CN117219248B - Medical instrument management method for disinfection supply room - Google Patents
Medical instrument management method for disinfection supply room Download PDFInfo
- Publication number
- CN117219248B CN117219248B CN202311481398.0A CN202311481398A CN117219248B CN 117219248 B CN117219248 B CN 117219248B CN 202311481398 A CN202311481398 A CN 202311481398A CN 117219248 B CN117219248 B CN 117219248B
- Authority
- CN
- China
- Prior art keywords
- pixel point
- window
- pixel
- acquiring
- illumination
- 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.)
- Active
Links
- 238000004659 sterilization and disinfection Methods 0.000 title claims abstract description 20
- 238000007726 management method Methods 0.000 title claims abstract description 19
- 238000005286 illumination Methods 0.000 claims abstract description 103
- 239000013598 vector Substances 0.000 claims abstract description 41
- 230000005856 abnormality Effects 0.000 claims description 16
- 238000000034 method Methods 0.000 claims description 15
- 230000002159 abnormal effect Effects 0.000 claims description 2
- 238000001514 detection method Methods 0.000 abstract description 16
- 238000004140 cleaning Methods 0.000 abstract description 10
- 238000012216 screening Methods 0.000 abstract description 3
- 238000012545 processing Methods 0.000 abstract description 2
- 230000001954 sterilising effect Effects 0.000 description 7
- 238000013528 artificial neural network Methods 0.000 description 3
- 238000005452 bending Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 230000000739 chaotic effect Effects 0.000 description 2
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 208000015181 infectious disease Diseases 0.000 description 2
- JEIPFZHSYJVQDO-UHFFFAOYSA-N iron(III) oxide Inorganic materials O=[Fe]O[Fe]=O JEIPFZHSYJVQDO-UHFFFAOYSA-N 0.000 description 2
- 230000001788 irregular Effects 0.000 description 2
- 238000012423 maintenance Methods 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000007797 corrosion Effects 0.000 description 1
- 238000005260 corrosion Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000003064 k means clustering Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 238000004806 packaging method and process Methods 0.000 description 1
- 238000012856 packing Methods 0.000 description 1
- 238000001356 surgical procedure Methods 0.000 description 1
Landscapes
- Image Processing (AREA)
Abstract
The invention relates to the technical field of data processing, in particular to a medical instrument management method for a disinfection supply room, which comprises the following steps: acquiring a single surgical instrument image, and acquiring a first illumination direction vector of each pixel point in each window in the single surgical instrument image; acquiring a first difference value according to the first illumination direction vector, acquiring gray consistency of each window, and further acquiring illumination distribution consistency of the windows; and acquiring the first pixel point according to the consistency of illumination distribution, further acquiring a second illumination direction vector of the first pixel point, and acquiring the anomaly degree of the first pixel point according to the cosine distance of the second illumination direction vector of different first pixel points, thereby screening out the pixel points of the dirty area. The invention avoids the interference of the uneven area of the medical instrument to the detection of the dirty area, improves the accuracy of the detection of the cleaning quality of the medical instrument, and is simple and efficient.
Description
Technical Field
The invention relates to the technical field of data processing, in particular to a medical instrument management method for a disinfection supply room.
Background
The sterilization supply room is an important department of hospitals to provide doctors with various kinds of sterile medical instruments and other various medical instruments. Therefore, medical instruments in the disinfection supply room are effectively managed, and the probability of surgical infection in the hospital can be reduced.
The medical instruments in the disinfection supply room need to be cleaned, disinfected, packed and the like, so that workers are easily confused, and once the workers are in error, the patients are infected (the cleaning is not clean, the cleaning effect is out of date, missed detection and the like), or the maintenance of other medical instruments is not facilitated (after corrosion and rust, the other medical instruments are induced to rust).
The existing disinfection supply room management system based on the RFID radio frequency technology records the current data such as the use and maintenance of each medical instrument by adding an RFID tag when packaging each medical instrument in the disinfection supply room. However, due to operator misoperation, such as missing a certain equipment cleaning, a cleaning label is still marked, and finally, unqualified products are filled into the packing bags. Once the medical device which is not cleaned or cleaned enters the operating room, the medical device can cause infection of a patient and even endanger the life of the patient. Therefore, the medical equipment in the disinfection supply room needs to be cleaned again on the operating table for quality detection.
