CN116402739A - Quality evaluation method and device for electronic endoscope detection flow - Google Patents
Quality evaluation method and device for electronic endoscope detection flow Download PDFInfo
- Publication number
- CN116402739A CN116402739A CN202211683331.0A CN202211683331A CN116402739A CN 116402739 A CN116402739 A CN 116402739A CN 202211683331 A CN202211683331 A CN 202211683331A CN 116402739 A CN116402739 A CN 116402739A
- Authority
- CN
- China
- Prior art keywords
- image sequence
- image
- basic
- electronic endoscope
- bit
- 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
- 238000000034 method Methods 0.000 title claims abstract description 58
- 238000001514 detection method Methods 0.000 title claims abstract description 45
- 238000013441 quality evaluation Methods 0.000 title claims abstract description 18
- 239000003550 marker Substances 0.000 claims abstract description 102
- 238000011156 evaluation Methods 0.000 claims abstract description 31
- 238000012216 screening Methods 0.000 claims abstract description 24
- 238000004364 calculation method Methods 0.000 claims description 23
- 238000004590 computer program Methods 0.000 claims description 20
- 238000007689 inspection Methods 0.000 claims description 17
- 230000008569 process Effects 0.000 claims description 16
- 238000001303 quality assessment method Methods 0.000 claims description 16
- 238000012545 processing Methods 0.000 claims description 10
- 230000006870 function Effects 0.000 claims description 6
- 238000003745 diagnosis Methods 0.000 abstract description 8
- 238000010606 normalization Methods 0.000 abstract description 7
- 238000010586 diagram Methods 0.000 description 6
- 238000012549 training Methods 0.000 description 6
- 210000002784 stomach Anatomy 0.000 description 4
- 238000012360 testing method Methods 0.000 description 4
- 230000008859 change Effects 0.000 description 3
- 238000013500 data storage Methods 0.000 description 2
- 238000013135 deep learning Methods 0.000 description 2
- 210000002409 epiglottis Anatomy 0.000 description 2
- 238000003908 quality control method Methods 0.000 description 2
- 230000035945 sensitivity Effects 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- 239000013598 vector Substances 0.000 description 2
- OKTJSMMVPCPJKN-UHFFFAOYSA-N Carbon Chemical compound [C] OKTJSMMVPCPJKN-UHFFFAOYSA-N 0.000 description 1
- 238000009825 accumulation Methods 0.000 description 1
- 230000001174 ascending effect Effects 0.000 description 1
- 238000012217 deletion Methods 0.000 description 1
- 230000037430 deletion Effects 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 229910021389 graphene Inorganic materials 0.000 description 1
- 230000001788 irregular Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000012163 sequencing technique Methods 0.000 description 1
- 230000001960 triggered effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0012—Biomedical image inspection
- G06T7/0014—Biomedical image inspection using an image reference approach
-
- 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
- G06V10/761—Proximity, similarity or dissimilarity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10016—Video; Image sequence
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10068—Endoscopic image
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20081—Training; Learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20084—Artificial neural networks [ANN]
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Quality & Reliability (AREA)
- Radiology & Medical Imaging (AREA)
- Artificial Intelligence (AREA)
- Computing Systems (AREA)
- Databases & Information Systems (AREA)
- Evolutionary Computation (AREA)
- Software Systems (AREA)
- Multimedia (AREA)
- Endoscopes (AREA)
Abstract
The application relates to a quality evaluation method and a quality evaluation device for an electronic endoscope detection flow, comprising the steps of receiving a basic image sequence shot by an electronic endoscope, and screening the basic image sequence to obtain a sample image sequence for highlighting a zone bit; analyzing the sample image sequence frame by frame, and selecting a target image sequence with a marker bit; performing similarity comparison on the target image sequence and a preset marker bit image sequence to obtain a marker bit image serving as a reference; and evaluating the accuracy of the basic image sequence according to the generation sequence of the zone bit images. The evaluation value corresponding to the operation of acquiring the basic image sequence is calculated based on the position mark of the marker image in the preset marker image sequence, so that the normalization of the electronic endoscope operation can be evaluated more accurately, the accuracy of the evaluation of the electronic endoscope operation can be improved, and meanwhile, the evaluation requirement under more complex diagnosis and treatment environments can be met through adjustment of the marker image.
Description
Technical Field
The present disclosure relates to the field of image processing, and in particular, to a quality evaluation method and apparatus for an electronic endoscope detection procedure.
Background
Electronic endoscopes, which are a conventional medical device, play an important role in various types of preoperative examinations, but have problems of irregular operation, incomplete observation, inaccurate diagnosis and evaluation due to uneven doctor level, and often have differences in the integrity of examination results. In order to reduce the impact of differences in inspection result integrity on diagnosis, it is necessary to introduce quality control schemes for the endoscopic detection procedure.
The existing quality control system based on the endoscope scene can only judge whether the shot image is accurate or not, but is not tightly combined with a specific examination type, and cannot adapt to the requirements of a clinical complex diagnosis and treatment environment.
Disclosure of Invention
Based on the foregoing, it is necessary to provide a quality evaluation method and apparatus capable of improving the quality of the detection procedure of the electronic endoscope based on the image similarity comparison result.
In a first aspect, the present application provides a quality assessment method for an electronic endoscope detection procedure.
