Deep vein thrombosis thrombolytic effect prediction method and system, storage medium and terminal

Abstract

The invention discloses a deep vein thrombosis thrombolysis curative effect prediction method and system, a storage medium and a terminal. The method comprises the steps of: obtaining MRI images of patients with deep vein thrombosis of lower extremities; training the MRI images based on a semantic segmentation network to obtain a deep learning semantic segmentation model; using the deep learning semantic segmentation model to extract high-dimensional semantic features of deep vein thrombosis of lower extremities, The clustering algorithm is used to filter the high-dimensional semantic features; according to the filtered semantic features, the thrombolytic efficacy prediction algorithm is used to predict the thrombolytic efficacy of deep vein thrombosis of lower extremities, and the prediction results of thrombolytic efficacy of deep vein thrombosis of lower extremities are obtained, and output the result. Based on the deep learning semantic segmentation network and magnetic resonance images, the present invention establishes a relationship model between semantic features and thrombolytic treatment effect of thrombus to effectively predict the thrombolytic efficacy of patient's thrombus, which reduces the burden on doctors and improves diagnosis. efficiency.

Description

technical field [0001] The present invention relates to the technical field of medical image processing, in particular to a method and system for predicting the curative effect of thrombolysis in deep vein thrombosis of lower extremities based on a semantic segmentation model, a storage medium and a terminal. Background technique [0002] Deep vein thrombosis (Deep Vein Thrombosis, DVT) is a disease caused by abnormal coagulation of blood in deep veins, which usually occurs in the lower extremities. The annual incidence is about 0.1%, and it has become the third major cardiovascular disease. In addition to causing symptoms such as swelling and pain in the lower extremities, DVT may also lead to serious complications such as pulmonary embolism, which may even be life-threatening. [0003] Since the onset of lower extremity DVT is relatively insidious, the symptoms and signs are atypical and easily confused with other diseases, making the symptomatic diagnosis of the disease u...

AI Technical Summary

Problems solved by technology

[0009] In view of the above-mentioned deficiencies in the prior art, the purpose of the present invention is to provide a method and system, storage medium and terminal for predicting the curative effect of thrombolysis in deep vein thrombosis of lower extremities based on semantic segmentation model, aiming to solve the problem that the prior art is based on the extraction of thrombus ROI region. The characteristics of radiomics often need to manually outline the thrombus, which is time-consuming, laborious, and highly subjective; at the same time, the technical process of feature screening is complicated, and the internal relationship between data cannot be fully explored

Images