At present, the cleaning quality detection of the medical instruments is usually carried out by advanced nurses or clinicians in front of an operating table, but because of the large number of medical instruments used in each operation, the manual detection needs a lot of time, and meanwhile, the detection may be missed.
Most medical instruments are uneven, such as bending portions of surgical bending forceps. If the existing image recognition technology is used for detecting the cleaning quality of the medical instrument, a light source on an operating table can form shadows in uneven areas of the medical instrument to interfere with detection of dirty areas, and accuracy of detecting the cleaning quality of the medical instrument is affected.
Disclosure of Invention
The present invention provides a medical instrument management method for a sterilization supply room to solve the existing problems.
The invention relates to a medical instrument management method for a disinfection supply room, which adopts the following technical scheme:
one embodiment of the present invention provides a medical instrument management method for sterilizing a supply room, the method including the steps of:
acquiring a medical instrument image and acquiring a single surgical instrument image;
acquiring a window of each pixel point in a single surgical instrument image, and acquiring a first illumination direction vector of each pixel point in the window; acquiring a plurality of first difference values of the window according to the first illumination direction vector of each pixel point in the window; counting the frequencies of all gray values appearing in the window, and acquiring the gray consistency of the window according to the frequencies; acquiring illumination distribution consistency of the window according to all the first difference values of the window and gray consistency of the window;
dividing all pixel points in a single surgical instrument image into two categories according to the illumination distribution consistency of the window of each pixel point in the single surgical instrument image by using a clustering algorithm; taking the average value of the illumination distribution consistency of windows of all pixel points in each category as the illumination distribution consistency of each category, and taking all pixel points in the category with large illumination distribution consistency as first pixel points;
acquiring a second illumination direction vector of each first pixel point; constructing an empty first pixel point sequence, and adding each first pixel point into the first pixel point sequence; calculating cosine distances of second illumination direction vectors of all adjacent two first pixel points in the first pixel point sequence to obtain a cosine distance sequence; acquiring the anomaly degree of each first pixel point according to the cosine distance sequence; and acquiring a dirty region according to the abnormal degree of all the first pixel points and a preset threshold value.
Preferably, the acquiring a window of each pixel in the image, and acquiring a first illumination direction vector of each pixel in the window includes:
constructing a window with a preset size for each pixel point in the image by taking each pixel point in the image as a center; and calculating the distance from each pixel point in each window to the central pixel point of the window and a direction cosine value, wherein the distance and the direction cosine value form a first illumination direction vector of each pixel point in the window.
Preferably, the obtaining the plurality of first differences of the window according to the first illumination direction vector of each pixel point in the window includes:
dividing pixels with the same first illumination direction vector in the window into a group to obtain a plurality of groups, wherein each group comprises two pixels, respectively calculating the absolute value of the difference value of the gray values of the two pixels and the central pixel in each group to obtain the illumination intensity variation degree of the two pixels, taking the illumination intensity variation degree of the two pixels as the difference value of each group, and obtaining the absolute value, wherein the first difference value of all groups is taken as the plurality of first difference values of the window.
Preferably, the gray consistency expression is:
wherein the method comprises the steps ofIs->Gray consistency of windows of the pixel points; />Is->The +.>The frequency of the individual gray values; />Is->The number of gray values occurring within the window of the individual pixel points; />Is an exponential function with a base of natural constant.
Preferably, the expression of the uniformity of the illumination distribution is:
wherein the method comprises the steps ofIs->The illumination distribution consistency of windows of the pixel points; />Is->The +.f. of the window of the individual pixels>A first difference value; />Is->The number of the first difference values of the windows of the pixel points; />Is->Gray consistency of windows of the pixel points; />Is an exponential function with a base of natural constant.