The method comprises the following steps:
receiving a basic image sequence shot by an electronic endoscope, and screening the basic image sequence to obtain a sample image sequence for highlighting a marker bit;
analyzing the sample image sequence frame by frame, and selecting a target image sequence with a marker bit;
performing similarity comparison on the target image sequence and a preset zone bit image sequence, and acquiring a zone bit image serving as a reference from the preset zone bit image sequence based on a comparison result;
and evaluating the accuracy of the basic image sequence according to the generation sequence of the zone bit images.
In one embodiment, the receiving the base image sequence captured by the electronic endoscope, and screening the base image sequence to obtain a sample image sequence for highlighting the marker bit includes:
receiving a basic image sequence shot by an electronic endoscope, and extracting a basic image from the basic image sequence;
sequentially calculating the image variation of two adjacent frames of basic images;
screening the basic image according to the numerical relation between the image variation and a preset threshold value, and constructing a sample image array based on the screened basic image.
In one embodiment, the calculating the image variation of the two adjacent frames of base images sequentially includes:
respectively calculating variances of the basic images of two adjacent frames; or (b)
And respectively calculating pixel values of the adjacent two frames of basic images.
In one embodiment, the filtering the base image according to the numerical relation between the image variation and a preset threshold value, and constructing a sample image array based on the filtered base image includes:
if the image variation is larger than a preset threshold, deleting the previous frame in the time dimension in the two adjacent frames of basic images;
and constructing a sample image sequence based on the rest of the basic images.
In one embodiment, the performing similarity comparison between the target image sequence and a preset flag bit image sequence, and obtaining a flag bit image serving as a reference from the preset flag bit image sequence based on a comparison result includes:
sequentially selecting each frame of target image from the target image sequence, and executing a preset similarity detection flow to obtain a reference marker bit image corresponding to each frame of target image;
the similarity detection flow is as follows:
calculating the similarity of a current frame target image and each frame of marker bit image in a preset marker bit image sequence, and obtaining a plurality of similarity results corresponding to the current frame target image;
and selecting a zone bit image corresponding to the maximum similarity from the multiple similarity results as a reference zone bit image of the current frame target image, and deleting the reference zone bit image from the preset zone bit image sequence.
In one embodiment, the updating the preset flag bit image sequence includes:
deleting a first zone bit image from the preset zone bit image sequence.
In one embodiment, the evaluating the accuracy of the base image sequence according to the generation order of the flag bit images includes:
establishing a calculation function based on the generating sequence of the mark bit images;
and generating an evaluation result corresponding to the basic image sequence according to the calculation result of the calculation function.
In a second aspect, the present application further provides a quality assessment apparatus for an electronic endoscope detection procedure. The device comprises:
the image processing module is used for receiving a basic image sequence shot by the electronic endoscope, screening the basic image sequence and obtaining a sample image sequence for highlighting the marker bit;
the image screening module is used for analyzing the sample image sequence frame by frame and selecting a target image sequence with a zone bit;
the image calculation module is used for comparing the similarity between the target image sequence and a preset marker bit image sequence, and acquiring a marker bit image serving as a reference purpose from the preset marker bit image sequence based on a comparison result;
and the image evaluation module is used for evaluating the accuracy of the basic image sequence according to the generation order of the zone bit images.
In a third aspect, the present application also provides a computer device. The computer device comprises a memory storing a computer program and a processor which when executing the computer program performs the steps of:
receiving a basic image sequence shot by an electronic endoscope, and screening the basic image sequence to obtain a sample image sequence for highlighting a marker bit;
analyzing the sample image sequence frame by frame, and selecting a target image sequence with a marker bit;
performing similarity comparison on the target image sequence and a preset zone bit image sequence, and acquiring a zone bit image serving as a reference from the preset zone bit image sequence based on a comparison result;
and evaluating the accuracy of the basic image sequence according to the generation sequence of the zone bit images.
In a fourth aspect, the present application also provides a computer-readable storage medium. The computer readable storage medium having stored thereon a computer program which when executed by a processor performs the steps of:
receiving a basic image sequence shot by an electronic endoscope, and screening the basic image sequence to obtain a sample image sequence for highlighting a marker bit;
analyzing the sample image sequence frame by frame, and selecting a target image sequence with a marker bit;
performing similarity comparison on the target image sequence and a preset zone bit image sequence, and acquiring a zone bit image serving as a reference from the preset zone bit image sequence based on a comparison result;
and evaluating the accuracy of the basic image sequence according to the generation sequence of the zone bit images.
In a fifth aspect, the present application also provides a computer program product. The computer program product comprises a computer program which, when executed by a processor, implements the steps of:
receiving a basic image sequence shot by an electronic endoscope, and screening the basic image sequence to obtain a sample image sequence for highlighting a marker bit;
analyzing the sample image sequence frame by frame, and selecting a target image sequence with a marker bit;
performing similarity comparison on the target image sequence and a preset zone bit image sequence, and acquiring a zone bit image serving as a reference from the preset zone bit image sequence based on a comparison result;
and evaluating the accuracy of the basic image sequence according to the generation sequence of the zone bit images.
