CN112102227A - Blood vessel optimal puncture point selection method based on blood vessel size characteristics - Google Patents
Blood vessel optimal puncture point selection method based on blood vessel size characteristics Download PDFInfo
- Publication number
- CN112102227A CN112102227A CN202010505894.5A CN202010505894A CN112102227A CN 112102227 A CN112102227 A CN 112102227A CN 202010505894 A CN202010505894 A CN 202010505894A CN 112102227 A CN112102227 A CN 112102227A
- Authority
- CN
- China
- Prior art keywords
- blood vessel
- image
- point
- puncture point
- optimal
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 210000004204 blood vessel Anatomy 0.000 title claims abstract description 240
- 238000010187 selection method Methods 0.000 title claims abstract description 6
- 230000009466 transformation Effects 0.000 claims abstract description 11
- 230000003044 adaptive effect Effects 0.000 claims abstract description 8
- 238000000034 method Methods 0.000 claims description 28
- 230000008569 process Effects 0.000 claims description 7
- 238000004364 calculation method Methods 0.000 claims description 6
- 238000001914 filtration Methods 0.000 claims description 6
- 230000000877 morphologic effect Effects 0.000 claims description 6
- 238000001514 detection method Methods 0.000 claims description 5
- 230000000694 effects Effects 0.000 claims description 4
- 239000008280 blood Substances 0.000 claims description 3
- 210000004369 blood Anatomy 0.000 claims description 3
- 210000003462 vein Anatomy 0.000 abstract description 10
- 238000000605 extraction Methods 0.000 abstract description 4
- 210000000707 wrist Anatomy 0.000 abstract 1
- 230000006870 function Effects 0.000 description 6
- 238000010241 blood sampling Methods 0.000 description 5
- 238000001802 infusion Methods 0.000 description 5
- 238000006243 chemical reaction Methods 0.000 description 3
- 238000001990 intravenous administration Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 2
- 238000005562 fading Methods 0.000 description 2
- 230000002349 favourable effect Effects 0.000 description 2
- 210000004209 hair Anatomy 0.000 description 2
- 239000011148 porous material Substances 0.000 description 2
- 206010002482 Angiosclerosis Diseases 0.000 description 1
- 206010011409 Cross infection Diseases 0.000 description 1
- 206010029803 Nosocomial infection Diseases 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
- 238000007920 subcutaneous administration Methods 0.000 description 1
- 210000004003 subcutaneous fat Anatomy 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0012—Biomedical image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/70—Denoising; Smoothing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/12—Edge-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/13—Edge detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/136—Segmentation; Edge detection involving thresholding
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/70—Determining position or orientation of objects or cameras
- G06T7/73—Determining position or orientation of objects or cameras using feature-based methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20024—Filtering details
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20036—Morphological image processing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30004—Biomedical image processing
- G06T2207/30101—Blood vessel; Artery; Vein; Vascular
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Radiology & Medical Imaging (AREA)
- Quality & Reliability (AREA)
- Image Processing (AREA)
Abstract
The invention discloses a blood vessel optimal puncture point selection method based on blood vessel size characteristics, which is characterized in that a central area of a vein infrared blood vessel image at an arm, a back of a hand or a wrist is selected as an interested area to be denoised, contrast is limited to be enhanced by an adaptive histogram equalization algorithm, adaptive threshold value binaryzation, image morphology processing, blood vessel contour extraction, traversal search of a blood vessel contour area with the largest area in each blood vessel contour, distance transformation algorithm extraction of a blood vessel center line and each position radius of a blood vessel, selection of a point with the largest blood vessel radius on the blood vessel center line and the relative curvature of the blood vessel center line smaller than a set threshold value as an optimal puncture point of the blood vessel, and obtaining the tangential direction of the point on the blood vessel center line. The invention realizes the automatic selection of the blood vessel puncture point on the infrared blood vessel image, has higher blood vessel puncture precision, and simultaneously improves the safety and the efficiency of blood vessel puncture.
Description
Technical Field
The invention relates to the technical field of biological characteristic information perception and identification, in particular to a blood vessel optimal puncture point selection method based on blood vessel size characteristics.