Preferably, the obtaining the second illumination direction vector of each first pixel point includes:
and acquiring a first illumination direction vector of a pixel point with the maximum gray value in a window of each first pixel point as a second illumination direction vector of the first pixel point.
Preferably, the adding each first pixel to the first pixel sequence includes:
starting from the first pixel point at the upper left corner in a single surgical instrument image, adding the first pixel point into a first pixel point sequence, acquiring the first pixel point which is nearest to the last first pixel point in the first pixel point sequence and does not belong to the first pixel point sequence, adding the first pixel point into the first pixel point sequence, repeatedly acquiring the first pixel point which is nearest to the last first pixel point in the first pixel point sequence and does not belong to the first pixel point sequence, adding the first pixel point into the first pixel point sequence, and stopping the operation until all the first pixel points are added into the first pixel point sequence.
Preferably, the expression of the degree of abnormality is:
wherein the method comprises the steps ofIs the +.>The degree of abnormality of the first pixel points; />Is the +.>A cosine distance; />Is the +.>A cosine distance; />Is the average value of all cosine distances; />The number of the first pixel points in the first pixel point sequence is the number of the first pixel points.
Preferably, the obtaining the dirty region according to the anomaly degree of all the first pixel points and the preset threshold value includes:
when the degree of abnormality of the first pixel point is larger than a preset threshold value, the first pixel point is a dirty area pixel point; when the degree of abnormality of the first pixel point is smaller than or equal to a preset threshold value, the first pixel point is a pixel point of a non-dirty area.
The beneficial effects of the invention are as follows: acquiring a single surgical instrument image, and acquiring a first illumination direction vector of each pixel point in each window in the single surgical instrument image; acquiring a first difference value according to the first illumination direction vector, acquiring gray consistency of each window, and further acquiring illumination distribution consistency of the windows; and acquiring the first pixel point according to the consistency of illumination distribution, further acquiring a second illumination direction vector of the first pixel point, and acquiring the anomaly degree of the first pixel point according to the cosine distance of the second illumination direction vector of different first pixel points, thereby screening out the pixel points of the dirty area. The invention avoids the interference of the uneven area of the medical instrument to the detection of the dirty area, improves the accuracy of the detection of the cleaning quality of the medical instrument, and is simple and efficient.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, it being obvious that the drawings in the following description are only some embodiments of the invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart of the steps of a medical device management method for sterilizing a supply compartment according to the present invention;
fig. 2 is a schematic view of a camera of a medical device management method for sterilizing a supply room according to the present invention.
Detailed Description
In order to further describe the technical means and effects adopted by the present invention to achieve the preset purposes, the following detailed description refers to the specific implementation, structure, characteristics and effects of a medical instrument management method for a disinfection supply room according to the present invention with reference to the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" means that the embodiments are not necessarily the same. Furthermore, the particular features, structures, or characteristics of one or more embodiments may be combined in any suitable manner.
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 specifically describes a specific embodiment of a medical instrument management method for sterilizing a supply room provided by the present invention with reference to the accompanying drawings.
Referring to fig. 1, a flowchart of steps in a medical device management method for sterilizing a supply compartment according to one embodiment of the present invention is shown, the method comprising the steps of:
101. medical instrument images are acquired, and a single surgical instrument image is acquired.
Firstly, acquiring medical instrument images, specifically: and erecting a uniform light source above the detection table. The camera is arranged right above the detection table, and the schematic diagram of the camera is shown in fig. 2, wherein A is the camera. The medical instrument image on the detection table is shot through the camera to obtain a medical instrument RGB image, and the medical instrument image is converted into a gray image for facilitating subsequent analysis.
Secondly, acquiring a single surgical instrument image, specifically: identification and detection of a single surgical instrument are performed through a Yolo4 neural network. The input of the network is a gray image of the medical instrument, and the input is a bounding box of a single surgical instrument; the training set is a medical instrument gray level image data set, the label of the training set is a surrounding frame of a single surgical instrument, and professional staff marks the medical instrument gray level image; the loss function is the loss function of the Yolo4 neural network.
