CN113012162A - Method and device for detecting cleanliness of endoscopy examination area and related equipment - Google Patents
Method and device for detecting cleanliness of endoscopy examination area and related equipment Download PDFInfo
- Publication number
- CN113012162A CN113012162A CN202110249821.9A CN202110249821A CN113012162A CN 113012162 A CN113012162 A CN 113012162A CN 202110249821 A CN202110249821 A CN 202110249821A CN 113012162 A CN113012162 A CN 113012162A
- Authority
- CN
- China
- Prior art keywords
- image
- cleanliness
- region
- endoscopic
- interest
- 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
- 230000003749 cleanliness Effects 0.000 title claims abstract description 161
- 238000001839 endoscopy Methods 0.000 title claims abstract description 32
- 238000000034 method Methods 0.000 title claims abstract description 32
- 238000001514 detection method Methods 0.000 claims abstract description 74
- 238000003709 image segmentation Methods 0.000 claims abstract description 32
- 238000003860 storage Methods 0.000 claims abstract description 13
- 238000004364 calculation method Methods 0.000 claims description 14
- 238000011010 flushing procedure Methods 0.000 claims description 12
- 238000004590 computer program Methods 0.000 claims description 8
- 230000009286 beneficial effect Effects 0.000 abstract description 2
- 238000004891 communication Methods 0.000 description 28
- 230000000968 intestinal effect Effects 0.000 description 12
- 239000007788 liquid Substances 0.000 description 12
- 210000001035 gastrointestinal tract Anatomy 0.000 description 10
- 230000006870 function Effects 0.000 description 9
- 238000003384 imaging method Methods 0.000 description 9
- 210000002784 stomach Anatomy 0.000 description 8
- 238000011156 evaluation Methods 0.000 description 7
- 230000002496 gastric effect Effects 0.000 description 7
- 230000008569 process Effects 0.000 description 7
- 238000012545 processing Methods 0.000 description 7
- 239000007787 solid Substances 0.000 description 7
- 210000001156 gastric mucosa Anatomy 0.000 description 6
- 210000004347 intestinal mucosa Anatomy 0.000 description 6
- 238000004422 calculation algorithm Methods 0.000 description 4
- 230000009471 action Effects 0.000 description 3
- 238000003745 diagnosis Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 201000010099 disease Diseases 0.000 description 3
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 3
- 238000007689 inspection Methods 0.000 description 3
- -1 residual stool Substances 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 2
- 210000003608 fece Anatomy 0.000 description 2
- 239000012530 fluid Substances 0.000 description 2
- 239000010794 food waste Substances 0.000 description 2
- 210000003736 gastrointestinal content Anatomy 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 210000003097 mucus Anatomy 0.000 description 2
- 238000003062 neural network model Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000002360 preparation method Methods 0.000 description 2
- 238000004445 quantitative analysis Methods 0.000 description 2
- 210000002700 urine Anatomy 0.000 description 2
- 208000019399 Colonic disease Diseases 0.000 description 1
- 210000000941 bile Anatomy 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 239000006260 foam Substances 0.000 description 1
- 238000002575 gastroscopy Methods 0.000 description 1
- 210000000936 intestine Anatomy 0.000 description 1
- 238000003973 irrigation Methods 0.000 description 1
- 230000002262 irrigation Effects 0.000 description 1
- 210000004400 mucous membrane Anatomy 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 238000003908 quality control method Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 210000001835 viscera Anatomy 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B1/00—Instruments for performing medical examinations of the interior of cavities or tubes of the body by visual or photographical inspection, e.g. endoscopes; Illuminating arrangements therefor
- A61B1/00002—Operational features of endoscopes
- A61B1/00004—Operational features of endoscopes characterised by electronic signal processing
- A61B1/00009—Operational features of endoscopes characterised by electronic signal processing of image signals during a use of endoscope
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10068—Endoscopic image
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20084—Artificial neural networks [ANN]
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- Surgery (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Pathology (AREA)
- Biomedical Technology (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Optics & Photonics (AREA)
- Signal Processing (AREA)
- Radiology & Medical Imaging (AREA)
- Geometry (AREA)
- Biophysics (AREA)
- Heart & Thoracic Surgery (AREA)
- Medical Informatics (AREA)
- Molecular Biology (AREA)
- Animal Behavior & Ethology (AREA)
- General Health & Medical Sciences (AREA)
- Public Health (AREA)
- Veterinary Medicine (AREA)
- Endoscopes (AREA)
Abstract
The application discloses a cleanliness detection method for an endoscopy examination area, which comprises the following steps: acquiring an endoscope image, and performing image segmentation operation on the endoscope image to obtain an image of a region of interest; wherein the image of the region of interest is an image of a region where the contents are located; calculating the image proportion of the region-of-interest image in the endoscope image; and determining a cleanliness score of the endoscopy examination area according to the image proportion, and outputting a cleanliness detection result according to the cleanliness score. The method and the device can improve the accuracy of detecting the cleanliness of the endoscopy examination area. The application also discloses a cleanliness detection device in the endoscopy examination area, an electronic device and a storage medium, which have the beneficial effects.
Description
Technical Field
The present disclosure relates to the field of electronic endoscopes, and in particular, to a method and an apparatus for detecting cleanliness in an endoscopic region, an electronic device, and a storage medium.