Background
The manual venipuncture mode is limited by the working fatigue of medical staff when facing a large number of patients, the efficiency is low, a large number of patients are easy to wait for hospitalization at the peak period of hospitalization, and the venipuncture is limited by the working experience of the medical staff, the difficulty in venipuncture operation of the medical staff who newly contact the venipuncture is high, the condition of the patient is unknown, if the venipuncture process is improper, cross infection is easy to cause, and the risk of the medical staff working is increased. In addition, the physique of the hospitalized patient is different, the clear outline position of the blood vessel cannot be observed by human eyes of some patients due to reasons of angiosclerosis, fine blood vessel, thick subcutaneous fat, dark skin color and the like, the operation difficulty of venipuncture of medical workers is increased invisibly, the success rate of one-time venipuncture is greatly reduced, and the hospitalization experience of the patients is brought with pain. Therefore, a new vein puncture point selection algorithm with higher accuracy and better safety of the selected point is needed to be designed according to the principle that the medical staff with experience selects the optimal vein puncture point.
Disclosure of Invention
The invention provides a blood vessel optimal puncture point selection method based on blood vessel size characteristics, which realizes automatic extraction of blood vessel puncture points on an infrared blood vessel image, has higher blood vessel puncture accuracy, and simultaneously improves the safety and efficiency of blood vessel puncture, and the method comprises the following steps:
selecting a central area of the infrared blood vessel image as an interested area for selecting an optimal puncture point of the blood vessel;
denoising and Gaussian filtering the image of the region of interest to obtain a denoised image;
carrying out image enhancement processing on the de-noised image to obtain an enhanced image;
carrying out image binarization processing on the enhanced image to obtain a binarized blood vessel image;
carrying out image morphological processing on the binary blood vessel image to obtain a blood vessel contour image;
carrying out contour detection processing on the blood vessel contour image to obtain a blood vessel maximum contour image;
processing the blood vessel maximum contour image by adopting a distance transformation algorithm, and extracting each point position on a blood vessel central line and each position radius of the blood vessel;
and selecting points, the curvatures of which meet the threshold requirement and the vessel radius of which is as large as possible, on the vessel central line as the optimal puncture point of the vessel according to the positions of the vessel central line and the radius of the vessel at the positions.
Specifically, the image enhancement processing specifically includes:
and carrying out image enhancement processing by adopting a contrast-limited self-adaptive histogram equalization algorithm.
Specifically, the image binarization processing specifically includes:
and (4) carrying out image binarization processing by adopting an adaptive threshold value binarization method.
Specifically, the image morphology processing specifically includes:
the image morphological opening and closing operation is adopted to process the image, the opening operation is carried out firstly and then the closing operation is carried out, or the closing operation is carried out firstly and then the opening operation is carried out, so that the effects of removing background noise points in the image and filling holes in a blood vessel contour region are achieved, and the blood vessel contour is smooth.
Specifically, the contour detection processing specifically includes:
and (5) extracting the blood vessel contour of the image, searching the blood vessel contour region with the largest blood vessel contour area and separating.
Specifically, the distance transformation algorithm processing specifically includes:
the distance transformation algorithm can obtain the pixel distance from each point in the blood vessel area in the blood vessel outline image to the image background, each row of distance maximum value points are selected as the points on the blood vessel central line, and the value obtained by the distance transformation algorithm of each point on the central line is also the blood vessel radius value of each position of the blood vessel.
Specifically, the specific process of selecting the point with the curvature on the center line of the blood vessel meeting the threshold requirement and the radius of the blood vessel as large as possible as the optimal puncture point of the blood vessel comprises the following steps:
selecting a point on the blood vessel central line where the radius of the blood vessel is maximum as a preselected puncture point;
obtaining a blood vessel centerline curve equation according to each point position on the blood vessel centerline, calculating to obtain the tangential direction of the preselected puncture point on the blood vessel centerline, and calculating the curvature of the preselected puncture point on the blood vessel centerline curve equation;
when the curvature of the preselected puncture point is larger than a set threshold value, excluding the point position, and reselecting the optimal puncture point of the blood vessel from the point concentration on the center line of the residual blood vessel according to the principle of maximum radius of the blood vessel;
and selecting the puncture point with the curvature smaller than the set threshold value as the final optimal puncture point of the blood vessel until the puncture point with the curvature smaller than the set threshold value is obtained.
