Deep learning based on CD3 histological slides for prediction of colon cancer outcome: analysis of three international stage III colon cancer cohorts

May 8, 2026OncoImmunologyOpen Access

View Full Paper

Ask AI

Bookmark

Share

Key Points

The study aims to develop a deep learning model to automate the analysis of CD3-stained histological slides for predicting outcomes in stage III colon cancer.
Analyzed 1737 patients across three international cohorts (PETACC08, PRODIGE-13, HARMONY).
Developed a deep learning model (VGG19) to identify tumor core and invasive margin regions from CD3-stained slides.
Used hierarchical classification to cluster patients based on features extracted from the models.
Deep learning classifiers identified distinct patient clusters with significantly different disease-free survival (DFS).
Patients in the favorable group had better DFS across all sets when analyzed by invasive margin and tumor core regions.

We only have this paper's title and publication details.

Answers are grounded in this paper and cite their sources.

Shows improved colon cancer outcome prediction in international cohorts, suggesting automated analysis enhances prognostic stratification.

No takes yet. Share an insight, caveat, or question.

Lecuelle et al. (2026) studied this question.

View Full Paper

Ask AI

Bookmark

Share