CN115797617A - Parathyroid gland identification method and intelligent endoscope camera system device - Google Patents
Parathyroid gland identification method and intelligent endoscope camera system device Download PDFInfo
- Publication number
- CN115797617A CN115797617A CN202211548101.3A CN202211548101A CN115797617A CN 115797617 A CN115797617 A CN 115797617A CN 202211548101 A CN202211548101 A CN 202211548101A CN 115797617 A CN115797617 A CN 115797617A
- Authority
- CN
- China
- Prior art keywords
- parathyroid gland
- image
- visible light
- images
- parathyroid
- 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
- 210000002990 parathyroid gland Anatomy 0.000 title claims abstract description 190
- 238000000034 method Methods 0.000 title claims abstract description 41
- 238000001514 detection method Methods 0.000 claims abstract description 7
- 238000007781 pre-processing Methods 0.000 claims description 5
- 238000004364 calculation method Methods 0.000 claims description 2
- 230000002708 enhancing effect Effects 0.000 claims description 2
- 238000002372 labelling Methods 0.000 claims description 2
- 238000005520 cutting process Methods 0.000 abstract description 7
- 230000006378 damage Effects 0.000 abstract description 6
- 208000027418 Wounds and injury Diseases 0.000 abstract description 5
- 208000014674 injury Diseases 0.000 abstract description 5
- 230000004927 fusion Effects 0.000 description 6
- 238000001356 surgical procedure Methods 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 210000001685 thyroid gland Anatomy 0.000 description 3
- 238000013528 artificial neural network Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000009826 distribution Methods 0.000 description 2
- 238000003860 storage Methods 0.000 description 2
- 210000003484 anatomy Anatomy 0.000 description 1
- 239000003814 drug Substances 0.000 description 1
- 238000003708 edge detection Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000000877 morphologic effect Effects 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 230000000849 parathyroid Effects 0.000 description 1
Images
Landscapes
- Endoscopes (AREA)
Abstract
The invention discloses a parathyroid gland identification method and an intelligent endoscope camera system device, the parathyroid gland identification method comprises the steps of collecting images in a cavity through an intelligent endoscope camera system, entering a parathyroid gland intelligent detection module to carry out target identification according to collected visible light images and near infrared images under an endoscope, calculating the position of a parathyroid gland in the images, judging whether the parathyroid gland exists in the images, calculating the position information of the parathyroid gland in the images, outputting parathyroid gland position images according to the detected parathyroid gland position information, and marking the parathyroid gland on the output images. Can reduce injury and even false cutting in the operation because the parathyroid gland can not be directly identified by naked eyes, and reduce the occurrence of medical accidents caused by parathyroid gland injury or false cutting.
Description
Technical Field
The invention relates to the technical field of medical equipment, in particular to a parathyroid gland identification method and an intelligent endoscope camera system device.
Background
With the progress of medical technology, an endoscope can be used for thyroid surgery. Laparoscopic nail surgery, with incisions much smaller than conventional open surgery, is popular with an increasing number of patients. Through the endoscope camera system, images under the endoscope are output to the display in real time for a doctor to watch. In the process of thyroid surgery, parathyroid gland needs to be protected, and sequelae caused by mistaken cutting are avoided.
Disclosure of Invention
This section is for the purpose of summarizing some aspects of embodiments of the invention and to briefly introduce some preferred embodiments. In this section, as well as in the abstract and the title of the invention of this application, simplifications or omissions may be made to avoid obscuring the purpose of the section, the abstract and the title, and such simplifications or omissions are not intended to limit the scope of the invention.
Therefore, the invention aims to provide a method for identifying parathyroid gland under a cavity mirror and an intelligent cavity mirror image pick-up system device with a parathyroid gland identification function, which can effectively reduce the occurrence of medical accidents due to the fact that the parathyroid gland cannot be found.
