CN115909302A - Data processing method for identifying disintegration performance of medicine - Google Patents
Data processing method for identifying disintegration performance of medicine Download PDFInfo
- Publication number
- CN115909302A CN115909302A CN202310221379.8A CN202310221379A CN115909302A CN 115909302 A CN115909302 A CN 115909302A CN 202310221379 A CN202310221379 A CN 202310221379A CN 115909302 A CN115909302 A CN 115909302A
- Authority
- CN
- China
- Prior art keywords
- drug
- pixel
- pixel point
- detected
- disintegration
- 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
Links
Images
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation
Landscapes
- Image Processing (AREA)
Abstract
The invention relates to the technical field of image data processing, in particular to a data processing method for identifying the disintegration performance of a medicament. The method comprises the following steps: acquiring a gray image of the medicine, determining a pixel point to be detected and a positioning pixel point, determining the roughness of the medicine edge around the positioning pixel point, and calculating the disintegration characteristic value of the pixel point to be detected according to the pixel point distance and the roughness between the pixel point to be detected and the positioning pixel point; determining a diffusion coefficient according to the principal component direction of the growth region, the principal component direction of the edge of the medicine around the positioning pixel point, the principal component direction of the medicine residue positioning region and the disintegration characteristic value; determining a target pixel point according to the diffusion coefficient, and determining the diffusion distance of a time point to be measured according to the positions of the target pixel point and the matched pixel point; and determining the uniform degree of drug disintegration according to the diffusion distances at different time points, and taking the uniform degree of drug disintegration as a data processing result. The invention can improve the accuracy of disintegration speed uniformity identification.
Description
Technical Field
The invention relates to the technical field of image data processing, in particular to a data processing method for identifying the disintegration performance of a medicament.
Background
The controlled release preparation is a pharmaceutical dosage form capable of releasing a fixed amount of drug per unit time, maintaining a stable blood concentration for a long time, and being not affected by the gastrointestinal environment. When the controlled release preparation is prepared, the slow constant speed or the nearly constant speed release in a specified solvent is required to be ensured, so that the continuous and stable therapeutic effect is achieved. Therefore, accurate identification of the release uniformity during disintegration of the drug is required.
In some related technologies, the area and volume change of a drug is usually used for estimating the drug disintegration speed, the mode of measuring the area and volume change of the drug can only determine the rough disintegration speed, and the identification accuracy and the identification precision of the drug disintegration uniformity performance are not enough.
Disclosure of Invention
In order to solve the technical problem of low accuracy of disintegration speed uniformity identification, the invention provides a data processing method for identifying the disintegration performance of a medicament, which adopts the following technical scheme:
the invention provides a data processing method for identifying the disintegration performance of a medicament, which comprises the following steps:
acquiring drug gray images of drugs to be identified at different time points in the disintegration process, optionally selecting a certain time point to be detected, and taking pixel points in an area surrounded by the drug edge of the time point to be detected and the drug edge of the last time point in the drug gray images as pixel points to be detected;
selecting a certain pixel point to be tested, determining a positioning pixel point of the pixel point to be tested at the medicine edge of the time point to be tested, determining the roughness of the medicine edge around the positioning pixel point, and calculating the disintegration characteristic value of the pixel point to be tested according to the pixel point distance between the pixel point to be tested and the positioning pixel point and the roughness;
performing region growing processing on the pixel points to be detected to obtain a growing region, and determining a drug residue positioning region according to the distribution of the pixel points in the drug gray level image of the time point to be detected; determining the diffusion coefficient of the pixel point to be detected according to the principal component direction of the growth area, the principal component direction of the drug edge around the positioning pixel point, the principal component direction of the drug residue positioning area and the disintegration characteristic value;
screening the pixel points to be detected according to the diffusion coefficient, determining target pixel points, determining pixel points which represent the same medicine particles with the target pixel points in the medicine gray-scale image at the last time point as matching pixel points, and determining the diffusion distance of the time point to be detected according to the positions of the target pixel points and the positions of the matching pixel points; and determining the uniform degree of drug disintegration according to the diffusion distances at different time points, and taking the uniform degree of drug disintegration as a data processing result.
Further, the determining the roughness of the edge of the medicine around the positioning pixel point includes:
determining a medicine edge formed by a preset number of pixel points around the positioning pixel point on the medicine edge of the time point to be detected as a medicine adjacent edge;
and carrying out low-pass filtering processing on the medicine adjacent edge to obtain a filtering edge, and calculating the absolute value of the difference between the number of pixel points in the filtering edge and the preset number to serve as the roughness.
Further, calculating the disintegration characteristic value of the pixel point to be detected according to the pixel point distance between the pixel point to be detected and the positioning pixel point and the roughness, and the method comprises the following steps:
determining the pixel point distance between the pixel point to be detected and the positioning pixel point as a positioning distance;
and calculating a product normalized value of the roughness and the positioning distance as the disintegration characteristic value.
Further, the determining a drug residue location area according to the distribution of the pixel points in the drug gray image at the time point to be detected includes:
determining a disintegrated drug region in the drug gray image of the time point to be detected, clustering the disintegrated drug region to obtain at least one clustering region, and taking the clustering region to which the positioning pixel point belongs as the drug residue positioning region.
