A method for predicting the risk of recurrence after surgery for pancreatic neuroendocrine tumors

Abstract

The present application discloses a method for predicting the risk of postoperative recurrence of pancreatic neuroendocrine tumors. The method includes acquiring several tumor slices in images to be predicted; and determining each tumor slice in the several tumor slices based on a preset segmentation model. Respectively corresponding feature maps; filtering several feature maps to obtain several target feature maps corresponding to the image to be predicted, and based on the several target feature maps, determining the feature vector of the image to be predicted; based on the feature vector and the preset prediction model, A prediction result corresponding to the image to be predicted is determined. This application uses the segmentation model to determine the feature vector as the input item of the prediction model, and determines the prediction result corresponding to the image to be predicted based on the feature map. In this way, the prediction result corresponding to the image to be predicted is determined through deep transfer learning, which can improve the prediction. the accuracy of the results.

Description

technical field [0001] The present application relates to the technical field of biomedical engineering, in particular to a method for predicting the risk of postoperative recurrence of pancreatic neuroendocrine tumors. Background technique [0002] Neuroendocrine neoplasms (NENs) originate from neuroendocrine cells and are tumors with complex biological behaviors. In recent years, the incidence of NENs has been increasing. In the Chinese population, the pancreas is the most common primary site of NENs, accounting for about 32% of all NENs. Pancreatic neuroendocrine neoplasms (pNENs) are generally treated with surgery when they have not metastasized. [0003] Based on this, postoperative recurrence is the main problem in the treatment of pNEN patients (including local recurrence and distant metastasis). Clinically, once postoperative recurrence is found in patients, active treatment should be performed as soon as possible to block or delay the progression of the disease. ...

AI Technical Summary

Problems solved by technology

However, considering the complexity of the biological behavior of pNENs, how to classify the recurrence risk of pNEN patients with different biological behaviors is an important clinical problem to be solved urgently.

Images