Graph-based multimodal multi-lesion DLBCL treatment response prediction from PET images

TL;DR

This paper introduces a graph neural network-based method that integrates multimodal clinical and PET imaging data to predict treatment response in DLBCL patients, outperforming traditional approaches.

Contribution

It presents a novel graph-based multimodal approach with a cross-attention module for improved prediction of treatment response in DLBCL.

Findings

Outperforms classical supervised methods in 2-year PFS classification

Effective integration of clinical and imaging data improves prediction accuracy

Validated on a large multicentric dataset of 583 patients

Abstract

Diffuse Large B-cell Lymphoma (DLBCL) is a lymphatic cancer involving one or more lymph nodes and extranodal sites. Its diagnostic and follow-up rely on Positron Emission Tomography (PET) and Computed Tomography (CT). After diagnosis, the number of nonresponding patients to standard front-line therapy remains significant (30-40%). This work aims to develop a computer-aided approach to identify high-risk patients requiring adapted treatment by efficiently exploiting all the information available for each patient, including both clinical and image data. We propose a method based on recent graph neural networks that combine imaging information from multiple lesions, and a cross-attention module to integrate different data modalities efficiently. The model is trained and evaluated on a private prospective multicentric dataset of 583 patients. Experimental results show that our proposed method outperforms classical supervised methods based on either clinical, imaging or both clinical and imaging data for the 2-year progression-free survival (PFS) classification accuracy.