Further, the determining the diffusion coefficient of the pixel point to be detected according to the principal component direction of the growth area, the principal component direction of the drug edge around the positioning pixel point, the principal component direction of the drug residue positioning area, and the disintegration characteristic value includes:
calculating the absolute value of the difference value between the principal component direction angle of the growth region and the principal component direction angle of the drug edge around the positioning pixel point as a first direction difference; calculating the absolute value of the difference value between the main component direction angle of the growth area and the main component direction angle of the drug residue positioning area at the time point to be detected as a second direction difference; calculating a ratio normalization value of the first direction difference and the second direction difference as a direction consistency coefficient;
calculating a product of the directional uniformity coefficient and the disintegration feature value as the diffusion coefficient.
Further, the screening the pixel points to be detected according to the diffusion coefficient to determine target pixel points includes:
and taking the pixel point to be detected with the diffusion coefficient larger than a preset coefficient threshold value as a target pixel point.
Further, the determining the diffusion distance of the time point to be measured according to the position of the target pixel point and the position of the matching pixel point includes:
mapping the target pixel point and the matching pixel point to a medicine gray image at the same time point, and determining the Euclidean distance between the two mapping pixel points as a mapping distance;
and calculating the mean value of the mapping distances between all the matched target pixel points and the matched pixel points to be used as the diffusion distance.
Further, the determining the uniform degree of drug disintegration according to the diffusion distances at different time points comprises:
calculating the difference mean value of the diffusion distances of all two adjacent time points, and taking the normalized value of the difference mean value as the disintegration uniformity degree of the medicine.
Further, the determining the positioning pixel point of the pixel point to be detected at the edge of the medicine at the time point to be detected includes:
and calculating Euclidean distances between the pixel points to be detected and all pixel points on the medicine edge of the time point to be detected respectively, and taking the pixel point corresponding to the minimum Euclidean distance as a positioning pixel point.
The invention has the following beneficial effects:
according to the method, the gray level images of the medicines at different time points are collected, the pixel point to be detected between the medicine edges at two adjacent time points is determined, analysis can be performed according to the change of the medicine edges after the medicines are dissolved, the pixel point to be detected is accurately determined, and the disintegration performance of the medicines can be conveniently analyzed according to the distribution characteristics of the pixel point to be detected; the method comprises the steps of determining the roughness of the edge of a medicine around a positioning pixel point, accurately representing the change of the edge of the medicine in the disintegration process according to the roughness, determining the disintegration characteristic value according to the distance between the disintegrated medicine particles and the medicine which is not disintegrated and the roughness, and effectively analyzing the morphological change of the medicine to be identified after disintegration, thereby determining the diffusion coefficient of a pixel point to be detected by combining the direction characteristics of the distribution of the pixel point in a medicine gray image, wherein the diffusion coefficient can effectively evaluate the disintegration condition of the pixel point to be detected, and analyze the direction consistency of the growth area of the pixel point to be detected and the residual trace of the medicine, effectively preventing the interference of an obvious edge formed when the medicine particle residue diffuses outwards, enabling the selection of a target pixel point to be more accurate, and better conforming to the objective rule of the residue of the newly dissolved medicine particles in the disintegration process of the medicine to be identified; through the position analysis of the target pixel point and the matching pixel point which represent the same drug particle between two adjacent time points, the diffusion distance of the drug particle between the two time points is accurately determined, the uniformity of the drug to be identified in the whole disintegration process is accurately determined according to the diffusion distances at different moments, the accurate test of the drug disintegration performance is effectively realized, the determination of the disintegration speed uniformity in the subsequent drug disintegration process is more accurate, and the reliability is higher.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions and advantages of the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and other drawings can be obtained by those skilled in the art without creative efforts.
Fig. 1 is a flowchart of a data processing method for identifying disintegration properties of a drug according to an embodiment of the present invention;
FIG. 2 is a schematic illustration of a drug disintegration region provided by an embodiment of the present invention;
FIG. 3 is a schematic diagram of an initial state of disintegration of a drug provided in accordance with an embodiment of the present invention;
figure 4 is a schematic diagram of a second state of drug disintegration provided by an embodiment of the invention;
figure 5 is a schematic diagram of a third state of drug disintegration provided by one embodiment of the invention.
Detailed Description
To further illustrate the technical means and effects of the present invention adopted to achieve the predetermined objects, the following detailed description, the structure, the features and the effects of a data processing method for drug disintegration performance identification according to the present invention are provided with the accompanying drawings and the preferred embodiments. In the following description, different "one embodiment" or "another embodiment" refers to not necessarily the same embodiment. Furthermore, the particular features, structures, or characteristics may be combined in any suitable manner in one or more embodiments.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.
The following describes a specific scheme of the data processing method for identifying the drug disintegration property provided by the present invention in detail with reference to the accompanying drawings.
Referring to fig. 1, a flow chart of a data processing method for drug disintegration performance identification according to an embodiment of the present invention is shown, where the method includes:
s101: acquiring the drug gray images of the drugs to be identified at different time points in the disintegration process, selecting a certain time point to be detected, and taking the pixel points in the region surrounded by the drug edge of the time point to be detected and the drug edge of the last time point in the drug gray images as the pixel points to be detected.
The drug is disintegrated by physically dissolving the drug in a solvent gradually with the passage of time, and the process is a process of converting a pill-shaped drug, a tablet-shaped drug and the like into small drug particles.
