CN114612475A - Bile duct support specification selection method and device - Google Patents

Bile duct support specification selection method and device Download PDF

Info

Publication number
CN114612475A
CN114612475A CN202210511435.7A CN202210511435A CN114612475A CN 114612475 A CN114612475 A CN 114612475A CN 202210511435 A CN202210511435 A CN 202210511435A CN 114612475 A CN114612475 A CN 114612475A
Authority
CN
China
Prior art keywords
guide wire
bile duct
area
duodenoscope
pixel
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.)
Granted
Application number
CN202210511435.7A
Other languages
Chinese (zh)
Other versions
CN114612475B (en
Inventor
季锐
冯健
邵学军
邵宏亭
张文琳
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Qingdao Medcare Digital Engineering Co ltd
Qilu Hospital of Shandong University
Original Assignee
Qingdao Medcare Digital Engineering Co ltd
Qilu Hospital of Shandong University
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Qingdao Medcare Digital Engineering Co ltd, Qilu Hospital of Shandong University filed Critical Qingdao Medcare Digital Engineering Co ltd
Priority to CN202210511435.7A priority Critical patent/CN114612475B/en
Publication of CN114612475A publication Critical patent/CN114612475A/en
Application granted granted Critical
Publication of CN114612475B publication Critical patent/CN114612475B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00Image analysis
    • G06T7/0002Inspection of images, e.g. flaw detection
    • G06T7/0012Biomedical image inspection
    • AHUMAN NECESSITIES
    • A61MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61BDIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B1/00Instruments for performing medical examinations of the interior of cavities or tubes of the body by visual or photographical inspection, e.g. endoscopes; Illuminating arrangements therefor
    • A61B1/273Instruments for performing medical examinations of the interior of cavities or tubes of the body by visual or photographical inspection, e.g. endoscopes; Illuminating arrangements therefor for the upper alimentary canal, e.g. oesophagoscopes, gastroscopes
    • AHUMAN NECESSITIES
    • A61MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61FFILTERS IMPLANTABLE INTO BLOOD VESSELS; PROSTHESES; DEVICES PROVIDING PATENCY TO, OR PREVENTING COLLAPSING OF, TUBULAR STRUCTURES OF THE BODY, e.g. STENTS; ORTHOPAEDIC, NURSING OR CONTRACEPTIVE DEVICES; FOMENTATION; TREATMENT OR PROTECTION OF EYES OR EARS; BANDAGES, DRESSINGS OR ABSORBENT PADS; FIRST-AID KITS
    • A61F2/00Filters implantable into blood vessels; Prostheses, i.e. artificial substitutes or replacements for parts of the body; Appliances for connecting them with the body; Devices providing patency to, or preventing collapsing of, tubular structures of the body, e.g. stents
    • A61F2/02Prostheses implantable into the body
    • A61F2/04Hollow or tubular parts of organs, e.g. bladders, tracheae, bronchi or bile ducts
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00Pattern recognition
    • G06F18/20Analysing
    • G06F18/23Clustering techniques
    • G06F18/232Non-hierarchical techniques
    • G06F18/2321Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00Image analysis
    • G06T7/10Segmentation; Edge detection
    • G06T7/11Region-based segmentation
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00Image analysis
    • G06T7/60Analysis of geometric attributes
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00Image analysis
    • G06T7/60Analysis of geometric attributes
    • G06T7/62Analysis of geometric attributes of area, perimeter, diameter or volume
    • AHUMAN NECESSITIES
    • A61MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61FFILTERS IMPLANTABLE INTO BLOOD VESSELS; PROSTHESES; DEVICES PROVIDING PATENCY TO, OR PREVENTING COLLAPSING OF, TUBULAR STRUCTURES OF THE BODY, e.g. STENTS; ORTHOPAEDIC, NURSING OR CONTRACEPTIVE DEVICES; FOMENTATION; TREATMENT OR PROTECTION OF EYES OR EARS; BANDAGES, DRESSINGS OR ABSORBENT PADS; FIRST-AID KITS
    • A61F2/00Filters implantable into blood vessels; Prostheses, i.e. artificial substitutes or replacements for parts of the body; Appliances for connecting them with the body; Devices providing patency to, or preventing collapsing of, tubular structures of the body, e.g. stents
    • A61F2/02Prostheses implantable into the body
    • A61F2/04Hollow or tubular parts of organs, e.g. bladders, tracheae, bronchi or bile ducts
    • A61F2002/041Bile ducts
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00Indexing scheme for image analysis or image enhancement
    • G06T2207/10Image acquisition modality
    • G06T2207/10068Endoscopic image
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00Indexing scheme for image analysis or image enhancement
    • G06T2207/30Subject of image; Context of image processing
    • G06T2207/30004Biomedical image processing
    • G06T2207/30028Colon; Small intestine

Abstract

The invention relates to the technical field of endoscope image processing, in particular to a method and a device for selecting specification of a bile duct stent, wherein the method comprises the following steps: identifying a duodenoscope area, a guide wire area and a bile duct area in a contrast image in endoscopic retrograde cholangiopancreatography, and determining a duodenoscope body pixel diameter in the duodenoscope area; determining whether bile duct stenosis exists or not according to the guide wire area and the bile duct area; if the bile duct stenosis exists, determining a corresponding target guide wire section according to the type of the bile duct stenosis; determining the pixel length of a target guide wire section, and calculating the physical length of the target guide wire section according to the pixel diameter of a duodenoscope body, the physical diameter of the duodenoscope body and the pixel length of the target guide wire section; and determining the specification of the bile duct stent to be implanted according to the physical length of the target guide wire section. The invention improves the accuracy of the specification selection of the bile duct stent and shortens the time length of exposing the medical care personnel-level patient to electromagnetic radiation in the ERCP operation process.