According to the quality evaluation method, the device, the computer equipment, the storage medium and the computer program product for the electronic endoscope detection flow, through selecting the marker bit image which can most represent the current electronic endoscope operation condition, the evaluation value corresponding to the operation of acquiring the basic image sequence is calculated based on the position mark of the marker bit image in the preset marker bit image sequence, the normalization of the electronic endoscope operation can be evaluated more accurately, the accuracy of the electronic endoscope operation evaluation can be improved, and meanwhile, the adjustment of the marker bit image can also be adapted to the evaluation requirements under more complex diagnosis and treatment environments.
Drawings
FIG. 1 is a diagram of an application environment for a quality assessment method for an electronic endoscope inspection procedure in one embodiment;
FIG. 2 is a flow diagram of a quality assessment method for an electronic endoscope detection flow in one embodiment;
FIG. 3 is a schematic diagram of a set of twinning networks used for similarity calculation in one embodiment;
FIG. 4 is a block diagram of a quality assessment device for an electronic endoscope detection procedure in one embodiment;
fig. 5 is an internal structural diagram of a computer device in one embodiment.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application will be further described in detail with reference to the accompanying drawings and examples. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the present application.
The quality evaluation method for the electronic endoscope detection flow provided by the embodiment of the application can be applied to an application environment shown in fig. 1. Wherein the terminal 102 communicates with the server 104 via a network. The data storage system may store data that the server 104 needs to process. The data storage system may be integrated on the server 104 or may be located on a cloud or other network server. A specific quality assessment method for the electronic endoscope detection flow is implemented in a terminal or a server. The terminal 102 may be, but is not limited to, various personal computers, notebook computers, smart phones, tablet computers, etc. The server 104 may be implemented as a stand-alone server or as a server cluster of multiple servers.
In one embodiment, as shown in fig. 2, a quality evaluation method for an electronic endoscope detection procedure is provided, and the method is applied to the terminal 102 in fig. 1 for illustration, and includes the following steps:
and S20, receiving a basic image sequence shot by the electronic endoscope, and screening the basic image sequence to obtain a sample image sequence for highlighting the zone bit.
The basic image sequence is a collection of a large number of basic images which are directly shot and acquired by the electronic endoscope in the clinical use process. However, considering that the evaluation operation based on the marker bit in the subsequent step needs to be adapted, a series of screening needs to be performed on the basic image sequence, so as to obtain a sample image sequence for highlighting the marker bit and being used in the subsequent processing process.
And S40, analyzing the sample image sequence frame by frame, and selecting a target image sequence with a zone bit.
The obtained sample image sequence is sent to a server for frame-by-frame analysis so as to select a target image with a marker bit from the sample image sequence and further form a target image sequence.
Typically, a deep learning network model is used to determine whether a preset flag bit exists in an image. The depth model is obtained by selecting marked bit image data from a large number of actual operation videos, dividing the data into training data and test data after manual marking, using the training data for model training, and using a model with specificity and sensitivity meeting requirements on the test data for detecting the marked bit.
It is noted that the marker bit herein refers to image information of some positions that are necessarily present during the routine examination by the electronic endoscope, such as the stomach depression, the stomach body, the pyriform fos, the epiglottis wall, and the like. Whether the image information at the positions is clear and complete is used as a reference for judging the inspection quality of the electronic endoscope, and whether the detection omission and the like occur in the inspection process or not can be accurately judged.
Step S60, performing similarity comparison on the target image sequence and a preset zone bit image sequence, and acquiring a zone bit image serving as a reference from the preset zone bit image sequence based on a comparison result.
The preset marker bit image sequence represents image features which are necessarily acquired in a regular electronic endoscope detection flow, so that the marker bit image sequence can be used as a detection standard for judging whether the electronic endoscope detection flow is compliant, the target image sequence and the preset marker bit image sequence are subjected to similarity comparison, and the marker bit image which can most represent the current electronic endoscope operation condition is selected, so that the current electronic endoscope operation can be evaluated in the subsequent steps conveniently.
And step S80, evaluating the accuracy of the basic image sequence according to the generation order of the zone bit images.
The evaluation is to calculate the evaluation value corresponding to the operation of acquiring the basic image sequence based on the position mark of the marker bit image in the preset marker bit image sequence according to the marker bit image extracted in the previous step, so that the normalization of the electronic endoscope operation can be evaluated more accurately.
According to the quality evaluation method for the electronic endoscope detection flow, after at least one basic image in the inspection task is acquired, whether the image has a marker bit is judged, the marker information obtained through recognition is searched and compared with the marker bit information in the base, the base is updated according to the comparison result, and finally the inspection task is evaluated based on the base and the recognition comparison result. By selecting the marker bit image which can most represent the current operation condition of the electronic endoscope, and calculating the evaluation value corresponding to the operation of acquiring the basic image sequence based on the position mark of the marker bit image in the preset marker bit image sequence, the normalization of the electronic endoscope operation can be evaluated more accurately, the accuracy of the electronic endoscope operation evaluation can be improved, and meanwhile, the evaluation requirement under more complex diagnosis and treatment environments can be met by adjusting the marker bit image.
In one embodiment, a base image sequence captured by an electronic endoscope is received, and the base image sequence is screened to obtain a sample image sequence for highlighting the marker bit, that is, step S20 includes:
step S22, receiving a basic image sequence shot by the electronic endoscope, and extracting a basic image from the basic image sequence;
step S24, sequentially calculating the image variation of two adjacent frames of basic images;
and S26, screening the basic image according to the numerical relation between the image variation and a preset threshold value, and constructing a sample image array for highlighting the marker bit based on the screened basic image.
