CN117456466A - Method, device, equipment and medium for controlling using quality of rubber barrier - Google Patents
Method, device, equipment and medium for controlling using quality of rubber barrier Download PDFInfo
- Publication number
- CN117456466A CN117456466A CN202311538888.XA CN202311538888A CN117456466A CN 117456466 A CN117456466 A CN 117456466A CN 202311538888 A CN202311538888 A CN 202311538888A CN 117456466 A CN117456466 A CN 117456466A
- Authority
- CN
- China
- Prior art keywords
- diagnosis
- treatment
- image
- images
- oral
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 230000004888 barrier function Effects 0.000 title claims abstract description 211
- 238000000034 method Methods 0.000 title claims abstract description 76
- 238000003745 diagnosis Methods 0.000 claims abstract description 303
- 210000000214 mouth Anatomy 0.000 claims abstract description 64
- 230000008569 process Effects 0.000 claims abstract description 32
- 238000012549 training Methods 0.000 claims description 43
- 238000003908 quality control method Methods 0.000 claims description 24
- 239000000463 material Substances 0.000 claims description 9
- 238000007781 pre-processing Methods 0.000 claims description 6
- 238000004364 calculation method Methods 0.000 abstract description 5
- 238000004590 computer program Methods 0.000 description 15
- 238000004891 communication Methods 0.000 description 8
- 230000006870 function Effects 0.000 description 8
- 238000010606 normalization Methods 0.000 description 6
- 238000012545 processing Methods 0.000 description 6
- 238000010586 diagram Methods 0.000 description 5
- 238000002955 isolation Methods 0.000 description 5
- 238000002372 labelling Methods 0.000 description 4
- 230000000694 effects Effects 0.000 description 3
- 238000012544 monitoring process Methods 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 239000003086 colorant Substances 0.000 description 2
- 238000007689 inspection Methods 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000004513 sizing Methods 0.000 description 2
- 238000007619 statistical method Methods 0.000 description 2
- 230000009471 action Effects 0.000 description 1
- 230000004913 activation Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000013145 classification model Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000013527 convolutional neural network Methods 0.000 description 1
- 230000002354 daily effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 210000004262 dental pulp cavity Anatomy 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 230000003203 everyday effect Effects 0.000 description 1
- 239000011521 glass Substances 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 238000011176 pooling Methods 0.000 description 1
- 210000003296 saliva Anatomy 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 230000001953 sensory effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000001356 surgical procedure Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/56—Extraction of image or video features relating to colour
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
- G06V10/75—Organisation of the matching processes, e.g. simultaneous or sequential comparisons of image or video features; Coarse-fine approaches, e.g. multi-scale approaches; using context analysis; Selection of dictionaries
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/764—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H30/00—ICT specially adapted for the handling or processing of medical images
- G16H30/40—ICT specially adapted for the handling or processing of medical images for processing medical images, e.g. editing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V2201/00—Indexing scheme relating to image or video recognition or understanding
- G06V2201/03—Recognition of patterns in medical or anatomical images
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Health & Medical Sciences (AREA)
- Evolutionary Computation (AREA)
- Databases & Information Systems (AREA)
- Computing Systems (AREA)
- Artificial Intelligence (AREA)
- Software Systems (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Radiology & Medical Imaging (AREA)
- Epidemiology (AREA)
- Primary Health Care (AREA)
- Public Health (AREA)
- Medical Treatment And Welfare Office Work (AREA)
Abstract
The invention discloses a method, a device, equipment and a medium for controlling the using quality of a rubber barrier, wherein the method comprises the following steps: acquiring a plurality of oral diagnosis and treatment images in the diagnosis and treatment process of a target diagnosis and treatment platform, removing irrelevant images from the oral diagnosis and treatment images, and determining a plurality of oral diagnosis and treatment images to be identified; wherein the oral cavity diagnosis and treatment image to be identified comprises diagnosis and treatment images of various categories; identifying a target rubber barrier image containing a rubber barrier from a plurality of to-be-identified oral diagnosis and treatment images based on a pre-trained rubber barrier image identification model; and determining the using completeness of the rubber barrier corresponding to the target diagnosis and treatment platform based on the identification marks of the diagnosis and treatment objects corresponding to the target rubber barrier images and the to-be-verified rubber barrier record information of the target diagnosis and treatment platform. According to the method and the device, the calculation result of the utilization rate of the rubber barrier is traceable, the accuracy of the use of the rubber barrier is improved, and the convenience and the effectiveness of the use supervision of the rubber barrier are improved.
Description
Technical Field
The embodiment of the invention relates to the technical field of data processing, in particular to a method, a device, equipment and a medium for controlling the quality of rubber barriers.
Background
In order to ensure the life safety of the subject in the oral diagnosis and treatment process, a rubber barrier isolation operation is required to be implemented. However, in the existing oral diagnosis and treatment process, there is a situation of missing the rubber barrier isolation, so it is important to efficiently monitor the use condition of the rubber barrier.
Currently, the usage of the rubber barrier is generally determined based on a payment list of the patient or a medical record written by the patient. However, the two data sources are indirect indexes, and whether the rubber barrier is actually used by the patient in the diagnosis and treatment process cannot be judged. If the supervision personnel are allowed to check on site, not only the labor cost is high, but also the monitoring efficiency is low. Based on this, there is a lack of efficient and reliable methods of monitoring the rubber barrier.
Disclosure of Invention
The invention provides a quality control method, a device, equipment and a medium for using a rubber barrier, so that the calculation result of the use rate of the rubber barrier can be traced, the use accuracy of the rubber barrier is improved, and the convenience and effectiveness of the use supervision of the rubber barrier are improved.
According to a first aspect of the present invention, there is provided a method of controlling the quality of use of a rubber dam, the method comprising:
acquiring a plurality of oral diagnosis and treatment images in the diagnosis and treatment process of a target diagnosis and treatment platform, removing irrelevant images from the oral diagnosis and treatment images, and determining a plurality of oral diagnosis and treatment images to be identified; wherein the oral cavity diagnosis and treatment image to be identified comprises diagnosis and treatment images of various categories;
Identifying a target rubber barrier image containing a rubber barrier from the plurality of to-be-identified oral diagnosis and treatment images based on a pre-trained rubber barrier image identification model;
and determining the using completeness of the rubber barrier corresponding to the target diagnosis and treatment platform based on the identification marks of the diagnosis and treatment objects corresponding to the target rubber barrier images and the to-be-verified rubber barrier record information of the target diagnosis and treatment platform.
