CN115861299A - Electronic endoscope quality control method and device based on two-dimensional reconstruction - Google Patents
Electronic endoscope quality control method and device based on two-dimensional reconstruction Download PDFInfo
- Publication number
- CN115861299A CN115861299A CN202310114159.5A CN202310114159A CN115861299A CN 115861299 A CN115861299 A CN 115861299A CN 202310114159 A CN202310114159 A CN 202310114159A CN 115861299 A CN115861299 A CN 115861299A
- Authority
- CN
- China
- Prior art keywords
- image
- splicing
- library
- spliced
- reconstructed
- 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
- 238000003908 quality control method Methods 0.000 title claims abstract description 33
- 238000000034 method Methods 0.000 claims abstract description 67
- 230000008569 process Effects 0.000 claims abstract description 49
- 238000004364 calculation method Methods 0.000 claims description 24
- 238000011156 evaluation Methods 0.000 claims description 19
- 238000004590 computer program Methods 0.000 claims description 18
- 239000003550 marker Substances 0.000 claims description 15
- 239000011159 matrix material Substances 0.000 claims description 9
- 238000007781 pre-processing Methods 0.000 claims description 5
- 238000007689 inspection Methods 0.000 abstract description 7
- 238000012544 monitoring process Methods 0.000 abstract description 2
- 238000012545 processing Methods 0.000 description 9
- 238000012549 training Methods 0.000 description 7
- 238000001514 detection method Methods 0.000 description 6
- 238000010586 diagram Methods 0.000 description 5
- 230000005540 biological transmission Effects 0.000 description 4
- 238000012360 testing method Methods 0.000 description 4
- 210000000626 ureter Anatomy 0.000 description 4
- 238000004422 calculation algorithm Methods 0.000 description 3
- 238000001839 endoscopy Methods 0.000 description 3
- 230000006399 behavior Effects 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 210000000056 organ Anatomy 0.000 description 2
- 230000035945 sensitivity 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
- 108010001267 Protein Subunits Proteins 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 229910021389 graphene Inorganic materials 0.000 description 1
- 230000001788 irregular Effects 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000000717 retained effect Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000001356 surgical procedure Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
Landscapes
- Endoscopes (AREA)
Abstract
The application relates to an electronic endoscope quality control method and device based on two-dimensional reconstruction. The method comprises the following steps: detecting key zone bits of original images shot by an electronic endoscope, and combining the original images with the key zone bits to obtain a reconstructed image library; selecting a splicing initial image and a first target image from a reconstructed image library, and carrying out image splicing on the initial image and the first target image to obtain a first spliced image; continuously selecting a second target image from the reconstructed image library and continuously performing image splicing with the first spliced image to obtain a second spliced image, and updating the reconstructed image library; and repeatedly executing the operation of obtaining the second spliced image to obtain a spliced two-dimensional reconstructed image, and comparing and evaluating the two-dimensional reconstructed image and a preset standard image. By adopting the method, the retrospective efficiency of the inspection result can be improved, the inspection flow is standardized, and the standardized monitoring of the quality of the shooting process of the endoscope is realized.
Description
Technical Field
The application relates to the technical field of video image processing, in particular to a quality control method and device of an electronic endoscope based on two-dimensional reconstruction.
Background
Endoscopes, as a conventional medical device, play an important role in various types of surgery. For example, an electronic nasopharyngoscope is used to check whether a nasopharyngolaryngeal region is diseased, and an electronic cystoscope is used to determine whether a diseased region exists inside the bladder, etc. Because the internal structure of the human body is complex and the parts needing to be checked are more, a doctor needs to evaluate the checking result in real time according to experience in the checking process.
However, the problems of uneven doctor level, irregular operation, inaccurate evaluation and the like easily occur, so that the judgment of the quality of the endoscope examination process is different, and the subsequent diagnosis of a patient is influenced.
Disclosure of Invention
In view of the above, it is necessary to provide a method and an apparatus for quality control of an electronic endoscope based on two-dimensional reconstruction, which can monitor the quality of an endoscopic procedure in a standardized manner.
In a first aspect, the application provides an electronic endoscope quality control method based on two-dimensional reconstruction. The method comprises the following steps:
detecting key zone bits of original images shot by an electronic endoscope, and combining the original images with the key zone bits to obtain a reconstructed image library;
selecting a splicing initial image from the reconstructed image library, performing matching degree calculation on the splicing initial image, and selecting a first target image based on a calculation result to perform image splicing with the splicing initial image to obtain a first spliced image;
continuously selecting a second target image from the reconstructed image library and continuously performing image splicing with the first spliced image to obtain a second spliced image, and updating the reconstructed image library;
repeatedly executing the operation of obtaining the second spliced image until the number of the target images in the reconstructed image library is zero, and obtaining a spliced two-dimensional reconstructed image;
and comparing the two-dimensional reconstruction image with a preset standard image, and evaluating the shooting process of the electronic endoscope based on the comparison result.
In one embodiment, after performing key marker detection on the original images captured by the electronic endoscope and combining the original images with the key markers to obtain a reconstructed image library, the method further includes:
preprocessing the original image in the reconstructed image library, and extracting key points of the preprocessed image;
and matching the key points between the preprocessed images to obtain the matching degree between the preprocessed images.
In one embodiment, the selecting a stitching start image from the reconstructed image library, performing matching degree calculation on the stitching start image, and selecting a first target image based on a calculation result to perform image stitching with the stitching start image to obtain a first stitched image includes:
selecting an original image with a preset special zone bit from the reconstructed image library as a splicing initial image;
selecting the original image with the key marker bit from the reconstructed image library and calculating the matching degree of the original image and the splicing initial image;
and selecting the original image with the highest matching degree as a first target image, and splicing the first target image and the splicing starting image to obtain a first spliced image.
In one embodiment, the selecting, from the reconstructed image library, an original image with a preset special flag as a stitching start image includes:
selecting an original image with a preset special zone bit from the reconstructed image library;
and correcting the image with the preset special zone bit to obtain a splicing initial image.