Background
An electronic endoscope (endoscopy) is a medical electronic optical instrument which can be inserted into the body cavity and internal organs of human body to make direct observation, diagnosis and treatment. The electronic endoscope may include a gastroscope, an enteroscope, and the like, and when the electronic endoscope collects an endoscopic image of a specific area, the cleanliness of the endoscopic area has a large influence on the imaging quality of the endoscopic image.
In the practical application process of the electronic endoscope, if the cleanliness of the endoscope examination area is not high, doctors are difficult to observe focuses, and the disease detection rate is affected. In order to improve the cleanliness of the endoscopic region, the related art generally relies on the working experience of the doctor to evaluate the cleanliness of the endoscopic region so as to take a flushing operation when the cleanliness is low. However, the above-described evaluation of cleanliness depending on experience is low in reliability, and the quality of endoscopy varies.
Therefore, how to improve the accuracy of detecting the cleanliness of the endoscopic examination area is a technical problem that needs to be solved by those skilled in the art at present.
Disclosure of Invention
An object of the present application is to provide a method and apparatus for detecting cleanliness of an endoscopy region, an electronic device, and a storage medium, which can improve accuracy of detecting cleanliness of an endoscopy region.
In order to solve the above technical problem, the present application provides a cleanliness detection method for an endoscopic area, the cleanliness detection method including:
acquiring an endoscope image, and performing image segmentation operation on the endoscope image to obtain an image of a region of interest; wherein the image of the region of interest is an image of a region where the contents are located;
calculating the image proportion of the region-of-interest image in the endoscope image;
and determining a cleanliness score of the endoscopy examination area according to the image proportion, and outputting a cleanliness detection result according to the cleanliness score.
Optionally, performing an image segmentation operation on the endoscope image to obtain an image of a region of interest, including:
extracting image features of the endoscopic image; wherein the image features include color information, luminance information, texture information, and boundary information;
and performing image segmentation operation on the endoscope image according to the image characteristics to obtain an image of the region of interest.
Optionally, calculating an image scale of the region of interest image in the endoscopic image includes:
counting the number of pixel points of the interested area image, and calculating the ratio of the number of the pixel points of the interested area image to the number of the pixel points of the endoscope image;
and setting the pixel point quantity proportion as the image proportion.
Optionally, performing an image segmentation operation on the endoscope image to obtain an image of a region of interest, including:
performing image segmentation operation on the endoscope image to obtain an interested area image of a plurality of contents;
correspondingly, calculating the image proportion of the region of interest image in the endoscope image comprises the following steps:
calculating an image scale of the image of interest of each of the contents in the endoscopic image.
Optionally, determining a cleanliness score of the endoscopic region according to the image scale includes:
and carrying out weighted calculation on the image proportion of the interested image of each content according to the weight value of the content to obtain the cleanliness score of the endoscopic region.
Optionally, outputting a cleanliness detection result according to the cleanliness score, including:
judging whether the cleanliness score is within a preset score interval;
if so, outputting a clean cleanliness detection result of the endoscopic area;
and if not, outputting a cleanliness detection result of the unclean endoscopy examination area.
Optionally, after outputting the result of detecting the unclean cleanliness of the endoscopic examination area, the method further includes:
and sending a voice prompt instruction to the client so that the client can broadcast the flushing operation prompt tone.
The present application also provides a cleanliness detection device of an endoscopy region, the cleanliness detection device including:
the image segmentation module is used for acquiring an endoscope image and executing image segmentation operation on the endoscope image to obtain an image of a region of interest; wherein the image of the region of interest is an image of a region where the contents are located;
the proportion calculation module is used for calculating the image proportion of the region-of-interest image in the endoscope image;
and the cleanliness detection module is used for determining a cleanliness score of the endoscopic area according to the image proportion and outputting a cleanliness detection result according to the cleanliness score.
The present application also provides a storage medium having stored thereon a computer program that, when executed, implements the steps performed by the above-described method of detecting cleanliness of an endoscopic examination region.
The application also provides an electronic device, which comprises a memory and a processor, wherein the memory is stored with a computer program, and the processor realizes the steps executed by the cleanliness detection method of the endoscopy examination area when calling the computer program in the memory.
The application provides a cleanliness detection method for an endoscopy examination area, which comprises the following steps: acquiring an endoscope image, and performing image segmentation operation on the endoscope image to obtain an image of a region of interest; calculating the image proportion of the region-of-interest image in the endoscope image; and determining a cleanliness score of the endoscopy examination area according to the image proportion, and outputting a cleanliness detection result according to the cleanliness score.
According to the method, after the endoscope image is acquired, the image of the interested area is obtained by carrying out image segmentation on the endoscope image, and the image of the interested area is an image of contents affecting the imaging quality of the endoscope. The degree of influence of the endoscope image by the contents can be determined according to the image proportion of the region-of-interest image in the endoscope image, and then the cleanliness score of the endoscope examination region can be obtained and the corresponding cleanliness detection result can be deleted. According to the method and the device, the cleanliness score can be determined based on the proportion of the images of the region of interest, the objective evaluation of the cleanliness can be realized, and the dependence on manual experience is not needed, so that the cleanliness detection scheme can improve the accuracy of detecting the cleanliness of the endoscopy region. The application also provides a cleanliness detection device, an electronic device and a storage medium in the endoscopy examination area, and the cleanliness detection device, the electronic device and the storage medium have the beneficial effects and are not repeated.