Description

Bile duct support specification selection method and device
Technical Field
The invention relates to the technical field of endoscope image processing, in particular to a method and a device for selecting specification of a bile duct stent.
Background
Endoscopic Retrograde Cholangiopancreatography (abbreviated as ERCP) originated in the late 60 s, which is a procedure in which a physician inserts a duodenoscope into the descending part of the duodenum, and performs x-ray radiography after injecting a contrast medium through the papilla of the duodenum, thereby displaying the pancreaticobiliary duct. The technology can successfully display the structure of the pancreaticobiliary duct so as to diagnose diseases such as bile duct calculus, bile duct stenosis and the like. As diagnostic uses shift to therapeutic uses, quality control of ERCP is key to improving its success rate and reducing complications.
The selection of proper specification of the biliary duct stent is not only beneficial to the successful implantation of the stent, but also beneficial to the improvement of the prognosis of the patient. The selection of the length of the bracket is determined by measuring the distance between the proximal obstruction end under the X-ray and the duodenal papilla, and the specific calculation mode is that the proximal end of the bracket is positioned 1cm above the obstruction section, and the distal end of the bracket is positioned 1cm outside the duodenal papilla.
The current biliary stent specifications are selected based on physician personal operating experience estimates, and there are several specific calculation methods, such as endoscope diameter estimation, cone length estimation, biliary marker estimation, and guidewire length estimation with retraction between two points. These approaches are not only not accurate enough, but also have long radiation exposure times, causing unnecessary injury to both the operator and the patient's body. How to rapidly and accurately measure the length of the stent to be placed in the examination process and reduce the radioscopy time becomes an important quality control index.
Disclosure of Invention
In order to solve the technical problems or at least partially solve the technical problems, the invention provides a bile duct stent specification selection method and a bile duct stent specification selection device.
In a first aspect, an embodiment of the present invention provides a method for selecting a specification of a biliary duct stent, including:
identifying a duodenoscope area, a guide wire area and a bile duct area in a contrast image in endoscopic retrograde cholangiopancreatography, and determining the duodenoscope body pixel diameter in the duodenoscope area;
determining whether a bile duct stenosis exists or not according to the guide wire area and the bile duct area; if the bile duct stenosis exists, determining a corresponding target guide wire section according to the type of the bile duct stenosis;
determining the pixel length of the target guide wire section, and calculating the physical length of the target guide wire section according to the duodenoscope body pixel diameter, the duodenoscope body physical diameter and the pixel length of the target guide wire section;
and determining the specification of the bile duct stent to be implanted according to the physical length of the target guide wire section.
In a second aspect, an embodiment of the present invention provides a biliary duct stent specification selecting device,
the first determination module is used for identifying a duodenoscope area, a guide wire area and a bile duct area in a contrast image in endoscopic retrograde cholangiopancreatography and determining the duodenoscope body pixel diameter in the duodenoscope area;
The second determination module is used for determining whether bile duct stenosis exists according to the guide wire area and the bile duct area; if the bile duct stenosis exists, determining a corresponding target guide wire section according to the type of the bile duct stenosis;
the third determining module is used for determining the pixel length of the target guide wire section and calculating the physical length of the target guide wire section according to the pixel diameter of the duodenoscope body, the physical diameter of the duodenoscope body and the pixel length of the target guide wire section;
and the fourth determining module is used for determining the specification of the bile duct stent to be implanted according to the physical length of the target guide wire section.
The specification selection method and device for the bile duct stent provided by the embodiment of the invention are characterized in that a duodenoscope area, a guide wire area and a bile duct area in a contrast image are firstly identified, the pixel diameter of a duodenoscope body is calculated, whether the bile duct is narrow or not is judged based on the guide wire area and the bile duct area, if so, a key target guide wire section is determined, the physical length of the target guide wire section is calculated based on the pixel diameter of the duodenoscope body, and finally, the length of the bile duct stent to be placed is calculated according to the physical length of the target guide wire section. The method automatically calculates the length of the bile duct stent to be implanted through image processing, mathematical operation and other modes, and the mode does not need to be estimated based on personal operation experience of doctors, so that the accuracy of specification selection of the bile duct stent can be improved, the radiation exposure time can be greatly shortened, and radiation injury to doctors and patients is reduced.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the invention and together with the description, serve to explain the principles of the invention.
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, and it is obvious for those skilled in the art that other drawings can be obtained according to the drawings without inventive exercise.
FIG. 1a is a schematic flow chart of a bile duct stent specification selection method according to an embodiment of the invention;
FIG. 1b is a schematic flow chart illustrating a bile duct stent specification selection method according to another embodiment of the invention;
FIG. 2a is a schematic view of an embodiment of the present invention illustrating identification of segmented guidewire and duodenoscope;
FIG. 2b is a schematic representation of the identification of segmented duodenoscope and bile duct in one embodiment of the present invention;
FIG. 2c is a schematic view of the overlap between the guidewire of FIG. 2a and the bile duct of FIG. 2 b;
FIG. 3a is a schematic representation of a duodenoscope region of an embodiment of the present invention;
FIG. 3b is a schematic diagram of a first scope region and a second scope region obtained by performing a second classification clustering on the duodenoscope region shown in FIG. 3 a;
FIG. 3c is a schematic view of the first mirror region of FIG. 3 b;
FIG. 4a is a schematic view of a longitudinal line intersecting a guidewire;
