School of Computer Science and Engineering, University of New South Wales, Sydney, Australia.
CSIRO Data61, Sydney, Australia.
Sci Rep. 2024 May 21;14(1):11616. doi: 10.1038/s41598-024-61024-3.
Accurate and early detection of pneumoconiosis using chest X-rays (CXR) is important for preventing the progression of this incurable disease. It is also a challenging task due to large variations in appearance, size and location of lesions in the lung regions as well as inter-class similarity and intra-class variance. Compared to traditional methods, Convolutional Neural Networks-based methods have shown improved results; however, these methods are still not applicable in clinical practice due to limited performance. In some cases, limited computing resources make it impractical to develop a model using whole CXR images. To address this problem, the lung fields are divided into six zones, each zone is classified separately and the zone classification results are then aggregated into an image classification score, based on state-of-the-art. In this study, we propose a dual lesion attention network (DLA-Net) for the classification of pneumoconiosis that can extract features from affected regions in a lung. This network consists of two main components: feature extraction and feature refinement. Feature extraction uses the pre-trained Xception model as the backbone to extract semantic information. To emphasise the lesion regions and improve the feature representation capability, the feature refinement component uses a DLA module that consists of two sub modules: channel attention (CA) and spatial attention (SA). The CA module focuses on the most important channels in the feature maps extracted by the backbone model, and the SA module highlights the spatial details of the affected regions. Thus, both attention modules combine to extract discriminative and rich contextual features to improve classification performance on pneumoconiosis. Experimental results show that the proposed DLA-Net outperforms state-of-the-art methods for pneumoconiosis classification.
使用胸部 X 射线 (CXR) 准确和早期检测尘肺对于防止这种无法治愈的疾病的进展非常重要。由于肺部病变的外观、大小和位置以及类间相似性和类内变异性存在很大差异，因此这也是一项具有挑战性的任务。与传统方法相比，基于卷积神经网络的方法已经显示出了改进的结果；然而，由于性能有限，这些方法在临床实践中仍然不适用。在某些情况下，有限的计算资源使得使用整个 CXR 图像开发模型变得不切实际。为了解决这个问题，将肺区域分为六个区，每个区分别进行分类，然后根据最新技术将区分类结果汇总为图像分类得分。在这项研究中，我们提出了一种用于尘肺病分类的双病变注意网络 (DLA-Net)，该网络可以从肺部受影响的区域中提取特征。该网络由两个主要组件组成：特征提取和特征细化。特征提取使用预先训练的 Xception 模型作为骨干网络来提取语义信息。为了强调病变区域并提高特征表示能力，特征细化组件使用 DLA 模块，该模块由两个子模块组成：通道注意力 (CA) 和空间注意力 (SA)。CA 模块关注骨干模型提取的特征图中最重要的通道，而 SA 模块突出受影响区域的空间细节。因此，两个注意力模块结合起来提取有区别的和丰富的上下文特征，以提高尘肺病分类的性能。实验结果表明，所提出的 DLA-Net 在尘肺病分类方面优于最新技术。