According to a second aspect of the present invention, there is provided a barrier use quality control device, the device comprising:
the image acquisition module is used for acquiring a plurality of oral diagnosis and treatment images in the diagnosis and treatment process of the target diagnosis and treatment platform, removing irrelevant images from the oral diagnosis and treatment images and determining a plurality of oral diagnosis and treatment images to be identified; wherein the oral cavity diagnosis and treatment image to be identified comprises diagnosis and treatment images of various categories;
the rubber barrier image recognition module is used for recognizing a target rubber barrier image containing a rubber barrier from the plurality of oral diagnosis and treatment images to be recognized based on a pre-trained rubber barrier image recognition model;
the using integrity determining module is used for determining the using integrity of the rubber barrier corresponding to the target diagnosis and treatment platform based on the identity of the diagnosis and treatment object corresponding to each target rubber barrier image and the to-be-verified rubber barrier record information of the target diagnosis and treatment platform.
According to a third aspect of the present invention, there is provided an electronic device comprising:
at least one processor; and a memory communicatively coupled to the at least one processor; the memory stores a computer program executable by the at least one processor, so that the at least one processor can execute the method for controlling the quality of the rubber barrier according to any embodiment of the invention.
According to a fourth aspect of the present invention, there is provided a computer readable storage medium storing computer instructions for causing a processor to execute the method for controlling the quality of use of a rubber barrier according to any one of the embodiments of the present invention.
According to the technical scheme, a plurality of oral cavity diagnosis and treatment images in the diagnosis and treatment process of the target diagnosis and treatment platform are obtained, irrelevant images are removed from the plurality of oral cavity diagnosis and treatment images, a plurality of to-be-identified oral cavity diagnosis and treatment images are determined, wherein the to-be-identified oral cavity diagnosis and treatment images comprise a plurality of types of diagnosis and treatment images, further, a target rubber barrier image comprising a rubber barrier is identified from the plurality of to-be-identified oral cavity diagnosis and treatment images based on a pre-trained rubber barrier image identification model, and further, the using completeness of the rubber barrier corresponding to the target diagnosis and treatment platform is determined based on identification marks of the to-be-treated objects corresponding to the target rubber barrier images and to-be-verified rubber barrier record information of the target diagnosis and treatment platform. According to the method and the device, the calculation result of the utilization rate of the rubber barrier is traceable, the accuracy of the use of the rubber barrier is improved, and the convenience and the effectiveness of the use supervision of the rubber barrier are improved.
It should be understood that the description in this section is not intended to identify key or critical features of the embodiments of the invention or to delineate the scope of the invention. Other features of the present invention will become apparent from the description that follows.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for the description of the embodiments will be briefly described below, and it is apparent that the drawings in the following description are only some embodiments of the present invention, and 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 a method for controlling the quality of a rubber dam according to a first embodiment of the present invention;
FIG. 2 is a flow chart of a method for controlling the quality of a rubber dam according to a second embodiment of the present invention;
FIG. 3 is a flow chart of a method for controlling the quality of use of a rubber dam according to a third embodiment of the present invention;
fig. 4 is a schematic structural diagram of a quality control device for a rubber dam according to a fourth embodiment of the present invention;
fig. 5 is a schematic structural diagram of an electronic device implementing a method for controlling quality of a rubber dam according to an embodiment of the present invention.
Detailed Description
In order that those skilled in the art will better understand the present invention, a technical solution in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in which it is apparent that the described embodiments are only some embodiments of the present invention, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the present invention without making any inventive effort, shall fall within the scope of the present invention.
It should be noted that the terms "first," "second," and the like in the description and the claims of the present invention and the above figures are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate such that the embodiments of the invention described herein may be implemented in sequences other than those illustrated or otherwise described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
Example 1
Fig. 1 is a flowchart of a method for controlling the usage quality of a rubber dam according to an embodiment of the present invention, where the method may be performed by a quality control device for rubber dam, and the quality control device for rubber dam may be implemented in hardware and/or software, and the quality control device for rubber dam may be configured in a terminal and/or a server. As shown in fig. 1, the method includes:
s110, acquiring a plurality of oral diagnosis and treatment images in the diagnosis and treatment process of the target diagnosis and treatment platform, removing irrelevant images from the oral diagnosis and treatment images, and determining a plurality of oral diagnosis and treatment images to be identified.
The target diagnosis and treatment platform is any mechanism capable of performing oral cavity diagnosis and treatment, such as a hospital, a clinic, a sanitary hospital and the like. The oral diagnosis and treatment image is various types of images generated by a subject in oral diagnosis and treatment. For example, the oral diagnosis and treatment image includes an X-ray image, a diagnosis and treatment bill image, a surgical procedure recording image, an inspection procedure recording image, and the like.
Wherein, the irrelevant image is an image irrelevant to the diagnosis and treatment process. For example, the extraneous image may be an image that contains a blue or green curtain, but does not contain the rubber barrier itself; the image may also be an image which contains text information and typesetting mode similar to those in diagnosis and treatment payment images, but is actually a webpage. The to-be-identified oral diagnosis and treatment image is an image to be used for identifying whether the rubber barrier is included or not, and the to-be-identified oral diagnosis and treatment image includes diagnosis and treatment images of various categories.
Specifically, in the process of oral diagnosis and treatment by the target diagnosis and treatment platform, a great number of oral diagnosis and treatment images, such as diagnosis and treatment payment list images, operation process recording images, inspection process recording images and the like, can be generated by the subject. In the oral diagnosis and treatment images, some images are images which are irrelevant to the diagnosis and treatment process, and the existence of the irrelevant images can introduce a large number of false positives, so that the classification effect is greatly weakened. Therefore, these extraneous images need to be removed from the original oral treatment images obtained. The preserved oral diagnosis and treatment images are images related to the oral diagnosis and treatment process, and the preserved images are the oral diagnosis and treatment images to be identified.
Preferably, the statistical method is applied to the color channel values, thereby eliminating extraneous images from the plurality of oral treatment images. For example, if the average value of the R, G, B three channels of a certain oral diagnosis and treatment image is higher than the first preset threshold value or lower than the second preset threshold value, the oral diagnosis and treatment image is determined to be an irrelevant image.
For example, a timing task is preset, and all oral diagnosis and treatment images generated by the target diagnosis and treatment platform in the diagnosis and treatment process are acquired at preset time every day within 24 hours before the preset time. Furthermore, based on a preset irrelevant image removing method, irrelevant images are removed from a large number of oral diagnosis and treatment images, and the oral diagnosis and treatment images to be identified related to the diagnosis and treatment process are reserved.