It can be understood that, in the disintegration process of the drug to be identified, the edge drug gradually diffuses outward along with the change of time, so that the original images of the drug to be identified at different time points in the disintegration process can be obtained, and then the original images at different time points are respectively subjected to image preprocessing to obtain a drug gray image, wherein the image preprocessing may specifically include image denoising processing and image graying processing, and the image preprocessing process is a technique well known in the art and is not described herein again.
For example, it may be set to acquire an original image every 5 minutes according to a priori experience, and then perform image preprocessing to obtain a gray-scale image of the drug, where an acquisition period of the original image may be adjusted according to actual performance identification requirements and specific situations of the drug, which is not limited herein.
In the embodiment of the invention, a certain time point can be selected from a plurality of time points in the drug disintegration process as the time point to be detected, and the drug gray level images of different time points to be detected can represent the drug disintegration state of the corresponding time point.
The last time point is the last sampling time point of the time point to be measured, and it can be understood that the disintegration performance of the drug at the time point to be measured can be determined according to the disintegration states of the drug at the last time point and the time point to be measured.
The edge of the medicine is the edge of the undisintegrated medicine to be identified, edge detection processing can be carried out on the solid medicine to be identified, and the edge of the medicine to be identified is obtained and used as the edge of the medicine. In the embodiment of the present invention, the drug edge at the time point to be measured and the drug edge at the previous time point may be obtained using a Canny edge detector, which is a well-known technique in the art and will not be described herein again.
It can be understood that, since the drug to be identified is in a state of being continuously disintegrated, the drug edges of the drug to be identified at adjacent time points will generate a certain difference, in the embodiment of the present invention, the region surrounded by the drug edge at the time point to be detected and the drug edge at the last time point may be used as the drug disintegration region between the last time point and the time point to be detected, and the pixel points corresponding to the drug disintegration region may be used as the pixel points to be detected. As shown in fig. 2, fig. 2 is a schematic diagram of a drug disintegration region provided by an embodiment of the present invention.
It can be understood that, at the last time point, the pixel point to be detected in the drug disintegration region is still on the drug to be identified, that is, still in an undisrupted state, and at the time point to be detected, the pixel point to be detected in the drug disintegration region becomes the pixel point in the disintegrated region, and in the drug disintegration process, part of disintegrated drug particles fall near the drug to be identified and diffuse around the drug to be identified along with the lapse of time, which indicates that the pixel point to be detected can represent the drug particles disintegrated from the last time point to the time point to be detected.
S102: and selecting a certain pixel point to be detected, determining a positioning pixel point of the pixel point to be detected at the medicine edge of the time point to be detected, determining the roughness of the medicine edge around the positioning pixel point, and calculating the disintegration characteristic value of the pixel point to be detected according to the pixel point distance and the roughness between the pixel point to be detected and the positioning pixel point.
In the embodiment of the invention, a certain pixel point to be detected can be selected optionally in the region enclosed by the medicament edge of the time point to be detected and the medicament edge of the last time point, so that the pixel point to be detected can be analyzed conveniently.
Further, in the embodiment of the present invention, determining the positioning pixel point of the pixel point to be detected at the edge of the drug at the time point to be detected includes: and calculating Euclidean distances between the pixel points to be detected and all pixel points on the medicament edge of the time point to be detected respectively, and taking the pixel point corresponding to the minimum Euclidean distance as a positioning pixel point.
The positioning pixel points are positioning points of the pixel points to be detected on the medicine edge of the time point to be detected, and can be used for representing the shortest positions of the pixel points to be detected on the medicine edge of the time point to be detected, therefore, euclidean distances between the pixel points to be detected and all pixel points in the medicine edge of the time point to be detected can be calculated, and the pixel points with the shortest Euclidean distances are selected as the positioning pixel points.
It can be understood that, because the medicine is in the process of normally disintegrating, the disintegrated medicine particles are scattered outwards in a linear mode basically, and therefore, the shortest Euclidean distances between the pixel points to be detected and all the pixel points in the medicine edge of the time point to be detected are calculated respectively, the positioning pixel points are determined through the shortest Euclidean distances, the direction of the connecting line between the pixel points to be detected is positioned, the medicine particles corresponding to the pixel points to be detected can be represented, the direction of disintegration and outward scattering at the last time point is carried out, and then the roughness of the medicine edge of the time point to be detected can be accurately determined through the positioning pixel points.
It can be understood that, during the disintegration process of the drug, the stronger the disintegration effect is, the stronger the change of the drug edge is, the rougher the corresponding drug edge is, the slower the disintegration process is, and the slower the change of the drug edge is, the smoother the corresponding drug edge is, and thus, the roughness of the drug edge can be used as the processing coefficient of the disintegration performance of the drug.
Further, in the embodiment of the present invention, determining the roughness of the edge of the medicine around the positioning pixel point includes: determining a medicine edge formed by a preset number of pixel points around a positioning pixel point on the medicine edge of a time point to be detected as a medicine adjacent edge; and performing low-pass filtering processing on the medicine adjacent edge to obtain a filtering edge, and calculating the absolute value of the difference between the number of pixel points in the filtering edge and the preset number to serve as the roughness.
