CN115019928A - Method, device and equipment for adjusting rehabilitation scheme in real time and readable storage medium - Google Patents
Method, device and equipment for adjusting rehabilitation scheme in real time and readable storage medium Download PDFInfo
- Publication number
- CN115019928A CN115019928A CN202210629259.7A CN202210629259A CN115019928A CN 115019928 A CN115019928 A CN 115019928A CN 202210629259 A CN202210629259 A CN 202210629259A CN 115019928 A CN115019928 A CN 115019928A
- Authority
- CN
- China
- Prior art keywords
- information
- rehabilitation
- rehabilitation training
- training scheme
- medical record
- 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
Images
Classifications
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H20/00—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/05—Detecting, measuring or recording for diagnosis by means of electric currents or magnetic fields; Measuring using microwaves or radio waves
- A61B5/055—Detecting, measuring or recording for diagnosis by means of electric currents or magnetic fields; Measuring using microwaves or radio waves involving electronic [EMR] or nuclear [NMR] magnetic resonance, e.g. magnetic resonance imaging
-
- 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
- G06T7/10—Segmentation; Edge detection
- G06T7/13—Edge detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/70—Determining position or orientation of objects or cameras
- G06T7/73—Determining position or orientation of objects or cameras using feature-based methods
-
- 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
- G06V10/762—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using clustering, e.g. of similar faces in social networks
-
- 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
- G06V10/764—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
-
- 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
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H30/00—ICT specially adapted for the handling or processing of medical images
- G16H30/40—ICT specially adapted for the handling or processing of medical images for processing medical images, e.g. editing
-
- 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
- G06T2207/10072—Tomographic images
- G06T2207/10088—Magnetic resonance imaging [MRI]
-
- 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
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30004—Biomedical image processing
- G06T2207/30016—Brain
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Physics & Mathematics (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Evolutionary Computation (AREA)
- Radiology & Medical Imaging (AREA)
- Public Health (AREA)
- Multimedia (AREA)
- Life Sciences & Earth Sciences (AREA)
- Software Systems (AREA)
- Artificial Intelligence (AREA)
- Databases & Information Systems (AREA)
- Computing Systems (AREA)
- Epidemiology (AREA)
- Primary Health Care (AREA)
- High Energy & Nuclear Physics (AREA)
- Surgery (AREA)
- Animal Behavior & Ethology (AREA)
- Veterinary Medicine (AREA)
- Molecular Biology (AREA)
- Heart & Thoracic Surgery (AREA)
- Biomedical Technology (AREA)
- Pathology (AREA)
- Biophysics (AREA)
- Quality & Reliability (AREA)
- Magnetic Resonance Imaging Apparatus (AREA)
Abstract
The invention relates to the field of auxiliary diagnosis and treatment, in particular to a method, a device, equipment and a readable storage medium for adjusting a rehabilitation scheme in real time, wherein the method comprises the steps of sending medical record information of a patient to a clustering model for classification to obtain medical record information of at least one category; sending all the categories of medical record information to a first rehabilitation training scheme distribution model for processing to obtain a first rehabilitation training scheme corresponding to the medical record information of each category; then acquiring real-time magnetic resonance imaging information of focus change in the rehabilitation training process of the patient; and sending the second information to the trained neural network model for processing to obtain a redistributed second rehabilitation training scheme. The focus change state is monitored in real time through magnetic imaging, the rehabilitation effect of the rehabilitation training scheme is judged, the rehabilitation scheme is redistributed, the pertinence of scheme distribution is increased by adopting a trained neural network model, the randomness of scheme distribution is reduced, and the rehabilitation training effect of a patient is increased.
Description
Technical Field
The invention relates to the field of auxiliary diagnosis and treatment, in particular to a method, a device, equipment and a readable storage medium for adjusting a rehabilitation scheme in real time.
Background
Stroke is also called stroke and cerebrovascular accident, and is an acute cerebrovascular disease, which is a group of diseases causing brain tissue damage caused by sudden rupture of cerebral vessels or blood failure to flow into brain due to vessel occlusion, including ischemic and hemorrhagic stroke. The method and the device are used for performing rehabilitation training after stroke treatment, people in the prior art adopt a scheme to perform rehabilitation treatment on patients, good rehabilitation effect cannot be achieved, the rehabilitation state of the patients can be monitored in real time, and the rehabilitation scheme can be adjusted in real time according to the rehabilitation state, so that the rehabilitation effect of the patients is enhanced, and the rehabilitation time and cost are reduced.