Particularly, after a plurality of oral cavity diagnosis and treatment images to be identified are obtained, the oral cavity diagnosis and treatment images to be identified are preprocessed. The preprocessing step includes at least one of sizing, color normalization, normalization to ensure consistency and comparability of the data. In particular, the oral diagnostic image to be identified is typically in raw high resolution form, and thus requires resizing to scale the image to a fixed size to match the input requirements of the model. For example, each of the oral diagnosis and treatment images to be identified is adjusted to an image size of 256×256. In this embodiment, since the image under the "containing the rubber barrier" label is expected to be mostly blue (B) and green (G) colors, the mean value of the R channel values is increased to balance in color normalization, that is, three-channel normalized mean value is changed from common [ R, G, B ] = [0.485,0.456,0.406] to [ R, G, B ] = [0.485,0.456,0.406], and three-channel normalized standard deviation is unified from common [0.229,0.224,0.225] to [0.5,0.5,0.5].
S120, identifying a target rubber barrier image containing the rubber barrier from a plurality of to-be-identified oral diagnosis and treatment images based on a pre-trained rubber barrier image identification model.
Wherein, the rubber barrier image recognition model is trained in advance. The rubber barrier image recognition model is used for recognizing which images in the to-be-recognized oral diagnosis and treatment images are target rubber barrier images containing the rubber barrier.
The rubber barrier (also called as a moisture-proof rubber barrier) is a rubber blanket which is used for separating water, and is used for separating teeth in the oral cavity diagnosis and treatment process, so that saliva in the oral cavity cannot flow into an operation area of a dentist. The rubber dam should be used in root canal treatment, but there is a case of missing in actual diagnosis and treatment, so the purpose of this embodiment is to: for subjects who should use a rubber dam, it is monitored whether they are truly using rubber dam isolation. The target rubber barrier image is an oral diagnosis and treatment image to be identified, wherein the oral diagnosis and treatment image contains the content of the rubber barrier image.
Specifically, each oral diagnosis and treatment image to be identified is respectively input into a rubber barrier image identification model, and the rubber barrier image identification model can output the image category corresponding to each oral diagnosis and treatment image to be identified. In this embodiment, the image categories include: panoramic image category, side image category, small dental film image category, including rubber barrier image category and paper material image category. Based on the above, the image of the oral diagnosis and treatment to be identified, which includes the category of the images of the rubber barrier, is outputted by the rubber barrier image identification model, and is determined as the target rubber barrier image.
S130, determining the using completeness of the rubber barrier corresponding to the target diagnosis and treatment platform based on the identification marks of the diagnosis and treatment objects corresponding to the target rubber barrier images and the to-be-verified rubber barrier record information of the target diagnosis and treatment platform.
The identity of the patient is a unique identity representing the identity information of the patient. For example, the identity of the subject is a registration order, a visit order, an identity code, etc. In this embodiment, each oral diagnosis and treatment image can trace back to the identity of the patient corresponding to the oral diagnosis and treatment image, so that the identity of the patient corresponding to each target rubber barrier image can be determined.
In this embodiment, diagnosis and treatment contents requiring the use of the rubber barrier isolation are preset, and these diagnosis and treatment contents may be referred to as target diagnosis and treatment contents. The barrier record information to be verified can be understood as: the target diagnosis and treatment content is opened by the diagnosis and treatment object, the target diagnosis and treatment content payment activity is completed by the diagnosis and treatment object, and the collection of identification marks of the diagnosis and treatment object completing the target diagnosis and treatment content payment is determined as the to-be-verified rubber barrier record information.
The using completeness of the rubber barrier is the ratio of the number of the objects to be treated of the rubber barrier to be used.
Specifically, determining the usage completeness of the rubber barrier corresponding to the target diagnosis and treatment platform specifically includes: matching the identification marks of the objects to be treated corresponding to the target rubber barrier images with the to-be-verified rubber barrier record information of the target diagnosis and treatment platform one by one, and determining the first number of objects to be treated with a matching relationship; and determining the using completeness of the rubber barrier corresponding to the target diagnosis and treatment platform based on the second number and the first number of the objects to be treated contained in the to-be-verified rubber barrier record information.
In this embodiment, the identity of the diagnosis target corresponding to each target rubber barrier image is matched with the to-be-verified rubber barrier record information one by one, and the identity of the diagnosis target corresponding to the target rubber barrier image in the to-be-verified rubber barrier record information is marked in a distinguishing manner, so that the diagnosis target with the matching relationship can be determined, the diagnosis targets with the matching relationship are counted, and the first number is obtained.
For example, if the target rubber barrier image a corresponds to the identity of the patient a, and the identity of the patient a exists in the record information of the rubber barrier to be verified, the identity of the patient a is labeled as "finished". The target rubber barrier image B corresponds to the identity mark B of the patient, the identity mark B of the patient cannot be found in the record information of the rubber barrier to be verified, and the identity mark B of the patient is marked with an unfinished label. The second number of the objects to be treated contained in the record information of the barriers to be verified can be directly determined by counting, and based on the second number, the ratio of the first number to the second number is used as the barrier usage completeness corresponding to the target diagnosis and treatment platform.
Meanwhile, the doctor receiving objects corresponding to the doctor receiving objects of the rubber barrier can be traced according to registration information, and the rubber barrier service conditions of each doctor receiving object and each diagnosis and treatment department can be summarized and counted to generate a rubber barrier daily quality control report, a rubber barrier week quality control report, a rubber barrier month quality control report, a rubber barrier year quality control report and the like, so that effective monitoring of the rubber barrier use is realized. Further, the quantitative information of the rubber barrier use condition of each of the patients is statistically analyzed, and the patients with more prominent rubber barrier missing use condition are corrected and improved according to the analysis result, so that the patients are prompted to use the rubber barrier isolation operation normally.
According to the technical scheme, a plurality of oral cavity diagnosis and treatment images in the diagnosis and treatment process of the target diagnosis and treatment platform are obtained, irrelevant images are removed from the plurality of oral cavity diagnosis and treatment images, a plurality of to-be-identified oral cavity diagnosis and treatment images are determined, wherein the to-be-identified oral cavity diagnosis and treatment images comprise a plurality of types of diagnosis and treatment images, further, a target rubber barrier image comprising a rubber barrier is identified from the plurality of to-be-identified oral cavity diagnosis and treatment images based on a pre-trained rubber barrier image identification model, and further, the using completeness of the rubber barrier corresponding to the target diagnosis and treatment platform is determined based on identification marks of the to-be-treated objects corresponding to the target rubber barrier images and to-be-verified rubber barrier record information of the target diagnosis and treatment platform. According to the method and the device, the calculation result of the utilization rate of the rubber barrier is traceable, the accuracy of the use of the rubber barrier is improved, and the convenience and the effectiveness of the use supervision of the rubber barrier are improved.