Wherein, the medicine closes on the edge, for the medicine edge of presetting a number of pixel components around the location pixel, the quantity of presetting, for the quantity of the pixel that sets up in advance according to prior experience, for example, the quantity of presetting can set up to 100, then correspond, with locating on the medicine edge that pixel left side 50 pixel and right side 50 pixel constitute the medicine and close on the edge, for example, when waiting to discern the medicine in the medicine grey image and be circular, then can close on the edge with the medicine of 50 pixel on the left side and right side 50 pixel components medicine.
In the embodiment of the present invention, butterworth filtering may be used to perform low-pass filtering processing on the drug-proximal edge, where butterworth filtering is a low-pass filter with a maximum flat amplitude response, and may convert a sudden protrusion or depression of a rougher edge into a smooth curve, and because the more rough the drug-proximal edge is, the more sudden protrusion or depression on the edge is, the better the filtering effect is when performing low-pass filtering processing on the drug-proximal edge using butterworth filtering, and butterworth filtering is a well-known technique in the art and will not be described herein. Of course, the present invention also supports, without limitation, the use of any of a variety of other possible filtering methods to perform low-pass filtering on the near edge of the drug.
According to the method, the filtering edge is obtained after the medicine adjacent edge is subjected to low-pass filtering processing, and the filtering edge is a relatively smooth edge, so that the absolute value of the difference between the number of the pixel points in the filtering edge and the preset number can be calculated as the roughness, and the roughness condition of the medicine adjacent edge can be more accurately and objectively represented by determining the filtering edge and calculating the absolute value of the difference between the number of the pixel points in the filtering edge and the preset number.
The disintegration characteristic value is a characteristic value of the strength degree of the drug corresponding to the pixel point to be detected in the disintegration process.
Further, in the embodiment of the present invention, calculating the disintegration characteristic value of the pixel point to be detected according to the pixel point distance and the roughness between the pixel point to be detected and the positioning pixel point includes: determining the pixel point distance between the pixel point to be detected and the positioning pixel point as a positioning distance; and calculating a product normalized value of the roughness and the positioning distance as a disintegration characteristic value, wherein the corresponding calculation formula is as follows:
、
in the formula (I), the compound is shown in the specification,
indicates the fifth->
The pixel point to be detected is at the fifth->
The disintegration characteristic value of each time point to be examined->
Index representing the pixel to be tested, and->
Index representing the time point to be examined>
Indicates the fifth->
The pixel point to be detected is at the fifth->
The roughness of the near edge of the drug corresponding to each time point to be examined, is measured>
Indicates the fifth->
The pixel point to be detected is at the fifth->
The positioning distance of the respective time point to be examined->
The normalization processing function is expressed, in an embodiment of the present invention, the normalization processing may select a maximum and minimum normalization processing method, and in subsequent steps, the maximum and minimum normalization processing method is adopted.
In the embodiment of the invention, the disintegration characteristic value can be used for representing the degree of change characteristic of the edge of a drug after the drug is disintegrated within a short time by taking a pixel point to be detected as a reference, and the disintegration characteristic is specifically represented as that the undisrupted drug is farther from the disintegrated drug and the disintegrated part of the drug has an irregular drug edge.
S103: performing region growing treatment on the pixel points to be detected to obtain a growing region, and determining a drug residue positioning region according to the distribution of the pixel points in the drug gray image at the time point to be detected; and determining the diffusion coefficient of the pixel point to be detected according to the principal component direction of the growth area, the principal component direction of the medicine edge around the positioning pixel point, the principal component direction of the medicine residue positioning area and the disintegration characteristic value.
In the embodiment of the invention, the region growing algorithm can be used for performing region growing treatment on the pixel points to be detected to obtain a growing region, wherein the region growing algorithm can form adjacent pixel points with the same property into a region, the pixel points to be detected are used as seed points of the region growing algorithm, the pixel points which represent medicines around the pixel points to be detected can be determined, and the growing region is formed.
Further, in the embodiment of the present invention, determining a drug residue positioning region according to the distribution of pixel points in the drug gray-scale image at the time point to be detected includes: determining a disintegrated drug region in the drug gray image at the time point to be detected, clustering the disintegrated drug region to obtain at least one clustering region, and taking the clustering region to which the positioning pixel points belong as a drug residue positioning region.
In the embodiment of the invention, all the pixel points representing the drugs in the drug gray image at the time point to be detected can be clustered, the Canny edge detection operator can be used for carrying out edge detection on the drug gray image at the time point to be detected, so as to determine the disintegrated drug region in the drug gray image at the time point to be detected, or the background pixel points and the drug pixel points can be distinguished in a binary detection manner, so as to obtain the disintegrated drug region, which is not limited.
In the embodiment of the invention, the clustering number can be determined according to prior experience, and then the disintegrated drug regions are clustered by using a k-means clustering algorithm, wherein the k value is the clustering number, and the k-means clustering algorithm is a technology well known in the art and is not described herein again.
In the embodiment of the present invention, the clustering region to which the positioning pixel belongs can be used as the drug residue positioning region, and it can be understood that in the same clustering region, the diffusion directions of the drug particles are substantially the same, and the diffusion directions corresponding to the pixel points in the drug residue positioning region are also substantially the same.
