We’re proud to share that a group of PANCAIM team members has published the results of their work in the project in renowned Gut journal!
A fusion-based deep-learning algorithm predicts PDAC metastasis based on primary tumour CT images: a multinational study
Diagnosing the presence of metastasis of pancreatic cancer is pivotal for patient management and treatment. Contrast-enhanced CT scans (CECT) are the cornerstone of diagnostic evaluation.
Within PANCAIM project, researchers have developed, trained and validated a convolutional neural network (CNN)-based model “PMPD” (Pancreatic cancer Metastasis Prediction Deep-learning algorithm) to predict the presence of metastases based on CECT images of the primary tumour. A high predictive performance was achieved across multiple datasets, including in external validation with a site-specific metastasis prediction achieving AUROCs up to 0.9273. In addition, the derived Metastasis Risk Score (MRS) significantly outperformed traditional metrics like resectability status and CA19-9 in predicting overall survival
This study pioneers the use of CNNs to non-invasively predict extrapancreatic metastasis, offering a powerful tool for personalized treatment planning and early intervention for PDAC patients.
Congrats to the involved PANCAIM members and their collaborators on this groundbreaking work!
Find the full article here: DOI: 10.1136/gutjnl-2024-334237
Xue N, Sabroso-Lasa S, Merino X, et al. A fusion-based deep-learning algorithm predicts PDAC metastasis based on primary tumour CT images: a multinational study. Gut Published Online First: 19 June 2025. doi: 10.1136/gutjnl-2024-334237
.
.
.
.
.
.
.
.
.
.
.
..