FIG. 4b is a schematic view of FIG. 4a rotated 90 degrees clockwise;
fig. 5 is a block diagram of a biliary stent specification selecting device according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present invention. All other embodiments, which can be obtained by a person skilled in the art without any inventive step based on the embodiments of the present invention, are within the scope of the present invention.
In a first aspect, an embodiment of the present invention provides a method for selecting a specification of a biliary duct stent.
Referring to fig. 1a and 1b, the specification selection method for the bile duct stent provided by the embodiment of the invention comprises the following steps of S10-S40:
s10, identifying a duodenoscope area, a guide wire area and a bile duct area in a contrast image in endoscopic retrograde cholangiopancreatography, and determining the duodenoscope body pixel diameter in the duodenoscope area;
Among them, Endoscopic Retrograde Cholangiopancreatography, or Endoscopic Retrograde cholangio pancreatography, abbreviated as ERCP. A contrast image is generated during the process and the method provided by the embodiment of the invention is realized based on the contrast image.
In a specific implementation, in S10, a duodenoscope region, a guide wire region, and a bile duct region in a contrast image in endoscopic retrograde cholangiopancreatography are identified, which includes: identifying and segmenting a duodenoscope region and a guide wire region in the contrast image by adopting a first segmentation model; and identifying and segmenting a duodenoscope region and a bile duct region in the contrast image by adopting a second segmentation model.
That is, the duodenoscope region, the guide wire region, and the bile duct region are identified using two segmentation models. For this purpose, a first segmentation model for identifying the duodenoscope region and the guide wire region and a second segmentation model for identifying the duodenoscope region and the bile duct region are constructed. The reason why the guide wire and the bile duct are identified separately here is: in general, the guide wire and the bile duct have overlapping areas and are greatly interfered with each other, and the narrow area is jointly judged based on the bile duct area and the guide wire area obtained by segmentation, so that the separate identification can ensure the effectiveness of subsequent logic inference.
Further, after a duodenoscope region, a guide wire region and a bile duct region are identified by using the two segmentation models, the duodenoscope region, the guide wire region and the bile duct region output by the first segmentation model and the second segmentation model may be subjected to preset clustering processing to filter abnormal points in each region.
For example, a DBSCAN Clustering algorithm (i.e., Density-Based Clustering algorithm) is used to perform Clustering on the output regions of the two segmentation models, so as to filter the abnormal points in the regions. In the clustering process, clustering can be performed on a duodenoscope region and a bile duct region in a low neighbor distance high core distance mode, and clustering can be performed on a guide wire in a high neighbor distance low core distance mode.
In specific implementation, the step S10 of determining the pixel diameter of the duodenoscope body in the duodenoscope region may specifically include the steps S11 to S14:
s11, performing closed operation morphological transformation on the duodenoscope area to remove the shielding of the guide wire on the duodenoscope body;
the duodenoscope region output by one of the segmentation models can be subjected to closed operation shape-change chemical transformation, namely, the duodenoscope region is subjected to expansion treatment and corrosion treatment, so that the shielding of a guide wire on the duodenoscope can be eliminated, and a complete communication region is formed.
S12, performing two-classification processing on the unblocked duodenoscope area to obtain a first scope body area and a second scope body area of the duodenoscope area, wherein the smoothness of the first scope body area is higher than that of the second scope body area;
it can be understood that, because the duodenoscope is curved, when calculating the body pixel diameter of the duodenoscope, only one section of the relatively straight part can be cut, and the body pixel diameter can be calculated by using the part.
For example, KMeans (i.e., euclidean distance based clustering algorithm) may be used to classify the duodenoscope region two times, which results in two regions: the smoothness of the first mirror body area is better than that of the second mirror body area, so that only the first mirror body area can be used in the subsequent calculation of the mirror body pixel diameter.
For example, the duodenoscope region shown in fig. 3a is subjected to two-class clustering to obtain two scope body regions, wherein the first scope body region is of the class a in fig. 3B, and the second scope body region is of the class B in fig. 3B. After the cutting, the first lens region shown in fig. 3c results.
S13, determining the pixel width of the minimum circumscribed rectangle of the first mirror body region, the outline area of the first mirror body region and the area of the minimum circumscribed rectangle of the first mirror body region;
Specifically, the edge of the first mirror body region can be extracted first to obtain the mirror body edge of the first mirror body region, the mirror body contour of the first mirror body region is determined according to the mirror body edge, and the minimum external rectangle of the mirror body contour is calculated, so that the pixel width of the minimum external rectangle of the first mirror body region is obtained, and further the area of the minimum external rectangle can be calculated. Meanwhile, the area of the outline of the mirror body can be calculated.
S14, determining the duodenoscope body pixel diameter according to the pixel width of the minimum circumscribed rectangle of the first scope body region, the outline area of the first scope body region and the area of the minimum circumscribed rectangle of the first scope body region.
After the pixel width of the minimum circumscribed rectangle of the first scope region, the outline area of the first scope region, and the area of the minimum circumscribed rectangle of the first scope region are calculated by S13, the duodenoscope scope body pixel diameter can be calculated using these data.
Further, since the scope edges in the first scope region are almost parallel, the duodenoscope scope pixel diameter may be calculated using a first calculation formula including:
Lp2=S1*La/S2
Lp2 is the duodenoscope body pixel diameter, S1 is the outline area of the first body region, S2 is the area of the minimum circumscribed rectangle of the first body region, and La is the pixel width of the minimum circumscribed rectangle of the first body region.
Therefore, the diameters of the pixels of the duodenoscope body can be obtained through the steps S11-S14.