Further, in the embodiment of the present invention, determining the diffusion coefficient of the pixel to be detected according to the principal component direction of the growth area, the principal component direction of the edge of the drug around the positioning pixel, the principal component direction of the drug residue positioning area, and the disintegration characteristic value includes: calculating the absolute value of the difference value between the principal component direction angle of the growth area and the principal component direction angle of the periphery of the positioning pixel point of the medicine edge to be used as a first direction difference; calculating the difference absolute value of the principal component direction angle of the growth area and the principal component direction angle of the drug residue positioning area in the time point to be detected as a second direction difference; calculating a ratio normalization value of the first direction difference and the second direction difference as a direction consistency coefficient; the product of the directional uniformity coefficient and the disintegration property value is calculated as a diffusion coefficient.
In the embodiment of the present invention, a Principal Component Analysis (PCA) method may be used to determine the Principal Component direction angle of the growth region, the Principal Component direction angle of the drug edge around the positioning pixel point, and the Principal Component direction angle of the drug residue positioning region, respectively, and the Principal Component Analysis is a technique well known in the art and will not be described herein.
The main component direction angle of the drug residue positioning region and the main component direction angle of the growth region can further represent the direction angle of diffusion of drug particles, and the main component direction angle of the drug edge around the positioning pixel point can represent the direction angle of the undisrupted drug edge, so that in other embodiments of the present invention, the corresponding diffusion coefficient calculation formula is:
in the formula (I), the compound is shown in the specification,
represents a fifth or fifth party>
The pixel point to be detected is at the fifth->
Diffusion coefficient at each time point to be examined>
Represents a fifth or fifth party>
The pixel point to be detected is at the fifth->
Disintegration characteristic value for individual time point to be determined>
Index representing the pixel to be tested, and->
Index representing the time point to be examined>
Represents the angle of the main component direction of the growing area, <' > or>
Direction angles of principal component representing a drug margin surrounding a located pixel point, based on a location of the principal component in the image>
A main component direction angle, representing a drug residue positioning area>
Represents a normalized processing function, <' > based on a normalized processing function>
For the purpose of securing the value, by means of ^ in the denominator>
Principal component orientation angle and drug for avoiding growth areaThe denominator is 0 when the principal component direction angles of the residual localization areas coincide.
Under the condition of not being influenced by external force, the normal diffusion direction of the drug to be identified after disintegration is the tangential direction of the drug edge, and the larger the difference between the main component direction of the growth area and the main component direction of the drug edge around the positioning pixel point is, the larger the diffusion coefficient is, the more the diffusion of the pixel point to be detected along the normal direction is represented; the principal component direction of the growth region and the principal component direction of the drug residue positioning region can both represent the main diffusion direction of the drug particles in a certain region, that is, under the condition of normal drug particle diffusion, the principal component direction of the corresponding growth region and the principal component direction of the drug residue positioning region should be consistent, and the difference between the principal component direction of the growth region and the principal component direction of the drug residue positioning region is smaller, the more the diffusion of the pixel point to be detected along the normal direction can be represented, that is, the diffusion coefficient is larger; the disintegration characteristic value can represent the disintegration degree of the pixel point to be detected, namely, the diffusion coefficient can be used for representing the consistency of the diffusion trace of the drug particles in the diffusion direction and the original position on the basis of the disintegration characteristic presented by the drug particles corresponding to the pixel point to be detected after disintegration.
The larger the diffusion coefficient is, the greater the consistency of the corresponding diffusion trace is, and the more likely the drug particles are to correspond to newly disintegrated drug particles between the previous time point and the time point to be detected; the difference between the main component direction of the growth area corresponding to the deposited drug particles and the main component direction of the drug residue positioning area is large, and the corresponding diffusion coefficient is small, so that newly disintegrated drug particle pixel points and deposited drug particle pixel points can be effectively distinguished according to the diffusion coefficient, and the method specifically refers to the following embodiments.
S104: screening the pixel points to be detected according to the diffusion coefficient, determining target pixel points, determining pixel points which represent the same medicine particles with the target pixel points in the medicine gray-scale image at the last time point as matching pixel points, and determining the diffusion distance of the time point to be detected according to the positions of the target pixel points and the matching pixel points; and determining the uniform degree of drug disintegration according to the diffusion distances at different time points, and taking the uniform degree of drug disintegration as a data processing result.
In the embodiment of the invention, the diffusion coefficients of all the pixels to be detected can be determined, and then the pixels to be detected are screened according to the diffusion coefficients to determine the target pixels.
As shown in fig. 3, fig. 4 and fig. 5, fig. 3 is a schematic diagram of an initial state of drug disintegration provided by an embodiment of the present invention, fig. 4 is a schematic diagram of a second state of drug disintegration provided by an embodiment of the present invention, and fig. 5 is a schematic diagram of a third state of drug disintegration provided by an embodiment of the present invention, it can be understood that, as the disintegration time elapses, the disintegration of the drug to be identified gradually transits from the initial state of fig. 3 to the third state of fig. 5, and the distribution state of the pixel points in the image of the edge of the drug particles that remain accumulated may affect the processing result of the drug disintegration process to be identified at the adjacent time points.
Further, in the embodiment of the present invention, the screening the to-be-detected pixel points according to the diffusion coefficient to determine the target pixel point includes: and taking the pixel point to be detected with the diffusion coefficient larger than the preset coefficient threshold value as a target pixel point.