Specifically, the blood vessel centerline curve equation is obtained by least square fitting based on a cubic polynomial according to the image coordinates of each point on the blood vessel centerline, and the expression is as follows:
f(x)＝a0+a1x+a2x2+a3x3 (1)
wherein f (x) is a vessel centerline fitting curve equation; x is the image coordinate of a point on the center line of the blood vessel; a is0～a3Is a polynomial coefficient;
according to the least square method, the fitting curve equation and the actual point residual error sum of squares are required to be minimum, and the expression is as follows:
wherein E is the sum of the squares of the residuals, requiring E to be minimal; f (x)i) Fitting coordinates of points on a curve for the centerline of the vessel; x is the number ofi、yiThe image coordinates of points on the center line of the blood vessel;
specifically, the tangent direction of the optimal blood vessel puncture point on the blood vessel centerline is determined by selecting points of a blood vessel centerline curve equation according to the puncture direction of the blood taking needle on the optimal blood vessel puncture point by a set number of points, and the calculation expression is as follows:
wherein k is the average slope at the optimal puncture point; n is the number of points on the central line of the blood vessel set by the optimal puncture point of the blood vessel along the puncture direction; f' (x)i) Fitting points on the center line of the blood vessel to obtain a first derivative function of a curve equation; x is the number ofiImage coordinates of points on the blood vessel centerline along the puncture direction for an optimal puncture point of the blood vessel, where x0And selecting the optimal puncture point image coordinates of the blood vessel.
Specifically, the curvature calculation expression of the selected optimal puncture point on the blood vessel centerline curve equation is as follows:
wherein K is curvature, and y' are respectively a first derivative function and a second derivative function of the curve equation of the centerline of the blood vessel obtained by fitting.
Compared with the prior art, the embodiment of the invention has the beneficial effects that:
(1) the invention provides a vein optimal puncture point selection algorithm based on vein size characteristics aiming at an infrared blood vessel image, extracts a blood vessel with the largest outline area in the infrared blood vessel image by imitating the principle of selecting a needle-inserting puncture point by artificial venipuncture, accords with the selection principle that medical personnel selects a subcutaneous superficial blood vessel, the blood vessel is thickest and clearest, and the blood vessel is straightest and most convenient to puncture, realizes automatic selection of a vein puncture point, and improves the accuracy and reliability of selection of an optimal vein puncture point and the safety of venipuncture.
(2) The blood vessel optimal puncture point selection algorithm based on the vein size characteristics is simple and convenient to operate and calculate, easy to implement and high in reliability, and the efficiency and the precision of extraction of puncture points are effectively improved. The invention is applied to the field of intelligent medical instruments, such as an intelligent intravenous infusion robot and a venous blood sampling robot, can liberate medical staff from complicated venipuncture work and high-risk work environments, is favorable for intelligently selecting an optimal puncture point and automatically completing the intravenous infusion and blood sampling actions of the intelligent intravenous infusion robot and the venous blood sampling robot, and is favorable for popularization and application of some intelligent medical instruments and equipment.
Drawings
Fig. 1 is a schematic flow chart of a method for selecting an optimal puncture point of a blood vessel based on a blood vessel size characteristic according to an embodiment of the present invention;
fig. 2 is a blood vessel original drawing (a) of a blood-sampled arm and a final selected puncture point effect drawing (b) provided by an embodiment of the present invention;
fig. 3 is a schematic diagram of a blood vessel optimal puncture point selection process based on blood vessel size characteristics according to an embodiment of the present invention;
fig. 4 is a schematic diagram of a blood vessel contour, a blood vessel centerline, an optimal puncture point and a tangent line of the blood vessel centerline at the puncture point according to an embodiment of the present invention.
Wherein: 1 is the vessel contour; 2 is the vessel centerline; 3 is the selected optimal puncture point; 4 is the tangent of the selected optimal puncture point on the centerline of the vessel.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is further described in detail below with reference to the accompanying drawings and examples. The present invention will be described in further detail. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention. In addition, the technical features involved in the embodiments of the present invention described below may be combined with each other as long as they do not conflict with each other.
Please refer to fig. 1, fig. 2, fig. 3 and fig. 4, wherein the reference numerals in fig. 2 and fig. 4 represent: 1 is the vessel contour; 2 is the vessel centerline; 3 is the selected optimal puncture point; 4 is the tangent of the selected optimal puncture point on the centerline of the vessel.