Example two
Fig. 2 is a flowchart of a quality control method for a rubber dam according to a second embodiment of the present invention, and S110 is further refined based on the foregoing embodiment. Wherein, the technical terms identical to or corresponding to the above embodiments are not repeated herein.
As shown in fig. 2, the method includes:
s210, acquiring a plurality of oral cavity diagnosis and treatment images in the diagnosis and treatment process of the target diagnosis and treatment platform.
S220, respectively determining first pixel values of three color channels of each oral diagnosis and treatment image.
The first pixel value comprises a characteristic value of each pixel value of the R channel, a characteristic value of each pixel value of the G channel and a characteristic value of each pixel value of the B channel. For example, the first pixel value is the average value of the pixel values of the R color channel, the G color channel and the B color channel of the oral diagnosis and treatment image.
In this embodiment, three-channel pixel values of each pixel point can be directly obtained for each oral diagnosis and treatment image. For each color channel, determining the characteristic value of the pixel value of the current color channel based on the pixel value of the current color channel of each pixel point, thereby obtaining the first pixel values of the three color channels.
S230, determining the oral diagnosis and treatment image with the first pixel value not in the preset pixel range as an irrelevant image, and eliminating the irrelevant image.
Wherein the preset pixel range is a pixel range determined in advance by two pixel thresholds.
Optionally, the predetermined pixel range includes: acquiring a plurality of historical oral diagnosis and treatment images to be identified; determining a reference pixel average value and a reference pixel standard value based on pixel values of three color channels of each historical oral diagnosis and treatment image to be identified; the preset pixel range is determined based on the reference pixel average value and the reference pixel standard value.
The historical oral diagnosis and treatment image to be identified is a historical oral diagnosis and treatment image with the historical irrelevant image removed.
In this embodiment, the historical oral diagnosis and treatment image to be identified is an image remained in the historical diagnosis and treatment period, and may be obtained from a database. And respectively determining the average value and the standard value of the pixel values of the R channel, the G channel and the B channel for each historical oral diagnosis and treatment image to be identified. And then, taking an average value according to the average value and the standard value of each historical oral diagnosis and treatment image to be identified, and obtaining a reference pixel average value and a reference pixel standard value.
Exemplary, the method for determining the average value of the reference pixel is as follows: and summing three channel numerical values of all the images in the historical oral diagnosis and treatment images to be identified, and dividing the three channel numerical values by the total number of the historical oral diagnosis and treatment images to be identified. The specific formula of the mean value mu is:
Wherein N is the total number of historical oral diagnosis and treatment images to be identified, r, g and b respectively represent three channels of red, green and blue, and D i (c) And (3) representing the value of the ith image in the historical oral diagnosis and treatment images to be identified on the c channel.
Similarly, the reference pixel standard value is calculated by: and calculating squares of absolute differences of three channel numerical values and the mean values of all images in the historical oral diagnosis and treatment images to be identified, dividing the squares by the sum of the total number of the images, and finally taking square roots to obtain standard differences. The specific formula is as follows:
wherein N is the total number of historical oral diagnosis and treatment images to be identified, r, g and b respectively represent three channels of red, green and blue, and D i (c) And (3) representing the numerical value of the ith image in the historical oral diagnosis and treatment images to be identified on the c channel, wherein mu is the average value of the c channel.
Further, determining the preset pixel range based on the reference pixel average value and the reference pixel standard value specifically includes: determining the difference between the average value of the reference pixels and the standard value of the double reference pixels as a minimum value threshold value of a preset pixel range; and determining the sum of the average value of the reference pixels and the standard value of the double reference pixels as the maximum value threshold of the preset pixel range.
In this embodiment, the average value of the reference pixels is denoted as μ, the standard value of the reference pixels is denoted as σ, the minimum threshold value is μ -2σ, the maximum threshold value is μ+2σ, and the preset pixel range is [ μ -2σ, μ+2σ ]. Based on this, the preset pixel ranges can be determined, respectively.
S240, determining the oral diagnosis and treatment image with the first pixel value within the preset pixel range as the oral diagnosis and treatment image to be identified.
In this embodiment, if the first pixel values of the three channels of the current oral diagnosis and treatment image are all within the preset pixel range, the current oral diagnosis and treatment image is determined to be the oral diagnosis and treatment image to be identified.
S250, identifying a target rubber barrier image containing the rubber barrier from a plurality of oral diagnosis and treatment images to be identified based on a rubber barrier image identification model trained in advance.
S260, determining the using completeness of the rubber barrier corresponding to the target diagnosis and treatment platform based on the identification marks of the diagnosis and treatment objects corresponding to the target rubber barrier images and the to-be-verified rubber barrier record information of the target diagnosis and treatment platform.
In the technical scheme of the embodiment of the invention, in the process of removing irrelevant images from a plurality of oral cavity diagnosis and treatment images, first pixel values of three color channels of each oral cavity diagnosis and treatment image are respectively determined, then the oral cavity diagnosis and treatment image with the first pixel value not in the preset pixel range is determined to be the irrelevant image, the irrelevant image is removed, and the oral cavity diagnosis and treatment image with the first pixel value in the preset pixel range is determined to be the oral cavity diagnosis and treatment image to be identified. The statistical method is applied to the color channel values, and irrelevant images can be accurately and efficiently removed, so that the situation of false alarm of the model is reduced, and the model classification effect is improved.
Example III
Fig. 3 is a flowchart of a quality control method for a rubber dam according to a third embodiment of the present invention, where the training process of the image recognition model of the rubber dam is described in detail on the basis of the foregoing embodiments, and the embodiments of the present invention may be combined with each of the alternatives in one or more embodiments. As shown in fig. 3, the quality control method for the rubber barrier comprises the following steps:
as shown in fig. 3, the method includes:
s310, training to obtain a rubber barrier image recognition model.
In this embodiment, the rubber dam image recognition model needs to be trained based on training samples.
Optionally, the specific steps of the rubber barrier image recognition model include:
s3101, acquiring a plurality of historical diagnosis and treatment images, and preprocessing each historical diagnosis and treatment image to obtain an oral diagnosis and treatment image to be trained.
The historical diagnosis and treatment image is a diagnosis and treatment process image reserved in the historical diagnosis and treatment period and can be obtained from a database. The historical diagnosis and treatment images comprise side category images, panoramic category images, including rubber barrier category images, including small dental film category images and paper material category images.
In this embodiment, after a certain number of history diagnostic images are acquired, each history diagnostic image is preprocessed. The preprocessing step includes at least one of sizing, color normalization, normalization to ensure consistency and comparability of the data. And determining the preprocessed historical diagnosis and treatment image as an oral diagnosis and treatment image to be trained.
