CN119048745A - A patient wound identification system for surgical care - Google Patents
A patient wound identification system for surgical care Download PDFInfo
- Publication number
- CN119048745A CN119048745A CN202411534322.4A CN202411534322A CN119048745A CN 119048745 A CN119048745 A CN 119048745A CN 202411534322 A CN202411534322 A CN 202411534322A CN 119048745 A CN119048745 A CN 119048745A
- Authority
- CN
- China
- Prior art keywords
- wound
- image
- certain
- historical
- area
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/25—Determination of region of interest [ROI] or a volume of interest [VOI]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0012—Biomedical image inspection
-
- 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
- G06T7/62—Analysis of geometric attributes of area, perimeter, diameter or volume
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
- G06V10/761—Proximity, similarity or dissimilarity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/82—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10016—Video; Image sequence
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20081—Training; Learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20084—Artificial neural networks [ANN]
-
- 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
- G06T2207/20112—Image segmentation details
- G06T2207/20132—Image cropping
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Multimedia (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Evolutionary Computation (AREA)
- Software Systems (AREA)
- Artificial Intelligence (AREA)
- Databases & Information Systems (AREA)
- Computing Systems (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Radiology & Medical Imaging (AREA)
- Quality & Reliability (AREA)
- Geometry (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a patient wound identification system for surgical nursing, which comprises an analysis module, a cutting module and a calculation module, wherein the analysis module is configured to acquire a real-time certain wound image, the certain wound image is subjected to similarity analysis with each historical wound image in a first wound image sequence according to a preset image identification model, the cutting module is configured to acquire a certain characteristic image corresponding to the certain historical wound image, the wound area of the certain wound image is cut according to the ratio of the certain characteristic image to the certain historical wound image to obtain a certain target wound image containing a to-be-identified wound area, and the calculation module is configured to slide on the edge of the to-be-identified wound area in the certain target wound image based on a preset dynamic sliding window and calculate the area of the real wound area in the to-be-identified wound area according to an identification result. The pixel point data volume required to be identified subsequently is reduced as much as possible, so that the identification efficiency and accuracy of the wound of the patient are improved.
Description
Technical Field
The invention belongs to the technical field of wound identification, and particularly relates to a patient wound identification system for surgical nursing.
Background
Clinically, the nursing and evaluation of chronic wounds are carried out by taking the length, width, depth and area of the wound surface, the angle and length of the diving/sinus/fistula, and the composition of the wound surface tissue, the liquid-permeable color and liquid-permeable amount, smell, the pain degree and frequency of the wound surface, the surrounding skin state and the like as observation reference indexes of nursing and treatment, so as to carry out wound evaluation, treatment improvement and recovery condition management and monitoring.
However, when the wound surface is photographed, medicines are coated on the wound surface and non-wound surface parts around the wound surface, and at this time, the photographed images are uploaded and recognized, and an interference area can be generated around the wound surface due to the influence of the color of the medicines or other factors, so that the image recognition model is difficult to accurately obtain the real wound surface range, the recognition quantity of the image recognition model is further increased, and the efficiency and the accuracy of the wound surface recognition are further influenced.
Disclosure of Invention
The invention provides a patient wound identification system for surgical nursing, which is used for solving the technical problem that an interference area is generated around a wound surface, so that an image identification model is difficult to accurately obtain the real wound surface range.
The present invention provides a patient wound identification system for surgical care comprising a memory and a processor executing a computer program stored by the memory to effect the steps of:
acquiring an original wound image and at least one historical wound image within a preset historical time period, wherein the original wound image is a wound image which only comprises an uncoated wound area before the preset historical time period, and at least one wound area is contained in any one of the historical wound images;
Sequencing the at least one historical wound image based on a time sequence to obtain a first wound image sequence corresponding to the preset historical time period, and comparing each historical wound image in the first wound image sequence with the original wound image based on a preset comparison rule to obtain a characteristic image corresponding to each historical wound image;
acquiring a real-time certain wound image, respectively carrying out similarity analysis on the certain wound image and each historical wound image in the first wound image sequence according to a preset image recognition model, and screening out a certain historical wound image associated with the certain wound image according to an analysis result, wherein the certain historical wound image is a historical wound image with the highest similarity with the certain wound image in the first wound image sequence;
Acquiring a certain characteristic image corresponding to the certain historical wound image, and cutting a wound area of the certain wound image according to the ratio of the certain characteristic image to the certain historical wound image to obtain a certain target wound image containing a wound area to be identified;
sliding on the edge of a wound area to be identified in the certain target wound image based on a preset dynamic sliding window, and calculating the area of a real wound area in the wound area to be identified according to an identification result, wherein the dynamic sliding window dynamically adjusts the size of the dynamic sliding window according to the current duty ratio of a target pixel point, and the target pixel point is a pixel point in the real wound area.
