Model training method and device and pulmonary arterial hypertension measuring method and device

Abstract

The invention provides a model training method and device and a pulmonary arterial hypertension measuring method and device. The model training method comprises the following steps: inputting sample data into an initial network model, wherein the sample data are marked with at least one of a pulmonary artery label, a bifurcation label and a background label, and the pulmonary artery tag and / or the bifurcation tag form a foreground tag; classifying the sample data by using a first classification branch to obtain a first classification result; classifying the sample data with the foreground label by using a second classification branch to obtain a second classification result; based on the first classification result and the second classification result, obtaining a final classification result, which is used for representing whether the sample data has bifurcation points or not; and performing model training according to the final classification result. According to the method, the sample data with a small number of samples are merged and discriminated in the training process, so that the phenomenon of class imbalance caused by a large data size difference between the samples in the model training process is avoided.

Description

technical field [0001] The present application relates to the field of deep learning technology, in particular to a method and device for model training, and a method and device for measuring pulmonary hypertension. Background technique [0002] Pulmonary hypertension is a hemodynamic and pathophysiological state in which pulmonary artery pressure rises above a certain threshold. Pulmonary hypertension can be an independent disease, a complication, or a syndrome. Its morbidity and mortality are high, so it is more important in clinical practice. At present, the main method of discrimination is to measure the diameter of the pulmonary artery to predict whether there is pulmonary hypertension, so the measurement of the diameter of the pulmonary artery becomes particularly important. [0003] At present, with the development of machine learning, combining machine learning with pulmonary hypertension prediction is the main trend of the moment. However, in the process of actual...

AI Technical Summary

Problems solved by technology

However, in the process of actual operation, due to the large gap in the sample data of the training pulmonary artery diameter, the problem of class imbalance occurs from time to time.

Images