Imaging-Based Deep Graph Neural Networks for Survival Analysis in Early Stage Lung Cancer Using CT: A Multicenter Study

Abstract

Background: Lung cancer is the leading cause of cancer-related mortality, and accurate prediction of patient survival can aid treatment planning and potentially improve outcomes. In this study, we proposed an automated system capable of lung segmentation and survival prediction using graph convolution neural network (GCN) with CT data in non-small cell lung cancer (NSCLC) patients.

Methods: In this retrospective study, we segmented 10 parts of the lung CT images and built individual lung graphs as inputs to train a GCN model to predict 5-year overall survival. A Cox proportional-hazard model, a set of machine learning (ML) models, a convolutional neural network based on tumor (Tumor-CNN), and the current TNM staging system were used as comparison.

Findings: A total of 1,705 patients (main cohort) and 125 patients (external validation cohort) with lung cancer (stages I and II) were included. The GCN model was significantly predictive of 5-year overall survival with an AUC of 0.732 (p < 0.0001). The model stratified patients into low- and high-risk groups, which were associated with overall survival (HR = 5.41; 95% CI:, 2.32-10.14; p < 0.0001). On external validation dataset, our GCN model achieved the AUC score of 0.678 (95% CI: 0.564-0.792; p < 0.0001).

Interpretation: The proposed GCN model outperformed all ML, Tumor-CNN, and TNM staging models. This study demonstrated the value of utilizing medical imaging graph structure data, resulting in a robust and effective model for the prediction of survival in early-stage lung cancer.

Keywords: cox proportional-hazards; graph convolutional networks; lung cancer; lung graph model; survival prediction.

Figure 1

Examples of airway and lung lobes segmentation. (A) Patient raw CT scan; (B) Airway segments produced by region-growing algorithm; (C) lung lobes segments, 3D; (D) Lung lobes segments, x-axial 2D; (E) Lung lobes segments, z-axial 2D.

Figure 2

The pipeline of building patients’ lung graph building.

Figure 3

Performance of GCN, TNM and Tumor-CNN models on testing dataset.

Figure 4

(A). Stage I Analysis: Performances of GCN models on OS prediction and RFS prediction separately; (B). Stage II Analysis: Performances of GCN models on OS prediction and RFS prediction separately.