病毒性肺炎X光图片分类研究

病毒性肺炎是全球大流行疾病,全球有数千万人确诊。X光影像学分析是临床诊断的重要手段之一。为了实现快速高效高精度地检测,本文LBP提取病毒性肺炎X光图片的纹理特征,利用SVM建立分类模型,对病毒性肺炎X光图片分类。训练集由NIH Chest X-ray Dataset中的正常样本和病毒性肺炎样本组成。分类平均正确率达到97.5%。本文提出的模型能较好地对病毒性肺炎图片进行分类。

Virus Disease 2019(Viral pneumonia) is a worldwide epidemic disease, with tens of millions of people worldwide diagnosed. X-ray imaging analysis is one of the important means of clinical diagnosis. Viral pneumonia lung X-ray image texture features were extracted by LBP. Then we employ SVM to classify the feature. The training set consisted samples from NIH Chest X-ray Dataset and Viral pneumonia lung X-ray image. The average accuracy of classification was 98.5%. The Viral pneumonia lung X-ray image can be classified by the model proposed in this paper.