Drug stability monitoring method and system based on image analysis

Abstract

The present application provides a drug stability monitoring method and system based on image analysis, which relates to the field of image processing technology. The method includes: obtaining multiple first images of the drug to be monitored; the multiple first images are taken under the same lighting conditions in a preset shooting cycle; for each first image, extracting color features, shape features and texture features from the first image; and obtaining the stability monitoring results of the drug to be monitored based on the color features, shape features and texture features.

Description

Technical Field

[0001] The present application relates to the field of image processing technology, and in particular to a drug stability monitoring method and system based on image analysis. Background Art

[0002] The stability of a drug refers to its ability to maintain its physical, chemical and biological properties under specified storage conditions. Drug stability monitoring is of great significance to ensure the safety and effectiveness of drugs. Traditional drug stability monitoring methods mainly include chemical analysis, physical testing and biological testing. Although these methods can provide relatively accurate results, they usually require complex instruments and equipment and professional operating skills, and are time-consuming, making it difficult to achieve real-time monitoring and large-scale application.

[0003] With the rapid development of image analysis technology, it has also been applied in drug stability monitoring. In related technologies, when performing drug stability analysis, drug images are taken to determine the color change of the drug, so as to obtain drug stability monitoring results based on the color change of the drug.

[0004] However, existing image analysis technology is based on the color changes of drugs, which leads to poor reliability and accuracy of monitoring results. Summary of the invention

[0005] The present application provides a drug stability monitoring method and system based on image analysis, which are used to improve the reliability and accuracy of drug stability monitoring results.

[0006] In a first aspect, the present application provides a drug stability monitoring method based on image analysis, the method comprising: obtaining multiple first images of the drug to be monitored; the multiple first images are captured under the same lighting conditions in a preset shooting period; for each first image, extracting color features, shape features and texture features from the first image; and obtaining the stability monitoring results of the drug to be monitored based on the color features, shape features and texture features.

[0007] Optionally, extracting color features from the first image includes: converting the first image from an RGB color space to an HSV color space to obtain a second image; respectively calculating the hue value of a hue channel, the saturation value of a saturation channel, and the brightness value of a brightness channel in the second image; drawing an HSV color space model according to the hue value of the hue channel, the saturation value of the saturation channel, and the brightness value of the brightness channel; and obtaining color features according to the HSV color space model.

[0008] Optionally, extracting shape features from the first image includes: converting the first image into a binary image by binarization processing; identifying drug edges of the drug to be monitored from the binary image; and calculating shape features based on the identified drug edges.

[0009] Optionally, extracting texture features from the first image includes: calculating a gray level co-occurrence matrix of the first image; and extracting texture features according to the gray level co-occurrence matrix.

[0010] Optionally, the stability monitoring results of the drug to be monitored are obtained based on the color characteristics, shape characteristics and texture characteristics, including: plotting the color feature change curve over time, the shape feature change curve over time and the texture feature change curve over time in the time sequence of a preset shooting cycle; determining the stability monitoring results of the drug to be monitored based on the color feature change curve over time, the shape feature change curve over time and the texture feature change curve over time; the stability monitoring results include the stability grade and the drug change trend.

[0011] Optionally, the method further includes: matching the first image with a preset standard drug image through a template matching algorithm to obtain a matching result.

[0012] Optionally, the matching result includes: a normal area and an abnormal area on the surface of the drug to be monitored; the normal area is an image area whose matching degree meets a first preset threshold; the abnormal area is an image area whose matching degree meets a second preset threshold.

[0013] Optionally, the method also includes: analyzing the changes in the number, position and size of abnormal areas on the surface of the monitored drug according to the time sequence of a preset shooting cycle; and drawing a curve of the changes of the abnormal areas over time based on the changes to obtain the stability monitoring results of the monitored drug.

[0014] In the second aspect, the present application provides a drug stability monitoring system based on image analysis, the system comprising: an image acquisition module, used to acquire multiple first images of the drug to be monitored; the multiple first images are taken under the same lighting conditions in a preset shooting period; an image processing module, used to extract color features, shape features and texture features from each first image; a data analysis module, used to obtain stability monitoring results of the drug to be monitored based on color features, shape features and texture features.