In one embodiment, the continuously selecting a second target image from the reconstructed image library and continuously performing image stitching with the first stitched image to obtain a second stitched image, and performing an update operation on the reconstructed image library includes:
selecting an image with the highest matching degree with the first spliced image from the reconstructed image library as a second target image;
splicing the second target image with the first spliced image to obtain a second spliced image;
deleting the second target image from the reconstructed image library.
In one embodiment, the stitching the second target image and the first stitched image to obtain a second stitched image includes:
selecting target feature points in the second target image and the first spliced image, and calculating a target homography matrix for splicing based on the target feature points;
and splicing the second target image and the first spliced image based on the target homography matrix to obtain a second spliced image.
In one embodiment, the comparing the two-dimensional reconstructed image with a preset standard image and evaluating a shooting process of the electronic endoscope based on a comparison result includes:
comparing the area of the two-dimensional reconstructed image with a preset standard image to obtain a first evaluation weight;
comparing the number of the key zone bits of the two-dimensional reconstructed image and the number of the key zone bits of the standard image to obtain a second evaluation weight;
and evaluating the shooting process of the electronic endoscope based on the first evaluation weight and the second evaluation weight.
In a second aspect, the present application also provides an electronic endoscope quality control device based on two-dimensional reconstruction, the device comprising:
the reconstructed image library module is used for detecting key zone bits of original images shot by the electronic endoscope and combining the original images with the key zone bits to obtain a reconstructed image library;
the first splicing module is used for selecting a splicing initial image from the reconstructed image library, calculating the matching degree of the splicing initial image, and selecting a first target image based on the calculation result to be subjected to image splicing with the splicing initial image to obtain a first spliced image;
the second splicing module is used for continuously selecting a second target image from the reconstructed image library and carrying out image splicing with the first spliced image to obtain a second spliced image, and updating the reconstructed image library;
the third splicing module is used for repeatedly executing the operation of obtaining the second spliced image until the number of the target images in the reconstructed image library is zero, so as to obtain a spliced two-dimensional reconstructed image;
and the evaluation module is used for comparing the two-dimensional reconstruction image with a preset standard image and evaluating the shooting process of the electronic endoscope based on the comparison result.
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 implementing the following steps when executing the computer program:
detecting key zone bits of original images shot by an electronic endoscope, and combining the original images with the key zone bits to obtain a reconstructed image library;
selecting a splicing initial image from the reconstructed image library, performing matching degree calculation on the splicing initial image, and selecting a first target image based on a calculation result to perform image splicing with the splicing initial image to obtain a first spliced image;
continuously selecting a second target image from the reconstructed image library and continuously performing image splicing with the first spliced image to obtain a second spliced image, and updating the reconstructed image library;
repeatedly executing the operation of obtaining the second spliced image until the number of the target images in the reconstructed image library is zero, and obtaining a spliced two-dimensional reconstructed image;
and comparing the two-dimensional reconstruction image with a preset standard image, and evaluating the shooting process of the electronic endoscope based on the comparison result.
In a fourth aspect, the present application further 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:
detecting key zone bits of original images shot by an electronic endoscope, and combining the original images with the key zone bits to obtain a reconstructed image library;
selecting a splicing initial image from the reconstructed image library, performing matching degree calculation on the splicing initial image, and selecting a first target image based on a calculation result to perform image splicing with the splicing initial image to obtain a first spliced image;
continuously selecting a second target image from the reconstructed image library and continuously performing image splicing with the first spliced image to obtain a second spliced image, and updating the reconstructed image library;
repeatedly executing the operation of obtaining the second spliced image until the number of the target images in the reconstructed image library is zero, and obtaining a spliced two-dimensional reconstructed image;
and comparing the two-dimensional reconstruction image with a preset standard image, and evaluating the shooting process of the electronic endoscope based on the comparison result.
According to the quality control method and device of the electronic endoscope based on the two-dimensional reconstruction, invalid pictures shot in the checking process are filtered through identification of the key zone, the reconstructed image library is obtained through combination of the original images with the key zone and serves as a data source of the subsequent two-dimensional unfolding reconstruction, the burden of data processing in the two-dimensional unfolding reconstruction is reduced, in the two-dimensional unfolding reconstruction process, the splicing initial image is determined firstly, the target image is determined according to the matching degree of the original images, the original images in the reconstructed image library are spliced one by one, so that the accurate two-dimensional reconstructed image is obtained, the checking result is convenient to trace back, the two-dimensional reconstructed image is compared with the preset standard image and evaluated, the standardized monitoring on the quality of the shooting process of the endoscope is completed, and the problem that a doctor judges the quality of the endoscope checking process according to subjective judgment has deviation is avoided.
Drawings
The accompanying drawings, which are included to provide a further understanding of the application and are incorporated in and constitute a part of this application, illustrate embodiment(s) of the application and together with the description serve to explain the application and not to limit the application. In the drawings:
FIG. 1 is a diagram of an application environment of an electronic endoscope quality control method based on two-dimensional reconstruction in one embodiment;
FIG. 2 is a schematic flow chart of an electronic endoscope quality control method based on two-dimensional reconstruction in one embodiment;
FIG. 3 is a schematic flow chart of a method for controlling the quality of an electronic endoscope based on two-dimensional reconstruction in a preferred embodiment;
FIG. 4a is a first original image taken by the electronic endoscope in a preferred embodiment;
FIG. 4b is a second original image taken by an electronic endoscope comprising a wire frame in a preferred embodiment;
FIG. 4c is a three-dimensional raw image taken by an electronic endoscope comprising a wire frame in a preferred embodiment;
FIG. 4d is a fourth original image taken by an electronic endoscope comprising a wire frame in a preferred embodiment;
FIG. 4e is a two-dimensional reconstructed image after stitching in a preferred embodiment;
FIG. 5 is a block diagram of an electronic endoscope quality control device based on two-dimensional reconstruction in one embodiment;
FIG. 6 is a diagram illustrating an internal structure of a computer device according to an embodiment.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application. All other embodiments obtained by a person of ordinary skill in the art based on the embodiments provided in the present application without any inventive step are within the scope of protection of the present application.
