Method and device for extracting focus area from medical image

Abstract

The embodiment of the invention discloses a method and device for extracting a focus area from a medical image, and the method comprises the steps: carrying out the curve fitting of an obtained CT image, and obtaining a closed curve in each layer of CT image; performing anti-distortion processing on the closed curve in each layer of CT image; carrying out grid construction on each closed curve subjected to the anti-distortion treatment to obtain a non-closed triangular grid with upper and lower openings, and calculating the area of each triangle and the volume of the focus area through the Heron's formula. According to the method and the device for extracting the focus area from the medical image disclosed by the embodiment of the invention, the maximum precision can be achieved under thecondition of given constraint through curve fitting and anti-distortion processing in combination with the computing power of a computer, and the method and the device can be used as an important reference. And an optimal solution can be achieved under the condition that constraint is manually given.

Description

technical field [0001] Embodiments of the present invention relate to the technical field of image processing, and in particular to a method and device for extracting lesion regions from medical images. Background technique [0002] The extraction of lesions can be divided into automatic extraction by computer and manual delineation. There are many computer algorithms, the common ones are grayscale feature extraction method, texture feature extraction method, and morphological feature extraction method. However, due to the complexity of actual images, more errors are often introduced, which are suitable for diagnostic assistance. There are still some methods for surgical reference. Insufficient; the traditional manual drawing method often adopts Bezier curve for fitting, and the degree of anti-distortion treatment is low, which often causes problems of difficulty in use and poor accuracy of calculation results. Contents of the invention [0003] To this end, the embodimen...

AI Technical Summary

Problems solved by technology

[0003] For this reason, the embodiments of the present invention provide a method and device for extracting lesion areas from medical images, so as to solve the technical problems of difficulty in use and poor accuracy of calculation results caused by low anti-distortion processing in the prior art

Images