School of Information Engineering, Zhengzhou University, Zhengzhou, China.
Department of Respiratory and Sleep Medicine, The First Affiliated Hospital of Zhengzhou University, Zhengzhou, China.
Int J Comput Assist Radiol Surg. 2022 Jun;17(6):1059-1068. doi: 10.1007/s11548-022-02576-5. Epub 2022 Mar 15.
Lung cancer usually presents as pulmonary nodules on early diagnostic images, and accurately estimating the malignancy of pulmonary nodules is crucial to the prevention and diagnosis of lung cancer. Recently, deep learning algorithms based on convolutional neural networks have shown potential for pulmonary nodules classification. However, the size of the nodules is very diverse, ranging from 3 to 30 mm, which makes classifying them to be a challenging task. In this study, we propose a novel architecture called Res-trans networks to classify nodules in computed tomography (CT) scans.
We designed local and global blocks to extract features that capture the long-range dependencies between pixels to adapt to the correct classification of lung nodules of different sizes. Specifically, we designed residual blocks with convolutional operations to extract local features and transformer blocks with self-attention to capture global features. Moreover, the Res-trans network has a sequence fusion block that aggregates and extracts the sequence feature information output by the transformer block that improves classification accuracy.
Our proposed method is extensively evaluated on the public LIDC-IDRI dataset, which contains 1,018 CT scans. A tenfold cross-validation result shows that our method obtains better performance with AUC = 0.9628 and Accuracy = 0.9292 compared with recently leading methods.
In this paper, a network that can capture local and global features is proposed to classify nodules in chest CT. Experimental results show that our proposed method has better classification performance and can help radiologists to accurately analyze lung nodules.
肺癌通常在早期诊断图像上表现为肺结节，准确估计肺结节的恶性程度对于肺癌的预防和诊断至关重要。最近，基于卷积神经网络的深度学习算法在肺结节分类方面显示出了潜力。然而，结节的大小非常多样化，范围从 3 到 30 毫米，这使得对它们进行分类成为一项具有挑战性的任务。在本研究中，我们提出了一种名为 Res-trans 网络的新架构，用于对计算机断层扫描（CT）扫描中的结节进行分类。
我们设计了局部和全局模块，以提取特征，这些特征可以捕捉像素之间的长程依赖关系，从而适应不同大小的肺结节的正确分类。具体来说，我们设计了具有卷积操作的残差模块来提取局部特征，以及具有自注意力的转换器模块来捕获全局特征。此外，Res-trans 网络具有序列融合模块，可以聚合和提取转换器模块输出的序列特征信息，从而提高分类准确性。
我们的方法在包含 1018 个 CT 扫描的公共 LIDC-IDRI 数据集上进行了广泛评估。十折交叉验证结果表明，与最近的领先方法相比，我们的方法具有更好的性能，AUC=0.9628，准确性=0.9292。
本文提出了一种能够捕获局部和全局特征的网络，用于对胸部 CT 中的结节进行分类。实验结果表明，我们提出的方法具有更好的分类性能，可以帮助放射科医生准确分析肺结节。