Inputting the gray level image of the medical instrument into the Yolo4 neural network to obtain a plurality of bounding boxes of the gray level image of the medical instrument, wherein each bounding box corresponds to a single surgical instrument. The image in each bounding box is color segmented to obtain a plurality of images containing only a single surgical instrument.
102. And acquiring pixel points of an illumination change area of the single surgical instrument image.
It should be noted that under the irradiation of the uniform light source, the gray values of the flattened areas on the single operation area are uniform, and the illumination degree of each position of the non-flattened areas such as the bent part of the operation bending forceps is inconsistent, so that the gray values of the pixel points show the characteristic of regular change. Due to the uneven dirt areas on a single surgical instrument, there is also a characteristic of regular variation in gray values of the dirt areas. To identify the dirty region, it is first necessary to identify the illumination change region in the single surgical instrument image.
In this embodiment, acquiring an illumination variation area of a single surgical instrument image specifically includes:
taking each pixel point in the image as the center, establishing one for each pixel pointA window of size, in this embodiment +.>In other embodiments the practitioner can set +.>Is of a size of (a) and (b). And calculating Euclidean distance from each pixel point to the central pixel point in each window and cosine value of the direction from each pixel point to the central pixel point, and taking a vector formed by the Euclidean distance and the cosine value as a first illumination direction vector of the corresponding pixel point in the window to represent illumination direction characteristics of the corresponding pixel point in the window.
It should be noted that, the light intensity of the pixel points in the light variation area changes regularly, the light direction in the local light variation area can be considered to be consistent, and the light intensity variation degree of the pixel points is proportional to the distance. The distances from two symmetrical pixel points of the line where the window center pixel point is located to the window center pixel point are consistent, so that the illumination intensity change degree from the two symmetrical pixel points of the line where the window center pixel point is located to the window center pixel point is basically consistent. Since cosine values are related toAxisymmetric, so that cosine values from two pixel points which are axisymmetric with the line where the central pixel point of the window is positioned to the central pixel point in the window are consistent. The Euclidean distance is positive, so that the first illumination direction vectors of two symmetrical pixel points in the window along the line axis of the pixel point at the center of the window are the same, and the illumination intensity variation degree of the pixel point relative to the center pixel point can be obtained through the consistency of the first illumination direction vectorsConsistency.
In this embodiment, the pixels with the same first illumination direction vector in each window are divided into a group to obtain a plurality of groups, each group includes two pixels, and the two pixels are in axisymmetric form with the central pixel. And respectively calculating absolute values of differences between gray values of two pixel points in a group and gray values of a central pixel point of the window, taking the absolute values as illumination intensity change degrees of the two pixel points, and taking the difference between the illumination intensity change degrees of the two pixel points and obtaining absolute values to obtain a first difference value, wherein the first difference value can reflect the consistency of the illumination intensity change degrees of the pixel points relative to the central pixel point. Similarly, a plurality of first differences are obtained as all the first differences for a window based on all the groups of the window.
It should be noted that, when all the first differences of the window are smaller, the higher the uniformity of the illumination intensity variation degree of the pixel point in the window relative to the central pixel point is, the more likely the window is an illumination variation area. However, there may be a case that gray values in the window of the over-illuminated area or the over-illuminated area are consistent, so that all the first differences of the window are smaller, and at this time, whether the window is an illumination change area needs to be measured by combining the consistency of the gray values in the window.
In this embodiment, the frequencies of all gray values appearing in the window are counted, and the gray consistency of the window is calculated according to the frequencies of all gray values appearing in the window. Specifically, the firstGray level uniformity of windows of individual pixels +.>The method comprises the following steps:
wherein the method comprises the steps ofIs->Gray consistency of windows of the pixel points; />Is->The +.>The frequency of the individual gray values; />Is->The number of gray values occurring within the window of the individual pixel points; />Is->The larger the entropy value of the gray value distribution in the window of each pixel point, the more chaotic the gray value in the window is. The smaller the entropy value is, the more uniform the gray value in the window is; />To be an exponential function based on natural constant +.>And (3) obtaining the gray level consistency of the window as a negative correlation normalization function of the entropy value, wherein the smaller the gray level consistency is, the more disordered the gray level value in the window is, and the larger the gray level consistency is, the more unified the gray level value in the window is.
