Deep Learning in Histopathology: Bridging the Gap Between Proof-of-Concept and Clinical Adoption
Despite deep learning algorithms matching trained pathologists in tasks like tumor detection and grading, very few have reached clinical implementation. This Nature Medicine review dissects the disconnect between published performance and real-world utility, examining challenges around regulatory approval, dataset representativeness, reproducibility, and integration into existing laboratory workflows. The authors provide a roadmap for translating computational pathology research into validated clinical tools.
The original study
Deep learning in histopathology: the path to the clinic.
- Authors
- van der Laak J, Litjens G, Ciompi F
- Journal
- Nature medicine
- Type
- Journal Article, Research Support, Non-U.S. Gov't, Review
- PMID
- 33990804
Original abstract
Machine learning techniques have great potential to improve medical diagnostics, offering ways to improve accuracy, reproducibility and speed, and to ease workloads for clinicians. In the field of histopathology, deep learning algorithms have been developed that perform similarly to trained pathologists for tasks such as tumor detection and grading. However, despite these promising results, very few algorithms have reached clinical implementation, challenging the balance between hope and hype for these new techniques. This Review provides an overview of the current state of the field, as well as describing the challenges that still need to be addressed before artificial intelligence in histopathology can achieve clinical value.