In particular, in this embodiment, since the images under the "containing the rubber" label are expected to be mostly blue (B) and green (G) colors, the average value of the R channel values is increased to balance during color normalization, that is, three-channel normalized average value is changed from common [ R, G, B ] = [0.485,0.456,0.406] to [ R, G, B ] = [0.485,0.456,0.406], and three-channel normalized standard deviation is unified from common [0.229,0.224,0.225] to [0.5,0.5,0.5].
S3102, classifying the plurality of oral cavity diagnosis and treatment images to be trained based on the image feature information of each oral cavity diagnosis and treatment image to be trained, and setting label information for each oral cavity diagnosis and treatment image to be trained in batches.
In practical application, in order to obtain a training sample with label information, the label information corresponding to each oral diagnosis and treatment image to be trained needs to be determined. Usually, label information of a sample is artificially marked, and the marking efficiency is high. In this embodiment, first, the plurality of oral cavity diagnosis and treatment images to be trained are divided into a plurality of categories, and the same label information is set uniformly for each oral cavity diagnosis and treatment image to be trained in the same category, so that the labeling efficiency is improved.
Preferably, the plurality of oral cavity diagnosis and treatment images to be trained can be classified based on the image characteristic information of each oral cavity diagnosis and treatment image to be trained. The image characteristic information comprises shape information and color information, the shape information is determined based on the length-width ratio of the oral diagnosis and treatment image to be trained, and the color information is determined based on the pixel value of the oral diagnosis and treatment image to be trained.
Illustratively, the image is divided into a landscape (aspect ratio about equal to 1.414), a portrait (aspect ratio about equal to 0.707) and a square-like (aspect ratio about equal to 1) based on the shape information. The image is divided into a black-and-white image and a color image according to the color information.
Specifically, based on the image feature information, classifying the plurality of oral diagnosis and treatment images to be trained specifically includes: classifying the multiple oral cavity diagnosis and treatment images to be trained, which are of which the shape information is a transverse image and the color information is a black-and-white image, into panoramic images; classifying the shape information as a longitudinal image and the color information as a plurality of oral cavity diagnosis and treatment images to be trained of a black-white image into side images; classifying a plurality of oral cavity diagnosis and treatment images to be trained, the shape information of which is a square-like image and the color information of which is a black-and-white image, into images containing small teeth; classifying the color information into a color chart, wherein the color channel pixel values and the blue channel pixel values are larger than a preset threshold value, and the color information is classified as a plurality of to-be-trained oral diagnosis and treatment images including a rubber barrier image; the multiple oral cavity diagnosis and treatment images to be trained, which do not belong to any of side images, panoramic images, including rubber barrier images and small dental film images, are classified as paper material images.
For example, the label information corresponding to the preset side category image, panoramic category image, including the rubber barrier category image, including the small dental film category image, and paper material category image is 1, 2, 3, 4, and 5, respectively. Uniformly setting a 1 label for each oral diagnosis and treatment image to be trained, which is classified as a panoramic image; uniformly setting a 2 label for each oral diagnosis and treatment image to be trained, which is classified as a side image; uniformly setting a 3 label for each oral cavity diagnosis and treatment image to be trained, which is classified as a small dental film image; uniformly setting a 4 label for each oral diagnosis and treatment image to be trained, which is classified as containing a rubber barrier image; and uniformly setting a 5 label for each oral diagnosis and treatment image to be trained, which is classified as a paper data image.
S3103, determining a training sample based on the plurality of oral diagnosis and treatment images to be trained and the label information.
In this embodiment, each oral diagnosis and treatment image to be trained and the corresponding label information are determined as a training sample, so as to obtain a training sample set.
S3104, training the to-be-trained rubber barrier image recognition model based on the training sample to obtain the rubber barrier image recognition model.
The to-be-trained rubber barrier image recognition model is a neural network classification model with model parameters being initial parameters. For example, the image recognition model of the rubber barrier to be trained is a classical three-layer convolutional neural network, and is matched with a ReLu activation layer and a maximum pooling layer. And (3) carrying out iterative training on the to-be-trained rubber barrier image recognition model to obtain the rubber barrier image recognition model with stable performance.
Specifically, any sample in the training sample set is used as a current training sample, the oral diagnosis and treatment image to be trained in the current training sample is input into the rubber barrier image recognition model to be trained, and the rubber barrier image recognition model to be trained can output an output classification result corresponding to the oral diagnosis and treatment image to be trained currently.
Further, a loss value is determined according to the output classification result and the label information of the current training sample. Correcting model parameters in the to-be-trained rubber barrier image recognition model based on the loss values, and converging a loss function in the to-be-trained rubber barrier image recognition model to serve as a training target to obtain the rubber barrier image recognition model.
Specifically, the training error of the loss function, that is, the loss parameter may be used as a condition for detecting whether the loss function currently reaches convergence, for example, whether the training error is smaller than a preset error or whether the error variation trend tends to be stable, or whether the current iteration number is equal to the preset number. If the detection reaches the convergence condition, for example, the training error of the loss function reaches less than the preset error or the error change tends to be stable, which indicates that the training of the to-be-trained rubber image recognition model is completed, and at the moment, the iterative training can be stopped. If the current condition of convergence is not detected, training the to-be-trained rubber barrier image recognition model by further acquiring a training sample until the training error of the loss function is within a preset range. When the training error of the loss function reaches convergence, the to-be-trained rubber barrier image recognition model can be used as the rubber barrier image recognition model.
S320, acquiring a plurality of oral diagnosis and treatment images in the diagnosis and treatment process of the target diagnosis and treatment platform, removing irrelevant images from the oral diagnosis and treatment images, and determining a plurality of oral diagnosis and treatment images to be identified.
S330, identifying a target rubber barrier image containing the rubber barrier from a plurality of to-be-identified oral diagnosis and treatment images based on a pre-trained rubber barrier image identification model.
S340, determining the using completeness of the rubber barrier corresponding to the target diagnosis and treatment platform based on the identification marks of the diagnosis and treatment objects corresponding to the target rubber barrier images and the to-be-verified rubber barrier record information of the target diagnosis and treatment platform.
