Exploring the business aspects of digital pathology, deep learning in cancers

Cancer remains one of the leading causes of morbidity and mortality worldwide. Deep learning in digital pathology has the potential to improve operational efficiency, costs, and care. We searched Web of Science, Arxiv, MedRxiv, Embase, PubMed, DBLP, Google Scholar, IEEE Xplore, and Cochrane databases for whole slide imaging and deep learning articles published between 2019 and 2023. The final six articles were selected from 776 articles identified through an inclusion criterion. Digital pathology services that utilize deep learning have the potential to enhance clinical workflow efficiencies and can have a positive impact on business activities. We anticipate cost reductions as deep learning technology advances and more companies enter the digital pathology ecosystem. However, the limited availability of business use cases, primarily due to publication bias, poses a challenge in medicine without clear examples to learn from. •AI in Digital Pathology: Improves cancer diagnosis accuracy and efficiency.•Cost Savings: Reduces diagnosis time and cuts costs significantly.•Adoption Barriers: High initial costs limit widespread use.•ROI: Varies.•DPaaS: Cloud-based AI tools lower costs and improve diagnostics.