To solve the above technical problem, according to an aspect of the present invention, the present invention provides the following technical solutions:
a parathyroid gland identification method comprises the following specific steps:
acquiring images in the cavity through an intelligent endoscope camera system;
entering a parathyroid gland intelligent detection module to carry out target identification according to the collected visible light image and near infrared image under the endoscope, calculating the position of a parathyroid gland in the image, judging whether the parathyroid gland exists in the image and calculating the position information of the parathyroid gland in the image;
and outputting a parathyroid gland position image according to the detected parathyroid gland position information, and labeling the parathyroid gland on the output image.
As a preferable scheme of the parathyroid gland identification method, the method for identifying the target by entering a parathyroid gland intelligent detection module according to the collected visible light image and the collected near infrared image under the endoscope comprises the following steps: the collected endoscopic images comprise visible light images and near infrared images, and parathyroid glands in the images are detected when a plurality of visible light images and near infrared images are collected, wherein the images are continuous visible light images and near infrared images collected by the intelligent endoscopic camera system or the images are extracted from the endoscopic images collected by the intelligent endoscopic camera system within a set time.
As a preferable aspect of the parathyroid gland identification method of the present invention, wherein, the detecting parathyroid gland existing in a plurality of visible light images and near infrared images comprises: and inputting the plurality of visible light images and the near infrared images into a parathyroid gland recognition model to respectively obtain parathyroid glands existing in the plurality of visible light images and the near infrared images under the endoscope, wherein the parathyroid gland recognition model is used for recognizing the parathyroid glands existing in the visible light images and the near infrared images under the endoscope.
As a preferable aspect of the parathyroid gland identification method of the present invention, wherein the inputting of the plurality of visible light images and near-infrared images into the parathyroid gland identification model comprises: the parathyroid gland identification model respectively identifies the visible light image and the near infrared image at the same moment each time, the identification result enters the parathyroid gland identification module to be judged, the visible light and near infrared identification result is calculated according to the set weight, and the final judgment result is obtained.
As a preferable aspect of the parathyroid gland identification method of the present invention, before inputting the plurality of visible light images and the plurality of near-infrared images into the parathyroid gland identification model, the method further includes: and carrying out preprocessing such as denoising and enhancing on the visible light image and the near infrared image acquired each time.
As a preferable scheme of the parathyroid gland identification method, after the endoscopic image is collected by the intelligent endoscopic camera system, the method further comprises: determining the position information of a parathyroid gland target frame in the endoscopic image according to the acquired endoscopic image every time, wherein the target frame is used for indicating an area with parathyroid gland;
and correspondingly storing the position information of the parathyroid gland target frame in the endoscopic image and the endoscopic image.
As a preferable aspect of the parathyroid gland identification method according to the present invention, the determining of the position information of the target frame in the endoscopic image includes: and inputting the single-time acquired endoscopic image into a parathyroid gland recognition model to respectively obtain the position information of the target frame in the endoscopic visible light image and the near infrared image, wherein the parathyroid gland recognition model is used for recognizing parathyroid glands existing in the endoscopic image.
As a preferable aspect of the method for identifying a parathyroid gland according to the present invention, the method further comprises: the method comprises the steps of collecting visible light images and near-infrared images under a cavity mirror once, and carrying out four-split screen display once, wherein the four-split screen display comprises a four-split screen display visible light image, a near-infrared image, a visible light near-infrared green fusion image and a visible light near-infrared gradient fusion image, and the split screen is a main screen and three auxiliary screens.
An intelligence chamber mirror camera system device with parathyroid discernment function includes:
the acquisition module is used for simultaneously acquiring visible light images and near-infrared images under the endoscope;
the identification module is used for identifying the collected visible light image and the near infrared image at the same time and identifying the parathyroid gland in the image;
and the judging module is used for performing weight calculation according to the parathyroid gland results in the identified visible light image and the near infrared image to obtain the final parathyroid gland judging result and the corresponding position information.
And the output module is used for overlapping the parathyroid gland position information and the main screen image and outputting the information to an external display.