According to the technical scheme, before the rubber barrier image recognition model is applied, a training sample is constructed so as to train the rubber barrier image recognition model to be trained based on the training sample, and therefore the rubber barrier image recognition model is obtained. The specific sample construction and model training process is as follows: acquiring a plurality of historical diagnosis and treatment images, and preprocessing each historical diagnosis and treatment image to obtain an oral cavity diagnosis and treatment image to be trained; the historical diagnosis and treatment image comprises a side image, a panoramic image, a rubber barrier image, a small tooth film image and a paper material image; classifying a plurality of oral cavity diagnosis and treatment images to be trained based on the image characteristic information of each oral cavity diagnosis and treatment image to be trained, and setting label information for each oral cavity diagnosis and treatment image to be trained in batches; determining a training sample based on a plurality of oral diagnosis and treatment images to be trained and the label information; training the to-be-trained rubber barrier image recognition model based on the training sample to obtain the rubber barrier image recognition model. In the embodiment, the oral cavity diagnosis and treatment images to be trained are pre-classified, and the label information is set for the oral cavity diagnosis and treatment images to be trained in batches, so that the sample labeling efficiency is improved. In the training process of the model, the initial model parameters can be corrected to obtain model parameters which are more in line with practical application, so that the robustness and the prediction accuracy of the rubber barrier image recognition model are improved, and the convenience and the effectiveness of the use supervision of the rubber barrier are further improved.
Example IV
Fig. 4 is a schematic structural diagram of a quality control device for a rubber dam according to a fourth embodiment of the present invention. As shown in fig. 4, the apparatus includes: an image acquisition module 410, a rubber dam image identification module 420, and a usage integrity determination module 430.
The image acquisition module 410 is configured to acquire a plurality of oral diagnosis and treatment images in a diagnosis and treatment process of the target diagnosis and treatment platform, reject irrelevant images from the plurality of oral diagnosis and treatment images, and determine a plurality of oral diagnosis and treatment images to be identified; wherein the oral cavity diagnosis and treatment image to be identified comprises diagnosis and treatment images of various categories;
a rubber dam image recognition module 420 for recognizing a target rubber dam image including a rubber dam from a plurality of oral diagnosis and treatment images to be recognized based on a rubber dam image recognition model trained in advance;
the usage integrity determination module 430 is configured to determine the usage integrity of the rubber barrier corresponding to the target diagnosis and treatment platform based on the identity of the diagnosis target corresponding to each target rubber barrier image and the to-be-verified rubber barrier record information of the target diagnosis and treatment platform.
According to the technical scheme, a plurality of oral cavity diagnosis and treatment images in the diagnosis and treatment process of the target diagnosis and treatment platform are obtained, irrelevant images are removed from the plurality of oral cavity diagnosis and treatment images, a plurality of to-be-identified oral cavity diagnosis and treatment images are determined, wherein the to-be-identified oral cavity diagnosis and treatment images comprise a plurality of types of diagnosis and treatment images, further, a target rubber barrier image comprising a rubber barrier is identified from the plurality of to-be-identified oral cavity diagnosis and treatment images based on a pre-trained rubber barrier image identification model, and further, the using completeness of the rubber barrier corresponding to the target diagnosis and treatment platform is determined based on identification marks of the to-be-treated objects corresponding to the target rubber barrier images and to-be-verified rubber barrier record information of the target diagnosis and treatment platform. According to the method and the device, the calculation result of the utilization rate of the rubber barrier is traceable, the accuracy of the use of the rubber barrier is improved, and the convenience and the effectiveness of the use supervision of the rubber barrier are improved.
Optionally, the image acquisition module 410 includes:
the pixel value determining unit is used for respectively determining first pixel values of three color channels of each oral diagnosis and treatment image;
the irrelevant image removing unit is used for determining the oral diagnosis and treatment image with the first pixel value not in the preset pixel range as an irrelevant image and removing the irrelevant image;
the image to be identified determining unit is used for determining the oral diagnosis and treatment image with the first pixel value within the preset pixel range as the oral diagnosis and treatment image to be identified.
Optionally, the device for controlling the quality of the rubber barrier further includes a preset pixel range determining module, which specifically includes:
the historical image acquisition unit is used for acquiring a plurality of historical oral diagnosis and treatment images to be identified;
the reference value determining unit is used for determining a reference pixel average value and a reference pixel standard value based on pixel values of three color channels of each historical oral diagnosis and treatment image to be identified;
and a preset range determining unit for determining a preset pixel range based on the reference pixel average value and the reference pixel standard value.
The preset range determining unit is specifically configured to determine a difference between the average value of the reference pixels and the standard value of the reference pixels twice as a minimum threshold value of the preset pixel range; and determining the sum of the average value of the reference pixels and the standard value of the double reference pixels as the maximum value threshold of the preset pixel range.
Optionally, the rubber barrier use quality control device further includes a model training module, specifically including:
the training image determining unit is used for acquiring a plurality of historical diagnosis and treatment images, and preprocessing each historical diagnosis and treatment image to obtain an oral cavity diagnosis and treatment image to be trained; the historical diagnosis and treatment image comprises a side image, a panoramic image, a rubber barrier image, a small tooth film image and a paper material image;
the labeling tag unit is used for classifying a plurality of oral cavity diagnosis and treatment images to be trained based on the image characteristic information of each oral cavity diagnosis and treatment image to be trained, and setting tag information for various oral cavity diagnosis and treatment images to be trained in batches;
the training sample determining unit is used for determining training samples based on the plurality of oral diagnosis and treatment images to be trained and the label information;
the model training unit is used for training the image recognition model of the rubber barrier to be trained based on the training sample to obtain the image recognition model of the rubber barrier.
The labeling unit further comprises an image classification subunit, and the image classification subunit is specifically configured to classify a plurality of oral diagnosis and treatment images to be trained, which are of which the shape information is a transverse image and the color information is a black-and-white image, into panoramic images; classifying the shape information as a longitudinal image and the color information as a plurality of oral cavity diagnosis and treatment images to be trained of a black-white image into side images; classifying a plurality of oral cavity diagnosis and treatment images to be trained, the shape information of which is a square-like image and the color information of which is a black-and-white image, into images containing small teeth; classifying the color information into a color chart, wherein the color channel pixel values and the blue channel pixel values are larger than a preset threshold value, and the color information is classified as a plurality of to-be-trained oral diagnosis and treatment images including a rubber barrier image; the multiple oral cavity diagnosis and treatment images to be trained, which do not belong to any of side images, panoramic images, including rubber barrier images and small dental film images, are classified as paper material images.
Optionally, the integrity determination module 430 is used, including:
the identity information matching unit is used for matching the identity marks of the objects to be diagnosed corresponding to the target rubber barrier images with the to-be-verified rubber barrier record information of the target diagnosis and treatment platform one by one, and determining the first number of the objects to be diagnosed with a matching relationship;
the using integrity determining unit is used for determining the using integrity of the rubber barrier corresponding to the target diagnosis and treatment platform based on the second number and the first number of the diagnosis and treatment objects contained in the rubber barrier record information to be verified.
The quality control device for the rubber barrier provided by the embodiment of the invention can execute the quality control method for the rubber barrier provided by any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the execution method.
