Long and short diameter estimation method based on medical image

Abstract

The invention relates to the field of medical image processing, and aims to provide a long and short diameter estimation method based on a medical image. The method includes the following steps: acquiring a target area image of to-be-measured long and short diameters in an ultrasonic image and a real size corresponding to a pixel point; acquiring an outer contour pixel point set according to the target area image, and performing coordinate transformation on the outer contour pixel point set; on the basis of the converted outer contour coordinate point set, searching two end points of the long diameter and estimating the length of the long diameter; and on the basis of the outer contour coordinate set and the long-diameter end points, searching short-diameter end points, and estimating the length of the short diameter. The contour of the target area can be directly obtained through analysis and calculation by a computer, especially for ultrasonic examination departments with large business handling capacity, a large amount of time can be saved. According to the method, a mode of traversing all outer contour points is adopted, and whether a non-target area exists on a candidate long-short-diameter line segment or not is checked; compared with manual operation, the accuracy of long and short diameter searching positions can be greatly improved.

Description

technical field [0001] The invention relates to the field of medical image processing, in particular to a method for estimating long and short diameters based on medical images. Background technique [0002] In the medical field, the long diameter refers to the longest line segment on the outer contour of a target (such as blood vessels, lymph nodes, tumors, etc.); the short diameter refers to the longest line segment perpendicular to the long diameter and on the outer contour . All points on the line connecting the major diameter and the minor diameter do not exceed the outer contour area of ​​the target. Dividing the long diameter by the short diameter is the aspect ratio, which can evaluate the degree to which the target is close to a circle. The long axis and short axis are used to characterize the shape of the target, which is an important medical quantitative feature. For example, if the long diameter of cervical lymph nodes exceeds the normal size, it indicates tha...

AI Technical Summary

Problems solved by technology

Limited by the doctor's own level and diagnosis time, the line segment marked by the doctor may not be the real long axis on the medical image, but just a line segment that is relatively close to the length of the long axis, which will affect the search for the short axis.

Images