And acquiring an illumination distribution consistency index of the window by combining all the first difference values of the window and the gray consistency of the window, and measuring whether the window is an illumination change area or not. Specifically, the firstLight distribution uniformity of windows of individual pixels +.>The method comprises the following steps:
wherein the method comprises the steps ofIs->The illumination distribution consistency of the windows of the pixel points is added with one to prevent the denominator from being 0; />Is->The +.f. of the window of the individual pixels>A first difference value; />Is->The number of the first difference values of the windows of the pixel points; />Is->Gray consistency of windows of the pixel points; />Is the sum of all first differences of the window; />To be an exponential function based on natural constant +.>As a sum of all first differences, whenThe larger the->The more likely the window of the individual pixels is the illumination variation area; conversely, the smaller the value, the more likely the window is a flat area; gray level uniformity of window->The larger the gray value distribution in the window is, the more uniform the gray value distribution in the window is, the gray consistency in the window is +.>The smaller the gray value distribution within the window, the more chaotic; when->The larger the window gray scale uniformity is, the larger the window illumination distribution uniformity is, the +.>The more likely the window of the individual pixels is the illumination variation area; conversely, whenThe smaller or the greater the gray level uniformity, the smaller the uniformity of the illumination distribution of the window, the more likely the window is a boundary region or flat region, i.e., a region that is too bright or too dark.
In this embodiment, the pixel points are classified by the illumination distribution consistency index, and the illumination change region is obtained. Specifically, clustering operation is carried out on all the pixel points according to the illumination distribution consistency of the window of each pixel point by using a K-means clustering algorithm, and the clustering category k=2 divides all the pixel points into two categories. Calculating the uniform mean value of the illumination distribution of the windows of all pixel points contained in each category as the illumination distribution of the corresponding categoryAnd the pixel points with large illumination distribution consistency are the pixel points of the illumination change area. And taking the pixel point with the category with large illumination distribution consistency as a first pixel point. The number of the first pixel points is recorded as。
Thus, the pixel points of the illumination change area of the single surgical instrument image are obtained.
103. And calculating the anomaly degree of the pixel points and identifying the dirty area.
The shape of the uneven area on the surgical instrument is regular, and the illumination direction is regular. The dirty areas are irregular in shape and disordered in illumination direction. Therefore, the dirty region can be identified according to the illumination direction of the pixel points of the illumination change region.
In this embodiment, a first illumination direction vector of a pixel having the largest gray value in a window of a first pixel is used as a second illumination direction vector of the first pixel to represent a local illumination direction of the first pixel. An empty first pixel point sequence is constructed, a first pixel point at the upper left corner of a single surgical instrument image is added into the first pixel point sequence, a first pixel point which is nearest to the last pixel point in the first pixel point sequence and is not added into the first pixel point sequence in the single surgical instrument image is obtained, the first pixel point is added into the first pixel point sequence, and the operation is repeated until all the first pixel points in the single surgical instrument image are added into the first pixel point sequence.
And calculating cosine distances of second illumination direction vectors of all adjacent two first pixel points in the first pixel point sequence to obtain a cosine distance sequence. Obtaining the average value of all cosine distances byAnd (3) representing. Each cosine distance corresponds to two adjacent first pixel points in the first pixel point sequence, namely, each first pixel point in the first pixel point sequence corresponds to two cosine distances except for one cosine distance between the first pixel point and the last first pixel point, such as the%>The first pixel point corresponds to the +.>First->A cosine distance of>，/>The number of the first pixel points. Acquiring the anomaly degree of each first pixel point according to the cosine distance corresponding to each first pixel point, such as +.>Abnormality degree +.>The method comprises the following steps:
wherein the method comprises the steps ofIs the +.>The degree of abnormality of the first pixel points; />Is the +.>A cosine distance; />Is the +.>A cosine distance; />Is the average value of all cosine distances; />The number of the first pixel points; when->Or->At the time->The first pixel point corresponds to only one cosine distance, and when the cosine distance is larger than the average value of all cosine distances, the first pixel point is +.>The local illumination disorder of the first pixel point +.>The first pixel may be a dirty region>The greater the degree of abnormality of the first pixel points; when->At the time->The first pixel point corresponds to two cosine distances, only the +.>When the cosine distances between each first pixel point and two adjacent first pixel points in the first pixel point time sequence are larger than the average value of all cosine distances, the first pixel point is +.>The local illumination disorder of the first pixel point +.>The first pixel may be a dirty region>The greater the degree of abnormality of the first pixel point.
