Nawaz Marriam, Nazir Tahira, Javed Ali, Malik Khalid Mahmood, Saudagar Abdul Khader Jilani, Khan Muhammad Badruddin, Abul Hasanat Mozaherul Hoque, AlTameem Abdullah, AlKhathami Mohammed
Department of Computer Science, University of Engineering and Technology, Taxila, Pakistan.
Department of Software Engineering, University of Engineering and Technology, Taxila, Pakistan.
Front Med (Lausanne). 2022 Nov 4;9:1005920. doi: 10.3389/fmed.2022.1005920. eCollection 2022.
In the last 2 years, we have witnessed multiple waves of coronavirus that affected millions of people around the globe. The proper cure for COVID-19 has not been diagnosed as vaccinated people also got infected with this disease. Precise and timely detection of COVID-19 can save human lives and protect them from complicated treatment procedures. Researchers have employed several medical imaging modalities like CT-Scan and X-ray for COVID-19 detection, however, little concentration is invested in the ECG imaging analysis. ECGs are quickly available image modality in comparison to CT-Scan and X-ray, therefore, we use them for diagnosing COVID-19. Efficient and effective detection of COVID-19 from the ECG signal is a complex and time-taking task, as researchers usually convert them into numeric values before applying any method which ultimately increases the computational burden. In this work, we tried to overcome these challenges by directly employing the ECG images in a deep-learning (DL)-based approach. More specifically, we introduce an Efficient-ECGNet method that presents an improved version of the EfficientNetV2-B4 model with additional dense layers and is capable of accurately classifying the ECG images into healthy, COVID-19, myocardial infarction (MI), abnormal heartbeats (AHB), and patients with Previous History of Myocardial Infarction (PMI) classes. Moreover, we introduce a module to measure the similarity of COVID-19-affected ECG images with the rest of the diseases. To the best of our knowledge, this is the first effort to approximate the correlation of COVID-19 patients with those having any previous or current history of cardio or respiratory disease. Further, we generate the heatmaps to demonstrate the accurate key-points computation ability of our method. We have performed extensive experimentation on a publicly available dataset to show the robustness of the proposed approach and confirmed that the Efficient-ECGNet framework is reliable to classify the ECG-based COVID-19 samples.
在过去两年中，我们目睹了多波冠状病毒疫情，全球数百万人受到影响。由于接种疫苗的人也感染了这种疾病，因此尚未确诊出针对新冠病毒病的有效治疗方法。对新冠病毒病进行准确及时的检测可以挽救生命，并使人们免受复杂治疗程序的困扰。研究人员已采用多种医学成像方式，如CT扫描和X光来检测新冠病毒病，然而，对心电图成像分析的关注较少。与CT扫描和X光相比，心电图是一种可快速获取的成像方式，因此，我们将其用于诊断新冠病毒病。从心电图信号中高效准确地检测新冠病毒病是一项复杂且耗时的任务，因为研究人员通常在应用任何方法之前将其转换为数值，这最终增加了计算负担。在这项工作中，我们试图通过在基于深度学习（DL）的方法中直接使用心电图图像来克服这些挑战。更具体地说，我们引入了一种高效心电图网络（Efficient - ECGNet）方法，该方法提出了EfficientNetV2 - B4模型的改进版本，增加了额外的密集层，能够将心电图图像准确分类为健康、新冠病毒病、心肌梗死（MI）、异常心跳（AHB）以及有心肌梗死既往史（PMI）的患者类别。此外，我们引入了一个模块来测量受新冠病毒病影响的心电图图像与其他疾病的相似性。据我们所知，这是首次尝试估算新冠病毒病患者与有任何心血管或呼吸系统疾病既往或当前病史患者之间的相关性。此外，我们生成了热图以展示我们方法准确的关键点计算能力。我们在一个公开可用的数据集上进行了广泛的实验，以展示所提出方法的稳健性，并证实高效心电图网络框架对基于心电图的新冠病毒病样本进行分类是可靠的。
