A method, medium and terminal device for predicting the risk of early recurrence of hepatocellular carcinoma after surgery

Abstract

The present application discloses a method for predicting the early recurrence risk of hepatocellular carcinoma after surgery. The method includes: acquiring the image to be predicted and the pathological information corresponding to the image to be predicted; based on a preset segmentation model, determining the A feature vector: determining a prediction result corresponding to the image to be predicted based on the feature vector, pathological information, and a preset prediction model. After obtaining the image to be predicted and pathological information, the application determines the feature vector corresponding to the image to be predicted through the segmentation model, and learns the feature vector and pathological information through the prediction model to obtain the prediction result, which reduces the risk of postoperative hepatocellular carcinoma. Early recurrence prediction depends on doctor's experience, which can improve the accuracy of early recurrence prediction after HCC surgery.

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 early recurrence of hepatocellular carcinoma after surgery. Background technique [0002] Hepatocellular carcinoma (hepatocellular carcinoma, HCC) is a common malignant tumor, accounting for 70-85% of the total burden of liver cancer worldwide, seriously affecting the life and safety of patients. The treatment of HCC uses tumor surgical resection and chemotherapy to eradicate cancer cells as much as possible and reduce the recurrence rate of cancer. However, a considerable proportion of patients still relapse after surgery. Studies have shown that portal vein invasion and intrahepatic cancer cell metastasis are the two most important factors in predicting recurrence, but recurrence is also affected by factors such as chronic hepatitis, liver cirrhosis, tumor number and tumor size, and the reasons are complex. The clin...

AI Technical Summary

Problems solved by technology

Studies have shown that portal vein invasion and intrahepatic cancer cell metastasis are the two most important factors in predicting recurrence, but recurrence is also affected by factors such as chronic hepatitis, liver cirrhosis, tumor number and tumor size, and the reasons are complex

The clinical judgment of the risk of intrahepatic recurrence often relies on the long-term accumulated experience of doctors on various risk factors, which cannot guarantee the accuracy of recurrence prediction

Images