S20, determining whether a bile duct stenosis exists according to the guide wire area and the bile duct area; if the bile duct stenosis exists, determining a corresponding target guide wire section according to the type of the bile duct stenosis;
it will be appreciated that where a stenosis is determined from the guide wire region and the bile duct region, it is necessary to determine the specification of the bile duct stent to be placed if a stenosis is present, otherwise the method need not be continued.
In specific implementation, the determining whether a stenosis region exists in a bile duct according to the guide wire region and the bile duct region in S20 may specifically include steps S21 to S22:
s21, determining a first guide wire area and a second guide wire area according to the guide wire area and the bile duct area; the first guide wire area is a guide wire area which is not covered by the bile duct, and the second guide wire area is a guide wire area which is covered by the bile duct;
Referring to fig. 2a, a guide wire and a duodenoscope are shown, with the thicker being the duodenoscope and the thinner being the guide wire. Referring to fig. 2b, a duodenoscope and bile duct are shown, the portion that appears to be divided into two segments in fig. 2b being the bile duct. Referring to fig. 2c, a duodenoscope is shown with a guidewire overlapping the bile duct. In fig. 2c, the guide wires are divided into 5 segments, the guide wire CD at the first segment is not overlapped with the bile duct, the guide wire DE at the second segment is overlapped with the bile duct, the guide wire EF at the third segment is not overlapped with the bile duct, the guide wire FH at the fourth segment is overlapped with the bile duct, and the guide wire HI at the fifth segment is not overlapped with the bile duct. Here, the first guide wire CD, the third guide wire EF, and the fifth guide wire HI are the first guide wire regions, and the second guide wire DE and the fourth guide wire FH are the second guide wire regions.
S22, judging whether the first guide wire region exists between the two second guide wire regions;
if so, the bile duct has a middle section stenosis;
if not, judging whether the guide wire length of the first guide wire area corresponding to the tail end of the bile duct is more than 1.5 cm; if so, there is a distal stenosis in the bile duct.
It can be understood that if a first guide wire region exists between two second guide wire regions, that is, a guide wire segment which is not covered by the bile duct exists between two guide wire segments which are covered by the bile duct, it indicates that the guide wire segment between the two guide wire segments which are covered by the bile duct is not covered by the bile duct, that is, the bile duct is very thin, for example, the third guide wire segment EF in fig. 2c, and it is considered that the bile duct has a medium segment stenosis.
If the first guide wire section does not exist between the two second guide wire regions, the situation of middle section stenosis does not exist, and at the moment, whether the situation of tail end stenosis exists or not is further judged, wherein the judgment mode is as follows: and judging whether the guide wire length of the first guide wire area corresponding to the tail end of the bile duct is more than 1.5cm, if so, judging that the tail end stenosis exists, otherwise, judging that the tail end stenosis does not exist.
Wherein the bile duct end corresponds to the first guide wire region, see for example the HI section in fig. 2 c. The second guide wire region corresponding to the bile duct end, see, for example, FH section in fig. 2 c. The H point corresponds to the end of the bile duct.
It will be appreciated that in one picture there is at most one type of stenosis, i.e. there is a mid-stenosis, or there is a terminal stenosis. The target guidewire segment is different for different stenosis types.
In a specific implementation, in S20, the target guide wire segment is determined according to the type of the biliary stricture, where the target guide wire segment includes at least one of the following:
(1) if the bile duct stenosis is a middle segment stenosis, one end of the target guide wire section is a first end of a first guide wire area positioned between two second guide wire areas, the other end of the target guide wire section is a second end of a second guide wire area corresponding to the tail end of the bile duct, and the first end is an end part which is far away from the tail end of the bile duct relative to the second end;
(2) If the type of the bile duct stenosis is end stenosis, one end of the target guide wire section is a second end of a second guide wire area corresponding to the end of the bile duct, and the other end of the target guide wire section is 1.5cm away from the second end of the first guide wire area corresponding to the end of the bile duct.
Wherein there are two ends per guide wire region: a first end and a second end. The first end is the end distal to the distal end of the bile duct and the second end is the end proximal to the distal end of the bile duct.
In (1), when there is a mid-segment stenosis, one end of the corresponding target guide wire segment is a first end of a first guide wire region between two second guide wire regions, for example, point E in fig. 2c, and the other end is a second end of a second guide wire region corresponding to the end of the bile duct, for example, point H in fig. 2c, that is, the target guide wire segment is an EH segment.
In (2), when there is a terminal stenosis, one end of the corresponding target guide wire segment is the second end of the second guide wire region corresponding to the bile duct terminal, for example, point H in fig. 2 c. The other end of the target guide wire end is 1.5cm from the second end of the first guide wire region corresponding to the bile duct end, for example, the point I of the HI section in fig. 2c extends outward by 1.5 cm. Namely, the target guide wire section is the guide wire section between the point H and the point I which extends outwards by 1.5 cm.
S30, determining the pixel length of the target guide wire section, and calculating the physical length of the target guide wire section according to the duodenoscope body pixel diameter, the duodenoscope body physical diameter and the pixel length of the target guide wire section;
it will be appreciated that the pixel length of the target guidewire segment may be the number of pixels of the target guidewire segment in the gradient direction.
In specific implementation, the determining the pixel length of the target guide wire segment in S30 may specifically include the following steps S31-S34:
s31, converting the pixel matrix corresponding to the image to obtain a rotated pixel matrix; wherein the rotated pixel matrix has guidewire longitudinal uniqueness;
for example, referring to fig. 4a, in the image, there are two intersections between a vertical straight line and the guide wire, and at this time, the pixel matrix corresponding to the image does not have longitudinal uniqueness of the guide wire, and at this time, the image cannot be subjected to polynomial curve fitting processing. And rotating the image shown in fig. 4a by 90 degrees clockwise to obtain the image shown in fig. 4b, and if a straight line is drawn in the image shown in fig. 4b along the longitudinal direction, and the straight line and the guide wire have only one intersection point, that is, the pixel matrix corresponding to the image shown in fig. 4b has guide wire longitudinal uniqueness, at this time, the image can be subjected to accurate polynomial fitting processing.
S32, traversing in the rotated pixel matrix, and forming a set by each pixel point of the target wire guide section;
for example, the pixel matrix corresponding to the image shown in fig. 4b is traversed, and the respective pixel points of the target guide wire segment form a set [ (x1, y1), (x2, y2), (x3, y 3)........... -% ], that is, the above third to fifth guide wires form a set.
S33, performing polynomial fitting processing on the set corresponding to the target guide wire section to obtain a corresponding fitting curve section;
for example, a mathematical coordinate system is established, and polynomial set processing is performed by using the set, so as to obtain a corresponding fitting curve segment, and the curve segment represents the corresponding target guide wire segment. For example, a polynomial fitting of degree 3 is performed on the set, the polynomial coefficients are returned, and then the polynomial coefficients are changed into a polynomial equation to obtain a fitting curve segment.
And S34, calculating the pixel length of the fitting curve segment corresponding to the target guide wire segment to obtain the pixel length of the target guide wire segment.
For example, the length of the fitted curve segment is calculated by using a differential method, so as to obtain the pixel length of the corresponding target guide wire segment.
Therefore, the pixel length of the target guide wire segment can be obtained through S31-S34.
The pixel diameter of the duodenoscope body is calculated in S10, the physical diameter of the duodenoscope body can be obtained through actual measurement, for example, 11.6mm, the pixel length of the target guide wire segment is also calculated in this step, and the physical length of the target guide wire segment can be calculated according to the data.
In specific implementation, in S30, calculating the physical length of the target guidewire segment according to the duodenoscope body pixel diameter, the duodenoscope body physical diameter, and the pixel length of the target guidewire segment, which may specifically include: calculating the physical length of the target guide wire section by adopting a second calculation formula, wherein the second calculation formula comprises the following steps:
Ld2=Lp1*Ld1/ Lp2
wherein Ld2 is the physical length of the target wire segment, Ld1 is the pixel length of the target wire segment, Lp1 is the duodenoscope body physical diameter, and Lp2 is the duodenoscope body pixel diameter.
It is understood that the physical length of the key guide wire segment can be obtained through the step S30, and the process can proceed to the step S40.
And S40, determining the specification of the bile duct stent to be placed according to the physical length of the target guide wire section.
The specification of the bile duct stent refers to the length of the bile duct stent.
In specific implementation, the determining, in S40, the specification of the biliary stent to be placed in the stenosis section according to the physical length of the target guidewire section may specifically include S41:
s41, calculating the length of the bile duct stent to be placed according to the physical length of the target guide wire section and the preset total stent allowance; the total support allowance is the sum of the lengths of the bile duct support exceeding the two ends of the target guide wire section.
Referring to fig. 2c, the biliary stent to be implanted needs to cover the guidewire segment between point E and point H due to the presence of the mid-segment stenosis. In practical situations, the biliary stent usually needs to be a certain length, e.g. 1cm, beyond the mid-narrow segment, and also needs to be a certain length, e.g. 1cm, beyond the duodenal papilla, so that the total stent margin is 2 cm. Namely, the length of the bile duct stent to be implanted, namely the specification of the bile duct stent to be implanted is obtained by adding 2cm to the length between the point E and the point H.
It will be appreciated that the physical length between the distal end of the mid-section stenosis and the duodenal papilla is actually the length between point E and point H.
It can be understood that the bile duct stent specification selection method provided by the embodiment of the invention firstly identifies a duodenoscope region, a guide wire region and a bile duct region in a contrast image, calculates a duodenoscope body pixel diameter, then judges whether a bile duct has stenosis or not based on the guide wire region and the bile duct region, determines a key target guide wire section if the bile duct has stenosis, calculates the physical length of the target guide wire section based on the duodenoscope body pixel diameter, and finally calculates the length of the bile duct stent to be placed according to the physical length of the target guide wire section. The method automatically calculates the length of the bile duct stent to be implanted through image processing, mathematical operation and other modes, and the mode does not need to be estimated based on personal operation experience of doctors, so that the accuracy of specification selection of the bile duct stent can be improved, the radiation exposure time can be greatly shortened, and radiation injury to doctors and patients is reduced.
In a second aspect, an embodiment of the present invention provides a biliary duct stent specification selecting device.
Referring to fig. 5, the apparatus may include:
the first determination module is used for identifying a duodenoscope area, a guide wire area and a bile duct area in a contrast image in endoscopic retrograde cholangiopancreatography and determining the duodenoscope body pixel diameter in the duodenoscope area;
the second determination module is used for determining whether bile duct stenosis exists according to the guide wire area and the bile duct area; if the bile duct stenosis exists, determining a corresponding target guide wire section according to the type of the bile duct stenosis;
the third determining module is used for determining the pixel length of the target guide wire section and calculating the physical length of the target guide wire section according to the pixel diameter of the duodenoscope body, the physical diameter of the duodenoscope body and the pixel length of the target guide wire section;
and the fourth determining module is used for determining the specification of the bile duct stent to be implanted according to the physical length of the target guide wire section.
In some embodiments, the first determining module specifically includes:
