What question did this study set out to answer?

This project aims to develop an AI-driven pipeline for evaluating the immune microenvironment of pancreatic ductal adenocarcinoma and identifying relevant clinical classifiers.

April 5, 2026

Abstract 83: AI-powered analysis of pancreatic ductal adenocarcinoma tissues to study the tumor immune ecosystem and identify novel classifiers.

Key Points

This project aims to develop an AI-driven pipeline for evaluating the immune microenvironment of pancreatic ductal adenocarcinoma and identifying relevant clinical classifiers.
Analyzed whole-slide images from 53 PDAC patients using H&E and specific stains for macrophages and fibrosis.
Employed a deep learning classifier to quantify tumor and stroma areas alongside spatial entropy measurements.
Utilized QuPath-based segmentation to assess macrophage abundance and fibrosis metrics, correlating immune features with tissue metrics.
Applied CTransPath for embedding extraction and UMAP projection to explore clustering patterns of immune features.
Achieved a global F1-score of 0.79 with the deep learning tissue classifier on PDAC slides.
Found that high macrophage abundance and spatial entropy relate to worse overall survival.
Integrating immune with tumor features enhanced patient stratification, especially in NAT-treated patients who showed increased fibrosis and reduced macrophage infiltration.

Abstract

Abstract Background: Digital pathology and artificial intelligence (AI) are emerging as powerful tools in immuno-oncology, enabling enhanced diagnostic and prognostic workflows. The current trend regards the application of AI on histopathological images to extract relevant features beyond human visual perception. Pancreatic ductal adenocarcinoma (PDAC) is one of the deadliest cancers worldwide, for which lack of efficient biomarkers to stratify patients and grade the response to therapy may play a significant impact. Aim: This project presents a computational pipeline integrating machine and deep learning approaches to characterize the PDAC tumor immune ecosystem and extract features with potential clinical relevance. Methods: Whole-slide images from 53 PDAC patients, including those treated and untreated with neoadjuvant chemotherapy (NAT), were analyzed. Slides were stained with H Part 1 (Regular Abstracts); 2026 Apr 17-22; San Diego, CA. Philadelphia (PA): AACR; Cancer Res 2026;86(7 Suppl):Abstract nr 83.

Perguntar à IA

Bookmark