Cerebral hemorrhage image processing method, device, computer device and storage medium

Abstract

Embodiments of the present application provide an image processing method, apparatus, computer device, and storage medium for intracerebral hemorrhage. The method comprises the following steps of: acquiring a CT plain film scanning image of cerebral hemorrhage in a Cartesian coordinate system, and taking the CT plain film scanning image as an original image, wherein, the original image comprises askull contour; Constructing a non-Cartesian coordinate system based on the skull contour, converting the original image into a new image in a non-Cartesian coordinate system, wherein the new image isexpanded along the skull contour in the non-Cartesian coordinate; Bleeding location and bleeding type are detected by the new image. Embodiments of the present application process images of intracerebral hemorrhage to provide a new angle for detection of intracerebral hemorrhage, facilitate the determination of bleeding location and bleeding type of intracerebral hemorrhage, and improve the accuracy of detection of intracerebral hemorrhage.

Description

technical field [0001] The present application relates to the technical field of image processing, and in particular to a method, device, computer equipment, and storage medium for image processing of cerebral hemorrhage. Background technique [0002] CT cerebral hemorrhage detection software currently on the market: MaxQ-AI's AccipioTM, and BioMindTM Tianzhiyi. Its function is to detect the location and amount of intracranial hemorrhage based on the plain CT scan image and artificial intelligence algorithm. According to public information, the detection is carried out in Cartesian coordinates. However, in some cases of cerebral hemorrhage, the location characteristics of the hemorrhage cannot be well highlighted only through the detection of the Cartesian coordinate system, which increases the difficulty of judging the location of the hemorrhage and classifying the hemorrhage. figure 1 It is some typical plain CT scan images based on the Cartesian coordinate system, in wh...

AI Technical Summary

Problems solved by technology

like figure 1 For the three types of bleeding (subscalp hematoma, subdural hematoma, and epidural hematoma) shown in the first row on the middle right, the blood tends to follow the skull, and the shape of the bleeding tends to be non-convex, such as meniscus The current detection method for non-convex hemorrhage increases the difficulty of cerebral hemorrhage detection, and it is not easy to achieve good results

Images