The optimal blood vessel puncture point selection algorithm method based on the vein size characteristics provided by the preferred embodiment of the invention mainly comprises the following steps:
step S110: the central area of the infrared blood vessel image shown in fig. 2(a) is selected as the region of interest for selecting the optimal puncture point for blood vessel puncture, so as to eliminate the influence of image background interference.
Specifically, firstly, a near-infrared camera is used to photograph the skin of a blood vessel part to be subjected to venipuncture, the blood vessel direction is required to be along the vertical direction of the image, and an infrared blood vessel image is obtained by photographing, as shown in fig. 2 (a). Then, a region of interest (target region) in the center of the infrared image is extracted, and the influence of the skin contour on the image is removed.
Step S120: denoising and Gaussian filtering are carried out on the selected infrared blood vessel region-of-interest image; noise points such as skin pores, hairs and spots exist near the blood vessel region in the infrared blood vessel image, and for the situation, denoising and Gaussian filtering are carried out on the infrared blood vessel image, so that the blood vessel contour becomes smooth while denoising and fading the noise points.
Specifically, denoising and gaussian filtering normalization processing are performed on the infrared blood vessel image of the region of interest in fig. 2(a), so that the blood vessel contour becomes smooth while denoising and fading noise points of the infrared blood vessel image of the region of interest, and fig. 3(a) is obtained.
Step S130: carrying out image enhancement processing on the blood vessel region of the figure 3(a) by adopting a contrast-limited adaptive histogram equalization algorithm (CLAHE); since the image contrast is reduced after denoising and gaussian filtering the infrared blood vessel image, the blood vessel region in fig. 3(a) can be enhanced by using a contrast-limited adaptive histogram equalization algorithm (CLAHE), as shown in fig. 3 (b).
Specifically, the image of fig. 3(a) is subjected to a constrained contrast adaptive histogram equalization algorithm (CLAHE) enhancement using a convolution kernel size of 8 × 8 and a contrast threshold of 4.
Step S140: carrying out image binarization processing on the image in the step (b) in the step (a) of FIG. 3 by adopting an adaptive threshold value binarization method; because the infrared blood vessel images of different patients have different qualities, the skin complexion factor directly influences the outline range of the blood vessel region in the image relative to the image skin background, aiming at the problem, the accuracy and the universality of extracting the blood vessel outline can be effectively improved by adopting the self-adaptive threshold value binarization method, and the image (c) is obtained after the self-adaptive threshold value binarization.
Step S150: after the image morphology opening and closing operation is respectively adopted to perform morphology processing on the image (c), and the infrared blood vessel image is binarized, as shown in the image (c), a plurality of skin pores, hairs and spots can form small spots to be distributed around the blood vessel contour, aiming at the situation, the image morphology opening and closing operation is adopted to remove burr noise points of the image background, and simultaneously, cavities in the blood vessel contour region are filled, so that the blood vessel contour is smooth, and the image 3(d) is obtained.
Specifically, fig. 3(c) is subjected to a closing operation and then an opening operation to obtain fig. 3(d), and the size of the morphological opening and closing operation convolution kernel is 24 × 24.
Step S160: extracting the blood vessel contour of the image 3(d) by contour detection, traversing and searching the blood vessel contour region with the largest blood vessel contour area, and separating to obtain a new blood vessel contour image, as shown in the image 3 (e); after the blood vessel contour of the infrared blood vessel image is extracted, a plurality of blood vessel contours with different sizes can be obtained, the obtained blood vessel contour with the largest area meets the principle that the blood vessel is thickest and most convenient to prick in manual selection of venipuncture points by traversing the blood vessel contour region with the largest blood vessel contour area, and then the blood vessel contour with the largest area is separated to obtain a new blood vessel image.
Specifically, the vessel contour is searched in a traversal manner, and only the vessel outer contour is traversed, after the vessel contour with the largest area is found, an image only containing the largest vessel contour is drawn, and then black and white inversion is performed on the image, so that fig. 3(e) is obtained.
Step S170: and (e) processing the image in the step (3) by adopting a distance conversion algorithm to obtain the distance from each point of the maximum outline area of the blood vessel to the image background, and further obtain each point position on the central line of the blood vessel and each position radius of the blood vessel.
