Department of Biomedicine and Prevention, University of Rome "Tor Vergata", Rome, Italy.
Department of Medicine, Surgery and Dentistry, "Scuola Medica Salernitana", University of Salerno, Fisciano, Italy.
Curr Med Imaging. 2021;17(9):1094-1102. doi: 10.2174/1573405617999210112195450.
One of the most challenging aspects related to Covid-19 is to establish the presence of infection in an early phase of the disease. Texture analysis might be an additional tool for the evaluation of Chest X-ray in patients with clinical suspicion of Covid-19 related pneumonia.
To evaluate the diagnostic performance of texture analysis and machine learning models for the diagnosis of Covid-19 interstitial pneumonia in Chest X-ray images.
Chest X-ray images were accessed from a publicly available repository(https://www.kaggle. com/tawsifurrahman/covid19-radiography-database). Lung areas were manually segmented using a polygonal region of interest covering both lung areas, using MaZda, a freely available software for texture analysis. A total of 308 features per ROI was extracted. One hundred-ten Covid-19 Chest X-ray images were selected for the final analysis.
Six models, namely NB, GLM, DL, GBT, ANN, and PLS-DA were selected and ensembled. According to Youden's index, the Covid-19 Ensemble Machine Learning Score showing the highest area under the curve (0.971±0.015) was 132.57. Assuming this cut-off the Ensemble model performance was estimated by evaluating both true and false positive/negative, resulting in 91.8% accuracy with 93% sensitivity and 90% specificity. Moving the cut-off value to -100, although the accuracy resulted lower (90.6%), the Ensemble Machine Learning showed 100% sensitivity, with 80% specificity.
Texture analysis of Chest X-ray images and machine learning algorithms may help in differentiating patients with Covid-19 pneumonia. Despite several limitations, this study can lay the ground for future research works in this field and help to develop more rapid and accurate screening tools for these patients.
与新冠病毒相关的最具挑战性的方面之一是在疾病早期确定感染的存在。纹理分析可能是评估临床怀疑患有新冠病毒相关肺炎的患者的胸部 X 射线的另一种工具。
评估纹理分析和机器学习模型在诊断胸部 X 射线图像中的新冠病毒间质性肺炎的诊断性能。
从一个公共存储库（https://www.kaggle.com/tawsifurrahman/covid19-radiography-database）访问胸部 X 射线图像。使用 MaZda 手动分割肺区域，MaZda 是一种免费的纹理分析软件，使用多边形感兴趣区域覆盖两个肺区域。每个 ROI 提取 308 个特征。最终分析共选择了 110 张新冠病毒的胸部 X 射线图像。
选择并集成了六个模型，即 NB、GLM、DL、GBT、ANN 和 PLS-DA。根据 Youden 指数，新冠病毒集成机器学习得分显示的最高曲线下面积（0.971±0.015）为 132.57。假设这个截止值，通过评估真阳性/假阳性和真阴性/假阴性，集成模型的性能估计为 91.8%的准确率，93%的灵敏度和 90%的特异性。将截止值移动到-100，尽管准确率较低（90.6%），但集成机器学习显示 100%的灵敏度和 80%的特异性。
胸部 X 射线图像的纹理分析和机器学习算法可以帮助区分新冠病毒肺炎患者。尽管存在一些局限性，但本研究可为该领域的未来研究工作奠定基础，并有助于为这些患者开发更快速和准确的筛选工具。