[0015] In a third aspect, the present application provides a computer device comprising: a processor, and a memory communicatively connected to the processor; the memory stores computer-executable instructions; the processor executes the computer-executable instructions stored in the memory to implement a drug stability monitoring method based on image analysis as described in any one of the first aspects of the present application.

[0016] The present application provides a drug stability monitoring method and system based on image analysis. The method takes multiple first images under the same lighting conditions, extracts color features, shape features, and texture features from each first image, and comprehensively evaluates the stability of the drug based on the color features, shape features, and texture features to obtain the stability monitoring results of the drug to be monitored. The method can effectively overcome the defects in the prior art and provide a new solution for drug stability monitoring. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] By reading the detailed description below with reference to the accompanying drawings, the above and other purposes, features and advantages of the exemplary embodiments of the present application will become readily understood. In the accompanying drawings, several embodiments of the present application are shown in an exemplary and non-limiting manner, wherein: Figure 1 A schematic diagram of a process for monitoring drug stability based on image analysis provided in an embodiment of the present application; Figure 2 A schematic diagram of the structure of a drug stability monitoring system based on image analysis provided in an embodiment of the present application; Figure 3 A schematic diagram of a computer device structure is provided for this application.

[0018] The above drawings have shown clear embodiments of the present application, which will be described in more detail later. These drawings and text descriptions are not intended to limit the scope of the present application in any way, but to illustrate the concept of the present application to those skilled in the art by referring to specific embodiments. DETAILED DESCRIPTION

[0019] Here, exemplary embodiments are described in detail, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments are not intended to represent all embodiments consistent with the present application. Instead, they are merely examples of methods and devices consistent with some aspects of the present application as detailed in the appended claims.

[0020] First, the technical terms involved in this application are explained: HSV color space: is a color space model that divides color into three independent components: hue, saturation, and value. These three components represent different attributes of color, making the color representation more intuitive and easy to understand. Among them, hue is used to represent the type or type of color. Saturation is used to represent the purity or brightness of the color, that is, the proportion of white or gray mixed in the color. Brightness is used to represent the lightness or darkness of the color.

[0021] Drug stability: refers to the ability of a drug to maintain its physical, chemical and biological properties under specified storage conditions.

[0022] Drug stability monitoring is of great significance to ensure the safety and effectiveness of drugs. Stable drugs can maintain their original efficacy and safety under specified storage conditions, while unstable drugs may degrade, deteriorate, or even produce harmful substances, posing a threat to patient health.

[0023] Commonly used drug stability monitoring methods include chemical analysis, physical testing, biological testing, and image-based preliminary testing. Among them, although chemical analysis, physical testing, and biological testing can provide relatively accurate results, they usually require complex instruments and equipment and professional operating skills, and are time-consuming, making it difficult to achieve real-time monitoring and large-scale application. The image-based preliminary testing method takes images of the drug and preliminarily determines changes in the drug's appearance, such as color changes, shape changes, etc.

[0024] Although image-based preliminary detection methods are simple and easy to use, they are limited to preliminary judgments of appearance changes, lack quantitative analysis, and are inaccurate. These methods can usually only provide qualitative results and cannot perform accurate quantitative analysis. Existing image analysis methods usually only focus on a single feature (such as color or shape) and fail to comprehensively evaluate multiple features, resulting in limited reliability and accuracy of monitoring results. This single-feature analysis method cannot fully reflect the stability changes of drugs and is prone to missed detection or misjudgment.

[0025] Based on this, the embodiment of the present application provides a drug stability monitoring method based on image analysis, which comprehensively evaluates the stability of the drug by taking multiple images under the same lighting conditions and extracting color features, shape features and texture features. The method is simple to operate, low cost, and highly real-time, which can effectively overcome the defects of the prior art and provide a new solution for drug stability monitoring.

