IEEE J Biomed Health Inform. 2021 Aug;25(8):3073-3081. doi: 10.1109/JBHI.2021.3053023. Epub 2021 Aug 5.
Lung parenchyma segmentation is valuable for improving the performance of lung nodule detection in computed tomography (CT) images. Traditionally, the two tasks are performed separately. This paper proposes a deep multi-task learning (MTL) approach to integrate these tasks for better lung nodule detection. Three new ideas lead to our proposed approach. First, lung parenchyma segmentation is used as the attention module and is combined with nodule detection in a single deep network. Second, lung nodule detection is performed in an anchor-free manner by dividing it into two subtasks, nodule center identification and nodule size regression. Third, a novel pyramid dilated convolution block (PDCB) is proposed to utilize the advantage of dilated convolution and tackle its gridding problem for better lung parenchyma segmentation. Based on these ideas, we design our end-to-end deep network architecture and corresponding MTL method to achieve lung parenchyma segmentation and nodule detection simultaneously. We evaluate the proposed approach on the commonly used Lung Nodule Analysis 2016 (LUNA16) dataset. The experimental results show the value of our contributions and demonstrate that our approach can yield significant improvements compared with state-of-the-art counterparts.
肺实质分割对于提高 CT 图像中肺结节检测的性能很有价值。传统上，这两个任务是分开进行的。本文提出了一种深度多任务学习（MTL）方法，将这两个任务集成在一起，以提高肺结节检测的性能。我们的方法有三个新的思路。首先，将肺实质分割作为注意力模块，并在单个深度网络中与结节检测相结合。其次，通过将肺结节检测分为两个子任务，即结节中心识别和结节大小回归，以无锚方式进行结节检测。第三，提出了一种新颖的金字塔扩张卷积块（PDCB），以利用扩张卷积的优势，并解决其网格问题，以更好地进行肺实质分割。基于这些思路，我们设计了端到端的深度网络架构和相应的 MTL 方法，以同时实现肺实质分割和结节检测。我们在常用的 Lung Nodule Analysis 2016（LUNA16）数据集上评估了所提出的方法。实验结果表明了我们的贡献的价值，并证明了与最先进的方法相比，我们的方法可以取得显著的改进。
