AI glossary · Advanced · Computer vision · Healthcare & bio
Digital pathology
Digital pathology is a way of doing pathology diagnosis in which tissue slides are scanned at high resolution into digital images that are then read, shared and analyzed on screen. It is also the technology that AI analysis builds on.
About this term
- Level
- Advanced · Specialist terms that need the inner workings
- Category
- Industry AI
- Fields
- Computer vision
- Industries
- Healthcare & bio
- Added
- 2026-10-10
How it works
Pathology is the field that diagnoses diseases such as cancer by examining, under a microscope, slides made from thin, stained sections of tissue taken from a patient. In digital pathology, a dedicated scanner captures the entire glass slide to create a whole slide image (WSI). The image is stored on a server, and pathologists read it on a monitor instead of a microscope, zooming in and out. Adding AI can help automate tasks such as marking suspicious areas, counting cells and measuring tumor proportion.
Digital pathology diagnosis workflow
- 1Slide preparationThinly section and stain tissue
- 2Full scanSave as high-resolution WSI
- 3AI analysisMark suspicious areas, count cells
- 4Pathologist readingReview on monitor, then diagnose
Why it matters
Once a slide becomes a file, it can be sent immediately to a distant expert for an opinion, which makes remote consultation easier. It can be stored for a long time and retrieved again without the risk of breaking or fading that glass slides carry. Above all, digital images become data that AI can learn from and analyze, which is used to reduce pathologists' repetitive workload and variation between readings. Expectations are especially high in regions with a shortage of pathologists.
Things to know
The image of a single slide is very large, so storage and network costs are high. Staining methods and scanners differ between hospitals, so the same tissue can look different in color, which can degrade AI performance. AI used for diagnosis often needs approval as medical device software. Final responsibility for the diagnosis still lies with the pathologist, and AI is generally used as an assistive tool.
Example
In large hospitals, all biopsy slides of stomach or colon tissue are scanned, AI first marks regions suspected of cancer, and the pathologist checks those areas first. For difficult cases, the scanned images are sometimes sent to experts at other hospitals for consultation.