A lower limb deep venous thrombosis thrombolysis curative effect prediction method and system based on machine learning

Abstract

The invention discloses a lower limb deep venous thrombosis thrombolysis curative effect prediction method and system based on machine learning. The method comprises the steps: obtaining an area of interest of lower limb deep venous thrombosis from an MRI image; Performing image omics feature extraction on the region of interest of the lower limb deep venous thrombosis; And predicting the curative effect of lower limb deep venous thrombosis thrombolysis by adopting a machine learning method according to an image omics feature extraction result. The invention discloses a lower limb deep venousthrombosis thrombolysis curative effect prediction method and system based on machine learning. lower limb deep venous thrombolysis curative effect prediction is performed through image omics featureextraction and a machine learning method; The MRI imaging omics method and the machine learning technology are combined to predict the thrombolysis curative effect of the deep venous thrombosis of the lower limbs, the curative effect evaluation work can be completed through prediction before thrombolysis treatment, the method does not depend on experience of doctors any more, and the thrombolysiscurative effect prediction result is more accurate and higher in efficiency. The method can be widely applied to the field of medical image processing.

Description

technical field [0001] The invention relates to the field of medical image processing, in particular to a method and system for predicting the curative effect of deep vein thrombosis of lower extremities based on machine learning. Background technique [0002] Deep vein thrombosis (Deep Vein Thrombosis, DVT) is a common disease that occurs in the deep veins of the lower extremities, with an annual incidence of about 0.1%, showing an increasing trend year by year, and has become the third major cardiovascular disease. In addition to symptoms such as lower limb swelling and pain, more than 50% of DVT patients are prone to concurrent pulmonary embolism, and the mortality rate exceeds 20%, which is called the "silent killer". [0003] There are many imaging methods currently used for DVT examination, including ultrasound, computed tomography (CT), magnetic resonance imaging (Magnetic Resonance Imaging, MRI), and digital subtraction techniques. As a non-invasive examination tech...

AI Technical Summary

Problems solved by technology

The effect of thrombolytic therapy is closely related to factors such as age, past medical history, lesion nature of blocked blood vessels, and course of disease. Doctors often need to comprehensively evaluate the patient’s thrombolytic effect through clinical symptoms and imaging data, and choose whether to perform thrombolytic therapy based on the evaluation results. Thrombolysis: If patients who are suitable for thrombolysis do not receive thrombolysis, the best treatment may be missed; if patients who are not suitable for thrombolysis receive thrombolysis, fatal injuries such as cerebral hemorrhage may occur

However, the clinical symptoms of DVT patients are usually subjective. For example, the discrepancies between the days of the medical history described by the patient and the actual number of days of the medical history will affect the evaluation results of the doctor; while the imaging evaluation is still in the research stage, doctors mostly observe the level and range of the thrombus signal and For the edema of the perivascular space, the curative effect of thrombolysis is evaluated based on experience, but the difference in experience among different doctors is likely to lead to uneven diagnostic results. Efficacy evaluation can only be carried out after suppository treatment, so the current evaluation method can no longer meet the growing clinical needs

Images