Method for calculating proportion of new coronal pneumonia lesion area based on deep learning

Abstract

The invention discloses a method for calculating the proportion of a new coronal pneumonia lesion area based on deep learning, which belongs to the technical field of lung measurement, and comprises the following steps: carrying out normalization processing on an original CT image set to adapt to data input of a deep learning model; respectively inputting CT image data in the training set into twonetwork learning models of 2 DUnet and 2.5 DUnet, and predicting a binary mask of a lung lesion area and a binary mask of a whole lung area; calculating the similarity between a binary mask predictedby the training set and a real label mask, and selecting an optimal network learning model; and by using the optimal network learning model, predicting lung lesion area masks and lung whole area masks for the CT images in the training set, and calculating the proportion between the lesion area masks and the whole area masks. According to the method, the lung lesion area and the effective mask ofthe whole lung are automatically segmented by utilizing a deep learning technology, so that the volume ratio of the lesion area is rapidly and accurately calculated.

Description

technical field [0001] The present invention relates to the technical field of lung measurement, in particular to a method for calculating the proportion of lesion areas of new coronary pneumonia based on deep learning. Background technique [0002] During the treatment of new coronary pneumonia, CT images play an important role in the diagnosis of new coronary pneumonia. Patients take CT images regularly to observe the development and changes of the disease. At present, there is no unified method for the quantitative analysis of the patient's lesion area. The measurement standard cannot quantitatively analyze the patient's disease trend, and manual observation of changes in the lesion area is prone to errors, which not only wastes a lot of manpower, but also reduces the efficiency of quantitative analysis. Contents of the invention [0003] The purpose of the present invention is to provide a method for calculating the proportion of new coronary pneumonia lesion areas bas...

AI Technical Summary

Problems solved by technology

[0003] The purpose of the present invention is to provide a method for calculating the proportion of new coronary pneumonia lesion areas based on deep learning in order to solve the above-mentioned problems of lack of measurement standards, large errors, and low efficiency in the quantitative analysis of pneumonia lesion areas. Accurately calculate the volume ratio between pneumonia and the entire lung area, which is conducive to the quantitative analysis of disease changes

Images