It should be noted that, due to the irregular dirt area, the illumination direction of the pixel points in the dirt area is disordered, so that the degree of abnormality of the pixel points is larger. The uneven area on the surgical instrument is regular in shape, and the illumination direction of the pixels in the area is regular, so that the abnormity degree of the pixels in the area is small. And measuring whether the first pixel point is a dirty region pixel point or not according to the degree of abnormality.
In the present embodiment, a threshold value is setWhen the degree of abnormality of the first pixel is greater than + ->When the area is considered to be a dirty area; when the degree of abnormality of the first pixel is less than or equal to +.>Then it is considered to be the region of surgical instrument irregularities. />Is a super parameter, in this embodiment +.>In other embodiments, the practitioner can set +.>Is a value of (2).
To this end, a single surgical instrument dirty region is obtained.
104. And performing medical instrument management of the disinfection supply room according to the identification result of the dirty region of the single surgical instrument.
For the surgical instruments in the dirty area, the replacement approval of the surgical instruments is required to be immediately carried out, and the surgical instruments are required to be replaced by going to a disinfection supply room so as to ensure the normal operation of the surgery.
According to the embodiment of the invention, the first illumination direction vector of each pixel point in each window in the single surgical instrument image is obtained by obtaining the single surgical instrument image; acquiring a first difference value according to the first illumination direction vector, acquiring gray consistency of each window, and further acquiring illumination distribution consistency of the windows; and acquiring the first pixel point according to the consistency of illumination distribution, further acquiring a second illumination direction vector of the first pixel point, and acquiring the anomaly degree of the first pixel point according to the cosine distance of the second illumination direction vector of different first pixel points, thereby screening out the pixel points of the dirty area. The invention avoids the interference of the uneven area of the medical instrument to the detection of the dirty area, improves the accuracy of the detection of the cleaning quality of the medical instrument, and is simple and efficient.
The foregoing description of the preferred embodiments of the invention is not intended to be limiting, but rather is intended to cover all modifications, equivalents, alternatives, and improvements that fall within the spirit and scope of the invention.
Claims (5)
1. A medical device management method for a disinfection supply room, characterized in that the method comprises the steps of:
acquiring a medical instrument image and acquiring a single surgical instrument image;
acquiring a window of each pixel point in a single surgical instrument image, and acquiring a first illumination direction vector of each pixel point in the window; acquiring a plurality of first difference values of the window according to the first illumination direction vector of each pixel point in the window; counting the frequencies of all gray values appearing in the window, and acquiring the gray consistency of the window according to the frequencies; acquiring illumination distribution consistency of the window according to all the first difference values of the window and gray consistency of the window;
dividing all pixel points in a single surgical instrument image into two categories according to the illumination distribution consistency of the window of each pixel point in the single surgical instrument image by using a clustering algorithm; taking the average value of the illumination distribution consistency of windows of all pixel points in each category as the illumination distribution consistency of each category, and taking all pixel points in the category with large illumination distribution consistency as first pixel points;
acquiring a second illumination direction vector of each first pixel point; constructing an empty first pixel point sequence, and adding each first pixel point into the first pixel point sequence; calculating cosine distances of second illumination direction vectors of all adjacent two first pixel points in the first pixel point sequence to obtain a cosine distance sequence; acquiring the anomaly degree of each first pixel point according to the cosine distance sequence; acquiring a dirty region according to the abnormal degrees of all the first pixel points and a preset threshold value;
the acquiring the window of each pixel point in the image, and the acquiring the first illumination direction vector of each pixel point in the window includes:
constructing a window with a preset size for each pixel point in the image by taking each pixel point in the image as a center; calculating the distance from each pixel point in each window to the central pixel point of the window and a direction cosine value, wherein the distance and the direction cosine value form a first illumination direction vector of each pixel point in the window;
the obtaining the second illumination direction vector of each first pixel point includes:
acquiring a first illumination direction vector of a pixel point with the maximum gray value in a window of each first pixel point as a second illumination direction vector of the first pixel point;
the expression of the illumination distribution consistency is as follows:
wherein the method comprises the steps ofIs->The illumination distribution consistency of windows of the pixel points; />Is->The +.f. of the window of the individual pixels>A first difference value; />Is->The number of the first difference values of the windows of the pixel points; />Is->Gray consistency of windows of the pixel points; />Is an exponential function with a natural constant as a base;
the expression of the degree of anomaly is:
wherein the method comprises the steps ofIs the +.>The degree of abnormality of the first pixel points; />Is the +.>A cosine distance; />Is the +.>A cosine distance; />Is the average value of all cosine distances; />The number of the first pixel points in the first pixel point sequence is the number of the first pixel points.
