Salem Salamh Ahmed B, Salamah Abdulrauf A, Akyüz Halil Ibrahim
Institute of Science, Material Science and Engineering, Kastamonu University, Kuzey Kent /P.O. Box, 37150, Kastamonu, Kastamonu, Turkey.
Tripoli Central Hospital, P.O. Box 15528, Tripoli, Libya.
Radiol Res Pract. 2021 Mar 18;2021:5554408. doi: 10.1155/2021/5554408. eCollection 2021.
The chest Computer Tomography (CT scan) is used in the diagnosis of coronavirus disease 2019 (COVID-19) and is an important complement to the Reverse Transcription Polymerase Chain Reaction (RT-PCR) test. The paper aims to improve the radiological diagnosis in the case of coronavirus disease COVID-19 pneumonia on forms of noninvasive approaches with conventional and high-resolution computer tomography (HRCT) scan images upon chest CT images of patients confirmed with mild to severe findings. The preliminary study is to compare the radiological findings of COVID-19 pneumonia in conventional chest CT images with images processed by a new tool and reviewed by expert radiologists. The researchers used a new filter called Golden Key Tool (GK-Tool) which has confirmed the improvement in the quality and diagnostic efficacy of images acquired using our modified images. Further, Convolution Neural Networks (CNNs) architecture called VGG face was used to classify chest CT images. The classification has been performed by using VGG face on various datasets which are considered as a protocol to diagnose COVID-19, Non-COVID-19 (other lung diseases), and normal cases (no findings on chest CT). Accordingly, the performance evaluation of the GK-Tool was fairly good as shown in the first set of results, where 80-95% of participants show a good to excellent assessment of the new images view in the case of COVID-19 patients. The results, in general, illustrate good recognition rates in the diagnosis and, therefore, would be significantly higher in normal cases with COVID-19. These results could reduce the radiologist's workload burden and play a major role in the decision-making process.
胸部计算机断层扫描（CT扫描）用于2019冠状病毒病（COVID-19）的诊断，是逆转录聚合酶链反应（RT-PCR）检测的重要补充。本文旨在通过常规和高分辨率计算机断层扫描（HRCT）扫描图像等非侵入性方法，对确诊为轻至重度COVID-19肺炎患者的胸部CT图像进行放射学诊断。初步研究是比较COVID-19肺炎在常规胸部CT图像与经新工具处理并由放射科专家审核的图像中的放射学表现。研究人员使用了一种名为金钥匙工具（GK-Tool）的新滤波器，该滤波器证实了使用我们修改后的图像获取的图像在质量和诊断效能方面有所提高。此外，还使用了一种名为VGG face的卷积神经网络（CNN）架构对胸部CT图像进行分类。分类是通过在各种数据集上使用VGG face进行的，这些数据集被视为诊断COVID-19、非COVID-19（其他肺部疾病）和正常病例（胸部CT无异常发现）的方案。因此，如第一组结果所示，GK-Tool的性能评估相当不错，在COVID-19患者中，80-95%的参与者对新图像的评价为良好至优秀。总体而言，这些结果在诊断中显示出良好的识别率，因此在COVID-19正常病例中的识别率会显著更高。这些结果可以减轻放射科医生的工作量负担，并在决策过程中发挥重要作用。
