CN-122023180-A - Subtraction image processing method and device, storage medium and electronic equipment

CN122023180ACN 122023180 ACN122023180 ACN 122023180ACN-122023180-A

Abstract

The embodiment of the application discloses a subtraction image processing method, a subtraction image processing device, a storage medium and electronic equipment, and relates to the field of image processing. According to the application, a first mask image and a full-film image of a target part are acquired, the first mask image is subjected to rigid calibration processing and elastic calibration preprocessing based on the full-film image to obtain a second mask image comprising a plurality of areas, whether the areas of the second mask image are mapped to areas with the same positions on the full-film image contain blood vessels or not is determined, calibration values of the areas on the second mask image are acquired by adopting different calibration modes respectively for the areas containing the blood vessels and the areas not containing the blood vessels, the second mask image is subjected to elastic calibration processing to obtain a third mask image, and the full-film image is subjected to subtraction processing to obtain a subtraction image of the target part. The application can improve the interference of angiography in elastic calibration of local area, improve the calibration accuracy, and better remove the motion artifact on the subtraction image, so that the subtraction image is cleaner.

Inventors

LIU QI
XUAN XIAO
CUI MINGZHI

Assignees

北京万东医疗科技股份有限公司

Dates

Publication Date: 20260512
Application Date: 20250903

Claims (10)

1. A method of processing a subtracted image, the method comprising: Acquiring a first mask image and a film-filling image of a target part; performing rigid calibration processing and elastic calibration preprocessing on the first mask image based on the image filling image to obtain a second mask image comprising a plurality of areas; Determining whether the region of the second mask image mapped to the region at the same position on the image contains blood vessels or not, and acquiring calibration values of each region on the second mask image in different calibration modes for the region containing the blood vessels and the region not containing the blood vessels; Performing elastic calibration processing on the second mask image based on calibration values respectively corresponding to a plurality of areas on the second mask image to obtain a third mask image; and performing subtraction processing on the film-filling image based on the third mask image to obtain a subtraction image of the target part.
2. The method according to claim 1, wherein determining whether the region of the second mask image mapped to the region at the same position on the image contains a blood vessel, and acquiring calibration values of each region on the second mask image by using different calibration methods for the region containing the blood vessel and the region not containing the blood vessel, respectively, comprises: judging whether the area has direction disorder according to offset field information obtained by carrying out elastic calibration pretreatment on each area on the second mask image, wherein the offset field information represents the local deformation direction and amplitude of the area; Determining that the region where the direction disorder condition exists is mapped to the region at the same position on the image of the map including blood vessels, and determining that an area where no directional disorder exists is mapped to the map identical positions on the film-filling image the region of (2) does not contain a blood vessel; And respectively adopting different calibration modes for the region containing the blood vessel and the region not containing the blood vessel to acquire the calibration values of each region on the second mask image.
3. The method according to claim 2, wherein the area where the direction disorder condition is determined to exist is mapped to the area at the same position on the image of the map and contains blood vessels, and before determining that the region where no directional disturbance exists is mapped to the region at the same position on the image of the map to contain no blood vessel, further comprises: Acquiring the average value of each region on the second mask image, and mapping the region of the second mask image to the neighborhood average value of the region at the same position on the image; The area where the direction disorder condition is determined to exist is mapped to the region at the same position on the map image contains a blood vessel, and determining that the region where the direction disorder does not exist is mapped to the region at the same position on the image of the map, including: Acquiring a first region with a direction disorder condition on the second mask image, and determining that the region of the first region mapped to the same position on the image contains blood vessels when the neighborhood average value of the second mask image and/or the image meets a preset condition; and acquiring a second area without direction disorder on the second mask image, and determining that the area, mapped to the same position on the image, of the second area does not contain blood vessels.
4. The method for processing a subtracted image according to claim 2, wherein the determining whether the region has a direction disorder according to offset field information obtained by performing elastic calibration preprocessing on each region on the second mask image includes: According to the offset field information obtained by the elastic calibration pretreatment of the area on the second mask image, the number of sub-areas with the offset condition of pixels in a plurality of sub-areas included in the area and the offset direction of the sub-areas with the offset condition of pixels are obtained, and the main offset direction and the auxiliary offset direction of the area are recorded; And judging whether the area has direction disorder according to the standard deviation among the main direction, the auxiliary direction and the numerical value representing the offset direction of the area.
5. The method according to claim 1, wherein determining whether the region of the second mask image mapped to the region at the same position on the image contains a blood vessel, and acquiring calibration values of each region on the second mask image by using different calibration methods for the region containing the blood vessel and the region not containing the blood vessel, respectively, comprises: Determining whether the region of the second mask image maps to the region of the same position on the image of the picture; Removing a blood vessel portion of the region containing blood vessels on the image of the surplus sheet to obtain a target region containing only non-blood vessel portions, mapping the target area of the film-forming image to the second the calibration value is calculated for the target area at the same position on the mask image, acquiring a calibration value of a region corresponding to the region containing the blood vessel on the second mask image; And performing calibration value calculation on the region which does not contain blood vessels on the image of the full mask and is mapped to the region at the same position of the image of the second mask, and obtaining the calibration value of the region corresponding to the region which does not contain blood vessels on the image of the second mask.
6. The method of processing a subtracted image according to claim 2, wherein the performing a rigid calibration process and an elastic calibration pre-process on the first mask image based on the image-filling image to obtain a second mask image including a plurality of regions includes: Performing rigid calibration processing on the first mask image based on the image filling image to obtain a second mask image; and carrying out elastic calibration pretreatment on the second mask image, and determining a plurality of characteristic points on the second mask image and offset field information of an area where the characteristic points are located.
7. The method for processing a subtracted image according to claim 1, wherein the performing elastic calibration processing on the second mask image based on calibration values corresponding to a plurality of regions on the second mask image, to obtain a third mask image, includes: And acquiring a global offset field of the second mask image according to the calibration values respectively corresponding to the multiple areas on the second mask image, and performing elastic calibration processing on the second mask image based on the global offset field to obtain a third mask image.
8. A subtraction image processing apparatus, the apparatus comprising: The image acquisition module is used for acquiring a first mask image and a film-filling image of the target part; the calibration processing module is used for carrying out rigid calibration processing and elastic calibration preprocessing on the first mask image based on the image-filling image to obtain a second mask image comprising a plurality of areas; The blood vessel distinguishing module is used for determining whether the region of the second mask image mapped to the region at the same position on the image contains blood vessels or not, and acquiring calibration values of each region on the second mask image in different calibration modes aiming at the region containing the blood vessels and the region not containing the blood vessels; the elastic calibration module is used for carrying out elastic calibration processing on the second mask image based on the calibration values corresponding to the multiple areas on the second mask image respectively to obtain a third mask image; and the subtraction processing module is used for carrying out subtraction processing on the film-filling image based on the third mask image to obtain a subtraction image of the target part.
9. A computer storage medium storing a plurality of instructions adapted to be loaded by a processor and to perform the method steps of any one of claims 1 to 7.
10. An electronic device comprising a processor and a memory, wherein the memory stores a computer program adapted to be loaded by the processor and to perform the method steps of any of claims 1-7.

Description

Subtraction image processing method and device, storage medium and electronic equipment Technical Field The present application relates to the field of image processing, and in particular, to a method and apparatus for processing a subtraction image, a storage medium, and an electronic device. Background Subtraction angiography is used in particular for displaying blood vessels of the human body, in order to be able to identify possible vascular abnormalities in the display, such as vascular stenosis (stenosis) or vascular dilation (aneurysm). In order to improve the visibility of blood vessels in an X-ray image, a contrast agent is added to the blood before the X-ray image is taken, so that the blood vessels are clearly highlighted from the background in the X-ray image. But in addition to the blood vessels, other structures or organs, such as bones, are often visible in the X-ray image, which may partially cover the blood vessels in the image. Subtraction angiography techniques are employed in order to avoid the above problems. In subtraction angiography, two digital radiographs of the same body region are taken under the same projection direction. One of the two photographs, i.e., a so-called mask, is taken without a contrast agent, and the other photograph, i.e., a so-called filling image (hereinafter referred to as a filling sheet), is taken with a contrast agent. By subtracting the digital image data of the two photographs obtained from the logarithmic measurements of the X-ray detector, the same anatomical background in the photographs disappears, thus giving only a pure vascular image. However, the above technique has a disadvantage in that, when the organ is photographed a plurality of times, both of the imaging involve positional errors. For example, errors caused by movement of the machine and errors caused by movement of the patient's body, which position errors cause artifacts in the film-fed image. Therefore, how to correct these errors is a current urgent problem. Disclosure of Invention The embodiment of the application provides a subtraction image processing method, a device, a storage medium and electronic equipment, which can solve the problems. The technical scheme is as follows: In a first aspect, an embodiment of the present application provides a subtraction image processing method, including: Acquiring a first mask image and a film-filling image of a target part; performing rigid calibration processing and elastic calibration preprocessing on the first mask image based on the image filling image to obtain a second mask image comprising a plurality of areas; Determining whether the region of the second mask image mapped to the region at the same position on the image contains blood vessels or not, and acquiring calibration values of each region on the second mask image in different calibration modes for the region containing the blood vessels and the region not containing the blood vessels; Performing elastic calibration processing on the second mask image based on calibration values respectively corresponding to a plurality of areas on the second mask image to obtain a third mask image; and performing subtraction processing on the film-filling image based on the third mask image to obtain a subtraction image of the target part. In a second aspect, an embodiment of the present application provides a subtraction image processing apparatus, including: The image acquisition module is used for acquiring a first mask image and a film-filling image of the target part; the calibration processing module is used for carrying out rigid calibration processing and elastic calibration preprocessing on the first mask image based on the image-filling image to obtain a second mask image comprising a plurality of areas; The blood vessel distinguishing module is used for determining whether the region of the second mask image mapped to the region at the same position on the image contains blood vessels or not, and acquiring calibration values of each region on the second mask image in different calibration modes aiming at the region containing the blood vessels and the region not containing the blood vessels; the elastic calibration module is used for carrying out elastic calibration processing on the second mask image based on the calibration values corresponding to the multiple areas on the second mask image respectively to obtain a third mask image; and the subtraction processing module is used for carrying out subtraction processing on the film-filling image based on the third mask image to obtain a subtraction image of the target part. In a third aspect, embodiments of the present application provide a computer storage medium storing a plurality of instructions adapted to be loaded by a processor and to perform the above-described method steps. In a fourth aspect, embodiments of the present application provide a computer program product storing a plurality of instructions adapted to be loaded by a