Encephaledema segmentation method and system based on support vector machine algorithm

Abstract

The invention provides an encephaledema segmentation method and system based on a support vector machine algorithm, which are applied to the medical diagnosis technology field. The encephaledema segmentation method comprises steps of using a plurality of CT images and a plurality of magnetic resonance T2 weighted images of patients suffering from first type hemorrhagic cerebral apoplexy to train a classifier based on the support vector machine algorithm, using the classifier to perform encephaledema segmentation on CT images of patients suffering from the second type hemorrhagic cerebral apoplexy, wherein the patients suffering from the first type hemorrhagic cerebral apoplexy have the CT images and the magnetic resonance T2 weighted images; and the patients suffering from the second type hemorrhagic cerebral apoplexy only have the CT images and do not have the magnetic resonance T2 weighted images. The invention utilizes few patients suffering from the hemorrhagic cerebral apoplexy having the CT images and the magnetic resonance T2 images to perform combined modeling, through studying, establishes a classifier which can identify the encephaledema on the CT from the CT image characteristics, can be applied to the patients who suffer from the hemorrhagic cerebral apoplexy and have the CT images and have no magnetic resonance T2 weighted images, and obtains the higher encephaledema segmentation accuracy.

Description

technical field [0001] The present invention relates to the technical field of medical diagnosis, in particular to a brain edema segmentation method and system based on a Support Vector Machine (Support Vector Machine, SVM) algorithm. Background technique [0002] Hemorrhagic stroke (IntracerebralHemorrhage, ICH) is the stroke with the highest mortality and disability rate, and its quantification will help to formulate appropriate treatment strategies. Cerebral edema after hemorrhage is a secondary injury that is extremely important for treatment strategies and prognosis. Clinically, the gold standard for detecting edema in ICH patients is magnetic resonance imaging (Magnetic Resonance Imaging, MRI) T2-weighted images. However, the sudden and urgent onset of ICH patients limits the use of MRI in ICH emergency treatment; at the same time, the imaging time of MRI Long and expensive, it is also one of the factors that make it difficult to use widely. For the quantification of...

AI Technical Summary

Problems solved by technology

However, the boundary between edema and surrounding tissue on CT images is blurred, and it is difficult to directly determine edema based on CT, and the segmentation accuracy is relatively low

Images