# Jakob Nikolas Kather

Source: https://onco.cc/people/jakob-nikolas-kather/  
OnCo record `jakob-nikolas-kather` (Person). Data CC BY-NC 4.0, attribute "Data from OnCo (onco.cc)"; commercial use needs a licence.

## TL;DR

Showed that deep learning can read genetic features like microsatellite instability directly from routine pathology slides.

## Summary

Jakob Nikolas Kather led the 2019 Nature Medicine study showing a deep-learning model can predict microsatellite instability from standard H&E slides in gastrointestinal cancer, opening the field of inferring molecular biomarkers from routine histology, and subsequent pan-cancer work predicting mutations and outcomes. He leads clinical AI research in Dresden, evaluates large language models for oncology, and is a practising GI oncologist.

## Fields

- Kind: Person
- Last checked: 2026-09-10
- Tags: ai; pathology; biomarkers; germany
- Role: Professor of Clinical Artificial Intelligence, Else Kröner Fresenius Center for Digital Health, TU Dresden; Medical Oncologist, NCT Dresden
- Specialisms: AI in oncology; Deep learning on histology; Biomarker prediction from slides; Large language models in medicine

## Sources

- PubMed: https://pubmed.ncbi.nlm.nih.gov/?term=Kather%20JN%5BAuthor%5D%20deep%20learning%20histology

## Connected records

- cancers: [Colorectal cancer](https://onco.cc/cancers/colorectal/), [Gastric & gastro-oesophageal junction cancer](https://onco.cc/cancers/gastric/)
- technologies: [Digital pathology & AI](https://onco.cc/technologies/digital-pathology-ai/), [Pathology & radiology foundation models](https://onco.cc/technologies/pathology-foundation-model/)
- institutions: [NCT/UCC Dresden, University Hospital Carl Gustav Carus](https://onco.cc/institutions/nct-dresden/)
- journals: [Nature Cancer](https://onco.cc/journals/nature-cancer/)

---
JSON: https://onco.cc/api/v1/entities/jakob-nikolas-kather.json