction of telepathology and faster access to reference pathology centres, to the introduction of artificial intelligence (AI)-based algorithms that enable automated analyses of virtualised pathological tissue sections. The latter topic is the subject of active research and comprises two main categories: i) diagnostic AI for typical pathology tasks, for example, quantification of predictive markers in immunohistochemical stains or tumour detection, grading, and subtyping based on routine haematoxylin and eosin stains, and ii) advanced applications involving detection of molecular genetic alterations and therapy-relevant image biomarkers, in the broadest sense. Conclusions: This paper reflects on aspects of digital transformation for pathology institutes, in terms of future development for precision oncology but also their status quo.