Drawings
In order to more clearly illustrate the embodiments of the present application, the drawings needed for the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and that other drawings can be obtained by those skilled in the art without inventive effort.
Fig. 1 is a flowchart of a cleanliness detection method for an endoscopic examination area according to an embodiment of the present disclosure;
FIG. 2 is a flow chart of another method for detecting cleanliness of an endoscopic region according to an embodiment of the present disclosure;
fig. 3 is a schematic diagram illustrating results of a system for scoring intestinal cleanliness according to an embodiment of the present disclosure;
fig. 4 is a schematic structural diagram of a cleanliness detection apparatus in an endoscopic examination area according to an embodiment of the present application.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are some embodiments of the present application, but not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
Referring to fig. 1, fig. 1 is a flowchart of a method for detecting cleanliness of an endoscopic examination area according to an embodiment of the present application, and the method includes the following specific steps:
s101: acquiring an endoscope image, and performing image segmentation operation on the endoscope image to obtain an image of a region of interest;
the present embodiment may be applied to an electronic endoscope or a cleanliness detection apparatus connected to the electronic endoscope, and the present embodiment does not limit a specific position corresponding to an acquired endoscopic image, for example, the endoscopic image may be a gastroscopic image or an enteroscope image.
After obtaining the endoscopic image, the present embodiment obtains a region-of-interest image, which is an image of contents in the endoscopic region, which is a substance affecting the endoscopic imaging quality in the endoscopic region, by performing an image segmentation operation on the endoscopic image. For example, during enteroscopy, the contents of the intestine may include clear fluid, turbid fluid, residual stool, solid stool, and the like; during a gastroscopy procedure, the contents of the stomach may include food debris, air bubbles, and the like.
S102: calculating the image proportion of the region-of-interest image in the endoscope image;
since the larger the image proportion of the region-of-interest image is, the larger the influence of the content on the imaging quality of the endoscope is, after the region-of-interest image in the endoscope image is obtained, the embodiment can calculate the image proportion of the region-of-interest image in the endoscope image, and further evaluate the cleanliness of the endoscopic examination region according to the image proportion.
As a possible implementation, the present embodiment may calculate the image proportions of all the images of the region of interest in the endoscopic image; as another possible implementation, the present embodiment may also calculate an image ratio of the region of interest image corresponding to each content in the endoscopic image.
S103: and determining a cleanliness score of the endoscopy examination area according to the image proportion, and outputting a cleanliness detection result according to the cleanliness score.
The image of the region of interest is a sub-region with poor imaging quality in the endoscopic image, and according to the image proportion of the image of the region of interest in the endoscopic image, the larger the image proportion is, the larger the distribution proportion of the content in the endoscopic region is, that is, the poorer the cleanliness is. According to the embodiment, the cleanliness score of the endoscopy examination area can be determined according to the image proportion, and then the corresponding cleanliness examination result is output according to the cleanliness score. Specifically, the present embodiment may preset a comparison table of the cleanliness scores and the cleanliness detection results, and determine the cleanliness detection results corresponding to the cleanliness scores by looking up the table.
The present embodiment obtains a region-of-interest image, which is an image of contents affecting the imaging quality of the endoscope, by performing image segmentation on the endoscopic image after the endoscopic image is acquired. The degree of influence of the endoscope image by the contents can be determined according to the image proportion of the region-of-interest image in the endoscope image, and then the cleanliness score of the endoscope examination region can be obtained and the corresponding cleanliness detection result can be deleted. According to the cleanliness detection method and the cleanliness detection system, the cleanliness score can be determined based on the proportion of the image of the region of interest, objective evaluation on cleanliness can be achieved, manual experience is not needed, and therefore the cleanliness detection scheme can improve the accuracy of detecting the cleanliness of the endoscopy region.
As a further introduction to the corresponding embodiment of fig. 1, the region-of-interest image may be acquired from the endoscopic image by: extracting image features of the endoscopic image; wherein the image features include color information, luminance information, texture information, and boundary information; and performing image segmentation operation on the endoscope image according to the image characteristics to obtain an image of the region of interest. Specifically, the present embodiment may input the image features into a neural network model, and determine the region-of-interest image in the endoscope image by using the neural network model.
As a further introduction to the corresponding embodiment of fig. 1, the image scale of the region-of-interest image may also be calculated by: counting the number of pixel points of the interested area image, and calculating the ratio of the number of the pixel points of the interested area image to the number of the pixel points of the endoscope image; and setting the pixel point quantity proportion as the image proportion. In the process, the image proportion of the image of the region of interest in the endoscope image is calculated by utilizing the pixel point quantity proportion, so that the calculation efficiency of the image proportion can be improved.
Referring to fig. 2, fig. 2 is a flowchart of another method for detecting cleanliness of an endoscopic region according to an embodiment of the present application, where the present embodiment provides a scheme for detecting cleanliness based on a type and a ratio of an image of a region of interest, which can further improve cleanliness detection accuracy, and the present embodiment may include the following steps:
s201: acquiring an endoscope image;
s202: performing image segmentation operation on the endoscope image to obtain an interested area image of various contents;
s203: calculating an image scale of the image of interest of each content in the endoscopic image;
s204: carrying out weighted calculation on the image proportion of the interested image of each content according to the weight value of the content to obtain a cleanliness score of the endoscopic region;
s205: and outputting a cleanliness detection result according to the cleanliness score.