[0026] The following specific embodiments are used to describe in detail the technical solution of the present application and how the technical solution of the present application solves the above-mentioned technical problems. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments. The embodiments of the present application will be described below in conjunction with the accompanying drawings.

[0027] Figure 1 The following is a schematic diagram of a method for monitoring drug stability based on image analysis provided in an embodiment of the present application. Figure 1 As shown, the method provided in the embodiment of the present application may include the following steps: 1100, obtaining a plurality of first images of the drug to be monitored; the plurality of first images are captured under the same lighting conditions in a preset capturing cycle.

[0028] 1200, for each first image, extract color features, shape features, and texture features from the first image.

[0029] 1300, obtaining stability monitoring results of the drug to be monitored based on color features, shape features, and texture features.

[0030] In drug stability monitoring, images of different periods need to be taken under the same lighting conditions for effective comparison and analysis. When acquiring images, it is necessary to select a high-resolution camera and use a fixed and stable light source to ensure consistent lighting conditions for each shot. Use a uniform and non-reflective background to avoid background effects on the image, thereby ensuring the image quality of the first image of the drug to be monitored.

[0031] When photographing the drugs to be monitored, it is necessary to photograph the same position of the drugs at the same angle, and each shot needs to add a timestamp or other mark to the image to track the shooting time of each picture. In the actual monitoring process, a fixed shooting cycle can be set according to actual needs, such as weekly, monthly, etc.

[0032] After obtaining multiple first images of the drug to be monitored, each first image is processed as follows: the color features, shape features and texture features of the drug are extracted from the first image. It can be understood that oxidation or other chemical reactions may occur during the storage of the drug, resulting in color changes, and color change is an important indicator of drug degradation. After long-term storage, the drug may deform, crack or dissolve, which can be detected by analyzing the shape and size changes of the drug. The microstructural changes on the surface of the drug are one of the important signs of drug stability. Texture analysis techniques, such as gray level co-occurrence matrix (GLCM), wavelet transform, etc., are used to extract texture features from drug images, and the stability of the drug is evaluated by comparing the changes in texture features at different time points.

[0033] Specifically, when extracting color features from the first image, the first image can be converted from the RGB color space to the HSV color space to obtain the second image. After that, the hue value of the hue channel, the saturation value of the saturation channel, and the brightness value of the brightness channel in the second image are calculated respectively; the HSV color space model is drawn according to the hue value of the hue channel, the saturation value of the saturation channel, and the brightness value of the brightness channel; and the color features are obtained according to the HSV color space model. Among them, the color features can be, for example, statistical features such as mean and variance. If the color changes significantly, it indicates that the drug may have undergone oxidation or other chemical reactions and has poor stability.

[0034] When extracting shape features from the first image, the first image can be converted into a binary image by binarization processing; the drug edge of the drug to be monitored is identified from the binary image; and the shape features are calculated based on the identified drug edge. The shape features may include geometric features such as the area, perimeter, and aspect ratio of the outline surrounded by the drug edge.

[0035] By comparing the edge contours of the drug at different time points, analyzing the changes in geometric features such as area, perimeter, and aspect ratio, and drawing a curve of the change in geometric features over time, it is observed whether there is obvious shape change. If the shape change is significant, it may indicate that the drug has undergone physical deformation or cracks and has poor stability.

[0036] When extracting texture features from the first image, the gray level co-occurrence matrix of the first image can be calculated; and texture features can be extracted based on the gray level co-occurrence matrix. Among them, texture features can include texture features such as contrast and energy. By comparing the gray level co-occurrence matrix (GLCM) features of the drug at different time points, analyzing the changes in texture features such as contrast, energy, and entropy, and plotting the change curve of texture features over time, it is observed whether there is a significant texture change. If the texture changes significantly, it may indicate that the microstructure of the drug surface has changed and the stability is poor.

