Newborn brain image segmentation method and model construction method based on deep learning

Abstract

The invention provides a newborn brain image segmentation method and model construction method based on deep learning. The method comprises the following steps: preprocessing a data set including a bimodal magnetic resonance image and a reference image; pre-constructing a feature enhancement bimodal segmentation network model FedNet, wherein the processed data set is used for training the feature enhancement bimodal segmentation network model FedNet, the processed data set is input into the trained feature enhancement bimodal segmentation network model FedNet, and a segmented two-dimensional image is output; reconstructing the segmented two-dimensional image, and outputting a segmented newborn brain magnetic resonance image with the same size as the pre-processed image. According to the invention, the down-sampling module is enhanced by adopting the dual-channel features, convolution and maximum pooling processing are respectively carried out through different modes, the diversity of the feature information output by the dual channels is fully combined, the up-sampling module is noticed in the invention, so that the segmentation network can have noticed features, and the accuracy of network segmentation is improved.

Description

technical field [0001] The invention belongs to the field of medical image segmentation, relates to pattern recognition and image processing technology, in particular to a newborn brain image segmentation method and a model construction method based on deep learning. Background technique [0002] Neonatal brain damage is particularly detrimental to normal development and relatively early neurodevelopment, mainly due to perinatal hypoxia and birth trauma. It is also a key factor in causing subsequent diseases such as cerebral palsy, mental retardation, and epilepsy. Neonatal brain magnetic resonance image (MRI) segmentation has always been an important part of clinical radiology. It helps to check the brain health of newborns, especially premature babies, and whether the nerves are developing soundly. Factors thus aid in the diagnosis of the neonatal brain. Therefore, segmentation of neonatal brain tissue is of great significance to the study of neonatal early brain develop...

AI Technical Summary

Problems solved by technology

[0005] In view of the deficiencies in the prior art, the purpose of the present invention is to provide a newborn brain image segmentation method and model construction method based on deep learning, and solve the technical problem of poor segmentation effect for multi-segmentation tasks in the prior art

Images