In the embodiment of the present invention, a preset coefficient threshold may be set for screening the pixel points to be detected, where the preset coefficient threshold is a threshold of a diffusion coefficient, optionally, the preset coefficient threshold is set to 0.8, and may be adjusted according to actual requirements, and no limitation is imposed on the adjustment.
In the embodiment of the invention, newly disintegrated drug particle pixel points and deposited drug particle pixel points can be effectively distinguished according to whether the diffusion coefficient is greater than the preset coefficient threshold value or not by setting the preset coefficient threshold value, that is, when the diffusion coefficient is greater than the preset coefficient threshold value, the pixel points to be detected can be represented as the newly disintegrated drug particle pixel points, when the diffusion coefficient is less than or equal to the preset coefficient threshold value, the pixel points to be detected can be represented as the deposited drug particle pixel points, and because the movement trend of the deposited drug particles in two spaced time points can not effectively represent the disintegration performance of the drug to be identified, the newly disintegrated drug particle pixel points can be used as target pixel points, that is, the pixel points to be detected with the diffusion coefficient greater than the preset coefficient threshold value can be used as target pixel points.
In the embodiment of the present invention, it may be determined that a pixel point representing the same drug particle as a target pixel point in a drug gray-scale image at a previous time point is a matching pixel point, when the same drug particle is characterized in two images, a marking method may be adopted to mark the drug particle at the previous time point, and then the matching pixel point in the drug gray-scale image at the previous time point is determined according to the marking, or a shape context algorithm may be used to determine the matching pixel point, where the shape context algorithm is a shape matching algorithm commonly used in the art, and is not described in detail herein, or any other possible implementation manner may be used, which is not limited herein.
Further, in the embodiment of the present invention, determining the diffusion distance of the time point to be measured according to the position of the target pixel point and the position of the matching pixel point includes: mapping the target pixel point and the matching pixel point to the medicine gray level image at the same time point, and determining the Euclidean distance between the two mapping pixel points as a mapping distance; and calculating the mean value of the mapping distances between all matched target pixel points and the matched pixel points as the diffusion distance.
In the embodiment of the invention, the target pixel point and the matching pixel point can be mapped to the gray-scale image of the medicine at the same time point, so that the Euclidean distance between the two mapping pixel points is determined as the mapping distance. The diffusion distance can be used for representing the disintegration condition of the drug to be identified from the last time point to the time point to be detected, and the larger the diffusion distance is, the stronger the disintegration is, and the smaller the diffusion distance is, the slower the disintegration is.
Correspondingly, the uniformity of disintegration can be determined from the diffusion distance in adjacent time periods. Further, in the embodiment of the present invention, the determining the uniform degree of drug disintegration according to the diffusion distances at different time points includes: calculating the difference mean value of the diffusion distances of all two adjacent time points, and taking the normalized value of the difference mean value as the disintegration uniformity of the medicine.
The disintegration uniformity degree is one of indexes of the disintegration performance of the medicine to be identified, and can be determined according to the difference value of the diffusion distances of two adjacent time points, the smaller the difference value is, the smaller the disintegration speed change of the two adjacent time points is, and the larger the disintegration uniformity is, so that the difference value mean value of the diffusion distances of all the two adjacent time points is determined, and the difference value mean value is subjected to normalization processing to be used as the disintegration uniformity degree of the medicine, so that the disintegration performance of the medicine can be objectively represented by the disintegration uniformity degree of the medicine.
After the embodiment of the invention determines the uniform degree of drug disintegration, the uniform degree of drug disintegration can be used as a data processing result, which is convenient for a related data processing system or related workers to record and count.
In summary, the invention collects the gray images of the drugs at different time points, and determines the pixel points to be tested between the drug edges at two adjacent time points, so that the analysis can be performed according to the change of the drug edges after the drugs are dissolved, the pixel points to be tested can be accurately determined, and the disintegration performance analysis of the drugs can be performed according to the distribution characteristics of the pixel points to be tested in the following process; the method comprises the steps of determining the roughness of the edge of a medicine around a positioning pixel point, accurately representing the change of the edge of the medicine in the disintegration process according to the roughness, determining the disintegration characteristic value according to the distance between the disintegrated medicine particles and the medicine which is not disintegrated and the roughness, and effectively analyzing the morphological change of the medicine to be identified after disintegration, thereby determining the diffusion coefficient of a pixel point to be detected by combining the direction characteristics of the distribution of the pixel point in a medicine gray image, wherein the diffusion coefficient can effectively evaluate the disintegration condition of the pixel point to be detected, and analyze the direction consistency of the growth area of the pixel point to be detected and the residual trace of the medicine, effectively preventing the interference of an obvious edge formed when the medicine particle residue diffuses outwards, enabling the selection of a target pixel point to be more accurate, and better conforming to the objective rule of the residue of the newly dissolved medicine particles in the disintegration process of the medicine to be identified; through the position analysis of the target pixel point and the matching pixel point which represent the same drug particle between two adjacent time points, the diffusion distance of the drug particle between the two time points is accurately determined, the uniformity of the drug to be identified in the whole disintegration process is accurately determined according to the diffusion distances at different moments, the accurate test of the drug disintegration performance is effectively realized, the determination of the disintegration speed uniformity in the subsequent drug disintegration process is more accurate, and the reliability is higher.
