Deep Multiple Instance Learning Model to Predict Outcome of Pancreatic Cancer Following Surgery
Authors:
- Caroline TruntzerCTCaroline Truntzer
- Dina OuahbiDODina Ouahbi
- Titouan HuppéTHTitouan Huppé
- David RageotDRDavid Rageot
- Alis IlieAIAlis Ilie
- Chloe MolimardCMChloe Molimard
- Françoise BeltjensFBFrançoise Beltjens
- Anthony BergeronABAnthony Bergeron
- Angelique VienotAVAngelique Vienot
- Christophe BorgCBChristophe Borg
- Franck MonnienFMFranck Monnien
- Frédéric BibeauFBFrédéric Bibeau
Open Access
- 2 December 2024
- journal article
- research article
- Published by MDPI AG in Biomedicines
- Vol. 12 (12) , 2754
Abstract
Background/Objectives: Pancreatic ductal adenocarcinoma (PDAC) is a cancer with very poor prognosis despite early surgical management. To date, only clinical variables are used to predict outcome for decision-making about adjuvant therapy. We sought to generate a deep learning approach based on hematoxylin and eosin (H&E) or hematoxylin, eosin and saffron (HES) whole slides to predict patients’ outcome, compare these new entities with known molecular subtypes and question their biological significance; Methods: We used as a training set a retrospective private cohort of 206 patients treated by surgery for PDAC cancer and a validation cohort of 166 non-metastatic patients from The Cancer Genome Atlas (TCGA) PDAC project. We estimated a multi-instance learning survival model to predict relapse in the training set and evaluated its performance in the validation set. RNAseq and exome data from the TCGA PDAC database were used to describe the transcriptomic and genomic features associated with deep learning classification; Results: Based on the estimation of an attention-based multi-instance learning survival model, we identified two groups of patients with a distinct prognosis. There was a significant difference in progression-free survival (PFS) between these two groups in the training set (hazard ratio HR = 0.72 [0.54;0.96]; p = 0.03) and in the validation set (HR = 0.63 [0.42;0.94]; p = 0.01). Transcriptomic and genomic features revealed that the poor prognosis group was associated with a squamous phenotype. Conclusions: Our study demonstrates that deep learning could be used to predict PDAC prognosis and offer assistance in better choosing adjuvant treatment.Keywords
This publication has 38 references indexed in Scilit:
- Development and validation of AI-assisted transcriptomic signatures to personalize adjuvant chemotherapy in patients with pancreatic ductal adenocarcinomaAnnals of Oncology, 2024
- Predicting the survival of patients with pancreatic neuroendocrine neoplasms using deep learning: A study based on Surveillance, Epidemiology, and End Results databaseCancer Medicine, 2023
- Current state of radiomic research in pancreatic cancer: focusing on study design and reproducibility of findingsEuropean Radiology, 2023
- SALL4‐related gene signature defines a specific stromal subset of pancreatic ductal adenocarcinoma with poor prognostic featuresMolecular Oncology, 2023
- Pan-cancer integrative histology-genomic analysis via multimodal deep learningCancer Cell, 2022
- Robust deep learning model for prognostic stratification of pancreatic ductal adenocarcinoma patientsiScience, 2021
- Surgery for Pancreatic Cancer after neoadjuvant treatmentAnnals of Gastroenterological Surgery, 2018
- Genomic and Molecular Landscape of DNA Damage Repair Deficiency across The Cancer Genome AtlasCell Reports, 2018
- Adjuvant Chemotherapy With Fluorouracil Plus Folinic Acid vs Gemcitabine Following Pancreatic Cancer ResectionJAMA, 2010
- Adjuvant Chemotherapy With Gemcitabine vs Observation in Patients Undergoing Curative-Intent Resection of Pancreatic CancerJAMA, 2007