It is obvious that the drawings in the following description are only examples or embodiments of the present application, and that it is also possible for a person skilled in the art to apply the present application to other similar contexts on the basis of these drawings without inventive effort. Moreover, it should be appreciated that in the development of any such actual implementation, as in any engineering or design project, numerous implementation-specific decisions must be made to achieve the developers' specific goals, such as compliance with system-related and business-related constraints, which may vary from one implementation to another.
Reference in the specification to "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment can be included in at least one embodiment of the specification. The appearances of the phrase in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments. Those of ordinary skill in the art will explicitly and implicitly appreciate that the embodiments described herein may be combined with other embodiments without conflict.
Unless defined otherwise, technical or scientific terms referred to herein shall have the ordinary meaning as understood by those of ordinary skill in the art to which this application belongs. Reference to "a," "an," "the," and similar words throughout this application are not to be construed as limiting in number, and may refer to the singular or the plural. The present application is directed to the use of the terms "including," "comprising," "having," and any variations thereof, which are intended to cover non-exclusive inclusions; for example, a process, method, system, article, or apparatus that comprises a list of steps or modules (elements) is not limited to the listed steps or elements, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus. Reference to "connected," "coupled," and the like in this application is not intended to be limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. The term "plurality" as referred to herein means two or more. "and/or" describes an association relationship of associated objects, meaning that three relationships may exist, for example, "A and/or B" may mean: a exists alone, A and B exist simultaneously, and B exists alone. The character "/" generally indicates that the former and latter associated objects are in an "or" relationship. Reference herein to the terms "first," "second," "third," and the like, are merely to distinguish similar objects and do not denote a particular ordering for the objects.
The method embodiments provided in the present embodiment may be executed in a terminal, a computer, or a similar computing device. For example, the method is executed on a terminal, and fig. 1 is a hardware configuration block diagram of the terminal of the quality control method of the electronic endoscope based on two-dimensional reconstruction according to the embodiment. As shown in fig. 1, the terminal may include one or more processors 102 (only one shown in fig. 1) and a memory 104 for storing data, wherein the processor 102 may include, but is not limited to, a processing device such as a microprocessor MCU or a programmable logic device FPGA. The terminal may also include a transmission device 106 for communication functions and an input-output device 108. It will be understood by those of ordinary skill in the art that the structure shown in fig. 1 is merely an illustration and is not intended to limit the structure of the terminal described above. For example, the terminal may also include more or fewer components than shown in FIG. 1, or have a different configuration than shown in FIG. 1.
The memory 104 can be used for storing computer programs, for example, software programs and modules of application software, such as a computer program corresponding to the quality control method of the electronic endoscope based on two-dimensional reconstruction in the present embodiment, and the processor 102 executes various functional applications and data processing by running the computer programs stored in the memory 104, so as to implement the method. The memory 104 may include high speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 104 may further include memory located remotely from the processor 102, which may be connected to the terminal over a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
The transmission device 106 is used to receive or transmit data via a network. The network described above includes a wireless network provided by a communication provider of the terminal. In one example, the transmission device 106 includes a Network adapter (NIC) that can be connected to other Network devices through a base station to communicate with the internet. In one example, the transmission device 106 may be a Radio Frequency (RF) module, which is used to communicate with the internet in a wireless manner.
In this embodiment, a two-dimensional reconstruction-based electronic endoscope quality control method is provided, and fig. 2 is a flowchart of the two-dimensional reconstruction-based electronic endoscope quality control method of this embodiment, as shown in fig. 2, the flowchart includes the following steps:
and step S210, performing key zone bit detection on the original images shot by the electronic endoscope, and combining the original images with the key zone bits to obtain a reconstructed image library.
And obtaining an original image from a video picture shot by the electronic endoscope in a frame-by-frame or frame skipping mode, sending the original image to a back-end server, and judging whether a key marker bit exists in the original image by using a depth model. The depth model obtaining process comprises the steps of selecting image data with key mark bits from a large number of actual operation videos, manually marking the image data with the key mark bits, dividing the data into training data and testing data, wherein the training data is used for model training, and the testing data is used for judging whether the specificity and the sensitivity of the trained depth model reach the standard or not. If the key flag is identified from the original image by the depth model, the original image is placed into a reconstructed image library for subsequent analysis. In addition, the image storage interface is opened for a doctor who performs examination, and the doctor can decide whether to store the current frame in the reconstructed image library or not. In consideration of unpredictability of doctor behaviors in the checking process, prior information of an image shooting sequence is not introduced, and subsequent registration quality can be well improved.
And S220, selecting a splicing initial image from the reconstructed image library, calculating the matching degree of the splicing initial image, selecting a first target image based on the calculation result, and performing image splicing on the first target image and the splicing initial image to obtain a first spliced image.
The initial image is an original image with a preset special marker bit, and the preset special marker bit represents a certain part or a local area of the organ to be checked. Selecting an original image from a reconstructed image library and carrying out matching degree calculation on the original image and a splicing initial image; and selecting the original image with the highest matching degree as a first target image, and splicing the first target image and the splicing starting image to obtain a first spliced image.
And step S230, continuously selecting a second target image from the reconstructed image library to be subjected to image splicing with the first spliced image to obtain a second spliced image, and updating the reconstructed image library.
Wherein, the reconstructed image library can be used as a target image except for the splicing initial image. And selecting an image with the highest matching degree with the first spliced image from the reconstructed image library as a second target image, splicing the second target image with the first spliced image to obtain a second spliced image, and deleting the target image from the reconstructed image library. The stitching start image is no longer used as the target image after being used, and the stitching start image may be deleted from the reconstructed image library.
And S240, repeatedly executing the operation of obtaining the second spliced image until the number of the images to be spliced in the reconstructed image library is zero, and obtaining the spliced two-dimensional reconstructed image.
And repeatedly executing the step S230 on the basis of finishing the second splicing, sequentially splicing the target images in the reconstructed image library, and finishing the splicing operation of the two-dimensional reconstructed images after the images in the reconstructed image library are all used. The two-dimensional reconstruction image can be output to the display equipment, so that the examination result of the electronic endoscope is comprehensively concentrated on one two-dimensional image, and the examination result can be conveniently displayed and traced back by a doctor in the later stage.
And step S250, comparing the two-dimensional reconstruction image with a preset standard image, and evaluating the shooting process of the electronic endoscope based on the comparison result.
The area size and the number of key marker bits of the two-dimensional reconstructed image and the preset standard image are compared, and the closer the area size and the number of the key marker bits of the two-dimensional reconstructed image and the preset standard image are, the higher the score of the completeness of the endoscope in the shooting process is. And evaluating the standard degree of the shooting process of the electronic endoscope according to the score of the completeness of the shooting process of the endoscope, and improving the quality of endoscopy.
According to the quality control method of the electronic endoscope based on the two-dimensional reconstruction, invalid pictures shot in the inspection process are identified and filtered through the key zone bits, the reconstructed image library is obtained through combining the original images with the key zone bits and serves as a data source of the subsequent two-dimensional unfolding reconstruction, the burden of data processing during the two-dimensional unfolding reconstruction is reduced, the splicing initial images are firstly determined in the two-dimensional unfolding reconstruction process, the target images are determined according to the matching degree between the original images, the original images in the reconstructed image library are spliced one by one, accurate two-dimensional reconstructed images are obtained, the two-dimensional reconstructed images are compared with the preset standard images and evaluated, the quality of the endoscope shooting process is monitored, and the problem that a doctor judges the quality of the endoscope inspection process according to subjective judgment to have deviation is avoided.
In one embodiment, based on the step S210, after performing key marker detection on the original images captured by the electronic endoscope and combining the original images with the key markers to obtain a reconstructed image library, the method further includes the following steps:
and step S260, preprocessing the original image in the reconstructed image library, and extracting key points of the preprocessed image.
Since step S210 is to detect all original images, and thus the images in the reconstruction library have a certain repetition rate, the images in the reconstruction library are preprocessed by the deduplication algorithm, and only a few pieces of similar original images with richer texture information are retained. Illustratively, the twin network is used to judge the similarity between images and calculate the texture degree of the images using canny texture. And for the preprocessed reconstructed image library, extracting key points of each original image by using a depth model or a traditional image processing algorithm.
And step S270, matching key points between the preprocessed images to obtain the matching degree between the preprocessed images.
The matching degree is calculated in the following mode, for each key point, features in a certain neighborhood range of the key point are extracted by using a pre-training model to obtain a feature vector, then the difference degree between the feature vectors is measured by using Euclidean distance or cosine similarity, the average value of the similarity degree between all the key points is used as the matching degree value between the two images, and a greedy algorithm can be introduced to reduce most of calculated amount.
In an embodiment, based on the step S220, selecting a splicing start image from the reconstructed image library, performing matching degree calculation on the splicing start image, and selecting a first target image and the splicing start image based on the calculation result to perform image splicing to obtain a first spliced image, which may specifically include the following steps:
step S221, selecting the original image with the preset special flag bit from the reconstructed image library as the stitching starting image.
In an embodiment, the step S221 specifically includes the following steps:
step S2211, selecting an original image with a preset special flag bit from the reconstructed image library.
Illustratively, a neural network model is used for detecting a preset special marker bit in an image reconstruction library, and an original image with the detected preset special marker bit is used as a first spliced image.
And step S2212, correcting the original image with the preset special zone bit to obtain a splicing initial image.
Exemplarily, the process comprises extracting key points of an original image with a preset special zone bit in an image reconstruction library, and extracting key points of a preset starting image with the preset special zone bit; and matching and calculating the key points of the two images to obtain a plurality of groups of corresponding key points, solving a rotation matrix based on the corresponding key points to obtain a rotation angle required by the original image, and rotating the rotation matrix to obtain a splicing start image for subsequent splicing operation.
The direction of the first image which is spliced is adaptively adjusted, and a reconstruction result which is closer to the use requirement can be obtained.
Step S222, selecting the original image with the key flag bit from the reconstructed image library, and performing matching calculation on the original image and the stitching start image.
And extracting key points of the original image and the splicing initial image, calculating the similarity of the key points, and taking the average value of the similarity between the key points as the matching degree value between the two images.
And step S223, selecting the original image with the highest matching degree as a first target image, and splicing the first target image and the splicing starting image to obtain a first spliced image.
The technical solutions of the steps S221 to S223 are used as a first step of completing the stitching of the two-dimensional reconstructed image, and a stitching start image is obtained by matching from the reconstructed image library through a preset special flag bit, so that a stitching start point and a stitching direction are defined, and the efficiency of two-dimensional expansion reconstruction of the electronic endoscope image is improved.
In an embodiment, based on the step S230, a second target image is continuously selected from the reconstructed image library to be image-stitched with the first stitched image, so as to obtain a second stitched image, and the reconstructed image library is updated, which may specifically include the following steps:
and S231, selecting an image with the highest matching degree with the first spliced image from the reconstructed image library as a second target image.
The matching degree can be obtained according to the matching degree in steps S260-S270.
And step S232, splicing the second target image and the first spliced image to obtain a second spliced image.
In an embodiment, the step S232 specifically includes the following steps:
step S2321, selecting target feature points in the second target image and the first spliced image, and calculating a target homography matrix for splicing based on the target feature points.
And S2322, splicing the second target image and the first spliced image based on the target homography matrix to obtain a second spliced image.
And the images shot at different angles are converted to the same visual angle through the target homography matrix, so that image splicing is realized.
In step S233, the second target image is deleted from the reconstructed image library.
The above steps S231 to S233 are used to find a target image for stitching with the stitching start image, thereby completing the second step of stitching the two-dimensional reconstructed image. Subsequently, the two-dimensional reconstructed images are gradually and completely spliced through step S240.
In an embodiment, in the step S250, comparing the two-dimensional reconstructed image with a preset standard image, and evaluating a shooting process of the electronic endoscope based on a comparison result may specifically include the following steps:
and step S251, comparing the areas of the two-dimensional reconstructed image and a preset standard image to obtain a first evaluation weight. In general, the smaller the value of the area difference, the higher the first evaluation weight score for evaluating the integrity of the endoscope in the shooting process.
And step S252, comparing the number of the key zone bits of the two-dimensional reconstructed image and the number of the key zone bits of the standard image to obtain a second evaluation weight. The number of all key mark bits in the target image and the splicing starting image which form the two-dimensional reconstruction image is counted, and if the number counting result is closer to the number of the mark bits in the standard image, the score for evaluating the completeness of the shooting process of the endoscope is higher.
And step 253, evaluating the shooting process of the electronic endoscope based on the first evaluation weight and the second evaluation weight.
By the quality control method of the electronic endoscope based on the two-dimensional reconstruction, the efficiency of backtracking of the inspection result is improved through the two-dimensional reconstruction image and the evaluation of the two-dimensional reconstruction image, the inspection flow of the electronic endoscope is greatly standardized, and the inspection quality is improved.
The present embodiment is described and illustrated below by means of preferred embodiments.
Fig. 3 is a flowchart of the electronic endoscope quality control method based on two-dimensional reconstruction according to the preferred embodiment.
And step S310, detecting key zone bits of the original images shot by the electronic endoscope, and combining the original images with the key zone bits to obtain a reconstructed image library.
Step S320, preprocessing the original image in the reconstructed image library, and extracting key points of the preprocessed image; and matching the key points between the preprocessed images to obtain the matching degree between the preprocessed images.
Step S330, selecting an original image with a preset special zone bit from a reconstructed image library; correcting the image with the preset special mark bit to obtain a splicing initial image; and selecting an original image with the highest matching degree with the splicing start image from the reconstructed image library as a first target image, and splicing the first target image and the splicing start image to obtain a first spliced image.
Step S340, selecting an image with the highest matching degree with the first spliced image from the reconstructed image library as a second target image; splicing the second target image with the first spliced image to obtain a second spliced image; the second target image is deleted from the reconstructed image library.
And step S350, repeatedly executing the operation of obtaining the second spliced image until the number of the target images in the reconstructed image library is zero, and obtaining a spliced two-dimensional reconstructed image.
And S360, comparing the two-dimensional reconstructed image with a preset standard image, and evaluating the shooting process of the electronic endoscope based on the comparison result of the image area size and the number of the key zone bits.
Taking an electronic endoscopy for bladder as an example, fig. 4a to 4d are original images captured by an electronic endoscope. And detecting key mark bits of the acquired figures 4a to 4d, and identifying a figure 4b with a right ureter mark bit, a figure 4c with a left ureter mark bit and a figure 4d with a bubble top mark bit, wherein the key mark bits are respectively positioned in a wire frame of an original image shot by the corresponding electronic endoscope. And combining the images with the key zone bits to obtain a reconstructed image library. Preprocessing an original image in the reconstructed image library, and extracting key points of the preprocessed image; and matching the key points between the preprocessed images to obtain the matching degree between the preprocessed images. Selecting an original image with a preset special zone bit from a reconstructed image library; correcting the image with the preset special mark bit to obtain a splicing initial image; and selecting an original image with the highest matching degree with the splicing starting image from the reconstructed image library as a first target image, and splicing the first target image and the splicing starting image to obtain a first spliced image. Selecting an image with the highest matching degree with the first spliced image from a reconstructed image library as a second target image; splicing the second target image with the first spliced image to obtain a second spliced image; the second target image is deleted from the reconstructed image library. The operation of obtaining the second stitched image is repeatedly performed until the number of target images in the reconstructed image library is zero, so as to obtain the two-dimensional reconstructed image which is stitched as shown in fig. 4 e.
The invalid picture shot in the examination process as shown in figure 4a is filtered by identifying the key mark position, a reconstructed image library is obtained by combining the original images with the key mark position and is used as a data source of the subsequent two-dimensional expansion reconstruction, the load of data processing in the two-dimensional expansion reconstruction is reduced, in the two-dimensional expansion reconstruction process, the splicing initial images are firstly determined, then the target images are determined according to the matching degree between the original images, the one-to-one splicing of the initial images in the reconstructed image library is realized, so that the accurate two-dimensional reconstructed image is obtained, the two-dimensional reconstructed image comprises the right ureter mark position, the left ureter mark position and the top bubble mark position, the integrity of the bladder inner wall of the two-dimensional reconstructed image can be judged, and therefore, a doctor can conveniently obtain the complete conclusion of the electronic endoscope examination process aiming at the bladder.
It should be understood that, although the steps in the flowcharts related to the embodiments are shown in sequence as indicated by the arrows, the steps are not necessarily executed in sequence as indicated by the arrows. The steps are not performed in the exact order shown and described, and may be performed in other orders, unless explicitly stated otherwise. Moreover, at least a part of the steps in the flowcharts related to the above embodiments may include multiple steps or multiple stages, which are not necessarily performed at the same time, but may be performed at different times, and the order of performing the steps or stages is not necessarily sequential, but may be performed alternately or alternately with other steps or at least a part of the steps or stages in other steps.
Based on the same inventive concept, the present embodiment further provides an electronic endoscope quality control device 50 based on two-dimensional reconstruction, and the system is used to implement the foregoing embodiments and preferred embodiments, which have already been described and are not described again. The terms "module," "unit," "sub-unit," and the like as used below may implement a combination of software and/or hardware of predetermined functions. While the system described in the embodiments below is preferably implemented in software, implementations in hardware, or a combination of software and hardware are also possible and contemplated.
In one embodiment, as shown in fig. 5, there is provided an electronic endoscope quality control device 50 based on two-dimensional reconstruction, comprising: reconstructed image library module 51, first stitching module 52, second stitching module 53, third stitching module 54, evaluation module 55, wherein:
and the reconstructed image library module 51 is used for detecting key zone bits of the original images shot by the electronic endoscope and combining the original images with the key zone bits to obtain a reconstructed image library.
And obtaining an original image from a video picture shot by the electronic endoscope in a frame-by-frame or frame skipping mode, sending the original image to a back-end server, and judging whether a key zone bit exists in the original image by using a depth model. The depth model obtaining process comprises the steps of selecting image data with key zone bits from a large number of actual operation videos, manually marking the image data with the key zone bits, dividing the data into training data and testing data, wherein the training data is used for model training, and the testing data is used for judging whether the specificity and the sensitivity of the trained depth model reach the standard or not. If the key zone bit is identified from the original image by the depth model, the original image is placed into a reconstructed image library for subsequent analysis. In addition, the image storage interface is opened for the doctor who performs examination, and the doctor can decide whether to store the current frame in the reconstructed image library. In consideration of unpredictability of doctor behaviors in the checking process, prior information of an image shooting sequence is not introduced, and subsequent registration quality can be well improved.
And the first stitching module 52 is configured to select a stitching start image from the reconstructed image library, perform matching degree calculation on the stitching start image, select a first target image based on the calculation result, and perform image stitching with the stitching start image to obtain a first stitched image.
The initial image is an original image with a preset special marker bit, and the preset special marker bit represents a given part or a local area of the organ to be inspected. Selecting an original image from a reconstructed image library and carrying out matching degree calculation on the original image and a splicing initial image; and selecting the original image with the highest matching degree as a first target image, and splicing the first target image and the splicing starting image to obtain a first spliced image.
And the second stitching module 53 is configured to continue to select a second target image from the reconstructed image library and perform image stitching with the first stitched image to obtain a second stitched image, and perform an updating operation on the reconstructed image library.
Wherein, the reconstructed image library can be used as a target image except for the splicing initial image. And selecting an image with the highest matching degree with the first spliced image from the reconstructed image library as a second target image, splicing the second target image with the first spliced image to obtain a second spliced image, and deleting the target image from the reconstructed image library. The stitching start image is no longer used as the target image after being used, and the stitching start image may be deleted from the reconstructed image library.
And the third splicing module 54 is configured to repeatedly perform the operation of obtaining the second spliced image until the number of the target images in the reconstructed image library is zero, so as to obtain a spliced two-dimensional reconstructed image.
And repeatedly executing the step S230 on the basis of finishing the second splicing, sequentially splicing the target images in the reconstructed image library, and finishing the splicing operation of the two-dimensional reconstructed images after the images in the reconstructed image library are all used. The two-dimensional reconstruction image can be output to the display equipment, so that the examination result of the electronic endoscope is comprehensively concentrated on one two-dimensional image, and the examination result can be conveniently displayed and traced back by a doctor in the later stage.
And the evaluation module 55 is configured to compare the two-dimensional reconstructed image with a preset standard image, and evaluate a shooting process of the electronic endoscope based on a comparison result.
The area size and the number of key zone bits of the two-dimensional reconstructed image and the preset standard image are compared, and the closer the area size and the number of key zone bits of the two-dimensional reconstructed image and the preset standard image are, the higher the score of the integrity of the shooting process of the endoscope is. And evaluating the standard degree of the shooting process of the electronic endoscope according to the score of the completeness of the shooting process of the endoscope, and improving the quality of endoscopy.
The respective modules in the above-described electronic endoscope quality control apparatus 50 based on two-dimensional reconstruction may be wholly or partially implemented by software, hardware, and a combination thereof. The modules can be embedded in a hardware form or independent from a processor in the computer device, and can also be stored in a memory in the computer device in a software form, so that the processor can call and execute operations corresponding to the modules.
In one embodiment, a computer device is provided, which may be a server, and the internal structure thereof may be as shown in fig. 6. 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, a computer program, and a database. The internal memory provides an environment for the operation of an operating system and computer programs in the non-volatile storage medium. The database of the computer device is used for storing the data of the electronic endoscope quality control based on two-dimensional reconstruction. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program is executed by a processor to implement an electronic endoscope quality control method based on two-dimensional reconstruction.
Those skilled in the art will appreciate that the architecture shown in fig. 6 is merely a block diagram of some of the structures associated with the disclosed aspects and is not intended to limit the computing devices to which the disclosed aspects apply, as particular computing devices may include more or less components than those 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 a computer program stored therein, the processor implementing the following steps when executing the computer program:
and step S210, performing key zone bit detection on the original images shot by the electronic endoscope, and combining the original images with the key zone bits to obtain a reconstructed image library.
And S220, selecting a splicing initial image from the reconstructed image library, calculating the matching degree of the splicing initial image, selecting a first target image based on the calculation result, and performing image splicing on the first target image and the splicing initial image to obtain a first spliced image.
And step S230, continuously selecting a second target image from the reconstructed image library to be subjected to image splicing with the first spliced image to obtain a second spliced image, and updating the reconstructed image library.
And step S240, repeatedly executing the operation of obtaining the second spliced image until the number of the target images in the reconstructed image library is zero, and obtaining the spliced two-dimensional reconstructed image.
And step S250, comparing the two-dimensional reconstruction image with a preset standard image, and evaluating the shooting process of the electronic endoscope based on the comparison result.
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:
and step S210, performing key zone bit detection on the original images shot by the electronic endoscope, and combining the original images with the key zone bits to obtain a reconstructed image library.
And S220, selecting a splicing initial image from the reconstructed image library, calculating the matching degree of the splicing initial image, selecting a first target image based on the calculation result, and performing image splicing on the first target image and the splicing initial image to obtain a first spliced image.
And step S230, continuously selecting a second target image from the reconstructed image library to be subjected to image splicing with the first spliced image to obtain a second spliced image, and updating the reconstructed image library.
And step S240, repeatedly executing the operation of obtaining the second spliced image until the number of the target images in the reconstructed image library is zero, and obtaining a spliced two-dimensional reconstructed image.
And step S250, comparing the two-dimensional reconstruction image with a preset standard image, and evaluating the shooting process of the electronic endoscope based on the comparison result.
In one embodiment, a computer program product is provided, comprising a computer program which, when executed by a processor, performs the steps of:
and step S210, performing key zone bit detection on the original images shot by the electronic endoscope, and combining the original images with the key zone bits to obtain a reconstructed image library.
And S220, selecting a splicing initial image from the reconstructed image library, calculating the matching degree of the splicing initial image, selecting a first target image based on the calculation result, and performing image splicing on the first target image and the splicing initial image to obtain a first spliced image.