It should be noted that: the precedence order of the above embodiments of the present invention is only for description, and does not represent the merits of the embodiments. The processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing may also be possible or may be advantageous.
All 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 other embodiments.
Claims (9)
1. A data processing method for drug disintegration property identification, the method comprising:
acquiring drug gray images of drugs to be identified at different time points in the disintegration process, optionally selecting a certain time point to be detected, and taking pixel points in an area surrounded by the drug edge of the time point to be detected and the drug edge of the last time point in the drug gray images as pixel points to be detected;
selecting a certain pixel point to be tested, determining a positioning pixel point of the pixel point to be tested at the medicine edge of the time point to be tested, determining the roughness of the medicine edge around the positioning pixel point, and calculating the disintegration characteristic value of the pixel point to be tested according to the pixel point distance between the pixel point to be tested and the positioning pixel point and the roughness;
performing region growing processing on the pixel points to be detected to obtain a growing region, and determining a drug residue positioning region according to the distribution of the pixel points in the drug gray level image of the time point to be detected; determining the diffusion coefficient of the pixel point to be detected according to the principal component direction of the growth area, the principal component direction of the drug edge around the positioning pixel point, the principal component direction of the drug residue positioning area and the disintegration characteristic value;
screening the pixel points to be detected according to the diffusion coefficient, determining target pixel points, determining pixel points which represent the same medicine particles with the target pixel points in the medicine gray-scale image at the last time point as matching pixel points, and determining the diffusion distance of the time point to be detected according to the positions of the target pixel points and the positions of the matching pixel points; and determining the uniform degree of drug disintegration according to the diffusion distances at different time points, and taking the uniform degree of drug disintegration as a data processing result.
2. The method of claim 1, wherein said determining the roughness of the edge of the drug around the localized pixel comprises:
determining a medicine edge formed by a preset number of pixel points around the positioning pixel point on the medicine edge of the time point to be detected as a medicine adjacent edge;
and performing low-pass filtering processing on the medicine adjacent edge to obtain a filtering edge, and calculating the absolute value of the difference between the number of pixel points in the filtering edge and the preset number to serve as the roughness.
3. The method of claim 1, wherein the calculating the disintegration feature value of the pixel to be measured according to the pixel distance between the pixel to be measured and the positioning pixel and the roughness comprises:
determining the pixel point distance between the pixel point to be detected and the positioning pixel point as a positioning distance;
and calculating a product normalized value of the roughness and the positioning distance as the disintegration characteristic value.
4. The method of claim 1, wherein the determining the drug residue location area according to the distribution of the pixel points in the drug gray-scale image of the time point to be measured comprises:
determining a disintegrated drug area in the drug gray image at the time point to be detected, clustering the disintegrated drug area to obtain at least one cluster area, and taking the cluster area to which the positioning pixel point belongs as the drug residue positioning area.
5. The method of claim 1, wherein the determining the diffusion coefficient of the pixel to be tested according to the principal component direction of the growth region, the principal component direction of the drug margin around the positioning pixel, the principal component direction of the drug residue positioning region and the disintegration feature value comprises:
calculating the absolute value of the difference value between the principal component direction angle of the growth region and the principal component direction angle of the drug edge around the positioning pixel point as a first direction difference; calculating the absolute value of the difference value between the main component direction angle of the growth area and the main component direction angle of the drug residue positioning area at the time point to be detected as a second direction difference; calculating a ratio normalization value of the first direction difference and the second direction difference as a direction consistency coefficient;
calculating a product of the directional uniformity coefficient and the disintegration feature value as the diffusion coefficient.
6. The method as claimed in claim 1, wherein the step of screening the pixel points to be detected according to the diffusion coefficient to determine target pixel points comprises:
and taking the pixel point to be detected with the diffusion coefficient larger than a preset coefficient threshold value as a target pixel point.
7. The method of claim 1, wherein the determining the diffusion distance of the time point to be measured according to the position of the target pixel point and the position of the matching pixel point comprises:
mapping the target pixel point and the matching pixel point to the medicine gray level image at the same time point, and determining the Euclidean distance between the two mapping pixel points as a mapping distance;
and calculating the mean value of the mapping distances between all the matched target pixel points and the matched pixel points to be used as the diffusion distance.
8. The method of claim 1, wherein said determining the degree of uniformity of drug disintegration from said diffusion distances at different time points comprises:
calculating the difference mean value of the diffusion distances of all two adjacent time points, and taking the normalized value of the difference mean value as the disintegration uniformity degree of the medicine.