In practice, it is necessary to process a basic image sequence captured by an electronic endoscope in order to obtain a target image sequence used for image comparison in a subsequent step.
The basic image sequence is a set of basic images obtained by shooting the electronic endoscope according to a preset time interval in the clinical use process. For ease of processing, the sequence of base images needs to be decomposed to obtain individual base images. Then, judging the variation between two adjacent basic images, and judging whether the two basic images have enough difference so as to delete one of the basic images; and after the deletion is finished, obtaining a sample image array formed based on the screened basic images.
The step S24 of sequentially calculating the image variation of the two adjacent frames of base images includes:
the variance of the two adjacent frames of basic images is calculated respectively or the pixel values of the two adjacent frames of basic images are calculated respectively.
In practice, there are two types of calculation of the amount of change between two adjacent base images: variance or pixel values are calculated. The former way is to count the variance of each frame of basic image, so that the operation of deleting image frames is triggered when the difference value of the variances of two frames of basic images exceeds a preset threshold value in the subsequent steps; the latter way is to calculate the pixel value of each frame of basic image, and in the subsequent step, the operation of deleting the image frame starts when the difference value of the pixel values of the two frames of basic images exceeds the preset threshold value.
In one embodiment, the basic image is screened according to the numerical relation between the image variation and the preset threshold, and the sample image array is constructed based on the screened basic image, and step S26 includes:
step S262, if the image variation is larger than the preset threshold, deleting the previous frame in the time dimension in the two adjacent frames of basic images;
step S264, a sample image sequence for highlighting the flag bit is constructed based on the remaining base image.
In implementation, if the image variation between two adjacent frames of base images is greater than a preset threshold, which indicates that the difference between two adjacent frames of base images is too large, there may be a situation that the corresponding areas of the base images are greatly shifted, and at this time, the earlier frame, i.e. the previous frame, of the two frames in the time dimension is preferentially deleted.
All the basic images are processed as described above, and a sample image sequence is constructed based on the remaining basic images.
In one embodiment, the target image sequence is compared with a preset flag bit image sequence in similarity, and a flag bit image serving as a reference is obtained from the preset flag bit image sequence based on a comparison result, that is, step S60 includes:
and sequentially selecting each frame of target image from the target image sequence, and executing a preset similarity detection flow to obtain a reference zone bit image corresponding to each frame of target image.
The similarity detection flow is as follows:
step S62, calculating the similarity of the target image of the current frame and each frame of marker bit image in a preset marker bit image sequence, and obtaining a plurality of similarity results corresponding to the target image of the current frame;
step S64, selecting a zone bit image corresponding to the maximum similarity from a plurality of similarity results as a reference zone bit image of the target image of the current frame, and deleting the reference zone bit image from a preset zone bit image sequence.
In implementation, the sample image sequence obtained in the step S20 is processed in the step S40 to obtain the target image sequence with the flag bit. And comparing the similarity between the target image sequence and a preset marker bit image sequence, selecting a marker bit image with the highest similarity with each frame of target image in the target image sequence from the target image sequence, and taking the serial number of the selected marker bit image, which represents the relative position in the preset marker bit image sequence, as a reference value of whether the electronic endoscope accords with the detection flow or not. And then in the subsequent step, compliance assessment is performed on the detection operation of the electronic endoscope based on the reference value herein.
Before a specific comparison operation, a preset marker bit image sequence needs to be described. The preset zone bit images provide a certain number of zone bit images for doctors based on priori knowledge and existing data. And taking the set of all the preset zone bit images as a base, and sequencing the zone bit images in the base according to the front-back sequence of the zone bit theory in the checking process.
After a preset mark bit image sequence is constructed, a comparison process can be performed, specifically:
selecting a first target image from a target image sequence, and calculating the similarity between the first target image and each frame of marker bit image in a preset marker bit image sequence; and selecting the zone bit image corresponding to the maximum similarity as a first zone bit image corresponding to the reference application of the first target image.
Illustratively, the set of base libraries is ψ, and
0<i.ltoreq.N, wherein ψ i For the marker bit image sequence, N is the total number of marker bits to be checked, the value range is a positive integer, and +.>
0<j.ltoreq.M, where α ij And the j-th bottom library image of the marker bit i is the number of comparison images required by a single marker bit in the bottom library, and the value range of i and j is a positive integer.
The main ideas of the comparison are as follows: and calculating the similarity between the images, and considering that the comparison is successful when the similarity reaches a threshold value.
For the first target image I rect The matching similarity result is shown in formula one:
acquisition of I sim The value of i, j is recorded as i sim And j sim 。
S in the formula I is similarity calculation of a frame of zone bit image in an image sequence of the first target image and a preset zone bit.
It should be noted that the calculation mode of the similarity calculation may typically be implemented through a set of twin networks, as shown in fig. 3, two Network models network_a and network_b each accept a graph as a Network input, and the two networks share a weight W, and each output a set of multidimensional feature vectors with the same dimension, so that the similarity S between two input images is determined by calculating the Distance < G (x 1), G (x 2) >, between the two output vectors.