Example five
Fig. 5 shows a schematic diagram of the structure of an electronic device 10 that may be used to implement an embodiment of the invention. Electronic devices are intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. Electronic equipment may also represent various forms of mobile devices, such as personal digital processing, cellular telephones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be exemplary only, and are not meant to limit implementations of the inventions described and/or claimed herein.
As shown in fig. 5, the electronic device 10 includes at least one processor 11, and a memory, such as a Read Only Memory (ROM) 12, a Random Access Memory (RAM) 13, etc., communicatively connected to the at least one processor 11, in which the memory stores a computer program executable by the at least one processor, and the processor 11 may perform various appropriate actions and processes according to the computer program stored in the Read Only Memory (ROM) 12 or the computer program loaded from the storage unit 18 into the Random Access Memory (RAM) 13. In the RAM13, various programs and data required for the operation of the electronic device 10 may also be stored. The processor 11, the ROM12 and the RAM13 are connected to each other via a bus 14. An input/output (I/O) interface 15 is also connected to bus 14.
Various components in the electronic device 10 are connected to the I/O interface 15, including: an input unit 16 such as a keyboard, a mouse, etc.; an output unit 17 such as various types of displays, speakers, and the like; a storage unit 18 such as a magnetic disk, an optical disk, or the like; and a communication unit 19 such as a network card, modem, wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information/data with other devices via a computer network, such as the internet, and/or various telecommunication networks.
The processor 11 may be a variety of general and/or special purpose processing components having processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), various specialized Artificial Intelligence (AI) computing chips, various processors running machine learning model algorithms, digital Signal Processors (DSPs), and any suitable processor, controller, microcontroller, etc. Processor 11 performs the various methods and processes described above, such as the barrier use quality control method.
In some embodiments, the barrier use quality control method may be implemented as a computer program tangibly embodied on a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program may be loaded and/or installed onto the electronic device 10 via the ROM12 and/or the communication unit 19. When the computer program is loaded into RAM13 and executed by processor 11, one or more steps of the barrier use quality control method described above may be performed. Alternatively, in other embodiments, processor 11 may be configured to perform the barrier use quality control method in any other suitable manner (e.g., by means of firmware).
Various implementations of the systems and techniques described here above may be implemented in digital electronic circuitry, integrated circuit systems, field Programmable Gate Arrays (FPGAs), application Specific Integrated Circuits (ASICs), application Specific Standard Products (ASSPs), systems On Chip (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs, the one or more computer programs may be executed and/or interpreted on a programmable system including at least one programmable processor, which may be a special purpose or general-purpose programmable processor, that may receive data and instructions from, and transmit data and instructions to, a storage system, at least one input device, and at least one output device.
A computer program for carrying out methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general purpose computer, special purpose computer, or other programmable barrier usage quality control device such that the computer programs, when executed by the processor, cause the functions/operations specified in the flowchart and/or block diagram block or blocks to be performed. The computer program may execute entirely on the machine, partly on the machine, as a stand-alone software package, partly on the machine and partly on a remote machine or entirely on the remote machine or server.
In the context of the present invention, a computer-readable storage medium may be a tangible medium that can contain, or store a computer program for use by or in connection with an instruction execution system, apparatus, or device. The computer readable storage medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. Alternatively, the computer readable storage medium may be a machine readable signal medium. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
To provide for interaction with a user, the systems and techniques described here can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to a user; and a keyboard and a pointing device (e.g., a mouse or a trackball) through which a user can provide input to the electronic device. Other kinds of devices may also be used to provide for interaction with a user; for example, feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form, including acoustic input, speech input, or tactile input.
The systems and techniques described here can be implemented in a computing system that includes a background component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such background, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local Area Networks (LANs), wide Area Networks (WANs), blockchain networks, and the internet.
The computing system may include clients and servers. The client and server are typically remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The server can be a cloud server, also called a cloud computing server or a cloud host, and is a host product in a cloud computing service system, so that the defects of high management difficulty and weak service expansibility in the traditional physical hosts and VPS service are overcome.
It should be appreciated that various forms of the flows shown above may be used to reorder, add, or delete steps. For example, the steps described in the present invention may be performed in parallel, sequentially, or in a different order, so long as the desired results of the technical solution of the present invention are achieved, and the present invention is not limited herein.
The above embodiments do not limit the scope of the present invention. It will be apparent to those skilled in the art that various modifications, combinations, sub-combinations and alternatives are possible, depending on design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the scope of the present invention.
Claims (10)
1. A method for controlling the quality of a rubber dam, comprising:
acquiring a plurality of oral diagnosis and treatment images in the diagnosis and treatment process of a target diagnosis and treatment platform, removing irrelevant images from the oral diagnosis and treatment images, and determining a plurality of oral diagnosis and treatment images to be identified; wherein the oral cavity diagnosis and treatment image to be identified comprises diagnosis and treatment images of various categories;
identifying a target rubber barrier image containing a rubber barrier from the plurality of to-be-identified oral diagnosis and treatment images based on a pre-trained rubber barrier image identification model;
And determining the using completeness of the rubber barrier corresponding to the target diagnosis and treatment platform based on the identification marks of the diagnosis and treatment objects corresponding to the target rubber barrier images and the to-be-verified rubber barrier record information of the target diagnosis and treatment platform.
2. The method of claim 1, wherein the removing extraneous images from the plurality of oral treatment images, determining a plurality of oral treatment images to be identified, comprises:
respectively determining first pixel values of three color channels of each oral diagnosis and treatment image;
determining the oral diagnosis and treatment image with the first pixel value not in the preset pixel range as an irrelevant image, and eliminating the irrelevant image;
and determining the oral diagnosis and treatment image with the first pixel value within a preset pixel range as an oral diagnosis and treatment image to be identified.
3. The method as recited in claim 2, further comprising:
a preset pixel range is preset;
the predetermined preset pixel range includes:
acquiring a plurality of historical oral diagnosis and treatment images to be identified;
determining a reference pixel average value and a reference pixel standard value based on pixel values of three color channels of each historical oral diagnosis and treatment image to be identified;
And determining a preset pixel range based on the reference pixel average value and the reference pixel standard value.
4. A method according to claim 3, wherein said determining a predetermined pixel range based on said reference pixel mean value and said reference pixel standard value comprises:
determining the difference between the reference pixel average value and the twice reference pixel standard value as the minimum value threshold of the preset pixel range;
and determining the sum of the reference pixel average value and the twice reference pixel standard value as a maximum value threshold value of the preset pixel range.
