COVIDScreen: explainable deep learning framework for differential diagnosis of COVID-19 using chest X-rays.
COVIDScreen: explainable deep learning framework for differential diagnosis of COVID-19 using chest X-rays.
复制标题
DOI：
10.1007/s00521-020-05636-6
复制
发表时间：
2021
影响因子：
6
通讯作者：
Babu RN
中科院分区：
文献类型：
--
作者：
Singh RK;Pandey R;Babu RN
COVID-19已成为一场全球危机，带来前所未有的社会经济挑战，危及我们未来数年的生活和生计。由于无法获得COVID-19疫苗，因此对人群进行快速检测有助于遏制感染病例的指数上升。由于缺乏RT-PCR检测试剂盒和迟迟得不到检测结果，需要有其他快速可靠的诊断方法。在这篇文章中，我们提出了一种新的基于深度学习的解决方案，使用胸部X射线，可以帮助快速分类COVID-19患者。所提出的解决方案使用图像增强、图像分割，并采用由四个CNN基学习器沿着朴素贝叶斯作为元学习器组成的改进的堆叠集成模型，将胸部X射线分类为三类，即COVID-19、肺炎和正常。一个有效的修剪策略，在所提出的框架中引入的结果，提高模型的性能，泛化能力，并降低模型的复杂性。我们通过使用Grad-CAM可视化将可解释性纳入我们的文章中，以建立对医疗AI系统的信任。此外，我们评估了多种最先进的GAN架构及其生成COVID-19胸部X射线真实合成样本的能力，以处理有限数量的训练样本。所提出的解决方案明显优于现有方法，在标准数据集上，COVID-19、正常和肺炎类的准确率为98.67%，Kappa评分为0.98，F-1评分分别为100、98和98。所提出的解决方案可用作患者评估的一个要素，沿着金标准临床和实验室测试。
COVID-19 has emerged as a global crisis with unprecedented socio-economic challenges, jeopardizing our lives and livelihoods for years to come. The unavailability of vaccines for COVID-19 has rendered rapid testing of the population instrumental in order to contain the exponential rise in cases of infection. Shortage of RT-PCR test kits and delays in obtaining test results calls for alternative methods of rapid and reliable diagnosis. In this article, we propose a novel deep learning-based solution using chest X-rays which can help in rapid triaging of COVID-19 patients. The proposed solution uses image enhancement, image segmentation, and employs a modified stacked ensemble model consisting of four CNN base-learners along with Naive Bayes as meta-learner to classify chest X-rays into three classes viz. COVID-19, pneumonia, and normal. An effective pruning strategy as introduced in the proposed framework results in increased model performance, generalizability, and decreased model complexity. We incorporate explainability in our article by using Grad-CAM visualization in order to establish trust in the medical AI system. Furthermore, we evaluate multiple state-of-the-art GAN architectures and their ability to generate realistic synthetic samples of COVID-19 chest X-rays to deal with limited numbers of training samples. The proposed solution significantly outperforms existing methods, with 98.67% accuracy, 0.98 Kappa score, and F-1 scores of 100, 98, and 98 for COVID-19, normal, and pneumonia classes, respectively, on standard datasets. The proposed solution can be used as one element of patient evaluation along with gold-standard clinical and laboratory testing.
登录
查看更多内容
影响因子：
5.7
作者：
Chen, Hao;Dou, Qi;Heng, Pheng-Ann
通讯作者：
Heng, Pheng-Ann
影响因子：
4.4
作者：
Apostolopoulos, Ioannis D.;Mpesiana, Tzani A.
通讯作者：
Mpesiana, Tzani A.
影响因子：
9.6
作者：
Adams, Hugo J. A.;Kwee, Thomas C.;Kwee, Robert M.
通讯作者：
Kwee, Robert M.
影响因子：
158.5
作者：
Arons, M. M.;Hatfield, K. M.;Jernigan, J. A.
通讯作者：
Jernigan, J. A.
影响因子：
6.1
作者：
Brunese L;Mercaldo F;Reginelli A;Santone A
通讯作者：
Santone A