Specifically, since the principle of the distance transformation algorithm is to calculate the shortest distance from each point in the white foreground region of the binary image to each point in the black background region of the image, the blood vessel contour needs to be turned from black to white, and the background becomes black, as shown in fig. 3 (e). The distance conversion algorithm used therein uses the euclidean distance to calculate the distance from each point in the white blood vessel region to the black background in fig. 3 (e).
Specifically, after the distance transformation algorithm obtains the pixel distance from each point in the blood vessel region in the blood vessel contour image to the image background, the image coordinates of each point on the blood vessel center line and the radius of each position of the blood vessel are obtained by scanning the maximum value of the distance from each row of pixel points in the blood vessel contour region to the background and the position of the point.
Step S180: according to the positions of the blood vessel center line and the radius of the blood vessel, selecting the point with the largest radius of the blood vessel on the blood vessel center line as a preselected puncture point, as shown in fig. 4-3; obtaining a blood vessel central line curve equation by fitting each point image coordinate on the blood vessel central line according to a least square method based on a cubic polynomial, as shown in fig. 4-2, and calculating to obtain the tangential direction of the preselected puncture point on the blood vessel central line, as shown in fig. 4-4; meanwhile, calculating the curvature of a preselected puncture point on a curve equation of the centerline of the blood vessel, and judging whether the curvature of the preselected puncture point meets the requirement of a threshold value; when the curvature of the preselected puncture point is larger than a set threshold value, excluding the point position, and reselecting the optimal puncture point of the blood vessel from the point concentration on the center line of the residual blood vessel according to the principle of maximum radius of the blood vessel; and selecting the puncture point with the curvature smaller than the set threshold value as the optimal puncture point of the blood vessel until the puncture point with the curvature smaller than the set threshold value is obtained. Specifically, in step S180, a point on the centerline of the blood vessel where the result of the concentrated distance conversion is the largest is selected as the to-be-determined optimal puncture point, which is the point where the radius of the blood vessel is the largest.
Preferably, the selected optimal puncture point position, the contour of the located blood vessel, and the centerline information may be superimposed on the image of the blood vessel original (fig. 2(a)), so that the medical staff can more intuitively observe the actual effect of the selected optimal puncture point on the whole blood vessel original, as shown in fig. 2 (b).
Specifically, in step S180, the blood vessel centerline curve equation is obtained by fitting a least square method based on a cubic polynomial according to each point position on the blood vessel centerline, and the expression is as follows:
f(x)＝a0+a1x+a2x2+a3x3 (1)
wherein f (x) is a vessel centerline fitting curve equation; x is the image coordinate of a point on the center line of the blood vessel; a is0～a3Is a polynomial coefficient;
according to the least square method, the fitting curve equation and the actual point residual error sum of squares are required to be minimum, and the expression is as follows:
wherein E is the sum of the squares of the residuals, requiring E to be minimal; f (x)i) Fitting coordinates of points on a curve for the centerline of the vessel; x is the number ofi、yiImage coordinates for points on the centerline of a blood vessel
Specifically, in step S180, the tangent direction of the optimal puncture point of the blood vessel on the blood vessel centerline is selected according to the puncture direction of the blood sampling or infusion needle on the optimal puncture point of the blood vessel by the set number of points to calculate the slope average, and the calculation expression is as follows:
wherein k is the average slope at the optimal puncture point; n is the number of points on the central line of the blood vessel set by the optimal puncture point of the blood vessel along the puncture direction; f' (x)i) In the blood vesselFitting points on the core line to obtain a first derivative function of a curve equation; x is the number ofiImage coordinates of points on the blood vessel centerline along the puncture direction for an optimal puncture point of the blood vessel, where x0And selecting the optimal puncture point image coordinates of the blood vessel.
Specifically, in step S180, the curvature calculation expression of the selected optimal puncture point on the blood vessel centerline curve equation is as follows:
wherein K is curvature, and y' are respectively a first derivative function and a second derivative function of the curve equation of the centerline of the blood vessel obtained by fitting.