5. The method as recited in claim 1, further comprising:
training to obtain the rubber barrier image recognition model;
the training to obtain the rubber barrier image recognition model comprises the following steps:
acquiring a plurality of historical diagnosis and treatment images, and preprocessing each historical diagnosis and treatment image to obtain an oral diagnosis and treatment image to be trained; the historical diagnosis and treatment image comprises a lateral image, a panoramic image, a rubber barrier image, a small dental film image and a paper material image;
classifying the plurality of oral cavity diagnosis and treatment images to be trained based on the image characteristic information of each oral cavity diagnosis and treatment image to be trained, and setting label information for each oral cavity diagnosis and treatment image to be trained in batches;
Determining a training sample based on the plurality of oral diagnosis and treatment images to be trained and the label information;
training the to-be-trained rubber barrier image recognition model based on the training sample to obtain the rubber barrier image recognition model.
6. The method of claim 5, wherein the image characteristic information includes shape information and color information, the shape information being determined based on an aspect ratio of the oral treatment images to be trained, the color information being determined based on pixel values of the oral treatment images to be trained, the classifying the plurality of oral treatment images to be trained based on the image characteristic information of each of the oral treatment images to be trained comprising:
classifying a plurality of oral cavity diagnosis and treatment images to be trained, wherein the shape information is a transverse image, the color information is a black-and-white image, and the oral cavity diagnosis and treatment images to be trained are classified as panoramic images;
classifying a plurality of oral cavity diagnosis and treatment images to be trained, of which the shape information is a longitudinal image and the color information is a black-white image, into side images;
classifying a plurality of oral cavity diagnosis and treatment images to be trained, the shape information of which is a square-like image and the color information of which is a black-white image, into images containing small teeth;
Classifying the multiple to-be-trained oral diagnosis and treatment images with color information as a color chart and color channel pixel values and blue channel pixel values being larger than preset thresholds into images containing rubber barriers;
classifying a plurality of oral diagnosis and treatment images to be trained, which do not belong to any of side images, panoramic images, including rubber barrier images and including small dental film images, into paper material images.
7. The method of claim 1, wherein determining the usage integrity of the rubber barrier corresponding to the target diagnosis and treat platform based on the identification of the diagnosis and treat object corresponding to each target rubber barrier image and the to-be-verified rubber barrier record information of the target diagnosis and treat platform comprises:
matching the identification marks of the objects to be treated corresponding to the target rubber barrier images with the to-be-verified rubber barrier record information of the target diagnosis and treatment platform one by one, and determining the first number of objects to be treated with a matching relationship;
and determining the using completeness of the rubber barrier corresponding to the target diagnosis and treatment platform based on the second number and the first number of the objects to be treated contained in the to-be-verified rubber barrier record information.
8. A barrier use quality control device, comprising:
The image acquisition module is used for acquiring a plurality of oral diagnosis and treatment images in the diagnosis and treatment process of the target diagnosis and treatment platform, removing irrelevant images from the oral diagnosis and treatment images and determining a plurality of oral diagnosis and treatment images to be identified; wherein the oral cavity diagnosis and treatment image to be identified comprises diagnosis and treatment images of various categories;
the rubber barrier image recognition module is used for recognizing a target rubber barrier image containing a rubber barrier from the plurality of oral diagnosis and treatment images to be recognized based on a pre-trained rubber barrier image recognition model;
the using integrity determining module is used for determining the using integrity of the rubber barrier corresponding to the target diagnosis and treatment platform based on the identity of the diagnosis and treatment object corresponding to each target rubber barrier image and the to-be-verified rubber barrier record information of the target diagnosis and treatment platform.
9. An electronic device, characterized in that the electronic device comprises:
one or more processors;
storage means for storing one or more programs,
the method of using quality control of a rubber dam as claimed in any one of claims 1 to 7 when the one or more programs are executed by the one or more processors.
10. A computer readable storage medium storing computer instructions for causing a processor to perform the method of controlling the quality of use of a rubber dam of any one of claims 1-7 when executed.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202311538888.XA CN117456466A (en) | 2023-11-17 | 2023-11-17 | Method, device, equipment and medium for controlling using quality of rubber barrier |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202311538888.XA CN117456466A (en) | 2023-11-17 | 2023-11-17 | Method, device, equipment and medium for controlling using quality of rubber barrier |
Publications (1)
Publication Number | Publication Date |
---|---|
CN117456466A true CN117456466A (en) | 2024-01-26 |
Family
ID=89596667
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202311538888.XA Pending CN117456466A (en) | 2023-11-17 | 2023-11-17 | Method, device, equipment and medium for controlling using quality of rubber barrier |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN117456466A (en) |
-
2023
- 2023-11-17 CN CN202311538888.XA patent/CN117456466A/en active Pending
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US20240087725A1 (en) | Systems and methods for automated medical image analysis | |
WO2015110411A1 (en) | Systems and methods for wound monitoring | |
WO2018196168A1 (en) | Image-based plant lesion recognition method and system, and computer apparatus | |
CN107248039A (en) | Real-time quality control method and device based on medical specimen detection project result | |
CN111008561A (en) | Livestock quantity determination method, terminal and computer storage medium | |
WO2021082433A1 (en) | Digital pathological image quality control method and apparatus | |
CN116681923A (en) | Automatic ophthalmic disease classification method and system based on artificial intelligence | |
CN113516639B (en) | Training method and device for oral cavity abnormality detection model based on panoramic X-ray film | |
CN111667457B (en) | Automatic identification method, system, terminal and storage medium for vertebral body information based on medical image | |
CN110060246A (en) | A kind of image processing method, equipment and storage medium | |
CN109801394B (en) | Staff attendance checking method and device, electronic equipment and readable storage medium | |
CN112263220A (en) | Endocrine disease intelligent diagnosis system | |
CN112818946A (en) | Training of age identification model, age identification method and device and electronic equipment | |
CN117456466A (en) | Method, device, equipment and medium for controlling using quality of rubber barrier | |
CN113487611B (en) | Dental film image processing method and system based on artificial intelligence | |
CN110909706A (en) | Method and device for judging person during daytime and night, electronic equipment and storage medium | |
CN115393314A (en) | Deep learning-based oral medical image identification method and system | |
CN111179226B (en) | Visual field diagram identification method and device and computer storage medium | |
CN115578370B (en) | Brain image-based metabolic region abnormality detection method and device | |
CN111915553A (en) | Part identification method and device based on time sequence modeling | |
ÇELİK | A Novel Deep Learning Model for Pain Intensity Evaluation | |
CN111513673A (en) | Image-based growth state monitoring method, device, equipment and storage medium | |
CN113408669B (en) | Image determining method and device, storage medium and electronic device | |
CN110689112A (en) | Data processing method and device | |
CN118134829A (en) | Dental image processing method and device |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination |