System Maintenance Notice

Please note that maintenance work is scheduled between 4 AM and 5 AM - CET. During this time, you may experience reduced performance. Thanks for your patience.

Publications

Journal Article Ahead of print 2 citations

PubMed: 42507965 DOI: 10.1200/JCO-26-00327

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

J Clin Oncol

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

Affiliations

  • Centre de Recherche sur l'Inflammation (CRI), Université Paris Cité, INSERM, U1149, CNRS, ERL 8252, Paris, France.
  • Else Kroener Fresenius Center for Digital Health, Medical Faculty Carl Gustav Carus, TUD Dresden University of Technology, Dresden, Germany.
  • Department of Pathology-FHU MOSAIC, Beaujon Hospital, Université Paris Cité, INSERM UMR1149, Clichy, France.
  • Cancer Research Center of Marseille (CRCM), INSERM, CNRS, Institute Paoli-Calmettes, Aix-Marseille University, Marseille, France.
  • Programa franco-argentino de estudio del Cáncer de Páncreas, Buenos Aires, Argentina.
  • Faculty of Medicine, Center for Pharmacological and Botanical Studies, Buenos Aires University, National Council for Scientific and Technical Research, Buenos Aires, Argentina.
  • Medical Oncology Department, University Hospital, Lille, France.
  • University of Lille, Lille, France.
  • Medical Oncology Department, ICANS, Strasbourg, France.
  • Department of Surgery, Memorial Sloan Kettering Cancer Center, New York, NY.
  • Medical Oncology Department, Institute Paoli-Calmettes, Marseille, France.
  • François Rabelais University, Tours, France.
  • Department of Hepatogastroenterology and Digestive Oncology, University Hospital of Tours, Tours, France.
  • Department of Oncology, Queen's University, Kingston, ON, Canada.
  • Hepatogastroenterology Department, Hospital Jean-Mermoz, Lyon, France.
  • Department of Medical Oncology, Lacassagne Center, Nice, France.
  • Medical Oncology Department, Institut de Cancérologie de Lorraine, Vandoeuvre-lès-Nancy, France.
  • Department of Medical Oncology, BC Cancer, Vancouver, BC, Canada.
  • Unicancer, R&D, Paris, France.
  • Digestive and Medical Oncology Department, Hospital Paul Brousse and University Paris-Saclay, Villejuif, France.
  • Department of Gastroenterology, Pitié-Salpêtrière Hospital-Sorbonne Université, Paris, France.
  • Department of Pancreatology and Digestive Oncology, APHP Nord, FHU MOSAIC, Beaujon Hospital, Clichy, France.
  • Department of Medicine I, University Hospital Dresden, Dresden, Germany.
  • Medical Oncology, National Center for Tumor Diseases (NCT), University Hospital Heidelberg, Heidelberg, Germany.

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.

MeSH

Intelligence, Pancreatic Neoplasms, Neoplasms, Drug Therapy, Biomarkers, Chemotherapy, Adjuvant, Deep Learning, Histology, Therapeutics, Medical Oncology, Learning, Artificial Intelligence, Chemotherapy