And step S230, continuously selecting a second target image from the reconstructed image library to be subjected to image splicing with the first spliced image to obtain a second spliced image, and updating the reconstructed image library.
And step S240, repeatedly executing the operation of obtaining the second spliced image until the number of the target images in the reconstructed image library is zero, and obtaining the spliced two-dimensional reconstructed image.
And step S250, comparing the two-dimensional reconstruction image with a preset standard image, and evaluating the shooting process of the electronic endoscope based on the comparison result.
It should be noted that, the user information (including but not limited to user device 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.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above may be implemented by hardware instructions of a computer program, which may be stored in a non-volatile computer-readable storage medium, and when executed, may include the processes of the embodiments of the methods described above. Any reference to memory, database, or other medium used in the 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 (MRAM), ferroelectric Random Access Memory (FRAM), phase Change Memory (PCM), graphene Memory, and the like. Volatile Memory can include Random Access Memory (RAM), external cache Memory, and the like. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM), among others. The databases referred to in various embodiments provided herein may include at least one of relational and non-relational databases. The non-relational database may include, but is not limited to, a block chain 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 devices, quantum computing based data processing logic devices, etc., without limitation.
All possible combinations of the technical features in the above embodiments may not be described for the sake of brevity, but should be considered as being within the scope of the present disclosure as long as there is no contradiction between the combinations of the technical features.
The above-mentioned embodiments only express several embodiments of the present application, and the description thereof is more specific and detailed, but not construed as limiting the scope of the present application. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, which falls within the scope of protection of the present application. Therefore, the protection scope of the present application shall be subject to the appended claims.
Claims (10)
1. An electronic endoscope quality control method based on two-dimensional reconstruction is characterized by comprising the following steps:
detecting key zone bits of original images shot by an electronic endoscope, and combining the original images with the key zone bits to obtain a reconstructed image library;
selecting a splicing initial image from the reconstruction image library, calculating the matching degree of the splicing initial image, selecting a first target image based on the calculation result, and performing image splicing on the first target image and the splicing initial image to obtain a first spliced image;
continuously selecting a second target image from the reconstructed image library and continuously performing image splicing with the first spliced image to obtain a second spliced image, and updating the reconstructed image library;
repeatedly executing the operation of obtaining the second spliced image until the number of the target images in the reconstructed image library is zero to obtain a spliced two-dimensional reconstructed image;
and comparing the two-dimensional reconstruction image with a preset standard image, and evaluating the shooting process of the electronic endoscope based on the comparison result.
2. The method for quality control of an electronic endoscope according to claim 1, wherein after detecting key marker bits in the original images captured by the electronic endoscope and combining the original images with the key marker bits to obtain a reconstructed image library, the method further comprises:
preprocessing the original image in the reconstructed image library, and extracting key points of the preprocessed image;
and matching the key points between the preprocessed images to obtain the matching degree between the preprocessed images.
3. The electronic endoscope quality control method based on two-dimensional reconstruction of claim 1, wherein the selecting a stitching start image from the reconstruction image library, performing matching degree calculation on the stitching start image, and selecting a first target image based on the calculation result to perform image stitching with the stitching start image to obtain a first stitched image comprises:
selecting an original image with a preset special zone bit from the reconstructed image library as a splicing initial image;
selecting the original image with the key marker bit from the reconstructed image library and calculating the matching degree of the original image and the splicing initial image;
and selecting the original image with the highest matching degree as a first target image, and splicing the first target image and the splicing starting image to obtain a first spliced image.
4. The quality control method of the electronic endoscope based on two-dimensional reconstruction as claimed in claim 3, wherein the selecting of the original image with the preset special flag bit from the reconstructed image library as the stitching starting image comprises:
selecting an original image with a preset special zone bit from the reconstructed image library;
and correcting the image with the preset special zone bit to obtain a splicing initial image.
5. The electronic endoscope quality control method based on two-dimensional reconstruction of claim 1, wherein the step of continuously selecting a second target image from the reconstructed image library and performing image stitching with the first stitched image to obtain a second stitched image, and performing an update operation on the reconstructed image library comprises:
selecting an image with the highest matching degree with the first spliced image from the reconstructed image library as a second target image;
splicing the second target image with the first spliced image to obtain a second spliced image;
deleting the second target image from the reconstructed image library.
6. The electronic endoscope quality control method based on two-dimensional reconstruction of claim 5, wherein the stitching the second target image and the first stitched image to obtain a second stitched image comprises:
selecting target feature points in the second target image and the first spliced image, and calculating a target homography matrix for splicing based on the target feature points;
and splicing the second target image and the first spliced image based on the target homography matrix to obtain a second spliced image.
7. The quality control method of the electronic endoscope based on the two-dimensional reconstruction as claimed in claim 1, wherein the comparing the two-dimensional reconstruction image with a preset standard image and evaluating the shooting process of the electronic endoscope based on the comparison result comprises:
comparing the area of the two-dimensional reconstructed image with a preset standard image to obtain a first evaluation weight;
comparing the number of the key zone bits of the two-dimensional reconstructed image and the number of the key zone bits of the standard image to obtain a second evaluation weight;
and evaluating the shooting process of the electronic endoscope based on the first evaluation weight and the second evaluation weight.
8. An electronic endoscope quality control device based on two-dimensional reconstruction, characterized in that the device comprises:
the reconstructed image library module is used for detecting key zone bits of original images shot by the electronic endoscope and combining the original images with the key zone bits to obtain a reconstructed image library;
the first splicing module is used for selecting a splicing initial image from the reconstructed image library, calculating the matching degree of the splicing initial image, and selecting a first target image based on the calculation result to be subjected to image splicing with the splicing initial image to obtain a first spliced image;
the second splicing module is used for continuously selecting a second target image from the reconstructed image library and carrying out image splicing with the first spliced image to obtain a second spliced image, and updating the reconstructed image library;
the third splicing module is used for repeatedly executing the operation of obtaining the second spliced image until the number of the target images in the reconstructed image library is zero, so as to obtain a spliced two-dimensional reconstructed image;
and the evaluation module is used for comparing the two-dimensional reconstruction image with a preset standard image and evaluating the shooting process of the electronic endoscope based on the comparison result.
