Apparatus and Method for Generating Medical Image Segmentation Deep-Learning Model Medical Image Segmentation Deep-Learning Model Generated Therefrom

摘要

The present invention is a device for generating a deep learning model for medical image fractionation, a training data generation/assignment unit for generating a training data set through a fractional result obtained by inputting a given medical image into an original medical image fractional deep learning model, After inputting the good task data and bad task data sampled from the training data sets for primary learning into the medical image fractional deep learning model, acquire the respective temporary weights using the output data according to the primary learning, and then train for secondary learning By inputting the Good Task data and Bad Task data sampled from the data sets into the medical image fractional deep learning model, the weights are updated by adding the gradients obtained using the weights obtained using the output data according to the second learning execution. It includes a learning control unit, the primary learning and secondary learning is repeated.