And after the corresponding zone bit images are screened out by carrying out the similarity calculation on the first target image, repeating the operation on each frame of target image remained in the target image sequence, so that all the single win target image sequences can be determined as zone bit images for reference purposes.
It is particularly noted that, after the corresponding flag bit image is screened out each time the similarity calculation is performed, the updating operation shown in step S66 must be performed.
Specifically, step S66 includes:
step S662, deleting the first zone bit image from the preset zone bit image sequence.
In implementation, according to the foregoing, the sequence number of the position of the selected flag bit image in the original preset flag bit image sequence based on similarity calculation is used as a key for subsequent evaluation, so in order to prevent sequence number confusion, after the corresponding flag bit image is selected by similarity calculation each time, the obtained flag bit image needs to be removed from the preset flag bit image sequence (i.e. the bottom library).
In one embodiment, the accuracy of the base image sequence is evaluated according to the generation order of the flag bit images, that is, step S80 includes:
step S82, a calculation function based on the generating sequence of the zone bit images is established;
step S84, an evaluation result corresponding to the basic image sequence is generated according to the calculation result of the calculation function.
In an implementation, at the bottom library ψ= { ψ 1 ,ψ 2 ,...,ψ N And N is the serial number of the marker bit, the marker bit images in the bottom library are arranged in ascending order according to the serial number, and the detected marker bit can be removed from the bottom library in the detection process, so that the sequence of the rest marker bit images is unchanged.
The checking score calculation flow is as follows, and the matching similarity result I is obtained sim And the corresponding flag bit sequence number i sim And image number j sim . If it matches the similarity result I sim If the number is greater than the set threshold value, the number is regarded as i sim The flag checking of (2) is completed.
But since there is a linear order of examination for each flag bit, the final score is also related to the order in which the examination is completed. Assuming that the number of the existing first flag bit image in the bottom library is i, the checking process score is initialized to 0 at the beginning of checking, and the checking completion number is i sim After the flag bit of (2), the score updating mode is shown in a formula II:
score+＝N-abs(i sim -i) formula two;
in the formula, score+ is a score accumulation calculator, N is the sequence number of the flag bit, and abs () is an absolute value operator. The meaning of equation two is: when the first flag bit image is just the flag bit image corresponding to the first target image, the value obtained by abs () is zero at this time, which means that the operation score corresponding to the first target image can take the maximum value N. Similarly, the larger the difference between the serial numbers of the target image and the corresponding flag bit image, the larger the value obtained by abs (), the smaller the score value corresponding to the target image, which means that the further the operation of the electronic endoscope corresponding to the target image deviates from the prescribed operation, the worse the evaluation value thereof.
When all the checks are completed, traversing the base, judging whether flag bits which are not checked are still existed, deducting score of score according to the importance degree of the preset flag bit if one flag bit exists, and reporting the missed check position to the system. The final score serves as a basis for evaluating the quality of this inspection.
According to the quality evaluation method for the electronic endoscope detection flow, after at least one basic image in the inspection task is acquired, whether the image has a marker bit is judged, the marker information obtained through recognition is searched and compared with the marker bit information in the base, the base is updated according to the comparison result, and finally the inspection task is evaluated based on the base and the recognition comparison result. By selecting the marker bit image which can most represent the current operation condition of the electronic endoscope, and calculating the evaluation value corresponding to the operation of acquiring the basic image sequence based on the position mark of the marker bit image in the preset marker bit image sequence, the normalization of the electronic endoscope operation can be evaluated more accurately, the accuracy of the electronic endoscope operation evaluation can be improved, and meanwhile, the evaluation requirement under more complex diagnosis and treatment environments can be met by adjusting the marker bit image.
It should be understood that, although the steps in the flowcharts related to the embodiments described above are sequentially shown as indicated by arrows, these steps are not necessarily sequentially performed in the order indicated by the arrows. The steps are not strictly limited to the order of execution unless explicitly recited herein, and the steps may be executed in other orders. Moreover, at least some of the steps in the flowcharts described in the above embodiments may include a plurality of steps or a plurality of stages, which are not necessarily performed at the same time, but may be performed at different times, and the order of the steps or stages is not necessarily performed sequentially, but may be performed alternately or alternately with at least some of the other steps or stages.
Based on the same inventive concept, the embodiment of the application also provides a quality evaluation device for the electronic endoscope detection process, which is used for realizing the quality evaluation method for the electronic endoscope detection process. The implementation of the solution provided by the device is similar to the implementation described in the above method, so the specific limitation in one or more embodiments of the quality assessment device for an electronic endoscope detection procedure provided below may be referred to the limitation of the quality assessment method for an electronic endoscope detection procedure hereinabove, and will not be repeated herein.
In one embodiment, as shown in fig. 4, there is provided a quality assessment device 40 for an electronic endoscope detection procedure, comprising: an image processing module 42, an image screening module 44, an image calculation module 46, and an image evaluation module 48, wherein:
the image processing module 42 is configured to receive a base image sequence captured by the electronic endoscope, and screen the base image sequence to obtain a sample image sequence for highlighting the marker bit;
the basic image sequence is a collection of a large number of basic images which are directly shot and acquired by the electronic endoscope in the clinical use process. However, considering that the evaluation operation based on the marker bit in the subsequent step needs to be adapted, a series of screening needs to be performed on the basic image sequence, so as to obtain a sample image sequence for highlighting the marker bit and being used in the subsequent processing process.
