IRCM-Caps：一种用于 COVID-19 的 X 射线图像检测方法。
IRCM-Caps: An X-ray image detection method for COVID-19.
机构信息
School of Computer Science and Engineering, North Minzu University, Yinchuan, China.
Key Laboratory of Intelligent Information Processing of Image and Graphics, State Ethnic Affairs Commission, Yinchuan, China.
出版信息
Clin Respir J. 2023 May;17(5):364-373. doi: 10.1111/crj.13599. Epub 2023 Mar 15.
OBJECTIVE
COVID-19 is ravaging the world, but traditional reverse transcription-polymerase reaction (RT-PCR) tests are time-consuming and have a high false-negative rate and lack of medical equipment. Therefore, lung imaging screening methods are proposed to diagnose COVID-19 due to its fast test speed. Currently, the commonly used convolutional neural network (CNN) model requires a large number of datasets, and the accuracy of the basic capsule network for multiple classification is limital. For this reason, this paper proposes a novel model based on CNN and CapsNet.
METHODS
The proposed model integrates CNN and CapsNet. And attention mechanism module and multi-branch lightweight module are applied to enhance performance. Use the contrast adaptive histogram equalization (CLAHE) algorithm to preprocess the image to enhance image contrast. The preprocessed images are input into the network for training, and ReLU was used as the activation function to adjust the parameters to achieve the optimal.
RESULT
The test dataset includes 1200 X-ray images (400 COVID-19, 400 viral pneumonia, and 400 normal), and we replace CNN of VGG16, InceptionV3, Xception, Inception-Resnet-v2, ResNet50, DenseNet121, and MoblieNetV2 and integrate with CapsNet. Compared with CapsNet, this network improves 6.96%, 7.83%, 9.37%, 10.47%, and 10.38% in accuracy, area under the curve (AUC), recall, and F1 scores, respectively. In the binary classification experiment, compared with CapsNet, the accuracy, AUC, accuracy, recall rate, and F1 score were increased by 5.33%, 5.34%, 2.88%, 8.00%, and 5.56%, respectively.
CONCLUSION
The proposed embedded the advantages of traditional convolutional neural network and capsule network and has a good classification effect on small COVID-19 X-ray image dataset.
目的
COVID-19 正在肆虐全球，但传统的逆转录-聚合酶链反应（RT-PCR）检测耗时且假阴性率高，且缺乏医疗设备。因此，由于其快速的测试速度，提出了肺部成像筛查方法来诊断 COVID-19。目前，常用的卷积神经网络（CNN）模型需要大量数据集，并且基本胶囊网络的多分类精度有限。为此，本文提出了一种基于 CNN 和 CapsNet 的新模型。
方法
所提出的模型集成了 CNN 和 CapsNet。并应用注意力机制模块和多分支轻量级模块来提高性能。使用对比度自适应直方图均衡（CLAHE）算法对图像进行预处理以增强图像对比度。将预处理后的图像输入网络进行训练，并使用 ReLU 作为激活函数来调整参数以达到最优。
结果
测试数据集包括 1200 张 X 射线图像（400 张 COVID-19、400 张病毒性肺炎和 400 张正常），我们用 VGG16、InceptionV3、Xception、Inception-Resnet-v2、ResNet50、DenseNet121 和 MoblieNetV2 中的 CNN 替换，并与 CapsNet 集成。与 CapsNet 相比，该网络在准确率、曲线下面积（AUC）、召回率和 F1 评分方面分别提高了 6.96%、7.83%、9.37%、10.47%和 10.38%。在二分类实验中，与 CapsNet 相比，准确率、AUC、准确率、召回率和 F1 评分分别提高了 5.33%、5.34%、2.88%、8.00%和 5.56%。
结论
所提出的模型嵌入了传统卷积神经网络和胶囊网络的优势，对小型 COVID-19 X 射线图像数据集具有良好的分类效果。
Zotero 插件