2. A medical device management method for a disinfection supply room according to claim 1, wherein said obtaining a plurality of first differences of said window from a first illumination direction vector of each pixel point within said window comprises:
dividing pixels with the same first illumination direction vector in the window into a group to obtain a plurality of groups, wherein each group comprises two pixels, respectively calculating the absolute value of the difference value of the gray values of the two pixels and the central pixel in each group to obtain the illumination intensity variation degree of the two pixels, taking the illumination intensity variation degree of the two pixels as the difference value of each group, and obtaining the absolute value, wherein the first difference value of all groups is taken as the plurality of first difference values of the window.
3. A medical instrument management method for a disinfection supply room according to claim 1, wherein said gradation consistency expression is:
wherein the method comprises the steps ofIs->Gray consistency of windows of the pixel points; />Is->The +.>The frequency of the individual gray values; />Is->The number of gray values occurring within the window of the individual pixel points; />Is an exponential function with a base of natural constant.
4. The medical device management method for a disinfection supply room according to claim 1, wherein said adding each first pixel to a first sequence of pixels comprises:
starting from the first pixel point at the upper left corner in a single surgical instrument image, adding the first pixel point into a first pixel point sequence, acquiring the first pixel point which is nearest to the last first pixel point in the first pixel point sequence and does not belong to the first pixel point sequence, adding the first pixel point into the first pixel point sequence, repeatedly acquiring the first pixel point which is nearest to the last first pixel point in the first pixel point sequence and does not belong to the first pixel point sequence, adding the first pixel point into the first pixel point sequence, and stopping the operation until all the first pixel points are added into the first pixel point sequence.
5. The medical device management method for a disinfection supply room according to claim 1, wherein said acquiring a dirty region according to the degree of abnormality of all first pixel points and a preset threshold value comprises:
when the degree of abnormality of the first pixel point is larger than a preset threshold value, the first pixel point is a dirty area pixel point; when the degree of abnormality of the first pixel point is smaller than or equal to a preset threshold value, the first pixel point is a pixel point of a non-dirty area.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311481398.0A CN117219248B (en) | 2023-11-09 | 2023-11-09 | Medical instrument management method for disinfection supply room |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311481398.0A CN117219248B (en) | 2023-11-09 | 2023-11-09 | Medical instrument management method for disinfection supply room |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117219248A CN117219248A (en) | 2023-12-12 |
| CN117219248B true CN117219248B (en) | 2024-02-23 |
Family
ID=89037467
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311481398.0A Active CN117219248B (en) | 2023-11-09 | 2023-11-09 | Medical instrument management method for disinfection supply room |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117219248B (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105930834A (en) * | 2016-07-01 | 2016-09-07 | 北京邮电大学 | Face identification method and apparatus based on spherical hashing binary coding |
| CN115834895A (en) * | 2023-02-22 | 2023-03-21 | 创银科技(南通)有限公司 | Data efficient compression storage method for unmanned aerial vehicle |
| CN115984836A (en) * | 2023-03-20 | 2023-04-18 | 山东杨嘉汽车制造有限公司 | Tank opening identification and positioning method for railway tank wagon |