Further, the comparing each historical wound image in the first wound image sequence with the original wound image based on the preset comparison rule, and obtaining the feature image corresponding to each historical wound image includes:
Aligning a first historical wound image in the first sequence of wound images with the original wound image and determining whether a wound area in the first historical wound image completely covers a wound area in the original wound image;
And if the first characteristic image is completely covered, removing a wound area in the original wound image from the first historical wound image to obtain a first characteristic image corresponding to the first historical wound image.
Further, after determining whether the wound area in the first historical wound image completely covers the wound area in the original wound image, the system further performs the steps of:
And if the first historical wound image is not completely covered, directly taking the image formed by all the features in the first historical wound image as a first feature image corresponding to the first historical wound image.
Further, the cutting the wound area of the certain wound image according to the ratio of the certain characteristic image to the certain historical wound image to obtain a certain target wound image including the wound area to be identified includes:
determining the number of predicted pixels in a predicted feature image corresponding to the certain wound image according to the ratio of the number of pixels in the certain feature image to the number of pixels in the certain historical wound image;
And according to the number of the predicted pixel points, performing pixel point cutting in the wound area of the certain wound image by adopting a preset cutting rule to obtain a certain target wound image containing the wound area to be identified, wherein the cutting rule is to remove the pixel points in a surrounding manner along the direction from the periphery to the inside of the wound area of the certain wound image.
Further, the sliding on the edge of the wound area to be identified in the certain target wound image based on the preset dynamic sliding window comprises:
Acquiring a first number of target pixel points in a dynamic sliding window at the current moment, and adjusting the size of the dynamic sliding window according to the ratio of the first number to the number of all pixel points in the dynamic sliding window, wherein a corresponding relationship with negative correlation exists among the size, the first number and the ratio of the number of all pixel points in the dynamic sliding window;
Continuing to slide the dynamic sliding window with the adjusted size on the edge of the wound area to be identified, and judging that the second number of target pixel points in the dynamic sliding window at the next moment is larger than a preset number threshold;
If the number of the target pixel points is not greater than the preset number threshold, obtaining a second number of the target pixel points in the dynamic sliding window at the next moment, and adjusting the size of the dynamic sliding window again according to the ratio of the second number to the number of all the pixel points in the dynamic sliding window.
Further, after determining that the second number of target pixel points in the dynamic sliding window at the next moment is greater than the preset number threshold, the system further performs the following steps:
and if the dynamic sliding window is larger than the preset quantity threshold, not adjusting the size of the dynamic sliding window at the next moment.
Further, the calculating the area of the real wound area in the wound area to be identified according to the identification result comprises:
Acquiring first target numbers of all target pixel points in a sliding region covered when the dynamic sliding window slides, and acquiring second target numbers of all target pixel points in other regions in the wound region to be identified, wherein the other regions are regions in the wound region to be identified except the sliding region;
and superposing the first target quantity and the second target quantity, and calculating to obtain the area of the real wound area in the wound area to be identified.