As a preferable scheme of the intelligent endoscope camera system device with parathyroid gland identification function, the identification module comprises:
the visible light image parathyroid gland identification module is used for identifying parathyroid glands and position information thereof in the visible light images;
and the near-infrared image parathyroid gland identification module is used for identifying parathyroid glands and position information thereof in the near-infrared image.
As a preferable scheme of the intelligent endoscope camera system device with parathyroid gland identification function, the judging module includes:
the weight setting module is used for setting weight coefficients of the recognition result of the parathyroid gland in the visible light image and the recognition result of the parathyroid gland in the near infrared image;
and the threshold setting module is used for setting a lower limit value of the weight coefficient, and judging that the parathyroid gland exists if the result calculated according to the weight coefficient is greater than the threshold, otherwise, judging that the parathyroid gland does not exist.
As a preferable scheme of the intelligent endoscope camera system device with parathyroid gland identification function, the output module further comprises:
and the first display module is used for displaying the image under the cavity mirror when the visible light image and the near-infrared image under the cavity mirror are acquired.
The second display module is used for displaying the fused image of the visible light image and the near-infrared image which are acquired under the endoscope of the endoscope each time;
and the third display module is used for overlapping an image displayed on the main screen with the position information of the parathyroid gland target frame output by the judgment module and displaying the overlapped image, and the target frame is used for indicating an area with parathyroid gland.
As a preferable scheme of the intelligent endoscope camera system device with parathyroid gland recognition function, the acquisition module comprises:
the visible light image acquisition unit is used for acquiring visible light images under the endoscope;
the near-infrared image acquisition unit is used for acquiring near-infrared images under the endoscope;
and the synchronization unit is used for controlling the visible light image acquisition unit and the near infrared image acquisition unit to synchronously acquire images.
Compared with the prior art, the invention has the following beneficial effects: when the endoscopic image is acquired through the intelligent endoscopic camera system, the paraglandular probably existing in the image is identified in real time according to the acquired endoscopic image, and the paraglandular is marked in the image in a target frame mode to remind a doctor to confirm a target area. Can reduce injury and even false cutting in the operation due to the fact that the parathyroid gland cannot be directly identified by naked eyes, improve the identification rate of the parathyroid gland, reduce the occurrence of medical accidents caused by parathyroid gland injury or false cutting, and is beneficial to improving the relationship between doctors and patients.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the present invention will be described in detail below with reference to the accompanying drawings and detailed embodiments, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings without inventive exercise. Wherein:
FIG. 1 is a flow chart of a parathyroid gland recognition method under an endoscope of the present invention;
FIG. 2 is a schematic block diagram of an intelligent endoscope camera system device of the present invention;
fig. 3 is a structural diagram of an intelligent endoscope camera system device.
Detailed Description
In order to make the aforementioned objects, features and advantages of the present invention more comprehensible, embodiments accompanying figures are described in detail below.
Next, the present invention will be described in detail with reference to the drawings, wherein for convenience of illustration, the cross-sectional view of the device structure is not enlarged partially according to the general scale, and the drawings are only examples, which should not limit the scope of the present invention. In addition, the three-dimensional dimensions of length, width and depth should be included in the actual fabrication.
To make the objects, technical solutions and advantages of the present invention more apparent, embodiments of the present invention will be described in detail with reference to the accompanying drawings.
Currently, parathyroid glands need to be protected during thyroid surgery. Because of individual difference of patients and different distribution positions of parathyroid glands, and because the parathyroid glands cannot be distinguished directly by human eyes, doctors are difficult to recognize and protect the parathyroid glands in real time in the operation, so that many patients need to take medicine for the whole life due to damage or even mistaken cutting of the parathyroid glands, and extra pain is caused to the patients.
Therefore, the embodiment of the application provides an endoscopic parathyroid gland identification method, an autofluorescence image of a parathyroid gland is captured by means of a near infrared camera, the parathyroid gland can be identified in real time in an operation by combining the anatomical structure position of the parathyroid gland in a visible light image, the position of the parathyroid gland is labeled, a doctor is reminded to confirm a labeled area, and medical accidents caused by parathyroid gland injury or mistaken cutting are reduced.
