Bronchiectasis Detection and Classification Based on Deep Learning

Bronchiectasis can cause pulmonary ventilation dysfunction, which will bring huge social and economic burden. Deep learning methods are rarely used in the detection and classification of bronchiectasis. Current studies on bronchiectasis mainly focus on high resolution CT (HRCT), ignoring the more common low-dose CT (LDCT). Methodologically, existing studies do not use an authoritative standard to classify the severity of bronchiectasis. In effect, the accuracy of detection and classification needs to be improved for practical application. According to the above problems, we adopt LDCT data, contrast two deep learning models for the detection and classification of bronchiectasis effect, then we use dilated convolution to promote deep learning model for detection and classification of bronchiectasis. Finally, we developed an automatic detection and scoring system for bronchiectasis combining with authoritative scoring standards. According to the experiments that the detection rate of bronchiectasis in LDCT images by our developed bronchiectasis detection and scoring system can reach 91.0