Fetal brain age estimation method and device based on depth imbalance regression

The invention relates to a fetal brain age estimation method and device based on depth imbalance regression, and the method comprises the steps: introducing labels into a fetal brain magnetic resonance image training set, and obtaining effective label density distribution through employing a label distribution smoothing strategy; establishing a multi-scale hierarchical segmentation fetus brain feature extraction regression network; constructing a regression focus mean square error loss function, and re-weighting the regression focus mean square error loss function by adopting effective label density; constructing a grade sorting similarity regularizer; and constructing a total loss function of the fetal brain feature extraction regression network by taking the re-weighted focus mean square error regression loss function as a main function and a grade sorting similarity regularizer as a balance regularization item. According to the method, the performance of the regression model can be remarkably improved, the