Artificial intelligence-powered H&E-based quantification of spatial tumor-infiltrating lymphocyte distribution identifies prognostic immune niches in colorectal cancer
AI analysis of routine tissue slides identifies immune cell patterns that predict cancer recurrence as reliably as specialized staining techniques.
AI analysis of H&E slides in 202 stage II–III CRC patients shows that spatial TIL distribution at the tumor-stromal border (TSB score) is an independent prognostic marker for recurrence-free survival, matching Immunoscore performance and working without additional IHC staining. AI-human agreement was comparable to inter-pathologist reliability, supporting potential clinical integration of AI-based spatial immune profiling from routine H&E slides.
What the study was
- Study design
- Retrospective cohort study with AI-based image analysis and validation against Immunoscore
- Population
- Stage II–III CRC patients (n=202), South Korea
- Sample size
- 202
- Category
- Diagnostics
- Maturity
- Validated
- Journal
- Cancer Immunology, Immunotherapy
Why it surfaced
Validated AI-based spatial immune profiling from routine H&E achieving Immunoscore-equivalent prognosis; reduces cost and complexity of immune profiling in CRC.
A plain-language summary of published research — not medical advice. Talk to a clinician about your own care.