Cost-Sensitive Uncertainty Hypergraph Learning for Identification of Lymph Node Involvement With CT Imaging

Abstract

Lung adenocarcinoma (LUAD) is the most common type of lung cancer. Accurate identification of lymph node (LN) involvement in patients with LUAD is crucial for prognosis and making decisions of the treatment strategy. CT imaging has been used as a tool to identify lymph node involvement. To tackle the shortage of high-quality data and improve the sensitivity of diagnosis, we propose a Cost-Sensitive Uncertainty Hypergraph Learning (CSUHL) model to identify the lymph node based on the CT images. We design a step named “Multi-Uncertainty Measurement” to measure the epistemic and the aleatoric uncertainty, respectively. Given the two types of attentional uncertainty weights, we further propose a cost-sensitive hypergraph learning to boost the sensitivity of diagnosing, targeting task-driven optimization of the clinical scenarios. Extensive qualitative and quantitative experiments on the real clinical dataset demonstrate our method is capable of accurately identifying the lymph node and outperforming state-of-the-art methods across the board.

Robustness Analysis of Deep Learning-Based Lung Cancer Classification Using Explainable Methods

“…Computed tomography (CT) images have been used to provide valuable information on tumor assessment in lung cancer, rising opportunities to the development of computeraided decision(CAD) systems able to automatically assess lung nodules malignancy risk [10], [11], [12], [13], [14]. Artificial Intelligence (AI) approaches can integrate complex features and extract relevant information from the images that can be used to predict the malignancy of lung nodules, helping the clinician to get an early and more accurate diagnosis.…”