Since the influence degree of each content on the imaging quality of the endoscope is different, the cleanliness score is obtained by performing weighted calculation according to the image proportion and the weight value corresponding to each content, and the accuracy of the cleanliness score can be improved.
The above process is illustrated by way of example: the types of contents of the endoscopic region may include: clear liquid, turbid liquid and solid excrement and urine, according to the influence degree of above-mentioned content to endoscope imaging quality, set up the weight value of clear liquid and be 1, the weight value of turbid liquid is 2, and the weight value of solid excrement and urine is 5. The cleanliness score is more than 0.5, and the cleanliness detection result is unclean; the cleanliness score is less than or equal to 0.5 point, and the cleanliness test result is clean. A higher cleanliness score indicates less cleanliness of the endoscopic region. If the image proportion of the clear liquid is determined to be 10%, the image proportion of the turbid liquid is determined to be 10%, the weight value of the solid feces is 5%, and the cleanliness score is 1 × 10% +2 × 10% +5 × 5% + 0.55 after the image segmentation operation, it can be determined that the endoscopic region is not clean.
As a further description of the embodiment corresponding to fig. 1, the present embodiment may output the cleanliness detection result by the following manner: judging whether the cleanliness score is within a preset score interval; if so, outputting a clean cleanliness detection result of the endoscopic area; and if not, outputting a cleanliness detection result of the unclean endoscopy examination area.
Further, after the cleanliness detection result that the endoscopy examination area is unclean is output, a voice prompt instruction can be sent to the client, so that the client can broadcast a flushing operation prompt tone. The user can carry out the flushing operation on the endoscopy examination area after hearing the flushing operation prompt tone so as to flush away the contents and further improve the detection quality. As a feasible implementation manner, the embodiment can also automatically perform flushing operation on the endoscopic region after outputting the detection result of unclean cleanliness of the endoscopic region, thereby improving the detection efficiency.
The flow described in the above embodiment is explained below by an embodiment in practical use.
The colonoscope is an important means for screening, diagnosing and treating colon diseases, the diagnosis accuracy and the treatment safety of the colonoscope are closely related to the quality of intestinal tract preparation, and the sufficient intestinal tract preparation can enable a patient to obtain higher intestinal tract cleanliness, so that the colonoscope has important significance for realizing high-quality enteroscope diagnosis and treatment. When the current electronic endoscope inspects the intestinal tract, contents such as opaque liquid, bubbles, foam, food residues and the like in the intestinal tract can only be judged by the operation experience of a doctor whether the contents affect the inspection of the intestinal tract mucous membrane. When more contents exist, the liquid in the intestinal tract is turbid or the solid excrement is blocked, and the like, the doctor can flush the contents. But whether the flushing operation is needed or not depends on the working experience of doctors, so that the intestinal examination quality is uneven.
Referring to fig. 3, fig. 3 is a schematic diagram illustrating results of an intestinal cleanliness scoring system according to an embodiment of the present application, which is capable of quantitatively evaluating the cleanliness of the intestinal tract and better guiding a doctor whether to perform an intestinal irrigation operation.
The intestinal cleanliness scoring system may include: a scoring system end, a communication end and a client end.
The scoring system end comprises an image receiving module and an algorithm identification module; the image receiving module is used for receiving an image transmitted from a client; the image processing module is used for receiving image data in real time, identifying and processing a single endoscope image, calling the algorithm model to automatically identify and score the image, and sending the scoring result of the current image to the communication module. And when the scoring result is higher than the set threshold value, sending a voice instruction.
Specifically, the image processing module at the scoring system end may have functions of content detection, pixel area calculation, scoring rule determination, scoring result output, and the like. The content detection function can be realized by the following modes: by adopting an image segmentation technology, a region of interest containing intestinal contents is extracted through characteristics such as color, brightness, texture, boundaries and the like. The region of interest may be specifically classified as clear liquid, turbid liquid, residual stool, solid stool, and the like. The function of calculating the pixel area can be realized by the following ways: calculating the extracted pixel points of the region of interest and determining the pixel area of the region; and dividing the pixel area by the pixel area of the whole image to obtain the percentage of the interested area in the whole image. And the intestinal tract cleanliness score in the scoring system is used for evaluating the cleanliness of the intestinal mucosa by using an Ottawa scale. Please refer to table 1, wherein table 1 is a table of intestinal cleanliness scores. The present embodiment can be divided into grades according to the content and the shielding area ratio in a single picture, and the grades are divided into: 0 minute, namely the ratio of the shelters is within 0 to 5 percent, and the observation of the intestinal mucosa is not influenced; 1 minute, namely the ratio area of turbid liquid or residual excrement is within 5-10%, which slightly influences the observation of intestinal mucosa; 2 minutes, the turbid liquid or residual excrement accounts for 10-30% of the specific area, and the intestinal mucosa observation is generally influenced; 3 minutes, namely the area of the feces is within 30-50%, which seriously affects the observation of the intestinal mucosa; 4 minutes, namely the solid excrement accounts for more than 50 percent of the area, and the observation of the intestinal mucosa is seriously influenced.