According to the patient wound identification system for surgical nursing, a real-time certain wound image is acquired, similarity analysis is carried out on the certain wound image and each historical wound image in the first wound image sequence according to the preset image identification model, and a certain historical wound image related to the certain wound image is screened out according to an analysis result, so that the fact that the certain wound image has the largest similarity, although the interval time distance is long, the change degree of the wound area is not large, the phenomenon is probably caused by the fact that a large interference area exists, namely an unreal wound area, therefore, a certain characteristic image corresponding to the certain historical wound image is acquired, the wound area of the certain wound image is cut according to the ratio of the certain characteristic image to the certain historical wound image, a certain target wound image containing the wound area to be identified is obtained, more unreal wound areas are removed from the certain target wound image compared with the certain characteristic image, the pixel point data quantity required to be identified later is reduced as much as possible, and the problem that the interference area is generated around the wound surface can be solved, and the real model of the wound surface is difficult to obtain the accurate identification range is solved.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for the description of the embodiments will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flowchart of steps performed in a patient wound identification system for surgical care, in accordance with one embodiment of the present invention;
FIG. 2 is a block diagram of a patient wound identification system for surgical care according to one embodiment of the present invention;
Fig. 3 is a schematic structural diagram of an electronic device according to an embodiment of the present invention.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention, and it is apparent that the described embodiments are some embodiments of the present invention, but not all embodiments of the present invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Referring to fig. 1, a flowchart of the steps performed in a patient wound identification system for surgical care of the present application is shown.
As shown in fig. 1, in step S101, an original wound image is acquired, and at least one historical wound image is acquired within a preset historical period, wherein the original wound image is a wound image only including an uncoated wound area before the preset historical period, and at least one wound area is included in any one of the historical wound images.
For example, imaging a wound of a patient before it is needed to be applied at that site can result in a wound image that includes only uncoated wound areas. Further, multiple historical wound images are acquired over a continuous period of time after administration, thereby facilitating subsequent analysis.
Step S102, sorting the at least one historical wound image based on a time sequence to obtain a first wound image sequence corresponding to the preset historical time period, and comparing each historical wound image in the first wound image sequence with the original wound image based on a preset comparison rule to obtain a feature image corresponding to each historical wound image.
In this step, each historical wound image is ordered based on a time sequence, resulting in a first sequence of wound images corresponding to a preset historical time period. Then, aligning a first historical wound image in the first wound image sequence with the original wound image, and judging whether a wound area in the first historical wound image completely covers the wound area in the original wound image, if so, indicating that the acquisition time of the first historical wound image is not far different from the acquisition time of the original wound image, generating a first condition that the wound area in the first historical wound image completely covers the wound area in the original wound image, possibly including an interference area containing medicine, so that the wound area in the original wound image is removed in the first historical wound image, and a first characteristic image corresponding to the first historical wound image is obtained, wherein the first characteristic image is possibly the interference area;
Further, a second case is generated in which the wound area in the first historical wound image completely covers the wound area in the original wound image, and the acquisition time of the first historical wound image is far different from the acquisition time of the original wound image, but the disturbance area containing the medicine is particularly large, so that the second case is caused, and therefore, the wound area containing the original wound image is removed from the first historical wound image, and a first characteristic image corresponding to the first historical wound image is obtained, and the first characteristic image is a partial disturbance area.
It should be noted that the method for aligning the first historical wound image in the first wound image sequence with the original wound image may be that a plurality of identical pixels in the first historical wound image and the original wound image are obtained, and the plurality of identical pixels are aligned, that is, the first historical wound image in the first wound image sequence is aligned with the original wound image.
In one embodiment, after determining whether the wound area in the first historical wound image completely covers the wound area in the original wound image, if not, the image formed by all the features in the first historical wound image is directly taken as the first feature image corresponding to the first historical wound image. In this way, the risk of removing the real wound area can be reduced, and the subsequent area calculation process of the real wound area is not easily affected.
Step S103, acquiring a real-time certain wound image, respectively carrying out similarity analysis on the certain wound image and each historical wound image in the first wound image sequence according to a preset image recognition model, and screening out a certain historical wound image associated with the certain wound image according to an analysis result, wherein the certain historical wound image is a historical wound image with the highest similarity with the certain wound image in the first wound image sequence.
In this step, the image recognition model is VGGNet network model, and the VGGNet network model is adopted to calculate the similarity between a certain wound image and each historical wound image in the first wound image sequence. VGGNet the network model is machine-learned using multiple sets of training images and inspection images.
