Domain Adaptive Lung Nodule Detection in X-ray Image
This work addresses domain adaptation for lung nodule detection in X-ray images, which is a domain-specific problem for medical imaging, and is incremental as it builds on existing methods with novel modules.
The paper tackles the problem of domain shift in lung nodule detection across X-ray images from different healthcare centers by introducing a domain adaptive approach that combines mean teacher self-training and contrastive learning, achieving improved detection performance as demonstrated in experiments on multiple datasets.
Medical images from different healthcare centers exhibit varied data distributions, posing significant challenges for adapting lung nodule detection due to the domain shift between training and application phases. Traditional unsupervised domain adaptive detection methods often struggle with this shift, leading to suboptimal outcomes. To overcome these challenges, we introduce a novel domain adaptive approach for lung nodule detection that leverages mean teacher self-training and contrastive learning. First, we propose a hierarchical contrastive learning strategy to refine nodule representations and enhance the distinction between nodules and background. Second, we introduce a nodule-level domain-invariant feature learning (NDL) module to capture domain-invariant features through adversarial learning across different domains. Additionally, we propose a new annotated dataset of X-ray images to aid in advancing lung nodule detection research. Extensive experiments conducted on multiple X-ray datasets demonstrate the efficacy of our approach in mitigating domain shift impacts.