[0037] After obtaining the color features, shape features and texture features, the stability monitoring results of the drugs to be monitored can be obtained based on the color features, shape features and texture features. Specifically, according to the time sequence of the preset shooting cycle, the curves of the color features changing over time, the curves of the shape features changing over time and the curves of the texture features changing over time are drawn; the stability monitoring results of the drugs to be monitored are determined based on the curves of the color features changing over time, the curves of the shape features changing over time and the curves of the texture features changing over time; the stability monitoring results include the stability level and the drug change trend.

[0038] For example, in color features, the hue mean changes from 100 to 105, the hue standard deviation changes from 10 to 12, the saturation mean changes from 50 to 55, the saturation standard deviation changes from 15 to 17, the value mean changes from 150 to 145, and the value standard deviation changes from 20 to 22. In shape features, the area changes from 1000 square pixels to 1020 square pixels, the perimeter changes from 120 pixels to 125 pixels, and the aspect ratio changes from 1.5 to 1.55. In texture features, the contrast changes from 100 to 105, the energy changes from 200 to 210, and the entropy changes from 0.8 to 0.85.

[0039] The stability monitoring results thus obtained may include: the color of the monitored drug deepens and tiny defects appear on the surface, indicating that the drug has undergone a slight oxidation reaction and has suffered slight physical damage during storage; changes in temperature and humidity may have a certain impact on the stability of the monitored drug.

[0040] The stability monitoring results may also include recommended measures, such as recommendations for storage conditions: store the drug in an environment where the temperature is controlled at 20°C ± 2°C and the humidity is controlled at 50% ± 5%. Recommendations for production processes: optimize packaging materials and use packaging with better moisture-proof and antioxidant properties. Recommendations for further research: conduct long-term stability tests to further verify the stability of the drug under different environmental conditions.

[0041] Furthermore, in some embodiments, defect detection can also be used to determine whether the monitored drug shows early signs of deterioration. Specifically, in the embodiments of the present application, the first image can be matched with the preset standard drug image through a template matching algorithm to obtain a matching result. The matching result includes: normal areas and abnormal areas on the surface of the monitored drug; the normal area is the image area whose matching degree meets the first preset threshold; the abnormal area is the image area whose matching degree meets the second preset threshold.

[0042] By using the template matching algorithm, the abnormal area on the surface of the monitored drug can be detected. The abnormal area may be the area of ​​defects such as spots and cracks on the surface of the monitored drug. When identifying abnormal areas and normal areas, the image can be segmented into different areas according to the distribution of pixel values, and then the threshold is automatically determined using Otsu's method.

[0043] After obtaining the matching results, the changes in the number, position and size of the abnormal areas on the surface of the monitored drug are analyzed according to the time sequence of the preset shooting cycle; the change curve of the abnormal area over time is drawn according to the changes to obtain the stability monitoring results of the monitored drug. Specifically, if the number of defects increases or the defects expand, it may indicate that the physical state of the drug has changed and the stability is poor.

[0044] Among them, the stability monitoring results of the monitored drugs may include stability grade and change trend. The stability grade can be divided into several grades according to the comprehensive evaluation of the above-mentioned characteristic changes, such as "stable", "slight change", "significant change", etc. The change trend can summarize the change trend of the monitored drugs at different time points and point out which characteristic changes are most significant.

[0045] For example, the evaluation of each feature can be listed. For example, for color features, the changes in statistical features such as color mean and variance are listed, with a change curve graph. For shape features, the changes in geometric features such as area, perimeter, aspect ratio, etc. are listed, with a change curve graph. For texture features, the changes in texture features such as contrast, energy, entropy, etc. are listed, with a change curve graph. For defect detection, the changes in the number, location, and size of defects are listed, with a change curve graph.

[0046] According to the technical solution of the embodiment of the present application, multiple first images are taken under the same lighting conditions, and for each first image, color features, shape features, and texture features are extracted from the first image; based on the color features, shape features, and texture features, the stability of the drug is comprehensively evaluated to obtain the stability monitoring results of the drug to be monitored. Thus, the features of the drug image can be extracted from multiple dimensions, and the stability of the drug can be evaluated by comparing the feature changes at different time points, forming a comprehensive evaluation system, which provides a scientific basis for the quality control and safety evaluation of the drug.