9. The method of claim 1, wherein said determining the location pixels of the pixel under test at the edge of the medication at the time point under test comprises:
and calculating Euclidean distances between the pixel points to be detected and all pixel points on the medicine edge of the time point to be detected respectively, and taking the pixel point corresponding to the minimum Euclidean distance as a positioning pixel point.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310221379.8A CN115909302B (en) | 2023-03-09 | 2023-03-09 | Data processing method for identifying drug disintegration performance |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310221379.8A CN115909302B (en) | 2023-03-09 | 2023-03-09 | Data processing method for identifying drug disintegration performance |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115909302A true CN115909302A (en) | 2023-04-04 |
| CN115909302B CN115909302B (en) | 2023-06-16 |
Family
ID=86495070
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310221379.8A Active CN115909302B (en) | 2023-03-09 | 2023-03-09 | Data processing method for identifying drug disintegration performance |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115909302B (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20130251194A1 (en) * | 2012-03-26 | 2013-09-26 | Gregory Gerhard SCHAMP | Range-cued object segmentation system and method |
| CN106447708A (en) * | 2016-10-10 | 2017-02-22 | 吉林大学 | OCT eye fundus image data registration method |
| CN106651847A (en) * | 2016-12-21 | 2017-05-10 | 浙江大学 | Remote sensing image fog information detection method |
| US20210212943A1 (en) * | 2018-09-19 | 2021-07-15 | Aron H. Blaesi | Dosage form comprising structured solid-solution framework of sparingly-soluble drug and method for manufacture thereof |
| CN114897773A (en) * | 2022-03-31 | 2022-08-12 | 海门王巢家具制造有限公司 | Distorted wood detection method and system based on image processing |
| CN115131396A (en) * | 2021-03-26 | 2022-09-30 | 同济大学 | Improved target tracking method in medical image based on frame difference |
| CN115273053A (en) * | 2022-09-28 | 2022-11-01 | 江苏南通鼎顺网络科技有限责任公司 | Drug disintegration performance identification method based on data processing |
-
2023
- 2023-03-09 CN CN202310221379.8A patent/CN115909302B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20130251194A1 (en) * | 2012-03-26 | 2013-09-26 | Gregory Gerhard SCHAMP | Range-cued object segmentation system and method |
| CN106447708A (en) * | 2016-10-10 | 2017-02-22 | 吉林大学 | OCT eye fundus image data registration method |
| CN106651847A (en) * | 2016-12-21 | 2017-05-10 | 浙江大学 | Remote sensing image fog information detection method |
| US20210212943A1 (en) * | 2018-09-19 | 2021-07-15 | Aron H. Blaesi | Dosage form comprising structured solid-solution framework of sparingly-soluble drug and method for manufacture thereof |
| CN115131396A (en) * | 2021-03-26 | 2022-09-30 | 同济大学 | Improved target tracking method in medical image based on frame difference |
| CN114897773A (en) * | 2022-03-31 | 2022-08-12 | 海门王巢家具制造有限公司 | Distorted wood detection method and system based on image processing |
| CN115273053A (en) * | 2022-09-28 | 2022-11-01 | 江苏南通鼎顺网络科技有限责任公司 | Drug disintegration performance identification method based on data processing |
Non-Patent Citations (3)
| Title |
|---|
| XIANZHEN YIN: "Cavities spatial distribution confined by microcrystalline cellulose particles determines tablet disintegration patterns", 《POWDER TECHNOLOGY》 * |
| 冷冰，张明: "生理屏障及结合和代谢对药物分子扩散的影响──扩散方程及数值求解", 中国医学物理学杂志, no. 02 * |
| 牟建民;孟桂兰;: "功能性胃肠病影像学检查技术研究与临床应用", 中国医学装备, no. 03 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115909302B (en) | 2023-06-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Chen et al. | Automated evaluation of tumor spheroid behavior in 3D culture using deep learning-based recognition | |
| WO2018040302A1 (en) | Method and system for measuring width of cut tobacco piece or cut stem, and server having said system | |
| CN103164692B (en) | A kind of special vehicle instrument automatic identification system based on computer vision and method | |
| JPH0475463B2 (en) | ||
| EP1629438B1 (en) | Automatic optimal view determination for cardiac acquisitions | |
| CN101996329A (en) | Device and method for detecting blood vessel deformation area | |
| Stanganelli et al. | Computer-aided diagnosis of melanocytic lesions | |
| CN115691722B (en) | Quality control method, device, equipment, medium and program product for medical data detection | |
| JPH0418267B2 (en) | ||
| CN117333489B (en) | Film damage detection device and detection system | |
| CN110490971B (en) | Method for reconstructing cell dynamic characteristic three-dimensional image under biological microscope | |
| CN117912712A (en) | Thyroid disease data intelligent management method and system based on big data | |
| CN113288214B (en) | Method and device for processing ultrasonic Doppler frequency spectrum data and readable storage medium | |
| CN117237747B (en) | Hardware defect classification and identification method based on artificial intelligence | |
| CN115909302A (en) | Data processing method for identifying disintegration performance of medicine | |
| Ahmed et al. | Segmentation techniques for morphometric measurements of blood cells: Overview and research challenges | |
| CN113191330A (en) | Method for identifying area growth pores by fusing secondary electrons and back scattering electron images | |
| KR20180007071A (en) | Method of determining patient case identity in digital pathology system | |
| CN114460005A (en) | Dynamic microscopic imaging red blood cell multi-angle morphology measuring method and system | |
| CN117906726B (en) | Abnormal detection system for weight data of live cattle body ruler | |
| CN111028906A (en) | Method for rapidly detecting positive charge amount of tissue cells | |
| CN109182453A (en) | A kind of control method of DNA ploidy body analytical equipment | |
| CN115908429B (en) | Method and system for detecting grinding precision of foot soaking powder | |
| CN115508844B (en) | Intelligent detection method for deviation of logistics conveyor based on laser radar | |
| CN112862804B (en) | System and method for processing retina blood vessel image |
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 |