According to the blood vessel optimal puncture point selection algorithm based on the blood vessel size characteristics, the blood vessel outline position, the blood vessel center line position, the tangent slope and curvature of the blood vessel to be subjected to venipuncture, and the blood vessel size characteristic information of each radius of the blood vessel are obtained by processing the vein infrared blood vessel images of the arm, the back of the hand, the middle elbow and the like, so that the optimal puncture point is selected, the automatic selection of the blood vessel puncture point is realized, the accuracy and reliability of the selection of the optimal puncture point and the safety of venipuncture are improved, and the problem that an intelligent infusion or blood sampling robot cannot select the accurate and reliable puncture point is solved.
It will be understood by those skilled in the art that the foregoing is only a preferred embodiment of the present invention, and is not intended to limit the invention, and that any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the scope of the present invention.
Claims (10)
1. A blood vessel optimal puncture point selection method based on blood vessel size characteristics is characterized in that,
selecting a central area of the infrared blood vessel image as an interested area for selecting an optimal puncture point of the blood vessel;
denoising and Gaussian filtering the image of the region of interest to obtain a denoised image;
carrying out image enhancement processing on the de-noised image to obtain an enhanced image;
carrying out image binarization processing on the enhanced image to obtain a binarized blood vessel image;
carrying out image morphological processing on the binary blood vessel image to obtain a blood vessel contour image;
carrying out contour detection processing on the blood vessel contour image to obtain a blood vessel maximum contour image;
processing the blood vessel maximum contour image by adopting a distance transformation algorithm, and extracting each point position on a blood vessel central line and each position radius of the blood vessel;
and selecting points, the curvatures of which meet the threshold requirement and the vessel radius of which is as large as possible, on the vessel central line as the optimal puncture point of the vessel according to the positions of the vessel central line and the radius of the vessel at the positions.
2. The method for selecting an optimal puncture point of a blood vessel according to claim 1, wherein the image enhancement process specifically comprises:
and carrying out image enhancement processing by adopting a contrast-limited self-adaptive histogram equalization algorithm.
3. The method for selecting the optimal puncture point of the blood vessel based on the blood vessel size characteristic according to claim 1, wherein the image binarization processing specifically comprises:
and (4) carrying out image binarization processing by adopting an adaptive threshold value binarization method.
4. The method for selecting an optimal puncture point of a blood vessel based on the blood vessel size characteristic according to claim 1, wherein the image morphological processing specifically comprises:
the image morphological opening and closing operation is adopted to process the image, the opening operation is carried out firstly and then the closing operation is carried out, or the closing operation is carried out firstly and then the opening operation is carried out, so that the effects of removing background noise points in the image and filling holes in the outline region of the blood vessel are achieved, and the outline of the blood vessel is smooth.
5. The method for selecting an optimal puncture point of a blood vessel based on the blood vessel size characteristic according to claim 1, wherein the contour detection processing specifically comprises:
and (5) extracting the blood vessel contour of the image, searching the blood vessel contour region with the largest blood vessel contour area and separating.
6. The method for selecting an optimal puncture point of a blood vessel based on the blood vessel size characteristic according to claim 1, wherein the distance transformation algorithm is specifically processed as follows:
the distance transformation algorithm can obtain the pixel distance from each point in the blood vessel area in the blood vessel outline image to the image background, each row of distance maximum value points are selected as the points on the blood vessel central line, and the value of the point on the blood vessel central line obtained by the distance transformation algorithm is also the blood vessel radius value of each position of the blood vessel.
7. The method for selecting the optimal puncture point of the blood vessel based on the blood vessel size characteristic according to claim 1, wherein the specific process of selecting the point on the center line of the blood vessel, the curvature of which meets the threshold requirement and the radius of the blood vessel is as large as possible, as the optimal puncture point of the blood vessel comprises the following steps:
selecting a point on the blood vessel central line where the radius of the blood vessel is maximum as a preselected puncture point;
obtaining a blood vessel centerline curve equation according to each point position on the blood vessel centerline, calculating to obtain the tangential direction of the preselected puncture point on the blood vessel centerline, and calculating the curvature of the preselected puncture point on the blood vessel centerline curve equation;
when the curvature of the preselected puncture point is larger than a set threshold value, excluding the point position, and reselecting the optimal puncture point of the blood vessel from the point concentration on the center line of the residual blood vessel according to the principle of maximum radius of the blood vessel;
and selecting the puncture point with the curvature smaller than the set threshold value as the final optimal puncture point of the blood vessel until the puncture point with the curvature smaller than the set threshold value is obtained.