9. A computer device comprising a memory and a processor, the memory storing a computer program, wherein the processor when executing the computer program implements the steps of the two-dimensional reconstruction based electronic endoscope quality control method according to any one of claims 1 to 7.
10. A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the steps of the method for quality control of an electronic endoscope based on a two-dimensional reconstruction according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310114159.5A CN115861299A (en) | 2023-02-15 | 2023-02-15 | Electronic endoscope quality control method and device based on two-dimensional reconstruction |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310114159.5A CN115861299A (en) | 2023-02-15 | 2023-02-15 | Electronic endoscope quality control method and device based on two-dimensional reconstruction |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115861299A true CN115861299A (en) | 2023-03-28 |
Family
ID=85658046
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310114159.5A Pending CN115861299A (en) | 2023-02-15 | 2023-02-15 | Electronic endoscope quality control method and device based on two-dimensional reconstruction |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115861299A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116473673A (en) * | 2023-06-20 | 2023-07-25 | 浙江华诺康科技有限公司 | Path planning method, device, system and storage medium for endoscope |
| CN117974440A (en) * | 2024-04-01 | 2024-05-03 | 四川省肿瘤医院 | Method and system for stitching endoscope images |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109907720A (en) * | 2019-04-12 | 2019-06-21 | 重庆金山医疗器械有限公司 | Video image dendoscope auxiliary examination method and video image dendoscope control system |
| CN113763298A (en) * | 2021-07-29 | 2021-12-07 | 浙江华诺康科技有限公司 | Endoscope image processing method, endoscope image processing device, endoscope, and storage medium |
| CN113989125A (en) * | 2021-12-27 | 2022-01-28 | 武汉楚精灵医疗科技有限公司 | Method and device for splicing endoscope images, computer equipment and storage medium |
| CN114581402A (en) * | 2022-03-03 | 2022-06-03 | 深圳市资福医疗技术有限公司 | Capsule endoscope quality inspection method, device and storage medium |
| CN115018839A (en) * | 2022-08-08 | 2022-09-06 | 浙江华诺康科技有限公司 | Image recognition method and device for medical examination and electronic device |
-
2023
- 2023-02-15 CN CN202310114159.5A patent/CN115861299A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109907720A (en) * | 2019-04-12 | 2019-06-21 | 重庆金山医疗器械有限公司 | Video image dendoscope auxiliary examination method and video image dendoscope control system |
| CN113763298A (en) * | 2021-07-29 | 2021-12-07 | 浙江华诺康科技有限公司 | Endoscope image processing method, endoscope image processing device, endoscope, and storage medium |
| CN113989125A (en) * | 2021-12-27 | 2022-01-28 | 武汉楚精灵医疗科技有限公司 | Method and device for splicing endoscope images, computer equipment and storage medium |
| CN114581402A (en) * | 2022-03-03 | 2022-06-03 | 深圳市资福医疗技术有限公司 | Capsule endoscope quality inspection method, device and storage medium |
| CN115018839A (en) * | 2022-08-08 | 2022-09-06 | 浙江华诺康科技有限公司 | Image recognition method and device for medical examination and electronic device |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116473673A (en) * | 2023-06-20 | 2023-07-25 | 浙江华诺康科技有限公司 | Path planning method, device, system and storage medium for endoscope |
| CN116473673B (en) * | 2023-06-20 | 2024-02-27 | 浙江华诺康科技有限公司 | Path planning method, device, system and storage medium for endoscope |
| CN117974440A (en) * | 2024-04-01 | 2024-05-03 | 四川省肿瘤医院 | Method and system for stitching endoscope images |
| CN117974440B (en) * | 2024-04-01 | 2024-06-07 | 四川省肿瘤医院 | Method and system for stitching endoscope images |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111340819B (en) | Image segmentation method, device and storage medium | |
| CN115861299A (en) | Electronic endoscope quality control method and device based on two-dimensional reconstruction | |
| KR102075293B1 (en) | Apparatus for predicting metadata of medical image and method thereof | |
| CN111292839B (en) | Image processing method, image processing device, computer equipment and storage medium | |
| CN101909510B (en) | Image processing device and image processing program | |
| US20150221116A1 (en) | Method of Overlap-Dependent Image Stitching for Images Captured Using a Capsule Camera | |
| EP3876192A1 (en) | Image recognition method and device, terminal apparatus, and medical system | |
| US20220296081A1 (en) | Method for real-time detection of objects, structures or patterns in a video, an associated system and an associated computer readable medium | |
| EP3998579B1 (en) | Medical image processing method, apparatus and device, medium and endoscope | |
| CN116091432A (en) | Quality control method and device for medical endoscopy and computer equipment | |
| JP2020010805A (en) | Specification device, program, specification method, information processing device, and specifier | |
| CN109328028A (en) | Image for capturing in selective body is with the system and method for display | |
| JP2017522072A (en) | Image reconstruction from in vivo multi-camera capsules with confidence matching | |
| WO2021250951A1 (en) | Program, information processing method, and information processing device | |
| WO2024012080A1 (en) | Endoscope auxiliary examination system, method, apparatus, and storage medium | |
| CN114554934A (en) | Program, information processing method, information processing apparatus, and diagnosis support system | |
| CN111091539B (en) | Network model training and medical image processing methods, devices, mediums and equipment | |
| CN114445406B (en) | Enteroscopy image analysis method and device and medical image processing equipment | |
| CN114332132A (en) | Image segmentation method and device and computer equipment | |
| CN115861298B (en) | Image processing method and device based on endoscopic visualization | |
| KR20230118054A (en) | Method and system for predicting biomarker expression in medical image | |
| CN116563118A (en) | Endoscopic image stitching method and device and computer equipment | |
| CN113706536B (en) | Sliding mirror risk early warning method and device and computer readable storage medium | |
| WO2022120869A1 (en) | Orientation identification method and device for intracerebral fragment electrode in craniocerebral medical image | |
| CN116205929A (en) | Ultrasonic fusion imaging method and device 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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20230328 |