TABLE 1 intestinal cleanliness score instruction sheet
According to the scoring rule, the embodiment can output a specific scoring score. In this embodiment, a warning threshold may be preset, for example, the threshold is set to 2 points, and when the score is less than 2 points, a general instruction is issued; and when the score is greater than or equal to 3 minutes, a warning instruction is sent. The specific scoring scores are displayed on a display module of the client and are stored in a storage module at the same time.
The communication end is arranged between the grading system end and the client end, and can receive the image data transmitted by the client end and carry out two-way communication with the client end; the communication terminal and the scoring system terminal keep two-way communication, and when receiving the command and the scoring result sent by the scoring system terminal, the communication terminal forwards the command and the scoring result to the client terminal.
The client comprises a communication module, a display module, a storage module and a voice module. The communication module is used for receiving image data acquired by the electronic endoscope, performing two-way communication with the electronic endoscope and receiving a scoring result and a command sent by the communication end; and sending the received image data collected from the electronic endoscope to a communication terminal. The display module is used for displaying the score received from the communication terminal in real time. The storage module is used for marking the image data according to the grading result and storing the image data in a local folder so as to be convenient for backtracking and reference. The voice module is used for receiving a voice command from the communication end, and when the warning command is received, the voice module gives out an alarm sound to remind a doctor to flush the intestinal tract; when a general instruction is received, the voice module does not send out alarm sound.
The implementation method of the storage module in the client side comprises the following steps: and receiving a grading result, correspondingly marking the grading result in the image data and storing the grading result in a local folder of the client, wherein a doctor can select to export the image data according to the grading in the later period without manually marking the image data again, so that the time of the doctor is saved, and the grading result can also be used as a reference index for teaching or data quality control of retrospective research.
Above-mentioned intestinal cleanliness system of grading can account for the content in the intestinal and carry out quantitative analysis to the intestinal cleanliness factor, has both alleviateed doctor's work burden and work load, realizes real time monitoring inspection quality, can standardize the scope operation again, promotes the all kinds of diseases detectable rate in intestinal.
When the electronic endoscope is used for examining the stomach, the contents of gastric mucus, water bubbles, bile, food residues and the like can only be judged by the operation experience of a doctor whether the contents affect the stomach examination. When more contents exist and gastric mucus is turbid, a doctor can take flushing operation to flush away the contents, so that the examination is facilitated. But whether the flushing operation is needed or not depends on the working experience of doctors, so that the quality of the stomach examination is uneven.
The embodiment also provides a system for scoring the cleanliness of the gastric cavity, which can quantitatively evaluate the cleanliness of the stomach and better guide a doctor whether to adopt a gastric cavity flushing operation. The gastric cavity cleanliness scoring system comprises a scoring system end, a communication end and a client end.
The scoring system end comprises an image receiving module and an algorithm identification module. The image receiving module is used for receiving the image transmitted from the client. The image processing module is used for receiving image data in real time, identifying and processing the image data individually, calling the algorithm model to automatically identify and score the image, and sending the scoring result of the current image to the communication module. And when the scoring result is higher than the set threshold value, sending a voice instruction.
The communication terminal is used for receiving the image data transmitted by the client and performing two-way communication with the client; the communication terminal and the scoring system terminal keep two-way communication, and when receiving the command and the scoring result sent by the scoring system terminal, the communication terminal forwards the command and the scoring result to the client terminal.
The client comprises a communication module, a display module and a voice module. The communication module is used for receiving image data acquired by the electronic endoscope equipment, performing two-way communication with the electronic endoscope equipment and receiving a scoring result and a command sent by the communication terminal; and sending the received image data collected from the electronic endoscope equipment to a communication terminal. The display module is used for displaying the score received from the communication terminal in real time. The voice module is used for receiving a voice command from the communication terminal; when receiving the warning instruction, the voice module sends out an alarm sound to remind a doctor to wash the gastric cavity.
The image processing module of the scoring system comprises: the system comprises a content detection function, a pixel area calculation function, a scoring rule judgment function, a scoring result output function and the like. The content detection function is implemented as follows: by adopting an image segmentation technology, the region of interest containing stomach contents is extracted through characteristics such as color, brightness, texture, boundary and the like. The pixel area calculation function is implemented as follows: calculating the extracted pixel points of the region of interest and determining the pixel area of the region; dividing the pixel area by the pixel area of the whole image to obtain the percentage of the area in the whole image. The scoring rule determination mode includes: the evaluation of the cleanliness of the gastric cavity in the evaluation system is divided into grades according to the percentage of the area of the content in a single picture, which covers the gastric mucosa, in the whole picture, and the grades are divided from poor to good: 4 minutes, namely the content accounts for more than 50 percent of the area, and the observation of the gastric mucosa is seriously influenced; 3 minutes, namely the content accounts for 30 to 50 percent of the specific area, so that the observation of the gastric mucosa is seriously influenced; 2 minutes, namely the content accounts for 15 to 30 percent of the specific area, and the observation of gastric mucosa is generally influenced; 1 minute, namely the content accounts for 5 to 15 percent of the area, and slightly influences the observation of gastric mucosa; 0 minute, namely the content accounts for 0 to 5 percent of the specific area, and the observation of the gastric mucosa is not influenced.