Step S104, a certain characteristic image corresponding to the certain historical wound image is obtained, and a certain target wound image containing the wound area to be identified is obtained by cutting the wound area of the certain wound image according to the ratio of the certain characteristic image to the certain historical wound image.
In the method, the number of predicted pixels in a predicted feature image corresponding to a certain wound image is determined according to the ratio of the number of pixels in the feature image to the number of pixels in a historical wound image, and pixel point cutting is performed in a wound area of the certain wound image according to the number of predicted pixels by adopting a preset cutting rule to obtain a certain target wound image containing a wound area to be identified, wherein the cutting rule is to remove the pixels in a surrounding manner along the direction from the periphery to the inside of the wound area of the certain wound image. By means of cutting, interference areas in a certain target wound image, such as interference areas generated by medicine colors or other factors, can be reduced as much as possible, so that the amount of data needed to be identified later is reduced.
Step S105, sliding on the edge of the wound area to be identified in the certain target wound image based on a preset dynamic sliding window, and calculating the area of the real wound area in the wound area to be identified according to the identification result, wherein the dynamic sliding window dynamically adjusts the size of the dynamic sliding window according to the current duty ratio of the target pixel point, and the target pixel point is a pixel point in the real wound area.
In the step, a first number of target pixel points in a dynamic sliding window at the current moment is obtained, the size of the dynamic sliding window is adjusted according to the ratio of the first number to the number of all pixel points in the dynamic sliding window, wherein a corresponding relationship of negative correlation exists among the size, the first number and the number of all pixel points in the dynamic sliding window, the dynamic sliding window with the adjusted size continues to slide on the edge of a wound area to be identified, the second number of target pixel points in the dynamic sliding window at the next moment is judged to be larger than a preset number threshold value, if the second number of target pixel points in the dynamic sliding window at the next moment is not larger than the preset number threshold value, the second number of target pixel points in the dynamic sliding window at the next moment is obtained, the size of the dynamic sliding window is adjusted again according to the ratio of the second number to the number of all pixel points in the dynamic sliding window, and if the second number of target pixel points in the dynamic sliding window is larger than the preset number threshold value, the dynamic sliding window at the next moment is not adjusted.
It should be noted that calculating the area of the real wound area in the wound area to be identified according to the identification result includes obtaining a first target number of all target pixels in a sliding area covered when the dynamic sliding window slides, and obtaining a second target number of all target pixels in other areas in the wound area to be identified, wherein the other areas are areas in the wound area to be identified except the sliding area, and superposing the first target number and the second target number, and calculating the area of the real wound area in the wound area to be identified. The process of obtaining the first target number and the second target number can also be achieved through a trained existing neural network.
In summary, the method of the present application obtains a real-time certain wound image, performs similarity analysis on the certain wound image and each historical wound image in the first wound image sequence according to a preset image recognition model, and screens out a certain historical wound image associated with the certain wound image according to an analysis result, so that the maximum similarity indicates that the certain wound image has a long interval time, but the change degree of the wound area is not great, which may cause that a larger interference area exists, namely, a non-real wound area, so that a certain characteristic image corresponding to the certain historical wound image is obtained, the wound area of the certain wound image is cut according to the ratio of the certain characteristic image to the certain historical wound image, a certain target wound image containing the wound area to be recognized is obtained, more non-real wound areas are removed from the certain target wound image compared with the certain characteristic image, and further, the pixel point data amount required to be recognized later is reduced as accurately as possible, and the problem that the interference area is generated around the wound surface of the wound is difficult to obtain the real image recognition model wound surface is solved.
Referring to fig. 2, a block diagram of a patient wound identification system for surgical care of the present application is shown.
As shown in fig. 2, the patient wound identification system 200 includes an acquisition module 210, a comparison module 220, an analysis module 230, a cropping module 240, and a calculation module 250.