| CN116152906A (en) * | 2021-11-18 | 2023-05-23 | 中国移动通信有限公司研究院 | Image recognition method, device, communication equipment and readable storage medium |
| CN116385448A (en) * | 2023-06-07 | 2023-07-04 | 深圳市华伟精密陶瓷有限公司 | Alumina ceramic surface machining defect detection method based on machine vision |
| CN116485785A (en) * | 2023-06-15 | 2023-07-25 | 无锡斯达新能源科技股份有限公司 | Surface defect detection method for solar cell |
-
2023
- 2023-11-09 CN CN202311481398.0A patent/CN117219248B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105930834A (en) * | 2016-07-01 | 2016-09-07 | 北京邮电大学 | Face identification method and apparatus based on spherical hashing binary coding |
| CN116152906A (en) * | 2021-11-18 | 2023-05-23 | 中国移动通信有限公司研究院 | Image recognition method, device, communication equipment and readable storage medium |
| CN115834895A (en) * | 2023-02-22 | 2023-03-21 | 创银科技(南通)有限公司 | Data efficient compression storage method for unmanned aerial vehicle |
| CN115984836A (en) * | 2023-03-20 | 2023-04-18 | 山东杨嘉汽车制造有限公司 | Tank opening identification and positioning method for railway tank wagon |
| CN116385448A (en) * | 2023-06-07 | 2023-07-04 | 深圳市华伟精密陶瓷有限公司 | Alumina ceramic surface machining defect detection method based on machine vision |
| CN116485785A (en) * | 2023-06-15 | 2023-07-25 | 无锡斯达新能源科技股份有限公司 | Surface defect detection method for solar cell |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117219248A (en) | 2023-12-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110838118B (en) | System and method for anomaly detection in medical procedures | |
| US20240169564A1 (en) | Tracking Surgical Items With Prediction Of Duplicate Imaging Of Items | |
| US8992416B2 (en) | Endoscope storage cabinet, tracking system, and signal emitting member | |
| US20200005936A1 (en) | Surgical instrument set and instrument management system | |
| JP2022535562A (en) | Systems and methods for tracking surgical instruments | |
| US9779504B1 (en) | Method and system for identifying anomalies in medical images especially those including one of a pair of symmetric body parts | |
| US9870615B2 (en) | Morphology identification in tissue samples based on comparison to named feature vectors | |
| JP7352399B2 (en) | Management system, information processing device, management method and program for managing records of sterilization processing | |
| CN117219248B (en) | Medical instrument management method for disinfection supply room | |
| CN110619621B (en) | Method, device, electronic equipment and storage medium for identifying rib area in image | |
| CN117409016A (en) | Automatic segmentation method for magnetic resonance image | |
| CN111986217B (en) | Image processing method, device and equipment | |
| US20200043605A1 (en) | Surgical instrument management system | |
| US20230343448A1 (en) | System and method for traceability and hygiene compliance management reprocessing of reusable medical devices and environments | |
| US11587229B2 (en) | Retained surgical items | |
| CN114496202A (en) | Intelligent system for equipment inspection and repair reporting | |
| US11335459B2 (en) | Surgical instrument set and instrument management system | |
| CN112289422A (en) | Endoscope cleaning and disinfecting flow monitoring system | |
| JP7398893B2 (en) | Management system, information processing device, program, and management method for managing records related to sterilization processing | |
| CN111462849A (en) | Multifunctional orthopedic surgery nursing system, nursing method and nursing terminal | |
| CN115662588B (en) | Regional medical disinfection supply-based full-flow information tracing system and method | |
| US20230360788A1 (en) | Information processing system, information processing method, and non-transitory computer readable medium | |
| KR102555602B1 (en) | Gum care system | |
| US20230306614A1 (en) | System and method for tracking surgical kit | |
| CN117414112A (en) | Neonate infection monitoring system and management method |
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 |