the model identification unit is used for identifying and segmenting a duodenoscope region and a guide wire region in the contrast image by adopting a first segmentation model; and identifying and segmenting a duodenoscope region and a bile duct region in the contrast image by adopting a second segmentation model.
Further, the first determining module is further configured to: and performing preset clustering processing on the duodenoscope region, the guide wire region and the bile duct region output by the first segmentation model and the second segmentation model to filter abnormal points in each region.
In some embodiments, the first determining module specifically includes:
the first transformation unit is used for performing closed operation morphological transformation on the duodenoscope region so as to remove the shielding of a guide wire on a duodenoscope body;
the first clustering unit is used for performing two-class clustering processing on the shielded duodenoscope region to obtain a first scope body region and a second scope body region of the duodenoscope region, wherein the smoothness of the first scope body region is higher than that of the second scope body region;
a first determination unit configured to determine a pixel width of a minimum bounding rectangle of the first mirror body region, an outline area of the first mirror body region, and an area of the minimum bounding rectangle of the first mirror body region;
and the second determining unit is used for determining the pixel diameter of the duodenoscope body according to the pixel width of the minimum circumscribed rectangle of the first scope body region, the outline area of the first scope body region and the area of the minimum circumscribed rectangle of the first scope body region.
Further, the second determining unit is specifically configured to: calculating the duodenoscope body pixel diameter by adopting a first calculation formula, wherein the first calculation formula comprises the following steps:
Lp2=S1*La/S2
lp2 is the duodenoscope body pixel diameter, S1 is the outline area of the first body region, S2 is the area of the minimum circumscribed rectangle of the first body region, and La is the pixel width of the minimum circumscribed rectangle of the first body region.
In some embodiments, the second determining module specifically includes:
a third determination unit, configured to determine a first guide wire region and a second guide wire region according to the guide wire region and the bile duct region; the first guide wire area is a guide wire area which is not covered by the bile duct, and the second guide wire area is a guide wire area which is covered by the bile duct;
a first judging unit, configured to judge whether the first guide wire region exists between two second guide wire regions; if so, the bile duct has a middle section stenosis; if not, judging whether the guide wire length of the first guide wire area corresponding to the tail end of the bile duct is more than 1.5 cm; if so, there is a distal stenosis in the bile duct.
Further, the second determining module further specifically includes:
a first target determination unit to: if the bile duct stenosis is a middle segment stenosis, one end of the target guide wire section is a first end of a first guide wire area positioned between two second guide wire areas, the other end of the target guide wire section is a second end of a second guide wire area corresponding to the tail end of the bile duct, and the first end is an end part which is far away from the tail end of the bile duct relative to the second end;
A second target determination unit to: if the type of the bile duct stenosis is end stenosis, one end of the target guide wire section is a second end of a second guide wire area corresponding to the end of the bile duct, and the other end of the target guide wire section is 1.5cm away from the second end of the first guide wire area corresponding to the end of the bile duct.
In some embodiments, the third determining module specifically includes:
the first rotating unit is used for rotating the pixel matrix corresponding to the image-making image to obtain a rotated pixel matrix; wherein the rotated pixel matrix has guidewire longitudinal uniqueness;
the set forming unit is used for traversing in the rotated pixel matrix and forming a set by each pixel point of the target wire guide section;
the curve fitting unit is used for carrying out polynomial fitting processing on the set corresponding to the target guide wire section to obtain a corresponding fitting curve section;
and the first calculating unit is used for calculating the pixel length of the fitting curve segment corresponding to the target guide wire segment to obtain the pixel length of the target guide wire segment.
In some embodiments, the third determining module comprises:
a second calculating unit, configured to calculate a physical length of the target guide wire segment by using a second calculation formula, where the second calculation formula includes:
Ld2=Lp1*Ld1/ Lp2
Wherein Ld2 is the physical length of the target wire segment, Ld1 is the pixel length of the target wire segment, Lp1 is the physical diameter of the duodenoscope body, and Lp2 is the pixel diameter of the duodenoscope body.
In some embodiments, the fourth determining module is specifically configured to: calculating the length of the bile duct stent to be placed according to the physical length of the target guide wire section and the preset total stent allowance; the total support allowance is the sum of the lengths of the bile duct support exceeding the two ends of the target guide wire section.
It is to be understood that for the explanation, the detailed description, the beneficial effects, the examples and the like of the related contents in the apparatus provided in the embodiment of the present invention, reference may be made to the corresponding parts in the method provided in the first aspect, and details are not described herein again.
The embodiments in the present specification are described in a progressive manner, and the same and similar parts among the embodiments are referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, as for the apparatus embodiment, since it is substantially similar to the method embodiment, the description is relatively simple, and for the relevant points, reference may be made to the partial description of the method embodiment.
Those skilled in the art will recognize that the functionality described in this disclosure may be implemented in hardware, software, firmware, or any combination thereof, in one or more of the examples described above. When implemented in software, the functions may be stored on or transmitted over as one or more instructions or code on a computer-readable medium.
The above-mentioned embodiments, objects, technical solutions and advantages of the present invention are further described in detail, it should be understood that the above-mentioned embodiments are only exemplary embodiments of the present invention, and are not intended to limit the scope of the present invention, and any modifications, equivalent substitutions, improvements and the like made on the basis of the technical solutions of the present invention should be included in the scope of the present invention.