The scoring result output process is as follows: presetting a warning threshold, for example, setting the threshold to 2 points, and when the score is less than 2 points, sending a general instruction; and when the score is greater than or equal to 3 minutes, a warning instruction is sent.
Above-mentioned stomach cavity cleanliness grading system can account for the content in the intestinal and compare the clean degree of stomach cavity and carry out quantitative analysis, has both alleviateed doctor's work burden and work load, realizes real time monitoring inspection quality, can standardize the scope operation again, promotes the all kinds of diseases detectable rate of stomach.
Referring to fig. 4, fig. 4 is a schematic structural view of a cleanliness detection apparatus for an endoscopic examination area according to an embodiment of the present application;
the apparatus may include:
an image segmentation module 100, configured to acquire an endoscopic image and perform an image segmentation operation on the endoscopic image to obtain an image of a region of interest; wherein the image of the region of interest is an image of a region where the contents are located;
a scale calculation module 200, configured to calculate an image scale of the region of interest image in the endoscopic image;
and the cleanliness detection module 300 is used for determining a cleanliness score of the endoscopy region according to the image proportion and outputting a cleanliness detection result according to the cleanliness score.
The present embodiment obtains a region-of-interest image, which is an image of contents affecting the imaging quality of the endoscope, by performing image segmentation on the endoscopic image after the endoscopic image is acquired. The degree of influence of the endoscope image by the contents can be determined according to the image proportion of the region-of-interest image in the endoscope image, and then the cleanliness score of the endoscope examination region can be obtained and the corresponding cleanliness detection result can be deleted. According to the cleanliness detection method and the cleanliness detection system, the cleanliness score can be determined based on the proportion of the image of the region of interest, objective evaluation on cleanliness can be achieved, manual experience is not needed, and therefore the cleanliness detection scheme can improve the accuracy of detecting the cleanliness of the endoscopy region.
Further, the image segmentation module 100 includes:
a feature extraction unit configured to extract an image feature of the endoscopic image; wherein the image features include color information, luminance information, texture information, and boundary information;
and the region-of-interest extracting unit is used for performing image segmentation operation on the endoscope image according to the image characteristics to obtain a region-of-interest image.
Further, the proportion calculation module 200 is configured to count the number of pixel points of the region-of-interest image, and calculate a ratio of the number of pixel points of the region-of-interest image to the number of pixel points of the endoscope image; and the image processing device is also used for setting the proportion of the number of the pixel points as the proportion of the image.
Further, the image segmentation module 100 includes:
an image acquisition unit for acquiring an endoscopic image;
a segmentation unit for performing an image segmentation operation on the endoscopic image to obtain region-of-interest images of a plurality of contents;
accordingly, a scale calculation module 200 is used for calculating the image scale of the image of interest of each of the contents in the endoscopic image.
Further, the cleanliness detection module 300 includes:
the evaluation unit is used for carrying out weighted calculation on the image proportion of the interested image of each content according to the weight value of the content to obtain a cleanliness score of the endoscopy examination area;
and the result output unit is used for outputting a cleanliness detection result according to the cleanliness score.
Further, the cleanliness detection module 300 is configured to determine a cleanliness score of the endoscopy region according to the image proportion, and further determine whether the cleanliness score is within a preset score interval; if so, outputting a clean cleanliness detection result of the endoscopic area; and if not, outputting a cleanliness detection result of the unclean endoscopy examination area.
Further, the method also comprises the following steps:
and the voice broadcasting module is used for sending a voice prompt instruction to the client after outputting a cleanliness detection result that the endoscopy examination area is unclean so that the client can broadcast a flushing operation prompt tone.
Since the embodiments of the apparatus portion and the method portion correspond to each other, please refer to the description of the embodiments of the method portion for the embodiments of the apparatus portion, which is not repeated here.
The present application also provides a storage medium having a computer program stored thereon, which when executed, may implement the steps provided by the above-described embodiments. The storage medium may include: various media capable of storing program codes, such as a usb disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk, or an optical disk.
The application further provides an electronic device, which may include a memory and a processor, where the memory stores a computer program, and the processor may implement the steps provided by the foregoing embodiments when calling the computer program in the memory. Of course, the electronic device may also include various network interfaces, power supplies, and the like.
The embodiments are described in a progressive manner in the specification, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments are referred to each other. The device disclosed by the embodiment corresponds to the method disclosed by the embodiment, so that the description is simple, and the relevant points can be referred to the method part for description. It should be noted that, for those skilled in the art, it is possible to make several improvements and modifications to the present application without departing from the principle of the present application, and such improvements and modifications also fall within the scope of the claims of the present application.
It is further noted that, in the present specification, relational terms such as first and second, and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.
Claims (10)
1. A method for detecting cleanliness of an endoscopic region, comprising:
acquiring an endoscope image, and performing image segmentation operation on the endoscope image to obtain an image of a region of interest; wherein the image of the region of interest is an image of a region where the contents are located;
calculating the image proportion of the region-of-interest image in the endoscope image;
and determining a cleanliness score of the endoscopy examination area according to the image proportion, and outputting a cleanliness detection result according to the cleanliness score.
