Radiologist-Level Two Novel and Robust Automated Computer-Aided Prediction Models for Early Detection of COVID-19 Infection from Chest X-ray Images.
Radiologist-Level Two Novel and Robust Automated Computer-Aided Prediction Models for Early Detection of COVID-19 Infection from Chest X-ray Images.
复制标题
DOI：
10.1007/s13369-021-05880-5
复制
发表时间：
2021-08-07
影响因子：
2.9
通讯作者：
Gupta D
中科院分区：
文献类型：
--
作者：
Khanna M;Agarwal A;Singh LK;Thawkar S;Khanna A;Gupta D
COVID-19是一种持续的大流行病，每天广泛传播，并达到显著的社区传播。X射线图像，计算机断层扫描（CT）图像和检测试剂盒（RT-PCR）是预测这种感染的三种容易获得的选择。与从X射线和CT图像中筛查COVID-19感染相比，可用于诊断COVID-19的检测试剂盒（RT-PCR）面临分析时间长、假阴性结果高、灵敏度和特异性差等问题。在COVID-19阳性患者中发现了X射线可以检测到的放射学特征。放射科医生可能会检查这些特征，但这是一个耗时且容易出错的过程（充满了观察者内部的差异）。因此，胸部X射线分析过程需要自动化，人工智能驱动的工具已被证明是提高准确性和加快分析时间的最佳选择，特别是在医学图像分析的情况下。我们列出了四个数据集和20个基于CNN的模型，使用16个详细的实验和五重交叉验证来测试和验证最好的模型。提出的两种模型，集成深度迁移学习CNN模型和混合LSTMCNN，表现最好。集成CNN的准确率高达99.78%（平均96.51%），F1得分高达0.9977（平均0.9682），AUC高达0.9978（平均0.9583）。LSTMCNN的准确率高达98.66%（平均96.46%），F1评分高达0.9974（平均0.9668），AUC高达0.9856（平均0.9645）。这两个最好的预训练的基于迁移学习的检测模型可以通过为患者提供正确和快速的预测来做出临床贡献。
COVID-19 is an ongoing pandemic that is widely spreading daily and reaches a significant community spread. X-ray images, computed tomography (CT) images and test kits (RT-PCR) are three easily available options for predicting this infection. Compared to the screening of COVID-19 infection from X-ray and CT images, the test kits(RT-PCR) available to diagnose COVID-19 face problems such as high analytical time, high false negative outcomes, poor sensitivity and specificity. Radiological signatures that X-rays can detect have been found in COVID-19 positive patients. Radiologists may examine these signatures, but it's a time-consuming and error-prone process (riddled with intra-observer variability). Thus, the chest X-ray analysis process needs to be automated, for which AI-driven tools have proven to be the best choice to increase accuracy and speed up analysis time, especially in the case of medical image analysis. We shortlisted four datasets and 20 CNN-based models to test and validate the best ones using 16 detailed experiments with fivefold cross-validation. The two proposed models, ensemble deep transfer learning CNN model and hybrid LSTMCNN, perform the best. The accuracy of ensemble CNN was up to 99.78% (96.51% average-wise), F1-score up to 0.9977 (0.9682 average-wise) and AUC up to 0.9978 (0.9583 average-wise). The accuracy of LSTMCNN was up to 98.66% (96.46% average-wise), F1-score up to 0.9974 (0.9668 average-wise) and AUC up to 0.9856 (0.9645 average-wise). These two best pre-trained transfer learning-based detection models can contribute clinically by offering the patients prediction correctly and rapidly.
登录
查看更多内容
DOI：
10.1007/s10489-020-01904-z
发表时间：
2021
期刊：
Applied intelligence (Dordrecht, Netherlands)
影响因子：
--
作者：
Goel T;Murugan R;Mirjalili S;Chakrabartty DK
通讯作者：
Chakrabartty DK
DOI：
10.1016/j.chaos.2020.110120
发表时间：
2020-11
期刊：
Chaos, solitons, and fractals
影响因子：
--
作者：
Alakus TB;Turkoglu I
通讯作者：
Turkoglu I
影响因子：
4.8
作者：
Das, N. Narayan;Kumar, N.;Singh, D.
通讯作者：
Singh, D.
DOI：
10.1007/s11548-020-02286-w
发表时间：
2021-01
影响因子：
3
作者：
Gifani P;Shalbaf A;Vafaeezadeh M
通讯作者：
Vafaeezadeh M
影响因子：
6.2
作者：
Gharbi, Michael;Chen, Jiawen;Durand, Fredo
通讯作者：
Durand, Fredo