The image screening module 44 is configured to analyze the sample image sequence frame by frame, and select a target image sequence with a flag bit;
the obtained sample image sequence is sent to a server for frame-by-frame analysis so as to select a target image with a marker bit from the sample image sequence and further form a target image sequence.
Typically, a deep learning network model is used to determine whether a preset flag bit exists in an image. The depth model is obtained by selecting marked bit image data from a large number of actual operation videos, dividing the data into training data and test data after manual marking, using the training data for model training, and using a model with specificity and sensitivity meeting requirements on the test data for detecting the marked bit.
It is noted that the marker bit herein refers to image information of some positions that are necessarily present during the routine examination by the electronic endoscope, such as the stomach depression, the stomach body, the pyriform fos, the epiglottis wall, and the like. Whether the image information at the positions is clear and complete is used as a reference for judging the inspection quality of the electronic endoscope, and whether the detection omission and the like occur in the inspection process or not can be accurately judged.
The image calculation module 46 is configured to compare the similarity between the target image sequence and a preset flag bit image sequence, and obtain a flag bit image serving as a reference purpose from the preset flag bit image sequence based on a comparison result;
the preset marker bit image sequence represents image features which are necessarily acquired in a regular electronic endoscope detection flow, so that the marker bit image sequence can be used as a detection standard for judging whether the electronic endoscope detection flow is compliant, the target image sequence and the preset marker bit image sequence are subjected to similarity comparison, and the marker bit image which can most represent the current electronic endoscope operation condition is selected, so that the current electronic endoscope operation can be evaluated in the subsequent steps conveniently.
And the image evaluation module 48 is used for evaluating the accuracy of the basic image sequence according to the generation order of the zone bit images.
The evaluation is to calculate the evaluation value corresponding to the operation of acquiring the basic image sequence based on the position mark of the marker bit image in the preset marker bit image sequence according to the marker bit image extracted in the previous step, so that the normalization of the electronic endoscope operation can be evaluated more accurately.
According to the quality evaluation device for the electronic endoscope detection flow, after at least one basic image in the inspection task is acquired, whether the image has a marker bit is judged, the marker information obtained through recognition is searched and compared with the marker bit information in the base, the base is updated according to the comparison result, and finally the inspection task is evaluated based on the base and the recognition comparison result. By selecting the marker bit image which can most represent the current operation condition of the electronic endoscope, and calculating the evaluation value corresponding to the operation of acquiring the basic image sequence based on the position mark of the marker bit image in the preset marker bit image sequence, the normalization of the electronic endoscope operation can be evaluated more accurately, the accuracy of the electronic endoscope operation evaluation can be improved, and meanwhile, the evaluation requirement under more complex diagnosis and treatment environments can be met by adjusting the marker bit image.
The above-described respective modules in the quality evaluation device for an electronic endoscope detection flow may be implemented in whole or in part by software, hardware, and combinations thereof. The above modules may be embedded in hardware or may be independent of a processor in the computer device, or may be stored in software in a memory in the computer device, so that the processor may call and execute operations corresponding to the above modules.
In one embodiment, a computer device is provided, which may be a server, the internal structure of which may be as shown in fig. 5. The computer device includes a processor, a memory, and a network interface connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, computer programs, and a database. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The database of the computer device is used to store XX data. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program, when executed by a processor, implements a quality assessment method for an electronic endoscope inspection procedure.
It will be appreciated by those skilled in the art that the structure shown in fig. 5 is merely a block diagram of some of the structures associated with the present application and is not limiting of the computer device to which the present application may be applied, and that a particular computer device may include more or fewer components than shown, or may combine certain components, or have a different arrangement of components.
In one embodiment, a computer device is provided comprising a memory and a processor, the memory having stored therein a computer program, the processor when executing the computer program performing the steps of:
step S20, receiving a basic image sequence shot by an electronic endoscope, and screening the basic image sequence to obtain a sample image sequence for highlighting the zone bit;
step S40, analyzing the sample image sequence frame by frame, and selecting a target image sequence with a zone bit; step S60, performing similarity comparison on the target image sequence and a preset zone bit image sequence, and acquiring a zone bit image serving as a reference from the preset zone bit image sequence based on a comparison result;
and step S80, evaluating the accuracy of the basic image sequence according to the generation order of the zone bit images.
In one embodiment, a computer readable storage medium is provided having a computer program stored thereon, which when executed by a processor, performs the steps of:
step S20, receiving a basic image sequence shot by an electronic endoscope, and screening the basic image sequence to obtain a sample image sequence for highlighting the zone bit;
step S40, analyzing the sample image sequence frame by frame, and selecting a target image sequence with a zone bit; step S60, performing similarity comparison on the target image sequence and a preset zone bit image sequence, and acquiring a zone bit image serving as a reference from the preset zone bit image sequence based on a comparison result;
and step S80, evaluating the accuracy of the basic image sequence according to the generation order of the zone bit images.