The parathyroid gland identification method provided in the examples of the present application will be described in detail below.
Fig. 1 is a flowchart of an instrument detection method provided in an embodiment of the present application, and referring to fig. 1, the method includes:
step 101: acquiring an image under a cavity mirror through an intelligent cavity mirror camera system;
it should be noted that the intelligent endoscope camera system can simultaneously acquire visible light (380-700 nm) images and near infrared (810-1100 nm) images under the endoscope and display the images, so that doctors can see the internal conditions of patients in time.
Step 102: preprocessing the image according to the collected visible light image and near-infrared image under the endoscope;
it should be noted that the acquired endoscopic image is subjected to image preprocessing, so that operations such as image detection and image display can be performed on the endoscopic image in the following. The image preprocessing may include filtering, image enhancement, image binarization, morphological operations, edge detection, and the like, which is not limited in this embodiment of the present application.
Step 103: identifying parathyroid glands in the images according to the preprocessed visible light images and the preprocessed near-infrared images;
wherein, the parathyroid gland which identifies the plurality of visible light images and near-infrared images under the endoscope can be as follows: and respectively inputting the multiple endoscopic visible light images and the near-infrared images into a visible light parathyroid gland recognition model and a near-infrared parathyroid gland recognition model to obtain confidence degrees and position information corresponding to the parathyroid glands in the multiple endoscopic visible light images and the near-infrared images.
The parathyroid gland identification model is used for identifying parathyroid glands appearing in a plurality of visible light images and near infrared images under the endoscope. The parathyroid gland identification model can be a neural network model such as a generation countermeasure network, a convolution neural network, a circulation neural network and the like.
In addition, the parathyroid gland recognition model can be obtained by training through visible light images and near infrared image samples comprising a large number of parathyroid glands in different scenes. For example, a plurality of training samples may be determined in advance, and for any one of the plurality of training samples, the sample data of the training sample is a plurality of endoscopic visible light images and near infrared images, and the label of the training sample is parathyroid gland appearing therein. Then, the plurality of training samples may be used to perform model training, specifically, the sample data in the plurality of training samples may be used as input, the labels of the plurality of training samples may be used as expected output, and model training is performed to obtain the parathyroid gland recognition model.
In step 103, in a possible case, the identification is performed according to the collected visible light image under the endoscope without identifying the near infrared image, or the identification is performed according to the collected near infrared image under the endoscope without identifying the visible light image. In this case, the parathyroid gland recognition model outputs only position information. For example, a plurality of training samples may be determined in advance, and for any one of the plurality of training samples, the sample data of the training sample is a plurality of endoscopic visible light images and near infrared images, and the label of the training sample is parathyroid gland appearing therein. Then, the plurality of training samples may be used to perform model training, specifically, the sample data in the plurality of training samples may be used as input, the labels of the plurality of training samples may be used as expected output, and model training is performed to obtain the parathyroid gland recognition model.
It should be noted that, in the embodiment of the present application, after the steps 101 and 102 are executed, the step 103 may be continuously executed. Thus, identification of the parathyroid gland is initiated at the same time as the endoscope begins to acquire the endoscopic image.
Alternatively, after receiving the external parathyroid gland opening instruction in step 102, the process may execute step 103. Therefore, in a scene without parathyroid gland identification, parathyroid gland identification is not executed, so that processing resources can be saved, and misjudgment can be avoided.
Step 104: and calculating the recognition results of the visible light and the near infrared according to the set weight every time the recognition results of the visible light image and the near infrared image are obtained, and outputting the confidence coefficient and the parathyroid gland target frame position information.
It should be noted that the formula of the confidence coefficient a is a = a × x1+ b × x2, where a is a weight coefficient of the visible light image, b is a weight coefficient of the near-infrared image, x1 is the confidence coefficient of the parathyroid gland contained in the visible light image, and x2 is the confidence coefficient of the parathyroid gland contained in the near-infrared image.