2. The cleanliness detection method according to claim 1, wherein performing an image segmentation operation on the endoscopic image to obtain a region-of-interest image comprises:
extracting image features of the endoscopic image; wherein the image features include color information, luminance information, texture information, and boundary information;
and performing image segmentation operation on the endoscope image according to the image characteristics to obtain an image of the region of interest.
3. The cleanliness detection method according to claim 1, wherein calculating an image scale of the region-of-interest image in the endoscopic image comprises:
counting the number of pixel points of the interested area image, and calculating the ratio of the number of the pixel points of the interested area image to the number of the pixel points of the endoscope image;
and setting the pixel point quantity proportion as the image proportion.
4. The cleanliness detection method according to claim 1, wherein performing an image segmentation operation on the endoscopic image to obtain a region-of-interest image comprises:
performing image segmentation operation on the endoscope image to obtain an interested area image of a plurality of contents;
correspondingly, calculating the image proportion of the region of interest image in the endoscope image comprises the following steps:
calculating an image scale of the image of interest of each of the contents in the endoscopic image.
5. The cleanliness detection method according to claim 4, wherein determining a cleanliness score of the endoscopic region from the image scale comprises:
and carrying out weighted calculation on the image proportion of the interested image of each content according to the weight value of the content to obtain the cleanliness score of the endoscopic region.
6. A cleanliness detection method according to any one of claims 1 to 5, wherein outputting a cleanliness detection result based on the cleanliness score comprises:
judging whether the cleanliness score is within a preset score interval;
if so, outputting a clean cleanliness detection result of the endoscopic area;
and if not, outputting a cleanliness detection result of the unclean endoscopy examination area.
7. The cleanliness detection method according to claim 6, further comprising, after outputting a cleanliness detection result that the endoscopic examination area is not clean:
and sending a voice prompt instruction to the client so that the client can broadcast the flushing operation prompt tone.
8. A cleanliness detection apparatus for an endoscopic examination region, comprising:
the image segmentation module is used for acquiring an endoscope image and executing image segmentation operation on the endoscope image to obtain an image of a region of interest; wherein the image of the region of interest is an image of a region where the contents are located;
the proportion calculation module is used for calculating the image proportion of the region-of-interest image in the endoscope image;
and the cleanliness detection module is used for determining a cleanliness score of the endoscopic area according to the image proportion and outputting a cleanliness detection result according to the cleanliness score.
9. An electronic apparatus characterized by comprising a memory in which a computer program is stored and a processor which, when calling the computer program in the memory, realizes the steps of the cleanliness detection method of the endoscopic examination region according to any one of claims 1 to 7.
10. A storage medium having stored thereon computer-executable instructions which, when loaded and executed by a processor, carry out the steps of a method of cleanliness detection of an endoscopic examination region according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110249821.9A CN113012162A (en) | 2021-03-08 | 2021-03-08 | Method and device for detecting cleanliness of endoscopy examination area and related equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110249821.9A CN113012162A (en) | 2021-03-08 | 2021-03-08 | Method and device for detecting cleanliness of endoscopy examination area and related equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113012162A true CN113012162A (en) | 2021-06-22 |
Family
ID=76408074
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110249821.9A Pending CN113012162A (en) | 2021-03-08 | 2021-03-08 | Method and device for detecting cleanliness of endoscopy examination area and related equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113012162A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113658179A (en) * | 2021-10-19 | 2021-11-16 | 武汉大学 | Method and device for detecting cleanliness of intestinal tract |
| CN115082448A (en) * | 2022-07-26 | 2022-09-20 | 青岛美迪康数字工程有限公司 | Method and device for scoring cleanliness of intestinal tract and computer equipment |
| WO2023030097A1 (en) * | 2021-09-03 | 2023-03-09 | 北京字节跳动网络技术有限公司 | Method and apparatus for determining cleanliness of tissue cavity, and readable medium and electronic device |
| CN116977253A (en) * | 2022-12-29 | 2023-10-31 | 开立生物医疗科技(武汉)有限公司 | Cleanliness detection method and device for endoscope, electronic equipment and medium |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104936505A (en) * | 2013-01-29 | 2015-09-23 | 捷锐士阿希迈公司(以奥林巴斯美国外科技术名义) | Navigation using pre-acquired image |
| CN107958453A (en) * | 2017-12-01 | 2018-04-24 | 深圳蓝韵医学影像有限公司 | Detection method, device and the computer-readable storage medium of galactophore image lesion region |
| US20190069757A1 (en) * | 2016-05-23 | 2019-03-07 | Olympus Corporation | Endoscopic image processing apparatus |
| US20200008653A1 (en) * | 2017-03-30 | 2020-01-09 | Fujifilm Corporation | Endoscope system and operation method therefor |