Claims (10)

1. A bile duct stent specification selection method is characterized by comprising the following steps:
identifying a duodenoscope area, a guide wire area and a bile duct area in a contrast image in endoscopic retrograde cholangiopancreatography, and determining the duodenoscope body pixel diameter in the duodenoscope area;
determining whether a bile duct stenosis exists or not according to the guide wire area and the bile duct area; if the bile duct stenosis exists, determining a corresponding target guide wire section according to the type of the bile duct stenosis;
Determining the pixel length of the target guide wire section, and calculating the physical length of the target guide wire section according to the duodenoscope body pixel diameter, the duodenoscope body physical diameter and the pixel length of the target guide wire section;
and determining the specification of the bile duct stent to be implanted according to the physical length of the target guide wire section.
2. The method of claim 1, wherein identifying a duodenoscope region, a guide wire region, and a bile duct region in an angiographic image in an endoscopic retrograde cholangiopancreatography includes:
identifying and segmenting a duodenoscope region and a guide wire region in the contrast image by adopting a first segmentation model; and identifying and segmenting a duodenoscope region and a bile duct region in the contrast image by adopting a second segmentation model.
3. The method of claim 1, wherein the determining a duodenoscope body pixel diameter in the duodenoscope region comprises:
performing closed operation morphological transformation on the duodenoscope area to remove the shielding of a guide wire on a duodenoscope body;
performing two-classification processing on the unblocked duodenoscope area to obtain a first scope body area and a second scope body area of the duodenoscope area, wherein the smoothness of the first scope body area is higher than that of the second scope body area;
Determining the pixel width of the minimum circumscribed rectangle of the first mirror body region, the outline area of the first mirror body region and the area of the minimum circumscribed rectangle of the first mirror body region;
and determining the pixel diameter of the duodenoscope body according to the pixel width of the minimum circumscribed rectangle of the first scope body region, the outline area of the first scope body region and the area of the minimum circumscribed rectangle of the first scope body region.
4. The method of claim 3, wherein said determining said duodenoscope body pixel diameter comprises: calculating the duodenoscope body pixel diameter by adopting a first calculation formula, wherein the first calculation formula comprises the following steps:
Lp2=S1*La/S2
lp2 is the duodenoscope body pixel diameter, S1 is the outline area of the first body region, S2 is the area of the minimum circumscribed rectangle of the first body region, and La is the pixel width of the minimum circumscribed rectangle of the first body region.
5. The method according to claim 1, wherein the determining whether a biliary stricture exists based on the guidewire region and the bile duct region comprises:
determining a first guide wire area and a second guide wire area according to the guide wire area and the bile duct area; the first guide wire area is a guide wire area which is not covered by the bile duct, and the second guide wire area is a guide wire area which is covered by the bile duct;
Judging whether the first guide wire region exists between the two second guide wire regions;
if so, the bile duct has a middle section stenosis;
if not, judging whether the guide wire length of the first guide wire area corresponding to the tail end of the bile duct is more than 1.5 cm; if so, there is a terminal stenosis in the bile duct.
6. The method of claim 5, wherein determining the corresponding target guidewire segment based on the type of biliary stricture comprises at least one of:
if the bile duct stenosis is a middle segment stenosis, one end of the target guide wire section is a first end of a first guide wire area positioned between two second guide wire areas, the other end of the target guide wire section is a second end of a second guide wire area corresponding to the tail end of the bile duct, and the first end is an end part which is far away from the tail end of the bile duct relative to the second end;
if the type of the bile duct stenosis is end stenosis, one end of the target guide wire section is a second end of a second guide wire area corresponding to the end of the bile duct, and the other end of the target guide wire section is 1.5cm away from the second end of the first guide wire area corresponding to the end of the bile duct.
7. The method of claim 1, wherein the determining the pixel length of the target guidewire segment comprises:
Rotating the pixel matrix corresponding to the image-making image to obtain a rotated pixel matrix; wherein the rotated pixel matrix has guidewire longitudinal uniqueness;
traversing in the rotated pixel matrix, and forming a set of all pixel points of the target wire section;
performing polynomial fitting processing on the set corresponding to the target guide wire section to obtain a corresponding fitting curve section;
and calculating the pixel length of the fitting curve segment corresponding to the target guide wire segment to obtain the pixel length of the target guide wire segment.
8. The method of claim 1, wherein calculating the physical length of the target guidewire segment from the duodenoscope body pixel diameter, the duodenoscope body physical diameter, and the pixel length of the target guidewire segment comprises: calculating the physical length of the target guide wire section by adopting a second calculation formula, wherein the second calculation formula comprises the following steps:
Ld2=Lp1*Ld1/ Lp2
wherein Ld2 is the physical length of the target wire segment, Ld1 is the pixel length of the target wire segment, Lp1 is the physical diameter of the duodenoscope body, and Lp2 is the pixel diameter of the duodenoscope body.
9. The method of claim 1, wherein determining the specification of the biliary stent to be placed based on the physical length of the target guidewire segment comprises:
Calculating the length of the bile duct stent to be implanted according to the physical length of the target guide wire section and the preset total stent allowance; the total support allowance is the sum of the lengths of the bile duct support exceeding the two ends of the target guide wire section.
10. A biliary stent specification selection device, comprising:
the first determination module is used for identifying a duodenoscope area, a guide wire area and a bile duct area in a contrast image in endoscopic retrograde cholangiopancreatography and determining the duodenoscope body pixel diameter in the duodenoscope area;
the second determination module is used for determining whether bile duct stenosis exists according to the guide wire area and the bile duct area; if the bile duct stenosis exists, determining a corresponding target guide wire section according to the type of the bile duct stenosis;
the third determining module is used for determining the pixel length of the target guide wire section and calculating the physical length of the target guide wire section according to the pixel diameter of the duodenoscope body, the physical diameter of the duodenoscope body and the pixel length of the target guide wire section;
and the fourth determining module is used for determining the specification of the bile duct stent to be implanted according to the physical length of the target guide wire section.
CN202210511435.7A 2022-05-12 2022-05-12 Bile duct support specification selection method and device Active CN114612475B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202210511435.7A CN114612475B (en) 2022-05-12 2022-05-12 Bile duct support specification selection method and device