It is worth noting that in the embodiment of the application, the position information of the target frame in each acquired visible light image and near-infrared image under the endoscope can be acquired in real time, and only one final confidence and the position information of the target frame are output after the step 104 is executed. Under the condition, any one of the visible light image, the near infrared image or the fusion image under the endoscope is displayed in real time, and meanwhile, the target frame can be displayed in the image of the main screen according to the parathyroid gland target frame position information of the image under the endoscope, which is displayed on the main screen, so that a doctor can timely know the position of the currently appearing parathyroid gland while watching the image under the endoscope.
It should be noted that the parathyroid gland target box display function may be manually turned on or off by the physician's option.
And 105, acquiring the visible light image and the near-infrared image under the endoscope once, and performing split-screen display once.
It should be noted that the split screen display can display a visible light image, a near-infrared image, a visible light near-infrared green fusion image, and a visible light near-infrared gradient fusion image, and the split screen is a main screen and a plurality of auxiliary screens. And the position information of the target frame of the parathyroid gland is displayed in a superposition manner with the image displayed on the main screen.
The method for identifying parathyroid gland under endoscope shown in fig. 1 can be applied to an intelligent endoscope camera system with parathyroid gland identification function, and the detailed description of the intelligent endoscope camera system with parathyroid gland identification function is provided with reference to fig. 2.
Fig. 2 and fig. 3 are a schematic block diagram and a structural diagram of an intelligent cavity mirror image capturing system device with a parathyroid gland identification function according to an embodiment of the present application, please refer to fig. 2 and fig. 3, the intelligent cavity mirror image capturing system with the parathyroid gland identification function may include: the device comprises a camera handle 201, an image acquisition module 202, an image processing module 203, a parathyroid gland identification module 204, a parathyroid gland distinguishing module 205, an image output module 206 and an image storage module 207.
The camera handle can receive visible light signals and near infrared signals at the same time, and converts the light signals into digital signals to be transmitted to the image acquisition module 202.
The image acquisition module 202 receives the digital signal transmitted by the camera handle, decodes the digital signal and transmits the decoded digital signal to the image processing module 203.
The image processing module 203 preprocesses the received visible light image and near-infrared image, and inputs the processed images to the parathyroid gland recognition module 204.
The parathyroid gland identification module comprises a visible light parathyroid gland identification module and a near infrared parathyroid gland identification module, the visible light parathyroid gland identification module identifies the preprocessed visible light parathyroid gland image, the near infrared parathyroid gland identification module identifies the preprocessed near infrared parathyroid gland image, and outputs the identified visible light parathyroid gland confidence coefficient, position information, near infrared parathyroid gland confidence coefficient and position information to the parathyroid gland distinguishing module 205. The main control chip of the identification module can be NPU, GPU or FPGA.
The parathyroid gland distinguishing module calculates the confidence coefficient and the position information input by the parathyroid gland recognition module according to the set weight to obtain the final confidence coefficient and position information, and if the confidence coefficient is greater than a set threshold value, the parathyroid gland is judged to output the target frame position information; and if the confidence coefficient is smaller than the set threshold value, judging that the parathyroid gland is not provided, and not outputting the parathyroid gland target frame position information.
The image output module 207 is divided into a main screen and an auxiliary screen for split-screen display, respectively displays a visible light image, a near-infrared image and a fusion image, and superimposes a parathyroid gland target frame and the main screen image.
The image storage module 206 records and stores the final image output by the image output module.
It should be noted that: the intelligent cavity mirror image pickup system device with the parathyroid gland identification function provided by the above embodiment is only exemplified by the division of the above functional modules when identifying the parathyroid gland, and in practical application, the above function distribution can be completed by different functional modules according to needs, that is, the internal structure of the device is divided into different functional modules to complete all or part of the above described functions. In addition, the intelligent endoscope camera system device with the parathyroid gland identification function provided by the embodiment and the embodiment of the parathyroid gland identification method under the endoscope belong to the same concept, and the specific implementation process is described in the embodiment of the method in detail and is not described again.
