Multi-task contrastive learning for automatic CT and X-ray diagnosis of COVID-19.
Multi-task contrastive learning for automatic CT and X-ray diagnosis of COVID-19.
复制标题
用于COVID-19自动CT和X射线诊断的多任务对比学习。
DOI：
10.1016/j.patcog.2021.107848
复制
发表时间：
2021-06
影响因子：
8
通讯作者：
Cai T
中科院分区：
文献类型：
--
作者：
Li J;Zhao G;Tao Y;Zhai P;Chen H;He H;Cai T
计算机断层扫描（CT）和X射线是诊断COVID-19的有效方法。尽管一些研究已经证明了深度学习在使用CT和X射线自动诊断COVID-19中的潜力，但对未知样本的泛化需要改进。为了解决这个问题，我们提出了对比多任务卷积神经网络（CMT-CNN），它由两个任务组成。主要任务是将COVID-19与其他肺炎和正常对照进行诊断。辅助任务是通过对比损失来鼓励局部聚集：首先，每个图像通过一系列增强（泊松噪声，旋转等）进行变换。然后，该模型被优化为在潜在空间中嵌入相同图像相似而不同图像不相似的表示。通过这种方式，CMT-CNN能够进行变换不变的预测，并且数据的扩展属性得到保留。我们证明，显然简单的辅助任务提供了强大的监督，以提高泛化。我们在CT数据集（4，758个样本）和X射线数据集（5，821个样本）上进行实验，这些数据集由开放数据集和我们医院收集的数据组成。实验结果表明，对比学习（作为插件模块）在CT（5.49%-6.45%）和X射线（0.96%-2.42%）上为深度学习模型带来了可靠的准确性提高，而无需额外的注释。我们的代码可以在线访问。
Computed tomography (CT) and X-ray are effective methods for diagnosing COVID-19. Although several studies have demonstrated the potential of deep learning in the automatic diagnosis of COVID-19 using CT and X-ray, the generalization on unseen samples needs to be improved. To tackle this problem, we present the contrastive multi-task convolutional neural network (CMT-CNN), which is composed of two tasks. The main task is to diagnose COVID-19 from other pneumonia and normal control. The auxiliary task is to encourage local aggregation though a contrastive loss: first, each image is transformed by a series of augmentations (Poisson noise, rotation, etc.). Then, the model is optimized to embed representations of a same image similar while different images dissimilar in a latent space. In this way, CMT-CNN is capable of making transformation-invariant predictions and the spread-out properties of data are preserved. We demonstrate that the apparently simple auxiliary task provides powerful supervisions to enhance generalization. We conduct experiments on a CT dataset (4,758 samples) and an X-ray dataset (5,821 samples) assembled by open datasets and data collected in our hospital. Experimental results demonstrate that contrastive learning (as plugin module) brings solid accuracy improvement for deep learning models on both CT (5.49%-6.45%) and X-ray (0.96%-2.42%) without requiring additional annotations. Our codes are accessible online.
登录
查看更多内容
泊松图像去模糊的字典学习方法
影响因子：
10.6
作者：
Ma, Liyan;Moisan, Lionel;Zeng, Tieyong
通讯作者：
Zeng, Tieyong
影响因子：
19.7
作者：
Li, Lin;Qin, Lixin;Xia, Jun
通讯作者：
Xia, Jun
影响因子：
82.9
作者：
Mei, Xueyan;Lee, Hao-Chih;Yang, Yang
通讯作者：
Yang, Yang
影响因子：
8
作者：
Ji, You;Sun, Shiliang
通讯作者：
Sun, Shiliang
影响因子：
10.6
作者：
Ouyang, Xi;Huo, Jiayu;Shen, Dinggang
通讯作者：
Shen, Dinggang