| CN111542856A (en) * | 2018-07-16 | 2020-08-14 | 华为技术有限公司 | Skin detection method and electronic equipment |
| CN112085730A (en) * | 2020-09-18 | 2020-12-15 | 上海联影医疗科技股份有限公司 | Region-of-interest component analysis method, device, electronic device and medium |
| CN112330585A (en) * | 2019-07-31 | 2021-02-05 | 北京金山云网络技术有限公司 | Image quality detection method and device and electronic equipment |
-
2021
- 2021-03-08 CN CN202110249821.9A patent/CN113012162A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104936505A (en) * | 2013-01-29 | 2015-09-23 | 捷锐士阿希迈公司(以奥林巴斯美国外科技术名义) | Navigation using pre-acquired image |
| US20190069757A1 (en) * | 2016-05-23 | 2019-03-07 | Olympus Corporation | Endoscopic image processing apparatus |
| US20200008653A1 (en) * | 2017-03-30 | 2020-01-09 | Fujifilm Corporation | Endoscope system and operation method therefor |
| CN107958453A (en) * | 2017-12-01 | 2018-04-24 | 深圳蓝韵医学影像有限公司 | Detection method, device and the computer-readable storage medium of galactophore image lesion region |
| CN111542856A (en) * | 2018-07-16 | 2020-08-14 | 华为技术有限公司 | Skin detection method and electronic equipment |
| CN112330585A (en) * | 2019-07-31 | 2021-02-05 | 北京金山云网络技术有限公司 | Image quality detection method and device and electronic equipment |
| CN112085730A (en) * | 2020-09-18 | 2020-12-15 | 上海联影医疗科技股份有限公司 | Region-of-interest component analysis method, device, electronic device and medium |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2023030097A1 (en) * | 2021-09-03 | 2023-03-09 | 北京字节跳动网络技术有限公司 | Method and apparatus for determining cleanliness of tissue cavity, and readable medium and electronic device |
| CN113658179A (en) * | 2021-10-19 | 2021-11-16 | 武汉大学 | Method and device for detecting cleanliness of intestinal tract |
| CN113658179B (en) * | 2021-10-19 | 2021-12-28 | 武汉大学 | Method and device for detecting cleanliness of intestinal tract |
| CN115082448A (en) * | 2022-07-26 | 2022-09-20 | 青岛美迪康数字工程有限公司 | Method and device for scoring cleanliness of intestinal tract and computer equipment |
| CN116977253A (en) * | 2022-12-29 | 2023-10-31 | 开立生物医疗科技(武汉)有限公司 | Cleanliness detection method and device for endoscope, electronic equipment and medium |
| CN116977253B (en) * | 2022-12-29 | 2024-03-19 | 开立生物医疗科技(武汉)有限公司 | Cleanliness detection method and device for endoscope, electronic equipment and medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113012162A (en) | Method and device for detecting cleanliness of endoscopy examination area and related equipment | |
| EP4018909A1 (en) | Deep learning-based diagnosis assistance system for early digestive tract cancer and examination apparatus | |
| CN109146884B (en) | Endoscopic examination monitoring method and device | |
| CN110916606A (en) | Real-time intestinal cleanliness scoring system and method based on artificial intelligence | |
| EP2181642A1 (en) | Image processing apparatus, image processing program, and image processing method | |
| Kodani et al. | Flexible colonoscopy in mice to evaluate the severity of colitis and colorectal tumors using a validated endoscopic scoring system | |
| EP1994878A1 (en) | Image processing device for medical use and image processing method for medical use | |
| CN110600122A (en) | Digestive tract image processing method and device and medical system | |
| Neumann et al. | Learning curve of virtual chromoendoscopy for the prediction of hyperplastic and adenomatous colorectal lesions: a prospective 2-center study | |
| CN111127426B (en) | Gastric mucosa cleanliness evaluation method and system based on deep learning | |
| CN113017702B (en) | Method and system for identifying extension length of small probe of ultrasonic endoscope and storage medium | |
| WO2020215807A1 (en) | Deep-learning-based method for improving colonoscope adenomatous polyp detection rate | |
| WO2023143014A1 (en) | Endoscope-assisted inspection method and device based on artificial intelligence | |
| CN109859827A (en) | Gastrointestinal Endoscopes operation horizontal points-scoring system and method in real time | |
| CN111839445A (en) | Narrow-band imaging detection method in colonoscopy based on image recognition | |
| CN113052844A (en) | Method and device for processing images in intestinal endoscope observation video and storage medium | |
| CN113962998A (en) | Method and device for evaluating effective endoscope withdrawal time of enteroscopy and storage medium | |
| CN114842000A (en) | Endoscope image quality evaluation method and system | |
| CN114359131A (en) | Helicobacter pylori stomach video full-automatic intelligent analysis system and marking method thereof | |
| JPWO2020152758A1 (en) | Image processing device, diagnostic support method and image processing program | |
| CN115444355B (en) | Endoscope lesion size information determining method, electronic equipment and storage medium | |
| Tran et al. | Support of deep learning to classify vocal fold images in flexible laryngoscopy | |
| WO2013150419A1 (en) | Quality-check during medical imaging procedure | |
| CN113972004A (en) | Deep learning-based multi-model fusion musculoskeletal ultrasonic diagnosis system | |
| CN114730478A (en) | System and method for processing electronic medical images to determine enhanced electronic medical images |
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 | ||
| TA01 | Transfer of patent application right | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20210819 Address after: 401120 1-1, 2-1, 3-1, building 5, No. 18, Cuiping Lane 2, Huixing street, Yubei District, Chongqing Applicant after: Chongqing Jinshan Medical Technology Research Institute Co.,Ltd. Address before: 401120 1 office buildings, Jinshan International Industrial City, 18 of Nei sang Road, Hui Xing street, Yubei District, Chongqing. Applicant before: CHONGQING JINSHAN MEDICAL APPLIANCE Co.,Ltd. |
|
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210622 |