While the invention has been described above with reference to an embodiment, various modifications may be made and equivalents may be substituted for elements thereof without departing from the scope of the invention. In particular, the various features of the disclosed embodiments of this invention can be used in any combination as long as there is no structural conflict, and the combination is not exhaustively described in this specification merely for the sake of brevity and resource savings. Therefore, it is intended that the invention not be limited to the particular embodiments disclosed, but that the invention will include all embodiments falling within the scope of the appended claims.
Claims (13)
1. A parathyroid gland identification method is characterized by comprising the following specific steps:
acquiring images in the cavity through an intelligent endoscope camera system;
entering a parathyroid gland intelligent detection module to carry out target identification according to the collected visible light image and near infrared image under the endoscope, calculating the position of a parathyroid gland in the image, judging whether the parathyroid gland exists in the image and calculating the position information of the parathyroid gland in the image;
and outputting a parathyroid gland position image according to the detected parathyroid gland position information, and labeling the parathyroid gland on the output image.
2. The parathyroid gland identification method according to claim 1, wherein the entering parathyroid gland intelligent detection module according to the collected visible light image and near infrared image under the cavity mirror for target identification comprises: the collected images under the endoscope comprise visible light images and near-infrared images, and parathyroid glands in the images are detected when a plurality of visible light images and near-infrared images are collected, wherein the images are continuous visible light images and near-infrared images collected by the intelligent endoscope camera system or the images under the endoscope are extracted from images under the endoscope collected by the intelligent endoscope camera system within a set time.
3. A parathyroid gland identification method according to claim 2, wherein said detecting parathyroid gland present in a plurality of visible light images and near infrared images comprises: and inputting the plurality of visible light images and the near infrared images into a parathyroid gland recognition model to respectively obtain parathyroid glands existing in the plurality of visible light images and the near infrared images under the endoscope, wherein the parathyroid gland recognition model is used for recognizing the parathyroid glands existing in the visible light images and the near infrared images under the endoscope.
4. A parathyroid gland identification method according to claim 3, wherein, inputting the plurality of visible light images and near infrared images into parathyroid gland identification model, comprises: the parathyroid gland identification model respectively identifies the visible light image and the near infrared image at the same moment each time, the identification result enters the parathyroid gland identification module to be judged, the visible light and near infrared identification result is calculated according to the set weight, and the final judgment result is obtained.
5. The parathyroid gland identification method according to claim 4, wherein before inputting the plurality of visible light images and near infrared images into the parathyroid gland identification model, the method further comprises: and carrying out preprocessing such as denoising and enhancing on the visible light image and the near infrared image acquired each time.
6. The parathyroid gland identification method according to claim 1, wherein after the endoscopic image is acquired by the intelligent endoscopic camera system, the method further comprises: determining the position information of a parathyroid gland target frame in the endoscopic image according to the acquired endoscopic image every time, wherein the target frame is used for indicating an area with parathyroid gland;
and correspondingly storing the position information of the parathyroid gland target frame in the endoscopic image and the endoscopic image.
7. A parathyroid gland identification method according to claim 6, wherein said determining target frame position information in the endoscopic image includes: and inputting the single-time acquired endoscopic image into a parathyroid gland recognition model to respectively obtain the position information of the target frame in the endoscopic visible light image and the near infrared image, wherein the parathyroid gland recognition model is used for recognizing parathyroid glands existing in the endoscopic image.
8. The parathyroid gland identification method according to claim 7, further including: the method comprises the steps of collecting visible light images and near infrared images under the endoscope once, and carrying out four-split screen display once, wherein the four-split screen display comprises a four-split screen display visible light image, a near infrared image, a visible light near infrared green fused image and a visible light near infrared gradient fused image, and the split screen is a main screen and three auxiliary screens.