8. The method for selecting an optimal puncture point of a blood vessel according to claim 7, wherein the curve equation of the center line of the blood vessel is obtained by least square fitting based on cubic polynomial according to the coordinates of each point image on the center line of the blood vessel, and the expression is as follows:
f(x)＝a0+a1x+a2x2+a3x3 (1)
wherein f (x) is a vessel centerline fitting curve equation; x is the image coordinate of a point on the center line of the blood vessel; a is0～a3Is a polynomial coefficient;
according to the least square method, the fitting curve equation and the actual point residual error sum of squares are required to be minimum, and the expression is as follows:
wherein E is the sum of the squares of the residuals, requiring E to be minimal; f (x)i) Fitting coordinates of points on a curve for the centerline of the vessel; x is the number ofi、yiIs the image coordinate of the point on the center line of the blood vessel.
9. The method for selecting the optimal blood vessel puncture point based on the blood vessel size characteristic according to claim 7, wherein the tangent direction of the optimal blood vessel puncture point on the blood vessel centerline is determined by selecting points of a curve equation of the blood vessel centerline according to the puncture direction of the blood taking needle on the optimal blood vessel puncture point by a set number of points, and calculating the average slope of the tangent line, wherein the calculation expression is as follows:
wherein k is the average slope at the optimal puncture point; n is the number of points on the central line of the blood vessel set by the optimal puncture point of the blood vessel along the puncture direction; f' (x)i) Obtained by fitting points on the centerline of the vesselA first derivative function of a curve equation; x is the number ofiImage coordinates of points on the blood vessel centerline along the puncture direction for an optimal puncture point of the blood vessel, where x0And selecting the optimal puncture point image coordinates of the blood vessel.
10. The method for selecting an optimal puncture point of a blood vessel according to claim 7, wherein the curvature calculation expression of the selected optimal puncture point on the curve equation of the centerline of the blood vessel is as follows:
wherein K is curvature, and y' are respectively a first derivative function and a second derivative function of the curve equation of the centerline of the blood vessel obtained by fitting.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010505894.5A CN112102227A (en) | 2020-06-05 | 2020-06-05 | Blood vessel optimal puncture point selection method based on blood vessel size characteristics |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010505894.5A CN112102227A (en) | 2020-06-05 | 2020-06-05 | Blood vessel optimal puncture point selection method based on blood vessel size characteristics |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112102227A true CN112102227A (en) | 2020-12-18 |
Family
ID=73750067
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010505894.5A Pending CN112102227A (en) | 2020-06-05 | 2020-06-05 | Blood vessel optimal puncture point selection method based on blood vessel size characteristics |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112102227A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112950578A (en) * | 2021-02-26 | 2021-06-11 | 北京伟浩君智能技术有限公司 | Blood vessel identification and positioning method and device based on two-dimensional image enhancement |
| CN113011333A (en) * | 2021-03-19 | 2021-06-22 | 哈尔滨工业大学 | System and method for obtaining optimal venipuncture point and direction based on near-infrared image |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101393644A (en) * | 2008-08-15 | 2009-03-25 | 华中科技大学 | Hepatic portal vein tree modeling method and system thereof |
| CN103914814A (en) * | 2012-12-28 | 2014-07-09 | 北京思创贯宇科技开发有限公司 | Image fusion method and system for CT coronary image and XA angiography image |
| CN104361626A (en) * | 2014-09-29 | 2015-02-18 | 北京理工大学 | Subcutaneous vein three-dimensional reconstruction method based on hybrid matching strategy |
| CN104408453A (en) * | 2014-09-29 | 2015-03-11 | 北京理工大学 | Near-infrared subcutaneous vein segmentation method based on multi-feature clustering |
| CN107361844A (en) * | 2017-06-20 | 2017-11-21 | 上海交通大学 | A kind of safety protecting method in robot assisted cardiovascular interventional operation |
| CN110176004A (en) * | 2019-04-24 | 2019-08-27 | 艾瑞迈迪科技石家庄有限公司 | A kind of liver subsection method and system |
