Medical image registration method based on IDC algorithm
A medical imaging and registration technology, applied in the medical field, can solve the problems of unsatisfactory registration accuracy and registration speed, and achieve the effects of accelerated registration speed, fast iteration, excellent registration accuracy and registration speed
Pending Publication Date: 2021-04-13
江苏集萃复合材料装备研究所有限公司
View PDF0 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Medical image registration is the process of spatially matching two medical images. To register medical image A to medical image B, use medical image B as a reference image and medical image A as a floating image to obtain medical image A Registration to the deformation field of medical image B, the common medical image registration method is mainly based on the gray value registration method, but this method has poor registration accuracy and registration accuracy when the medical image quality is poor and the deformation is large. Accurate speed is not ideal
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0026] The specific embodiments of the present invention will be further described below in conjunction with the accompanying drawings.
[0027] This application discloses a medical image registration method based on IDC algorithm, please refer to figure 1 Shown in the flow chart, the method comprises the steps:
[0028] In step S1, the electronic probe is used to scan and analyze the operation area and select several reference points. This application uses electronic probes to select points, compared with some existing methods that require implanting titanium screws in the human body as a reference, causing less additional damage to patients.
[0029] In step S2, the preoperative medical image of the operation area is obtained as a floating image F, and the intraoperative medical image of the operation area is obtained as a fixed image S.
[0030] Step S3, determining the position of each reference point in the floating image to obtain a floating image point set, which incl...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The invention discloses a medical image registration method based on an IDC algorithm, and relates to the technical field of medical treatment, and the method comprises the steps: carrying out the scanning analysis of an operation region through an electronic probe, selecting a plurality of reference points, respectively determining the positions of all reference points in a floating image and a fixed image, and obtaining a floating image point set and a fixed image point set; determining the nearest point of each point in the floating image point set in the fixed image point set as a matching point to form a matching point pair, and obtaining an initial loss function according to the Euclidean distance of the matching point pair; and decomposing a matrix formed by each group of matching point pairs by utilizing an SVD (singular value decomposition) algorithm to obtain a rotation matrix and a translation matrix, and processing and updating floating function iteration until an initial loss function does not exceed a loss function threshold value, and importing the floating image and the fixed image into an improved registration neural network to obtain a deformation field. The method is excellent in registration precision and registration speed, and small in harm to a patient.
Description
technical field [0001] The invention relates to the field of medical technology, in particular to a medical image registration method based on an IDC algorithm. Background technique [0002] Medical image registration technology is the basis of medical image processing, and plays an important role in image information fusion, auxiliary diagnosis, surgical planning and interventional navigation system. Medical image registration is the process of spatially matching two medical images. To register medical image A to medical image B, use medical image B as a reference image and medical image A as a floating image to obtain medical image A Registration to the deformation field of medical image B, the common medical image registration method is mainly based on the gray value registration method, but this method has poor registration accuracy and registration accuracy when the medical image quality is poor and the deformation is large. Accurate speed is not ideal. Contents of t...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More Patent Type & Authority Applications(China)
IPC IPC(8): G06T7/33G06T7/11G06T7/136G06T7/187G06N3/04G06N3/08
CPCG06T7/33G06T7/11G06T7/136G06T7/187G06N3/08G06T2207/20081G06T2207/20084G06T2207/20132G06T2207/30004G06N3/045Y02T10/40
Inventor 张秋菊宁萌代霖昆
Owner 江苏集萃复合材料装备研究所有限公司