9. An intelligent cavity mirror camera system device with parathyroid gland recognition function, which is applied to the parathyroid gland recognition method according to any one of claims 1-8, and is characterized by comprising the following steps:
the acquisition module is used for simultaneously acquiring visible light images and near-infrared images under the endoscope;
the identification module is used for identifying the collected visible light image and the near infrared image at the same time and identifying the parathyroid gland in the image;
the judging module is used for carrying out weight calculation according to the parathyroid gland results in the identified visible light image and the near infrared image to obtain the final parathyroid gland judging result and the corresponding position information;
and the output module is used for overlapping the parathyroid gland position information and the main screen image and outputting the result to an external display.
10. An intelligent endoscope camera system device with parathyroid gland identification function according to claim 9, characterized in that, said identification module includes:
the visible light image parathyroid gland identification module is used for identifying parathyroid gland and position information thereof in the visible light image;
and the near-infrared image parathyroid gland identification module is used for identifying parathyroid glands and position information thereof in the near-infrared images.
11. An intelligent endoscope camera system device with parathyroid gland identification function according to claim 9, wherein said judgment module comprises:
the weight setting module is used for setting the weight coefficients of the recognition result of the parathyroid gland in the visible light image and the recognition result of the parathyroid gland in the near infrared image;
and the threshold setting module is used for setting a lower limit value of the weight coefficient, and judging that the parathyroid gland exists if a result calculated according to the weight coefficient is greater than the threshold, otherwise, the parathyroid gland does not exist.
12. An intelligent endoscope camera system device with parathyroid gland identification function according to claim 9, characterized in that, said output module further comprises:
the first display module is used for displaying the image under the cavity mirror when the visible light image and the near infrared image under the cavity mirror are acquired;
the second display module is used for displaying the fused image of the visible light image and the near-infrared image which are acquired under the endoscope of the endoscope each time;
and the third display module is used for overlapping an image displayed on the main screen and the position information of the parathyroid gland target frame output by the judgment module and displaying the overlapped image, and the target frame is used for indicating an area with parathyroid gland.
13. An intelligent endoscope camera system device with parathyroid gland identification function according to claim 9, wherein said collection module includes:
the visible light image acquisition unit is used for acquiring visible light images under the endoscope;
the near-infrared image acquisition unit is used for acquiring near-infrared images under the endoscope;
and the synchronization unit is used for controlling the visible light image acquisition unit and the near infrared image acquisition unit to synchronously acquire images.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211548101.3A CN115797617A (en) | 2022-12-05 | 2022-12-05 | Parathyroid gland identification method and intelligent endoscope camera system device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211548101.3A CN115797617A (en) | 2022-12-05 | 2022-12-05 | Parathyroid gland identification method and intelligent endoscope camera system device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115797617A true CN115797617A (en) | 2023-03-14 |
Family
ID=85445584
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211548101.3A Pending CN115797617A (en) | 2022-12-05 | 2022-12-05 | Parathyroid gland identification method and intelligent endoscope camera system device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115797617A (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105975908A (en) * | 2016-04-26 | 2016-09-28 | 汉柏科技有限公司 | Face recognition method and device thereof |
| CN110929566A (en) * | 2019-10-16 | 2020-03-27 | 厦门大学 | Human face living body detection method based on visible light and near-infrared binocular camera |