In one embodiment, a computer program product is provided comprising a computer program which, when executed by a processor, performs the steps of:
step S20, receiving a basic image sequence shot by an electronic endoscope, and screening the basic image sequence to obtain a sample image sequence for highlighting the zone bit;
step S40, analyzing the sample image sequence frame by frame, and selecting a target image sequence with a zone bit; step S60, performing similarity comparison on the target image sequence and a preset zone bit image sequence, and acquiring a zone bit image serving as a reference from the preset zone bit image sequence based on a comparison result;
and step S80, evaluating the accuracy of the basic image sequence according to the generation order of the zone bit images.
It should be noted that, user information (including but not limited to user equipment information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, presented data, etc.) referred to in the present application are information and data authorized by the user or sufficiently authorized by each party.
Those skilled in the art will appreciate that implementing all or part of the above described methods may be accomplished by way of a computer program stored on a non-transitory computer readable storage medium, which when executed, may comprise the steps of the embodiments of the methods described above. Any reference to memory, database, or other medium used in the various embodiments provided herein may include at least one of non-volatile and volatile memory. The nonvolatile Memory may include Read-Only Memory (ROM), magnetic tape, floppy disk, flash Memory, optical Memory, high density embedded nonvolatile Memory, resistive random access Memory (ReRAM), magnetic random access Memory (Magnetoresistive Random Access Memory, MRAM), ferroelectric Memory (Ferroelectric Random Access Memory, FRAM), phase change Memory (Phase Change Memory, PCM), graphene Memory, and the like. Volatile memory can include random access memory (Random Access Memory, RAM) or external cache memory, and the like. By way of illustration, and not limitation, RAM can be in the form of a variety of forms, such as static random access memory (Static Random Access Memory, SRAM) or dynamic random access memory (Dynamic Random Access Memory, DRAM), and the like. The databases referred to in the various embodiments provided herein may include at least one of relational databases and non-relational databases. The non-relational database may include, but is not limited to, a blockchain-based distributed database, and the like. The processors referred to in the embodiments provided herein may be general purpose processors, central processing units, graphics processors, digital signal processors, programmable logic units, quantum computing-based data processing logic units, etc., without being limited thereto.
The technical features of the above embodiments may be arbitrarily combined, and all possible combinations of the technical features in the above embodiments are not described for brevity of description, however, as long as there is no contradiction between the combinations of the technical features, they should be considered as the scope of the description.
The above examples only represent a few embodiments of the present application, which are described in more detail and are not to be construed as limiting the scope of the present application. It should be noted that it would be apparent to those skilled in the art that various modifications and improvements could be made without departing from the spirit of the present application, which would be within the scope of the present application. Accordingly, the scope of protection of the present application shall be subject to the appended claims.
Claims (10)
1. A quality assessment method for an electronic endoscope detection procedure, the quality assessment method comprising:
receiving a basic image sequence shot by an electronic endoscope, and screening the basic image sequence to obtain a sample image sequence for highlighting a marker bit;
analyzing the sample image sequence frame by frame, and selecting a target image sequence with a marker bit;
performing similarity comparison on the target image sequence and a preset zone bit image sequence, and acquiring a zone bit image serving as a reference from the preset zone bit image sequence based on a comparison result;
and evaluating the accuracy of the basic image sequence according to the generation sequence of the zone bit images.
2. The method for evaluating the quality of an electronic endoscope inspection procedure according to claim 1, wherein the receiving a basic image sequence captured by an electronic endoscope, and screening the basic image sequence to obtain a sample image sequence for highlighting a marker bit, comprises:
receiving a basic image sequence shot by an electronic endoscope, and extracting a basic image from the basic image sequence;
sequentially calculating the image variation of two adjacent frames of basic images;
screening the basic image according to the numerical relation between the image variation and a preset threshold value, and constructing a sample image array for highlighting the marker bit based on the screened basic image.
3. The quality evaluation method for an electronic endoscope inspection process according to claim 2, wherein the sequentially calculating the image variation amounts of the adjacent two frames of the basic images includes:
respectively calculating variances of the basic images of two adjacent frames; or (b)
And respectively calculating pixel values of the adjacent two frames of basic images.
4. The quality evaluation method for an electronic endoscope detection procedure according to claim 2, wherein the screening the base image according to the numerical relation between the image variation and a preset threshold value, and constructing a sample image array for highlighting a flag bit based on the screened base image, comprises:
if the image variation is larger than a preset threshold, deleting the previous frame in the time dimension in the two adjacent frames of basic images;
and constructing a sample image sequence for highlighting the zone bit based on the rest of the basic images.
5. The quality evaluation method for an electronic endoscope detection procedure according to claim 1, wherein the performing similarity comparison between the target image sequence and a preset flag bit image sequence, and acquiring a flag bit image for reference use from the preset flag bit image sequence based on a comparison result, comprises:
sequentially selecting each frame of target image from the target image sequence, and executing a preset similarity detection flow to obtain a reference marker bit image corresponding to each frame of target image;
the similarity detection flow is as follows:
calculating the similarity of a current frame target image and each frame of marker bit image in a preset marker bit image sequence, and obtaining a plurality of similarity results corresponding to the current frame target image;
and selecting a zone bit image corresponding to the maximum similarity from the multiple similarity results as a reference zone bit image of the current frame target image, and deleting the reference zone bit image from the preset zone bit image sequence.
6. The method for quality assessment of an electronic endoscope inspection procedure according to claim 5, wherein updating the preset marker bit image sequence comprises:
deleting a first zone bit image from the preset zone bit image sequence.
