Unsupervised contrastive learning based transformer for lung nodule detection.
Unsupervised contrastive learning based transformer for lung nodule detection.
复制标题
DOI：
10.1088/1361-6560/ac92ba
复制
发表时间：
2022-10-07
影响因子：
3.5
通讯作者：
中科院分区：
文献类型：
--
作者：
早期发现肺结节与计算机断层扫描（CT）是至关重要的肺癌患者的生存时间和更好的生活质量。在这种情况下，计算机辅助检测/诊断（CAD）被证明是有价值的第二或并发读者。然而，肺结节的准确检测对于这样的CAD系统甚至放射科医师来说仍然是一个挑战，这不仅是由于肺结节的大小、位置和外观的可变性，而且还由于肺结构的复杂性。这导致CAD的假阳性率很高，影响了其临床疗效。受最近的计算机视觉技术的启发，在这里，我们提出了一个自我监督的区域为基础的三维Transformer模型，以确定一组候选区域之间的肺结节。具体而言，开发了一种3D视觉Transformer，其将CT体积划分为一系列非重叠立方体，从具有嵌入层的每个立方体中提取嵌入特征，并使用自注意机制分析所有嵌入特征以进行预测。为了在相对较小的数据集上有效地训练Transformer模型，使用基于区域的对比学习方法通过用公共CT图像预训练3D Transformer来提高性能。实验结果表明，与常用的3D卷积神经网络相比，该方法可以显着提高肺结节筛选的性能。这项研究表明了一个很有前途的方向，以提高目前的CAD系统的肺结节检测的性能。
Early detection of lung nodules with computed tomography (CT) is critical for the longer survival of lung cancer patients and better quality of life. Computer-aided detection/diagnosis (CAD) is proven valuable as a second or concurrent reader in this context. However, accurate detection of lung nodules remains a challenge for such CAD systems and even radiologists due to not only the variability in size, location, and appearance of lung nodules but also the complexity of lung structures. This leads to a high false-positive rate with CAD, compromising its clinical efficacy. Motivated by recent computer vision techniques, here we present a self-supervised region-based 3D transformer model to identify lung nodules among a set of candidate regions. Specifically, a 3D vision transformer is developed that divides a CT volume into a sequence of non-overlap cubes, extracts embedding features from each cube with an embedding layer, and analyzes all embedding features with a self-attention mechanism for the prediction. To effectively train the transformer model on a relatively small dataset, the region-based contrastive learning method is used to boost the performance by pre-training the 3D transformer with public CT images. Our experiments show that the proposed method can significantly improve the performance of lung nodule screening in comparison with the commonly used 3D convolutional neural networks. This study demonstrates a promising direction to improve the performance of current CAD systems for lung nodule detection.
登录
查看更多内容
影响因子：
8
作者：
Al-Shabi, Mundher;Shak, Kelvin;Tan, Maxine
通讯作者：
Tan, Maxine
影响因子：
4.6
作者：
Dou, Qi;Chen, Hao;Heng, Pheng-Ann
通讯作者：
Heng, Pheng-Ann
影响因子：
10.9
作者：
Messay, Temesguen;Hardie, Russell C.;Rogers, Steven K.
通讯作者：
Rogers, Steven K.
影响因子：
5.8
作者：
Blandin Knight S;Crosbie PA;Balata H;Chudziak J;Hussell T;Dive C
通讯作者：
Dive C
影响因子：
2.4
作者：
Armato, Samuel G., III;Drukker, Karen;Clarke, Laurence P.
通讯作者：
Clarke, Laurence P.