| CN112329624A (en) * | 2020-11-05 | 2021-02-05 | 北京地平线信息技术有限公司 | Living body detection method and apparatus, storage medium, and electronic device |
| CN112656369A (en) * | 2020-11-30 | 2021-04-16 | 浙江大学医学院附属第一医院 | AR technology-based near-infrared fluorescent parathyroid gland identification enhancement method |
| CN113205141A (en) * | 2021-05-08 | 2021-08-03 | 脉得智能科技(无锡)有限公司 | Parathyroid gland identification method based on image fusion technology |
| CN113520271A (en) * | 2021-06-23 | 2021-10-22 | 王松 | Parathyroid gland function imaging method and system and endoscope |
| CN114120038A (en) * | 2021-11-26 | 2022-03-01 | 中国科学院长春光学精密机械与物理研究所 | Parathyroid gland identification method based on hyperspectral imaging technology and model training |
| CN114170213A (en) * | 2021-12-15 | 2022-03-11 | 高永楷 | Parathyroid gland identification method based on image fusion technology |
-
2022
- 2022-12-05 CN CN202211548101.3A patent/CN115797617A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105975908A (en) * | 2016-04-26 | 2016-09-28 | 汉柏科技有限公司 | Face recognition method and device thereof |
| CN110929566A (en) * | 2019-10-16 | 2020-03-27 | 厦门大学 | Human face living body detection method based on visible light and near-infrared binocular camera |
| CN112329624A (en) * | 2020-11-05 | 2021-02-05 | 北京地平线信息技术有限公司 | Living body detection method and apparatus, storage medium, and electronic device |
| CN112656369A (en) * | 2020-11-30 | 2021-04-16 | 浙江大学医学院附属第一医院 | AR technology-based near-infrared fluorescent parathyroid gland identification enhancement method |
| CN113205141A (en) * | 2021-05-08 | 2021-08-03 | 脉得智能科技(无锡)有限公司 | Parathyroid gland identification method based on image fusion technology |
| CN113520271A (en) * | 2021-06-23 | 2021-10-22 | 王松 | Parathyroid gland function imaging method and system and endoscope |
| CN114120038A (en) * | 2021-11-26 | 2022-03-01 | 中国科学院长春光学精密机械与物理研究所 | Parathyroid gland identification method based on hyperspectral imaging technology and model training |
| CN114170213A (en) * | 2021-12-15 | 2022-03-11 | 高永楷 | Parathyroid gland identification method based on image fusion technology |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US12051199B2 (en) | Image processing method and apparatus, server, medical image processing device and storage medium | |
| WO2017030747A1 (en) | Reconstruction with object detection for images captured from a capsule camera | |
| CN110909780A (en) | Image recognition model training and image recognition method, device and system | |
| WO2021147429A1 (en) | Endoscopic image display method, apparatus, computer device, and storage medium | |
| US20110013846A1 (en) | Image processing apparatus and image processing method | |
| US20110025844A1 (en) | Image processing apparatus and method for displaying images | |
| CN110662476B (en) | Information processing apparatus, control method, and program | |
| CN110974306B (en) | System for discernment and location pancreas neuroendocrine tumour under ultrasonic endoscope | |
| CN103327883A (en) | Medical image processing device and medical image processing method | |
| CN113888518A (en) | Laryngopharynx endoscope tumor detection and benign and malignant classification method based on deep learning segmentation and classification multitask | |
| CN113129287A (en) | Automatic lesion mapping method for upper gastrointestinal endoscope image | |
| CN114004969A (en) | Endoscope image focal zone detection method, device, equipment and storage medium | |
| US20060036948A1 (en) | Image selection device and image selecting method | |
| CN113139937A (en) | Digestive tract endoscope video image identification method based on deep learning | |
| CN113792663B (en) | Method, device and storage medium for detecting drunk driving and fatigue driving of driver | |
| WO2012121488A2 (en) | Method for processing medical blood vessel image | |
| CN111666911A (en) | Micro-expression data expansion method and device | |
| JPH0235358A (en) | Image processing method for taking out glandular cavity of stomack tissue | |
| CN111860079B (en) | Living body image detection method and device and electronic equipment | |
| CN115797617A (en) | Parathyroid gland identification method and intelligent endoscope camera system device | |
| CN115082739A (en) | Endoscope evaluation method and system based on convolutional neural network | |
| US9854958B1 (en) | System and method for automatic processing of images from an autonomous endoscopic capsule | |
| CN110960194B (en) | Ear phase acquisition device and acquisition method | |
| Gallo et al. | WCE video segmentation using textons | |
| KR102623871B1 (en) | Processing system and method for medical image |
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 |