Developing a Histology-Based Artificial Intelligence Biomarker to Predict Adjuvant Chemotherapy Benefit in Pancreatic Cancer

PURPOSE The choice of adjuvant chemotherapy in pancreatic ductal adenocarcinoma (PDAC) is mainly guided by patients' general condition. We hypothesized that tumor morphology may predict differential treatment benefit and tested whether deep learning applied to histology images could derive a biomarker of relative benefit from gemcitabine (GEM) versus modified FOLFIRINOX (mFOLFIRINOX) in resected PDAC. PATIENTS AND METHODS Standard whole-slide images from a retrospective multicentric series of 231 patients who underwent curative-intent pancreatectomy and received adjuvant mFOLFIRINOX (n = 54) or GEM (n = 177) were used to train regimen-specific histology models on disease-free survival (DFS), which were then combined into PANCprAId, a biomarker estimating personalized relative benefit from adjuvant GEM versus mFOLFIRINOX. External validation was performed in the randomized PRODIGE-24/CCTG PA6 trial (n = 313). RESULTS In PRODIGE-24/CCTG PA6, the treatment-specific histology scores used to construct PANCprAId stratified outcomes among patients treated with GEM (hazard ratio [HR], 1.69 [95% CI, 1.04 to 2.73]; P = .03) and mFOLFIRINOX (HR, 2.02 [95% CI, 1.4 to 3.0]; P < .001). When combined into PANCprAId, the biomarker identified subgroups with differential relative benefit from adjuvant GEM versus mFOLFIRINOX, with significant treatment interactions for DFS (interaction P = .003) and cancer-specific survival (interaction P = .001). Predicted sensitivity to each regimen was associated with distinct epithelial and stromal features. CONCLUSION Histology-based deep learning can derive a predictive biomarker of relative benefit from adjuvant GEM versus mFOLFIRINOX in resected PDAC.

Authors

Institutions

Publication Details

Journal
Journal of Clinical Oncology
Published
2026-07-27
DOI
https://doi.org/10.1200/jco-26-00327
Primary Topic
Pancreatic and Hepatic Oncology Research
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Developing a Histology-Based Artificial Intelligence Biomarker to Predict Adjuvant Chemotherapy Benefit in Pancreatic Cancer

Alice C. Wei, Emmanuel Mitry, Nelson Dusetti, Marjorie Mauduit et al.
Journal of Clinical Oncology
Pancreatic and Hepatic Oncology Research
article

Developing a Histology-Based Artificial Intelligence Biomarker to Predict Adjuvant Chemotherapy Benefit in Pancreatic Cancer

Alice C. Wei, Emmanuel Mitry, Nelson Dusetti, Marjorie Mauduit, Vinciane Rebours, Méher Ben Abdelghani, James Biagi, Louis de Mestier, Taib Bourega, Thierry Conroy, Rémy Nicolle, Srividhya Sainath, Anthony Turpin, Pascal Artru, Ludovic Evesque, Asier Rabasco Meneghetti, Nathalie Colnot, Jérôme Cros, Jean‐Baptiste Bachet, Diana Mendes, Aurélien Lambert, Thierry Lecomte, Matthieu Tihy, Camille Pignolet, Pascal Hammel, Miguel Albuquerque, Julien de Martino, Audrey Beaufils, Théau Blanchard, X Y Jiang, Nicolas Fraunhoffer, Daniel J. Renouf, Jakob Nikolas Kather
article en

Abstract

PURPOSE The choice of adjuvant chemotherapy in pancreatic ductal adenocarcinoma (PDAC) is mainly guided by patients' general condition. We hypothesized that tumor morphology may predict differential treatment benefit and tested whether deep learning applied to histology images could derive a biomarker of relative benefit from gemcitabine (GEM) versus modified FOLFIRINOX (mFOLFIRINOX) in resected PDAC. PATIENTS AND METHODS Standard whole-slide images from a retrospective multicentric series of 231 patients who underwent curative-intent pancreatectomy and received adjuvant mFOLFIRINOX (n = 54) or GEM (n = 177) were used to train regimen-specific histology models on disease-free survival (DFS), which were then combined into PANCprAId, a biomarker estimating personalized relative benefit from adjuvant GEM versus mFOLFIRINOX. External validation was performed in the randomized PRODIGE-24/CCTG PA6 trial (n = 313). RESULTS In PRODIGE-24/CCTG PA6, the treatment-specific histology scores used to construct PANCprAId stratified outcomes among patients treated with GEM (hazard ratio [HR], 1.69 [95% CI, 1.04 to 2.73]; P = .03) and mFOLFIRINOX (HR, 2.02 [95% CI, 1.4 to 3.0]; P < .001). When combined into PANCprAId, the biomarker identified subgroups with differential relative benefit from adjuvant GEM versus mFOLFIRINOX, with significant treatment interactions for DFS (interaction P = .003) and cancer-specific survival (interaction P = .001). Predicted sensitivity to each regimen was associated with distinct epithelial and stromal features. CONCLUSION Histology-based deep learning can derive a predictive biomarker of relative benefit from adjuvant GEM versus mFOLFIRINOX in resected PDAC.

Journal of Clinical Oncology
Université de Tours (FR), Centre National de la Recherche Scientifique (FR), Memorial Sloan Kettering Cancer Center (US), Inserm (FR), Queen's University (CA), Université Paris Cité (FR), Heidelberg University (DE), Université de Lille (FR), Hôpital Beaujon (FR), University Hospital Heidelberg (DE), Sorbonne Université (FR), Institut de Cancérologie Strasbourg (FR), Lille’s Cardiology Hospital (FR), Centre Hospitalier Universitaire de Tours (FR), National Council for Scientific Research (LB), Institut de Cancérologie de Lorraine (FR), National Center for Tumor Diseases (DE), Pitié-Salpêtrière Hospital (FR), Hôpital Privé Jean Mermo (FR), Centre de Recherche sur l'Inflammation (FR), Argentine Water and Sanitation (Argentina) (AR), UniCancer Group (FR), Centre de Recherche en Cancérologie de Marseille (FR), Institut Paoli-Calmettes (FR), Centre Antoine Lacassagne (FR), University Hospital Carl Gustav Carus (DE), Hôpital Paul-Brousse (FR), Else Kröner Fresenius Center for Digital Health (DE)
Openalex Percentile: Top 12%
Pancreatic and Hepatic Oncology Research
DOIOpen Access PDFOpenAlex
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.