Full-automatic identification and evaluation method for pulmonary ventilation dysfunction in dynamic chest photography

The invention discloses a dynamic chest photography pulmonary ventilation dysfunction full-automatic identification and evaluation method. The method comprises the steps that a first original image and a first pulmonary ventilation imaging image of dynamic chest photography in a DICOM file are acquired; obtaining a first lung field mask according to a semantic segmentation model and the first original image; according to the first original image and the first lung field mask, performing segmentation processing on the first lung ventilation imaging image to obtain a second lung ventilation imaging image; and according to the first original image, the first lung field mask and the second lung ventilation imaging image, training and testing an image classification model to obtain a target full-automatic identification and evaluation model. The method can improve the efficiency of analyzing the image of the dynamic chest photography, and can be widely applied to the technical field of image processing. 本发明公开了一种动态