School of Mechanical Engineering, Shanghai Jiao Tong University, Shanghai 200240, China.
Department of Pulmonary, Shanghai Chest Hospital, Shanghai Jiao Tong University, Shanghai 200240, China.
Sensors (Basel). 2021 Apr 13;21(8):2734. doi: 10.3390/s21082734.
In order to develop appropriate treatment and rehabilitation plans with regard to different subpathological types (PILs and IAs) of lung nodules, it is important to diagnose them through low-dose spiral computed tomography (LDCT) during routine screening before surgery. Based on the characteristics of different subpathological lung nodules expressed from LDCT images, we propose a multi-dimension and multi-feature hybrid learning neural network in this paper. Our network consists of a 2D network part and a 3D network part. The feature vectors extracted from the 2D network and 3D network are further learned by XGBoost. Through this formation, the network can better integrate the feature information from the 2D and 3D networks. The main learning block of the network is a residual block combined with attention mechanism. This learning block enables the network to learn better from multiple features and pay more attention to the key feature map among all the feature maps in different channels. We conduct experiments on our dataset collected from a cooperating hospital. The results show that the accuracy, sensitivity and specificity of our network are 83%, 86%, 80%, respectively It is feasible to use this network to classify the subpathological type of lung nodule through routine screening.
为了针对肺结节的不同亚病理类型（PIL 和 IAs）制定合适的治疗和康复计划，在手术前的常规筛查中通过低剂量螺旋 CT（LDCT）进行诊断非常重要。基于 LDCT 图像中表达的不同亚病理肺结节的特征，我们在本文中提出了一种多维和多特征混合学习神经网络。我们的网络由 2D 网络部分和 3D 网络部分组成。从 2D 网络和 3D 网络中提取的特征向量由 XGBoost 进一步学习。通过这种方式，网络可以更好地整合来自 2D 和 3D 网络的特征信息。网络的主要学习块是结合注意力机制的残差块。这个学习块使网络能够从多个特征中更好地学习，并在不同通道的所有特征图中更加关注关键特征图。我们在合作医院收集的数据集上进行了实验。结果表明，我们的网络的准确率、敏感度和特异性分别为 83%、86%和 80%，通过常规筛查使用该网络对肺结节的亚病理类型进行分类是可行的。
