High-risk Factor Prediction in Lung Cancer Using Thin CT Scans: An Attention-Enhanced Graph Convolutional Network Approach

TL;DR

This paper presents an innovative attention-enhanced graph convolutional network that leverages CT scan data to predict high-risk factors in stage I lung cancer, aiding surgical decision-making.

Contribution

It introduces a novel AE-GCN model that captures spatial nodule features using graph structures and attention mechanisms, improving preoperative risk assessment.

Findings

Effective classification of high-risk factors demonstrated on real-world data

Enhanced feature extraction through combined attention mechanisms and pre-trained VGG

Potential to assist surgeons in surgical planning for lung cancer patients

Abstract

Lung cancer, particularly in its advanced stages, remains a leading cause of death globally. Though early detection via low-dose computed tomography (CT) is promising, the identification of high-risk factors crucial for surgical mode selection remains a challenge. Addressing this, our study introduces an Attention-Enhanced Graph Convolutional Network (AE-GCN) model to classify whether there are high-risk factors in stage I lung cancer based on the preoperative CT images. This will aid surgeons in determining the optimal surgical method before the operation. Unlike previous studies that relied on 3D patch techniques to represent nodule spatial features, our method employs a GCN model to capture the spatial characteristics of pulmonary nodules. Specifically, we regard each slice of the nodule as a graph vertex, and the inherent spatial relationships between slices form the edges. Then, to enhance the expression of nodule features, we integrated both channel and spatial attention mechanisms with a pre-trained VGG model for adaptive feature extraction from pulmonary nodules. Lastly, the effectiveness of the proposed method is demonstrated using real-world data collected from the hospitals, thereby emphasizing its potential utility in the clinical practice.