[0047] Figure 2 This is a schematic diagram of the structure of the drug stability monitoring system based on image analysis provided in the embodiment of the present application. Figure 2 As shown, the system 2000 of this embodiment may include: The image acquisition module 2100 is used to acquire multiple first images of the drug to be monitored; the multiple first images are captured under the same lighting conditions in a preset shooting cycle.

[0048] The image processing module 2200 is used to extract color features, shape features and texture features from each first image.

[0049] The data analysis module 2300 is used to obtain the stability monitoring results of the drug to be monitored based on the color characteristics, shape characteristics and texture characteristics.

[0050] In one embodiment, the image processing module 2200 can be specifically used to convert a first image from an RGB color space to an HSV color space to obtain a second image; respectively calculate the hue value of the hue channel, the saturation value of the saturation channel, and the brightness value of the brightness channel in the second image; draw an HSV color space model according to the hue value of the hue channel, the saturation value of the saturation channel, and the brightness value of the brightness channel; and obtain color features according to the HSV color space model.

[0051] In one embodiment, the image processing module 2200 can be specifically used to convert the first image into a binary image through binarization processing; identify the drug edge of the drug to be monitored from the binary image; and calculate the shape feature based on the identified drug edge.

[0052] In one embodiment, the image processing module 2200 may be specifically used to calculate the gray level co-occurrence matrix of the first image; and extract texture features according to the gray level co-occurrence matrix.

[0053] In one embodiment, the data analysis module 2300 can be specifically used to draw the color feature change curve over time, the shape feature change curve over time, and the texture feature change curve over time according to the time sequence of a preset shooting cycle; determine the stability monitoring results of the drug to be monitored based on the color feature change curve over time, the shape feature change curve over time, and the texture feature change curve over time; the stability monitoring results include the stability level and the drug change trend.

[0054] In one embodiment, the image processing module 2200 can also be used to match the first image with a preset standard drug image through a template matching algorithm to obtain a matching result. The matching result includes: a normal area and an abnormal area on the surface of the drug to be monitored; the normal area is an image area whose matching degree meets a first preset threshold; the abnormal area is an image area whose matching degree meets a second preset threshold.

[0055] In one embodiment, the data analysis module 2300 can also be used to analyze the changes in the number, position and size of abnormal areas on the surface of the monitored drug according to the time sequence of a preset shooting cycle; and draw a curve of the changes of the abnormal areas over time based on the changes to obtain the stability monitoring results of the monitored drug.

[0056] The drug stability detection system based on image analysis of this embodiment can be used to implement the technical solution of the above-mentioned method embodiment. Its implementation principle and technical effect are similar and will not be repeated here.

[0057] Figure 3 A schematic diagram of a computer device structure is provided for this application. Figure 3 As shown, the computer device 300 may specifically include a processor 320 and a memory 330. The memory stores computer-executable instructions; the processor executes the computer-executable instructions stored in the memory to implement the drug stability monitoring method based on image analysis in any of the aforementioned method embodiments.

[0058] It should be understood that the present application is not limited to the precise structures that have been described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present application is limited only by the appended claims.

[0059] In the description of the present application, it should be noted that the terms "first", "second" and "third" are only used for descriptive purposes and cannot be understood as indicating or implying relative importance.

[0060] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described devices, equipment and units can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0061] In the embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. The device embodiments described above are merely schematic. For example, the division of units is only a logical function division, and there may be other division methods in actual implementation; for example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some communication interfaces, and the indirect coupling or communication connection of devices or units can be electrical, mechanical or other forms.

[0062] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0063] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0064] If the function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a non-volatile computer-readable storage medium that is executable by a processor. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods of each embodiment of the present application.

