Pneumonia, caused by microorganisms, is a severely contagious disease that damages one or both the lungs of the patients. Early detection and treatment are typically favored to recover infected patients since untreated pneumonia can lead to major complications in the elderly (>65 years) and children (<5 years). The objectives of this work are to develop several models to evaluate big X-ray images (XRIs) of the chest, to determine whether the images show/do not show signs of pneumonia, and to compare the models based on their accuracy, precision, recall, loss, and receiver operating characteristic area under the ROC curve scores. Enhanced convolutional neural network (CNN), VGG-19, ResNet-50, and ResNet-50 with fine-tuning are some of the deep learning (DL) algorithms employed in this study. By training the transfer learning model and enhanced CNN model using a big data set, these techniques are used to identify pneumonia. The data set for the study was obtained from Kaggle. It should be noted that the data set has been expanded to include further records. This data set included 5863 chest XRIs, which were categorized into 3 different folders (i.e., train, val, test). These data are produced every day from personnel records and Internet of Medical Things devices. According to the experimental findings, the ResNet-50 model showed the lowest accuracy, that is, 82.8%, while the enhanced CNN model showed the highest accuracy of 92.4%. Owing to its high accuracy, enhanced CNN was regarded as the best model in this study. The techniques developed in this study outperformed the popular ensemble techniques, and the models showed better results than those generated by cutting-edge methods. Our study implication is that a DL models can detect the progression of pneumonia, which improves the general diagnostic accuracy and gives patients new hope for speedy treatment. Since enhanced CNN and ResNet-50 showed the highest accuracy compared with other algorithms, it was concluded that these techniques could be effectively used to identify pneumonia after performing fine-tuning.

中文翻译：

---

在胸部 X 射线图像上使用增强型卷积神经网络模型检测肺炎。

由微生物引起的肺炎是一种严重的传染性疾病，会损害患者的一个或两个肺部。早期发现和治疗通常有利于感染患者康复，因为未经治疗的肺炎可导致老年人（>65 岁）和儿童（<5 岁）出现严重并发症。这项工作的目标是开发几种模型来评估胸部的大型 X 射线图像 (XRI)，确定图像是否显示/不显示肺炎迹象，并根据模型的准确度、精确度、 ROC 曲线得分下的召回率、丢失率和接受者操作特征面积。增强型卷积神经网络 (CNN)、VGG-19、ResNet-50 和带有微调的 ResNet-50 是本研究中采用的一些深度学习 (DL) 算法。通过使用大数据集训练迁移学习模型和增强的 CNN 模型，这些技术可用于识别肺炎。该研究的数据集来自 Kaggle。应该注意的是，数据集已经扩展到包括更多记录。该数据集包括 5863 个胸部 XRI，分为 3 个不同的文件夹（即训练、验证、测试）。这些数据每天都从人员记录和医疗物联网设备中产生。根据实验结果，ResNet-50模型的准确率最低，为82.8%，而增强CNN模型的准确率最高，为92.4%。由于其高精度，增强 CNN 被认为是本研究中的最佳模型。本研究开发的技术优于流行的集成技术，这些模型显示出比尖端方法产生的结果更好的结果。我们的研究意义在于，DL 模型可以检测肺炎的进展，从而提高一般诊断的准确性，并为患者提供快速治疗的新希望。由于增强的 CNN 和 ResNet-50 与其他算法相比显示出最高的准确性，因此得出结论，这些技术在进行微调后可以有效地用于识别肺炎。