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202210511435.7A CN114612475B (en) 2022-05-12 2022-05-12 Bile duct support specification selection method and device

Publications (2)

Publication Number Publication Date
CN114612475A true CN114612475A (en) 2022-06-10
CN114612475B CN114612475B (en) 2022-09-23

Family

ID=81870533

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202210511435.7A Active CN114612475B (en) 2022-05-12 2022-05-12 Bile duct support specification selection method and device

Country Status (1)

Country Link
CN (1) CN114612475B (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114820600A (en) * 2022-06-27 2022-07-29 天津恒宇医疗科技有限公司 Coronary artery intravascular stent detection method and system based on OCT image

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
DE102007008205A1 (en) * 2007-02-20 2008-08-21 Frimberger, Eckart, Prof. Dr. Med. ERCP training model (ERCP-TM) for endoscopic diagnosis and therapy in the area of the pancreo-biliary system
US20100056910A1 (en) * 2008-09-02 2010-03-04 Yutaka Yanuma Guidewire catheter
CN109584229A (en) * 2018-11-28 2019-04-05 武汉大学人民医院(湖北省人民医院) A kind of real-time assistant diagnosis system of Endoscopic retrograde cholangio-pancreatiography art and method
CN110974419A (en) * 2019-12-24 2020-04-10 武汉大学 Guide wire navigation method and system for portal stenosis in endoscopic biliary stent implantation
CN111105873A (en) * 2019-12-24 2020-05-05 武汉大学 Auxiliary diagnosis and measurement method and system in endoscopic retrograde cholangiopancreatography
CN111773519A (en) * 2020-07-28 2020-10-16 上海市东方医院(同济大学附属东方医院) Double-cavity bile pancreatic duct radiography conduit
CN114344678A (en) * 2021-12-31 2022-04-15 武汉大学 Guide wire length measuring device and method for ERCP

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
DE102007008205A1 (en) * 2007-02-20 2008-08-21 Frimberger, Eckart, Prof. Dr. Med. ERCP training model (ERCP-TM) for endoscopic diagnosis and therapy in the area of the pancreo-biliary system
US20100056910A1 (en) * 2008-09-02 2010-03-04 Yutaka Yanuma Guidewire catheter
CN109584229A (en) * 2018-11-28 2019-04-05 武汉大学人民医院(湖北省人民医院) A kind of real-time assistant diagnosis system of Endoscopic retrograde cholangio-pancreatiography art and method
CN110974419A (en) * 2019-12-24 2020-04-10 武汉大学 Guide wire navigation method and system for portal stenosis in endoscopic biliary stent implantation
CN111105873A (en) * 2019-12-24 2020-05-05 武汉大学 Auxiliary diagnosis and measurement method and system in endoscopic retrograde cholangiopancreatography
CN111773519A (en) * 2020-07-28 2020-10-16 上海市东方医院(同济大学附属东方医院) Double-cavity bile pancreatic duct radiography conduit
CN114344678A (en) * 2021-12-31 2022-04-15 武汉大学 Guide wire length measuring device and method for ERCP

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
WENJIE W.等: "Design of coaxial intervention catheter robot for Endoscopic Retrograde Cholangio-Pancreatography", 《2020 CHINESE AUTOMATION CONGRESS (CAC)》 *
孙雄 等: "经胰管胆胰管隔膜切开术及双导丝术在困难性插管ERCP中的应用及安全性分析", 《中国内镜杂志》 *

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114820600A (en) * 2022-06-27 2022-07-29 天津恒宇医疗科技有限公司 Coronary artery intravascular stent detection method and system based on OCT image
CN114820600B (en) * 2022-06-27 2022-09-27 天津恒宇医疗科技有限公司 Coronary artery intravascular stent detection method and system based on OCT image

Also Published As

Publication number Publication date
CN114612475B (en) 2022-09-23

Similar Documents

Publication Publication Date Title
Lareyre et al. A fully automated pipeline for mining abdominal aortic aneurysm using image segmentation
US7551758B2 (en) Medical viewing system and method for detecting borders of an object of interest in noisy images
Zhou et al. The detection and quantification of retinopathy using digital angiograms
US8000507B2 (en) Viewing system for control of PTCA angiograms
US9084531B2 (en) Providing real-time marker detection for a stent in medical imaging
US8121367B2 (en) Method and system for vessel segmentation in fluoroscopic images
JP4430937B2 (en) Medical viewing system and method for spatial enhancement of structures in noisy images
CN110974419B (en) Guide wire navigation method and system for portal stenosis in endoscopic biliary stent implantation
CN106846347B (en) OCT-based analysis system and analysis method before stent implantation
CN114612475B (en) Bile duct support specification selection method and device
US20150087972A1 (en) Dynamic overlay of anatomy from angiography to fluoroscopy
JP2008519639A (en) Apparatus and method for medical image registration
US20220319004A1 (en) Automatic vessel analysis from 2d images
Oğul et al. Eliminating rib shadows in chest radiographic images providing diagnostic assistance
US20090129654A1 (en) Image analysis of tube tip positioning
CN113947205A (en) Neural network model training method, computer-readable storage medium and device
Lu et al. Fully automated colon segmentation for the computation of complete colon centerline in virtual colonoscopy
Mitra et al. Peak trekking of hierarchy mountain for the detection of cerebral aneurysm using modified Hough circle transform
CN116649994A (en) Intelligent fusion method, device, equipment and medium for CTA and DSA images
CN116309264A (en) Contrast image determination method and contrast image determination device
JP2005528946A (en) Angiography display overlay technology that tracks the interventional position of blood vessels
US11523744B2 (en) Interaction monitoring of non-invasive imaging based FFR
CN114176775B (en) Calibration method, device, equipment and medium for ERCP selective bile duct intubation
Lalinia et al. Coronary Vessel Segmentation in X-ray Angiography Images using Edge-based Tracking Method
JP2023130134A (en) Program, information processing method, and information processing device

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
GR01 Patent grant
GR01 Patent grant