[0065] Finally, it should be noted that the above embodiments are only specific implementation methods of the present application, which are used to illustrate the technical solution of the present application, rather than to limit it. The protection scope of the present application is not limited thereto. Although the present application is described in detail with reference to the above embodiments, ordinary technicians in the field should understand that any technician familiar with the technical field can still modify the technical solution recorded in the above embodiments within the technical scope disclosed in the present application, or can easily think of changes, or make equivalent replacements for some of the technical features therein; and these modifications, changes or replacements do not make the essence of the corresponding technical solution deviate from the spirit and scope of the technical solution of the embodiment of the present application, and should be included in the protection scope of the present application. Therefore, the protection scope of the present application shall be based on the protection scope of the claims.

[0066] In addition, although the operations of the method of the present application are described in a specific order in the drawings, this does not require or imply that the operations must be performed in this specific order, or that all the operations shown must be performed to achieve the desired results. Additionally or alternatively, some steps may be omitted, multiple steps may be combined into one step, and / or one step may be decomposed into multiple steps.

Claims

1. A drug stability monitoring method based on image analysis, characterized in that: The method comprises: Acquire multiple first images of the drug to be monitored; the multiple first images are taken under the same lighting conditions in a preset shooting cycle; For each of the first images, extracting color features, shape features, and texture features from the first image; The stability monitoring result of the drug to be monitored is obtained according to the color feature, the shape feature and the texture feature.

2. The method according to claim 1, characterized in that The step of extracting color features from the first image comprises: Convert the first image from the RGB color space to the HSV color space to obtain a second image; Respectively calculating the hue value of the hue channel, the saturation value of the saturation channel, and the brightness value of the brightness channel in the second image; Draw an HSV color space model according to the hue value of the hue channel, the saturation value of the saturation channel, and the brightness value of the brightness channel; The color feature is obtained according to the HSV color space model.

3. The method according to claim 1, characterized in that: The step of extracting shape features from the first image comprises: Converting the first image into a binary image by binarization processing; Identifying the edge of the drug to be monitored from the binary image; The shape feature is calculated based on the identified edge of the medicine.

4. The method according to claim 1, characterized in that: The extracting texture features from the first image comprises: Calculating a gray level co-occurrence matrix of the first image; The texture features are extracted according to the gray level co-occurrence matrix.

5. The method according to any one of claims 1 to 4, characterized in that: The step of obtaining the stability monitoring result of the drug to be monitored according to the color feature, the shape feature and the texture feature includes: According to the time sequence of the preset shooting cycle, a curve of the change of the color feature over time, a curve of the change of the shape feature over time, and a curve of the change of the texture feature over time are drawn; The stability monitoring result of the drug to be monitored is determined based on the curve of the color feature changing over time, the curve of the shape feature changing over time, and the curve of the texture feature changing over time; the stability monitoring result includes the stability grade and the drug change trend.

6. The method according to claim 5, characterized in that The method further comprises: The first image is matched with a preset standard drug image through a template matching algorithm to obtain a matching result.

7. The method according to claim 6, characterized in that The matching result includes: a normal area and an abnormal area on the surface of the drug to be monitored; the normal area is an image area whose matching degree meets a first preset threshold; and the abnormal area is an image area whose matching degree meets a second preset threshold.

8. The method according to claim 7, characterized in that The method further comprises: Analyzing the changes in the number, position and size of the abnormal areas on the surface of the drug to be monitored according to the time sequence of the preset shooting cycle; A curve of the abnormal area changing over time is drawn according to the change to obtain the stability monitoring result of the drug to be monitored.

9. A drug stability monitoring system based on image analysis, characterized in that: The system comprises: An image acquisition module, used to acquire a plurality of first images of the drug to be monitored; the plurality of first images are captured under the same lighting conditions in a preset capture cycle; An image processing module, configured to extract color features, shape features, and texture features from each of the first images; A data analysis module is used to obtain the stability monitoring result of the drug to be monitored based on the color feature, the shape feature and the texture feature.

10. A computer device, characterized in that: include: A processor, and a memory communicatively connected to the processor; The memory stores computer-executable instructions; The processor executes the computer-executable instructions stored in the memory to implement the drug stability monitoring method based on image analysis according to any one of claims 1 to 8.

Images