-
2020
- 2020-06-05 CN CN202010505894.5A patent/CN112102227A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101393644A (en) * | 2008-08-15 | 2009-03-25 | 华中科技大学 | Hepatic portal vein tree modeling method and system thereof |
| CN103914814A (en) * | 2012-12-28 | 2014-07-09 | 北京思创贯宇科技开发有限公司 | Image fusion method and system for CT coronary image and XA angiography image |
| CN104361626A (en) * | 2014-09-29 | 2015-02-18 | 北京理工大学 | Subcutaneous vein three-dimensional reconstruction method based on hybrid matching strategy |
| CN104408453A (en) * | 2014-09-29 | 2015-03-11 | 北京理工大学 | Near-infrared subcutaneous vein segmentation method based on multi-feature clustering |
| CN107361844A (en) * | 2017-06-20 | 2017-11-21 | 上海交通大学 | A kind of safety protecting method in robot assisted cardiovascular interventional operation |
| CN110176004A (en) * | 2019-04-24 | 2019-08-27 | 艾瑞迈迪科技石家庄有限公司 | A kind of liver subsection method and system |
Non-Patent Citations (1)
| Title |
|---|
| 李翊华 等: "基于微血栓运动分析的微血管特征结构自动提取", 生物物理学报, no. 02, 30 June 1996 (1996-06-30) * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112950578A (en) * | 2021-02-26 | 2021-06-11 | 北京伟浩君智能技术有限公司 | Blood vessel identification and positioning method and device based on two-dimensional image enhancement |
| CN113011333A (en) * | 2021-03-19 | 2021-06-22 | 哈尔滨工业大学 | System and method for obtaining optimal venipuncture point and direction based on near-infrared image |
| CN113011333B (en) * | 2021-03-19 | 2022-11-18 | 哈尔滨工业大学 | System and method for obtaining optimal venipuncture point and direction based on near-infrared image |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106156754B (en) | A kind of multi-modal preprocess method of finger based on maximum circumscribed matrix region of interesting extraction and bilateral filtering | |
| Zhang et al. | Finger vein image enhancement based on guided tri-Gaussian filters | |
| Gagnon et al. | Procedure to detect anatomical structures in optical fundus images | |
| CN107564048B (en) | Feature registration method based on bifurcation point | |
| CN112102227A (en) | Blood vessel optimal puncture point selection method based on blood vessel size characteristics | |
| CN110751636B (en) | Fundus image retinal arteriosclerosis detection method based on improved coding and decoding network | |
| CN110555380A (en) | Finger vein identification method based on Center Loss function | |
| CN117649357B (en) | Ultrasonic image processing method based on image enhancement | |
| CN107194928B (en) | Vision-based automatic extraction method for vein blood sampling needle pricking points | |
| CN112883824A (en) | Finger vein feature recognition device for intelligent blood sampling and recognition method thereof | |
| CN109583331A (en) | Human wrist arteries and veins mouth position precise positioning method based on deep learning | |
| CN108280448B (en) | Finger vein pressing graph distinguishing method and device and finger vein identification method | |
| CN111339828A (en) | Vein developing identification method based on combination of infrared image and ultrasonic Doppler | |
| CN112137721B (en) | Method for positioning needle point and vessel wall depth of puncture needle based on ultrasonic image | |
| CN112075981B (en) | Venipuncture robot control method, device and computer-readable storage medium | |
| CN112183518B (en) | Automatic vein target determination method, device and equipment | |
| CN111899272B (en) | Fundus image blood vessel segmentation method based on coupling neural network and line connector | |
| CN109886220A (en) | A kind of characteristics extraction and comparison algorithm of finger vein image | |
| Sutanty et al. | Retinal blood vessel segmentation and bifurcation detection using combined filters | |
| CN111144331A (en) | Elbow vein image elbow median vein identification method and elbow image acquisition device | |
| CN114677713A (en) | Near-infrared light-based arm vein blood sampling point identification method and system | |
| Guo et al. | A novel algorithm of dorsal hand vein image segmentation by integrating matched filter and local binary fitting level set model | |
| CN112927199B (en) | Method for selecting injection point for non-intravenous injection treatment | |
| CN108304776A (en) | Refer to the method, apparatus and storage medium of vein image intercommunication identification | |
| CN108564031A (en) | Single-frame near-infrared palm image recognition method based on multi-mode fusion |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |