A Novel Multi-modal Population-graph based Framework for Patients of Esophageal Squamous Cell Cancer Prognostic Risk Prediction

Prognostic risk prediction is pivotal for clinicians to appraise the patient’s esophageal squamous cell cancer (ESCC) progression status precisely and tailor individualized  therapy  treatment  plans.  Currently,  CT-based multi-modal prognostic risk prediction methods have gradually attracted the attention of researchers for their universality, which is also able to be applied in scenarios of preoperative  prognostic  risk  assessment  in  the  early  stages of cancer. However, much of the current work focuses only on CT images of the primary tumor, ignoring the important role that CT images of lymph nodes play in prognostic risk prediction. Additionally, it is important to consider and ex- plore the inter-patient feature similarity in prognosis when developing models. To solve these problems, we proposed a  novel  multi-modal  population-graph  based  framework leveraging CT images including primary tumor and lymph nodes combined with clinical, hematology, and radiomics data for ESCC prognostic risk prediction. A patient population graph was constructed to excavate the homogeneity and heterogeneity of inter-patient feature embedding. More over, a novel node-level multi-task joint loss was proposed for graph model optimization through a supervised-based task  and  an  unsupervised-based  task.  Sufficient  experi mental results show that our model achieved state-of-the-art performance compared with other baseline models as well  as  the  gold  standard  on  discriminative  ability,  risk stratification, and clinical utility. The core code is available at https://github.com/wuchengyu123/MPGSurv.