7. The quality assessment method for an electronic endoscope detection procedure according to claim 1, wherein the assessing the accuracy of the base image sequence according to the generation order of the marker bit images comprises:
establishing a calculation function based on the generating sequence of the mark bit images;
and generating an evaluation result corresponding to the basic image sequence according to the calculation result of the calculation function.
8. A quality assessment device for an electronic endoscope detection procedure, the quality assessment device comprising:
the image processing module is used for receiving a basic image sequence shot by the electronic endoscope, screening the basic image sequence and obtaining a sample image sequence for highlighting the marker bit;
the image screening module is used for analyzing the sample image sequence frame by frame and selecting a target image sequence with a zone bit;
the image calculation module is used for comparing the similarity between the target image sequence and a preset marker bit image sequence, and acquiring a marker bit image serving as a reference purpose from the preset marker bit image sequence based on a comparison result;
and the image evaluation module is used for evaluating the accuracy of the basic image sequence according to the generation order of the zone bit images.
9. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor implements the steps of the method of any of claims 1 to 7 when the computer program is executed.
10. A computer readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, implements the steps of the method of any of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211683331.0A CN116402739A (en) | 2022-12-27 | 2022-12-27 | Quality evaluation method and device for electronic endoscope detection flow |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211683331.0A CN116402739A (en) | 2022-12-27 | 2022-12-27 | Quality evaluation method and device for electronic endoscope detection flow |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116402739A true CN116402739A (en) | 2023-07-07 |
Family
ID=87012915
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211683331.0A Pending CN116402739A (en) | 2022-12-27 | 2022-12-27 | Quality evaluation method and device for electronic endoscope detection flow |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116402739A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116664563A (en) * | 2023-07-27 | 2023-08-29 | 浙江杜比医疗科技有限公司 | New adjuvant chemotherapy curative effect evaluation system, equipment and medium |
| CN117095450A (en) * | 2023-10-20 | 2023-11-21 | 武汉大学人民医院（湖北省人民医院） | Eye dryness evaluation system based on images |
-
2022
- 2022-12-27 CN CN202211683331.0A patent/CN116402739A/en active Pending
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116664563A (en) * | 2023-07-27 | 2023-08-29 | 浙江杜比医疗科技有限公司 | New adjuvant chemotherapy curative effect evaluation system, equipment and medium |
| CN116664563B (en) * | 2023-07-27 | 2023-11-24 | 浙江杜比医疗科技有限公司 | New adjuvant chemotherapy curative effect evaluation system, equipment and medium |
| CN117095450A (en) * | 2023-10-20 | 2023-11-21 | 武汉大学人民医院（湖北省人民医院） | Eye dryness evaluation system based on images |
| CN117095450B (en) * | 2023-10-20 | 2024-01-09 | 武汉大学人民医院（湖北省人民医院） | Eye dryness evaluation system based on images |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110598765B (en) | Sample generation method, device, computer equipment and storage medium | |
| CN116402739A (en) | Quality evaluation method and device for electronic endoscope detection flow | |
| CN111524137B (en) | Cell identification counting method and device based on image identification and computer equipment | |
| TWI660277B (en) | Information processing device and information processing method | |
| CN109903282B (en) | Cell counting method, system, device and storage medium | |
| CN110335248B (en) | Medical image focus detection method, device, computer equipment and storage medium | |
| JP2021530773A (en) | Image-based relationship analysis methods and their systems | |
| EP2793164A1 (en) | Method and system for determining a phenotype of a neoplasm in a human or animal body | |
| CN106295710B (en) | Image local feature matching process, device and terminal based on non-geometric constraint | |
| EP4287190A2 (en) | Method and apparatus for machine learning based identification of structural variants in cancer genomes | |
| CN114169460A (en) | Sample screening method, sample screening device, computer equipment and storage medium | |
| CN114708264B (en) | Light spot quality judging method, device, equipment and storage medium | |
| CN116007504A (en) | Crack detection module, device and computer equipment based on image technology | |
| CN113673318B (en) | Motion detection method, motion detection device, computer equipment and storage medium | |
| CN115526855A (en) | Method and device for detecting subfissure defect of battery piece, computer equipment and storage medium | |
| CN112863602B (en) | Chromosome abnormality detection method, chromosome abnormality detection device, chromosome abnormality detection computer device, and chromosome abnormality detection storage medium | |
| CN112802012A (en) | Pathological image detection method, pathological image detection device, computer equipment and storage medium | |
| US20220334205A1 (en) | Detection of Bio-Markers in Functional MRI Scans | |
| WO2022229671A1 (en) | Detection of bio-markers in functional mri scans | |
| Mencattini et al. | Uncertainty-based feature selection for improved adequacy of dermoscopic image classification | |
| CN110728615B (en) | Steganalysis method based on sequential hypothesis testing, terminal device and storage medium | |
| CN111553418B (en) | Method and device for detecting neuron reconstruction errors and computer equipment | |
| CN117240521A (en) | Abnormal data detection method, device, computer equipment and storage medium | |
| CN116824692A (en) | Human behavior recognition method, device, computer equipment and storage medium | |
| CN114943874A (en) | Data dividing method and device, computer equipment and storage medium |
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 |