Smadi Ahmad Al, Abugabah Ahed, Al-Smadi Ahmad Mohammad, Almotairi Sultan
School of Artificial Intelligence, Xidian University, No. 2 South Taibai Road, Xian, 710071, China.
College of Technological Innovation, Zayed University, Abu Dhabi Campus, UAE.
Inform Med Unlocked. 2022;32:101059. doi: 10.1016/j.imu.2022.101059. Epub 2022 Aug 24.
COVID-19 detection from medical imaging is a difficult challenge that has piqued the interest of experts worldwide. Chest X-rays and computed tomography (CT) scanning are the essential imaging modalities for diagnosing COVID-19. All researchers focus their efforts on developing viable methods and rapid treatment procedures for this pandemic. Fast and accurate automated detection approaches have been devised to alleviate the need for medical professionals. Deep Learning (DL) technologies have successfully recognized COVID-19 situations. This paper proposes a developed set of nine deep learning models for diagnosing COVID-19 based on transfer learning and implementation in a novel architecture (SEL-COVIDNET). We include a global average pooling layer, flattening, and two dense layers that are fully connected. The model's effectiveness is evaluated using balanced and unbalanced COVID-19 radiography datasets. After that, our model's performance is analyzed using six evaluation measures: accuracy, sensitivity, specificity, precision, F1-score, and Matthew's correlation coefficient (MCC). Experiments demonstrated that the proposed SEL-COVIDNET with tuned DenseNet121, InceptionResNetV2, and MobileNetV3Large models outperformed the results of comparative SOTA for multi-class classification (COVID-19 vs. No-finding vs. Pneumonia) in terms of accuracy (98.52%), specificity (98.5%), sensitivity (98.5%), precision (98.7%), F1-score (98.7%), and MCC (97.5%). For the COVID-19 vs. No-finding classification, our method had an accuracy of 99.77%, a specificity of 99.85%, a sensitivity of 99.85%, a precision of 99.55%, an F1-score of 99.7%, and an MCC of 99.4%. The proposed model offers an accurate approach for detecting COVID-19 patients, which aids in the containment of the COVID-19 pandemic.
从医学影像中检测新型冠状病毒肺炎（COVID-19）是一项艰巨的挑战，已引起全球专家的关注。胸部X光和计算机断层扫描（CT）是诊断COVID-19的重要影像检查方式。所有研究人员都致力于为这场大流行开发可行的方法和快速治疗程序。已设计出快速准确的自动检测方法，以减轻对医学专业人员的需求。深度学习（DL）技术已成功识别出COVID-19的情况。本文基于迁移学习提出了一组九个用于诊断COVID-19的深度学习模型，并在一种新颖的架构（SEL-COVIDNET）中实现。我们包括一个全局平均池化层、展平层和两个全连接的密集层。使用平衡和不平衡的COVID-19射线照相数据集评估模型的有效性。之后，使用六种评估指标分析我们模型的性能：准确率、灵敏度、特异性、精确率、F1分数和马修斯相关系数（MCC）。实验表明，所提出的带有调优的DenseNet121、InceptionResNetV2和MobileNetV3Large模型的SEL-COVIDNET在多类分类（COVID-19与无异常与肺炎）方面的准确率（98.52%）、特异性（98.5%）、灵敏度（98.5%）、精确率（98.7%）、F1分数（98.7%）和MCC（97.5%）方面优于比较的当前最优方法。对于COVID-19与无异常分类，我们的方法准确率为99.77%，特异性为99.85%，灵敏度为99.85%，精确率为99.55%，F1分数为99.7%，MCC为99.4%。所提出的模型为检测COVID-19患者提供了一种准确的方法，有助于控制COVID-19大流行。