The system comprises an acquisition module 210 configured to acquire an original wound image and at least one historical wound image within a preset historical time period, wherein the original wound image is a wound image only comprising an uncoated wound area before the preset historical time period, any one historical wound image comprises at least one wound area, a comparison module 220 configured to sort the at least one historical wound image based on time sequence to obtain a first wound image sequence corresponding to the preset historical time period, compare each historical wound image in the first wound image sequence with the original wound image respectively based on a preset comparison rule to obtain characteristic images corresponding to each historical wound image, an analysis module 230 configured to acquire a real-time wound image, analyze the similarity of each historical wound image in the first wound image sequence according to a preset image identification model, screen out a historical wound image associated with the certain wound image according to the analysis result, wherein the wound image is a wound image sequence corresponding to the first wound image, cut out a certain wound image corresponding to the characteristic image of the certain wound image, and the historical image is obtained by a certain wound image identification module, cut out the wound image corresponding to the certain wound image identification module comprises a certain wound image identification module 250, the method comprises the steps of sliding on the edge of a wound area to be identified in a certain target wound image based on a preset dynamic sliding window, and calculating the area of a real wound area in the wound area to be identified according to an identification result, wherein the dynamic sliding window dynamically adjusts the size of the dynamic sliding window according to the current duty ratio of a target pixel point, and the target pixel point is a pixel point in the real wound area.
It should be understood that the modules depicted in fig. 2 correspond to the various steps in the method described with reference to fig. 1. Thus, the operations and features described above for the method and the corresponding technical effects are equally applicable to the modules in fig. 2, and are not described here again.
In other embodiments, embodiments of the present invention also provide a computer readable storage medium having stored thereon a computer program, which when executed by a processor, causes the processor to perform the patient wound identification method for surgical care of any of the method embodiments described above;
As one embodiment, the computer-readable storage medium of the present invention stores computer-executable instructions configured to:
acquiring an original wound image and at least one historical wound image within a preset historical time period, wherein the original wound image is a wound image which only comprises an uncoated wound area before the preset historical time period, and at least one wound area is contained in any one of the historical wound images;
Sequencing the at least one historical wound image based on a time sequence to obtain a first wound image sequence corresponding to the preset historical time period, and comparing each historical wound image in the first wound image sequence with the original wound image based on a preset comparison rule to obtain a characteristic image corresponding to each historical wound image;
acquiring a real-time certain wound image, respectively carrying out similarity analysis on the certain wound image and each historical wound image in the first wound image sequence according to a preset image recognition model, and screening out a certain historical wound image associated with the certain wound image according to an analysis result, wherein the certain historical wound image is a historical wound image with the highest similarity with the certain wound image in the first wound image sequence;
Acquiring a certain characteristic image corresponding to the certain historical wound image, and cutting a wound area of the certain wound image according to the ratio of the certain characteristic image to the certain historical wound image to obtain a certain target wound image containing a wound area to be identified;
sliding on the edge of a wound area to be identified in the certain target wound image based on a preset dynamic sliding window, and calculating the area of a real wound area in the wound area to be identified according to an identification result, wherein the dynamic sliding window dynamically adjusts the size of the dynamic sliding window according to the current duty ratio of a target pixel point, and the target pixel point is a pixel point in the real wound area.
The computer readable storage medium may include a stored program area that may store an operating system, applications required for at least one function, and a stored data area that may store data created from use of the patient wound identification system for surgical care, etc. In addition, the computer-readable storage medium may include high-speed random access memory, and may also include memory, such as at least one magnetic disk storage device, flash memory device, or other non-volatile solid-state storage device. In some embodiments, the computer readable storage medium optionally includes memory remotely located with respect to the processor, which may be connected to the patient wound identification system for surgical care through a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
Fig. 3 is a schematic structural diagram of an electronic device according to an embodiment of the present invention, and as shown in fig. 3, the device includes a processor 310 and a memory 320. The electronic device may further comprise input means 330 and output means 340. The processor 310, memory 320, input device 330, and output device 340 may be connected by a bus or other means, for example in fig. 3. Memory 320 is the computer-readable storage medium described above. The processor 310 performs various functional applications of the server and data processing, i.e., implements the patient wound identification method for surgical care of the above-described method embodiments, by running non-volatile software programs, instructions, and modules stored in the memory 320. The input device 330 may receive entered numerical or character information and generate key signal inputs related to user settings and functional controls of the patient wound identification system for surgical care. The output device 340 may include a display device such as a display screen.
The electronic equipment can execute the method provided by the embodiment of the invention, and has the corresponding functional modules and beneficial effects of the execution method. Technical details not described in detail in this embodiment may be found in the methods provided in the embodiments of the present invention.
As one embodiment, the electronic device is applied to a patient wound identification system for surgical care and used for a client, and comprises at least one processor and a memory in communication connection with the at least one processor, wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can:
acquiring an original wound image and at least one historical wound image within a preset historical time period, wherein the original wound image is a wound image which only comprises an uncoated wound area before the preset historical time period, and at least one wound area is contained in any one of the historical wound images;
Sequencing the at least one historical wound image based on a time sequence to obtain a first wound image sequence corresponding to the preset historical time period, and comparing each historical wound image in the first wound image sequence with the original wound image based on a preset comparison rule to obtain a characteristic image corresponding to each historical wound image;
acquiring a real-time certain wound image, respectively carrying out similarity analysis on the certain wound image and each historical wound image in the first wound image sequence according to a preset image recognition model, and screening out a certain historical wound image associated with the certain wound image according to an analysis result, wherein the certain historical wound image is a historical wound image with the highest similarity with the certain wound image in the first wound image sequence;
Acquiring a certain characteristic image corresponding to the certain historical wound image, and cutting a wound area of the certain wound image according to the ratio of the certain characteristic image to the certain historical wound image to obtain a certain target wound image containing a wound area to be identified;
sliding on the edge of a wound area to be identified in the certain target wound image based on a preset dynamic sliding window, and calculating the area of a real wound area in the wound area to be identified according to an identification result, wherein the dynamic sliding window dynamically adjusts the size of the dynamic sliding window according to the current duty ratio of a target pixel point, and the target pixel point is a pixel point in the real wound area.
From the above description of the embodiments, it will be apparent to those skilled in the art that the embodiments may be implemented by means of software plus necessary general hardware platforms, or of course may be implemented by means of hardware. Based on such understanding, the foregoing technical solutions may be embodied essentially or in part in the form of a software product, which may be stored in a computer-readable storage medium, such as a ROM/RAM, a magnetic disk, an optical disk, etc., including several instructions to cause a computer device (which may be a personal computer, a server, or a network device, etc.) to perform the various embodiments or methods of some parts of the embodiments.
It should be noted that the above-mentioned embodiments are merely for illustrating the technical solution of the present invention, and not for limiting the same, and although the present invention has been described in detail with reference to the above-mentioned embodiments, it should be understood by those skilled in the art that the technical solution described in the above-mentioned embodiments may be modified or some technical features may be equivalently replaced, and these modifications or substitutions do not make the essence of the corresponding technical solution deviate from the spirit and scope of the technical solution of the embodiments of the present invention.
Claims (7)
1. A patient wound identification system for surgical care comprising a memory and a processor executing a computer program stored by the memory to effect the steps of:
acquiring an original wound image and at least one historical wound image within a preset historical time period, wherein the original wound image is a wound image which only comprises an uncoated wound area before the preset historical time period, and at least one wound area is contained in any one of the historical wound images;
Sequencing the at least one historical wound image based on a time sequence to obtain a first wound image sequence corresponding to the preset historical time period, and comparing each historical wound image in the first wound image sequence with the original wound image based on a preset comparison rule to obtain a characteristic image corresponding to each historical wound image;
acquiring a real-time certain wound image, respectively carrying out similarity analysis on the certain wound image and each historical wound image in the first wound image sequence according to a preset image recognition model, and screening out a certain historical wound image associated with the certain wound image according to an analysis result, wherein the certain historical wound image is a historical wound image with the highest similarity with the certain wound image in the first wound image sequence;
Acquiring a certain characteristic image corresponding to the certain historical wound image, and cutting a wound area of the certain wound image according to the ratio of the certain characteristic image to the certain historical wound image to obtain a certain target wound image containing a wound area to be identified;
sliding on the edge of a wound area to be identified in the certain target wound image based on a preset dynamic sliding window, and calculating the area of a real wound area in the wound area to be identified according to an identification result, wherein the dynamic sliding window dynamically adjusts the size of the dynamic sliding window according to the current duty ratio of a target pixel point, and the target pixel point is a pixel point in the real wound area.
2. The patient wound identification system for surgical care of claim 1, wherein comparing each of the historical wound images in the first sequence of wound images with the original wound image based on a preset comparison rule, respectively, to obtain a feature image corresponding to each of the historical wound images comprises:
Aligning a first historical wound image in the first sequence of wound images with the original wound image and determining whether a wound area in the first historical wound image completely covers a wound area in the original wound image;
And if the first characteristic image is completely covered, removing a wound area in the original wound image from the first historical wound image to obtain a first characteristic image corresponding to the first historical wound image.
3. A patient wound identification system for surgical care according to claim 2, wherein after determining whether a wound area in the first historical wound image completely covers a wound area in the original wound image, the system further performs the steps of:
And if the first historical wound image is not completely covered, directly taking the image formed by all the features in the first historical wound image as a first feature image corresponding to the first historical wound image.
4. A patient wound identification system for surgical care according to claim 1, wherein the cropping the wound area of the certain wound image according to the ratio of the certain characteristic image to the certain historical wound image to obtain a certain target wound image including the wound area to be identified comprises:
determining the number of predicted pixels in a predicted feature image corresponding to the certain wound image according to the ratio of the number of pixels in the certain feature image to the number of pixels in the certain historical wound image;
And according to the number of the predicted pixel points, performing pixel point cutting in the wound area of the certain wound image by adopting a preset cutting rule to obtain a certain target wound image containing the wound area to be identified, wherein the cutting rule is to remove the pixel points in a surrounding manner along the direction from the periphery to the inside of the wound area of the certain wound image.
5. A patient wound identification system for surgical care according to claim 1, wherein the sliding over the edge of the wound area to be identified in the certain target wound image based on a preset dynamic sliding window comprises:
Acquiring a first number of target pixel points in a dynamic sliding window at the current moment, and adjusting the size of the dynamic sliding window according to the ratio of the first number to the number of all pixel points in the dynamic sliding window, wherein a corresponding relationship with negative correlation exists among the size, the first number and the ratio of the number of all pixel points in the dynamic sliding window;
Continuing to slide the dynamic sliding window with the adjusted size on the edge of the wound area to be identified, and judging that the second number of target pixel points in the dynamic sliding window at the next moment is larger than a preset number threshold;
If the number of the target pixel points is not greater than the preset number threshold, obtaining a second number of the target pixel points in the dynamic sliding window at the next moment, and adjusting the size of the dynamic sliding window again according to the ratio of the second number to the number of all the pixel points in the dynamic sliding window.
6. The patient wound identification system for surgical care of claim 5, wherein after determining that the second number of target pixels in the dynamic sliding window at the next time is greater than the preset number threshold, the system further performs the steps of:
and if the dynamic sliding window is larger than the preset quantity threshold, not adjusting the size of the dynamic sliding window at the next moment.
