AI Science Tracker
EN

Automating tumor-stroma ratio quantification in colon cancer patients from the UNITED study.

Leiden University Medical Center · 30 Dec 2025 · medicine

Discovery

Automating tumor-stroma ratio quantification in colon cancer patients from the UNITED study.

Source check: Source checked. Not independent scientific confirmation.

Finding: In 853 cases, 298 were stroma-high at the automated 77% threshold; 3-year DFS was 71% versus 82%, with adjusted HR 1.46 (p=0.016). The source also reports worse OS. Deep-learning pixel segmentation (EfficientNetB0 encoder/UNet++ decoder) classifies 11 tissue classes on H&E whole-slide images; the pipeline calculates automated tumor–stroma ratio. Testing: The tool was applied to digitized UNITED cohort slides and compared with clinical outcomes and trained pathologist TSR assessments; the association is prognostic, retrospective, and does not demonstrate prospective clinical utility or treatment causation.. A deep-learning tissue-segmentation tool automatically quantified tumor–stroma ratio in 853 stage II/III colon-cancer cases; stroma-high status was associated with worse disease-free survival (adjusted HR 1.46, p=0.016). This is a prognostic association in the UNITED cohort, not evidence that AI-guided care improves outcomes. Source affiliation was not stated in the reviewed case checks and was unavailable in the local bibliographic cache.

Technology: Deep-learning pixel segmentation (EfficientNetB0 encoder/UNet++ decoder) classifies 11 tissue classes on H&E whole-slide images; the pipeline calculates automated tumor–stroma ratio.

Publication: Peer-reviewed paper · Test context: retrospective or benchmark. Catalog categories, not an evidence grade.

AI contribution
Deep-learning pixel segmentation (EfficientNetB0 encoder/UNet++ decoder) classifies 11 tissue classes on H&E whole-slide images; the pipeline calculates automated tumor–stroma ratio.
Test and result
The tool was applied to digitized UNITED cohort slides and compared with clinical outcomes and trained pathologist TSR assessments; the association is prognostic, retrospective, and does not demonstrate prospective clinical utility or treatment causation.
Limitation / still unknown
A deep-learning tissue-segmentation tool automatically quantified tumor–stroma ratio in 853 stage II/III colon-cancer cases; stroma-high status was associated with worse disease-free survival (adjusted HR 1.46, p=0.016). This is a prognostic association in the UNITED cohort, not evidence that AI-guided care improves outcomes.
Evidence sources and annotation context

Evidence context (descriptions follow the cited sources; test type is a catalog classification):

Evidence sources: https://pmc.ncbi.nlm.nih.gov/articles/PMC12804037/ · https://europepmc.org/article/MED/41468683

Source checked · editorial details

The source page was checked against this entry. Independent confirmation is not assessed by this label.

Source type: paper. Paper: not linked in this catalog; this does not mean no paper exists.

Review date: 22 Nov 2026. Review scope: Primary result-bearing material for the stated method, result and evaluation, with bibliographic version information..

No follow-up recorded; this is not a claim that no follow-up exists. Follow-up review scope and date are not recorded. No source-supported relationships recorded.

Editorial assessment: Impact 3/5 · Validation 2/5 · Novelty 3/5. Impact and novelty are editorial judgments; validation follows the annotated test type where one exists. Not an evidence grade. Scoring criteria.

Open in the full catalog for filters, charts and related discoveries. Browse medicine discoveries.

Related catalog entries

Links use documented relationships where available, plus shared catalog context. A shared topic or model family does not establish a scientific dependency.