Cross-level information fusion medical image segmentation method

The invention provides a cross-level information fusion medical image segmentation method, which comprises the following steps of: constructing a cross-level information fusion model, sending preprocessed data into an encoder to extract features, carrying out feature extraction on the features after each time of encoding again, fusing the features with the information after the previous level of encoding, sending the fused information into a decoder to decode, and finally obtaining the cross-level information fusion medical image. And inputting the preprocessed training set and verification set image data into the cross-level information fusion model for training, transmitting each image in the test set image data into the trained cross-level information fusion model for prediction, and obtaining a segmentation result. According to the cross-level information fusion medical image segmentation method provided by the invention, features of different levels can be fused, context information can be effectively ex