7. A patient wound identification system for surgical care according to claim 1, wherein the calculating the area of the real wound area of the wound area to be identified from the identification result comprises:
Acquiring first target numbers of all target pixel points in a sliding region covered when the dynamic sliding window slides, and acquiring second target numbers of all target pixel points in other regions in the wound region to be identified, wherein the other regions are regions in the wound region to be identified except the sliding region;
and superposing the first target quantity and the second target quantity, and calculating to obtain the area of the real wound area in the wound area to be identified.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202411534322.4A CN119048745A (en) | 2024-10-31 | 2024-10-31 | A patient wound identification system for surgical care |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202411534322.4A CN119048745A (en) | 2024-10-31 | 2024-10-31 | A patient wound identification system for surgical care |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN119048745A true CN119048745A (en) | 2024-11-29 |
Family
ID=93586216
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202411534322.4A Pending CN119048745A (en) | 2024-10-31 | 2024-10-31 | A patient wound identification system for surgical care |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN119048745A (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108814613A (en) * | 2018-05-21 | 2018-11-16 | 中南大学湘雅医院 | Intelligent wound measuring method and mobile measuring terminal |
| CN114913153A (en) * | 2022-05-16 | 2022-08-16 | 北京理工大学 | Deep learning technology-based wound identification and area measurement system and method |
| EP4138033A1 (en) * | 2021-08-18 | 2023-02-22 | Wistron Corporation | Portable electronic device and wound-size measuring method using the same |
| CN117523235A (en) * | 2024-01-02 | 2024-02-06 | 大连壹致科技有限公司 | A patient wound intelligent identification system for surgical nursing |
-
2024
- 2024-10-31 CN CN202411534322.4A patent/CN119048745A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108814613A (en) * | 2018-05-21 | 2018-11-16 | 中南大学湘雅医院 | Intelligent wound measuring method and mobile measuring terminal |
| EP4138033A1 (en) * | 2021-08-18 | 2023-02-22 | Wistron Corporation | Portable electronic device and wound-size measuring method using the same |
| CN114913153A (en) * | 2022-05-16 | 2022-08-16 | 北京理工大学 | Deep learning technology-based wound identification and area measurement system and method |
| CN117523235A (en) * | 2024-01-02 | 2024-02-06 | 大连壹致科技有限公司 | A patient wound intelligent identification system for surgical nursing |
Non-Patent Citations (2)
| Title |
|---|
| HE XC 等: "Integrated Wound Recognition in Bandages for Intelligent Treatment", ADVANCED HEALTHCARE MATERIALS, 30 November 2020 (2020-11-30) * |
| 叶巧玲: "基于深度学习的足部伤口图像分割方法的设计与构建", 黑龙江中医药, 15 October 2023 (2023-10-15) * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109886997B (en) | Identification frame determining method and device based on target detection and terminal equipment | |
| CN110929728B (en) | Image region-of-interest dividing method, image segmentation method and device | |
| KR101640998B1 (en) | Image processing apparatus and image processing method | |
| CN105917353B (en) | Feature extraction and matching for biological identification and template renewal | |
| AU2019345828B2 (en) | Method and apparatus for generating three-dimensional model, device, and storage medium | |
| Kobylin et al. | Comparison of standard image edge detection techniques and of method based on wavelet transform | |
| CN111695462B (en) | Face recognition method, device, storage medium and server | |
| CN111862044A (en) | Ultrasound image processing method, apparatus, computer equipment and storage medium | |
| CN110059700B (en) | Image moire recognition method and device, computer equipment and storage medium | |
| CN108765264B (en) | Image beautifying method, device, equipment and storage medium | |
| CN111914665A (en) | Face shielding detection method, device, equipment and storage medium | |
| CN111815606B (en) | Image quality evaluation method, storage medium, and computing device | |
| CN108734127B (en) | Age identification value adjusting method, age identification value adjusting device, age identification value adjusting equipment and storage medium | |
| CN111862033A (en) | Medical image processing method, device, image processing equipment and storage medium | |
| CN114219936B (en) | Target detection method, electronic device, storage medium and computer program product | |
| Ribeiro et al. | Handling inter-annotator agreement for automated skin lesion segmentation | |
| Almoussa et al. | Automated vasculature extraction from placenta images | |
| CN110111382B (en) | Irregular area calculation method and device, computer equipment and storage medium | |
| DE102020207974B4 (en) | SYSTEMS AND METHODS FOR DETECTING MOTION DURING 3D DATA RECONSTRUCTION | |
| CN102306307A (en) | Positioning method of fixed point noise in color microscopic image sequence | |
| Dwaich et al. | Signature texture features extraction using GLCM approach in android studio | |
| CN109712134B (en) | Iris image quality evaluation method and device and electronic equipment | |
| CN119048745A (en) | A patient wound identification system for surgical care | |
| CN114187303A (en) | Oral cavity image processing method, device, electronic equipment and computer storage medium | |
| JP5383486B2 (en) | Method and apparatus for operating a device for cerebral hemorrhage segmentation |
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 |