Disclosure of Invention
The present invention aims to provide a method, an apparatus, a device and a readable storage medium for adjusting a rehabilitation program in real time to improve the above problems. In order to achieve the purpose, the technical scheme adopted by the invention is as follows:
in one aspect, the present application provides a method for adjusting a rehabilitation regimen in real time, the method comprising: acquiring first information, wherein the first information is medical record information of a magnetic resonance image containing a stroke focus; sending the first information to a clustering model for classification to obtain medical record information of at least one category; sending all the categories of medical record information to a first rehabilitation training scheme distribution model for processing to obtain a first rehabilitation training scheme corresponding to the medical record information of each category; acquiring second information, wherein the second information comprises magnetic resonance imaging information of real-time lesion change in the rehabilitation training process of a patient; and sending the second information to the trained neural network model for processing to obtain a redistributed second rehabilitation training scheme, wherein the neural network model is a model for adjusting parameters of the neural network model based on the second information and determining the second rehabilitation training scheme.
In a second aspect, an embodiment of the present application provides an apparatus for adjusting a rehabilitation regimen in real time, including:
the first acquisition unit is used for acquiring first information, wherein the first information is medical record information of a magnetic resonance image containing a stroke focus;
the classification unit is used for sending the first information to a clustering model for classification to obtain medical record information of at least one category;
the first distribution unit is used for sending all the types of medical record information to the first rehabilitation training scheme distribution model for processing to obtain a first rehabilitation training scheme corresponding to the medical record information of each type;
the second acquisition unit is used for acquiring second information, and the second information comprises magnetic resonance imaging information of real-time focus change in the rehabilitation training process of the patient;
and the second distribution unit is used for sending the second information to the trained neural network model for processing to obtain a redistributed second rehabilitation training scheme, and the neural network model is a model for adjusting parameters of the neural network model based on the second information and determining the second rehabilitation training scheme.
In a third aspect, an embodiment of the present application provides an apparatus for adjusting a rehabilitation regimen in real time, where the apparatus includes a memory and a processor. The memory is used for storing a computer program; the processor is used for realizing the steps of the method for adjusting the rehabilitation scheme in real time when executing the computer program.
In a fourth aspect, the present application provides a readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements the steps of the method for adjusting a rehabilitation regimen in real time.
The invention has the beneficial effects that:
according to the method, the focus of the cerebral apoplexy patient after the rehabilitation training is monitored in real time by adopting a magnetic resonance imaging mode, the change condition of the focus of the cerebral apoplexy patient after the rehabilitation training is judged, and the rehabilitation training scheme is redistributed based on the change condition of the focus.
Additional features and advantages of the invention will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by the practice of the embodiments of the invention. The objectives and other advantages of the invention will be realized and attained by the structure particularly pointed out in the written description and claims hereof as well as the appended drawings.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings needed to be used in the embodiments will be briefly described below, it should be understood that the following drawings only illustrate some embodiments of the present invention and therefore should not be considered as limiting the scope, and for those skilled in the art, other related drawings can be obtained according to the drawings without inventive efforts.
FIG. 1 is a schematic flow chart illustrating a method for adjusting a rehabilitation regimen in real time according to an embodiment of the present invention;
FIG. 2 is a schematic structural diagram of an apparatus for real-time adjustment of a rehabilitation regimen according to an embodiment of the present invention;
fig. 3 is a schematic structural diagram of an apparatus for adjusting a rehabilitation regimen in real time according to an embodiment of the present invention.
The labels in the figure are: 701. a first acquisition unit; 702. a classification unit; 703. a first distribution unit; 704. a second acquisition unit; 705. a second distributing unit; 7021. a first processing subunit; 7022. a second processing subunit; 7023. a third processing subunit; 7024. a first clustering subunit; 7025. a second clustering subunit; 7031. a fourth processing subunit; 7032. a calculation subunit; 7033. a first comparison subunit; 7034. an iteration subunit; 7051. a second comparison subunit; 7052. a first judgment subunit; 7053. a fifth processing subunit; 7054. a second judgment subunit; 70511. a sixth processing subunit; 70512. a seventh processing subunit; 70513. a third comparison subunit; 70514. a third judgment subunit; 70541. acquiring a subunit; 70542. an eighth processing subunit; 70543. a fourth judgment subunit; 70544. a fifth judging subunit; 800. a device to adjust the rehabilitation regimen in real time; 801. a processor; 802. a memory; 803. a multimedia component; 804. an I/O interface; 805. a communication component.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present invention. The components of embodiments of the present invention generally described and illustrated in the figures herein may be arranged and designed in a wide variety of different configurations. Thus, the following detailed description of the embodiments of the present invention, presented in the figures, is not intended to limit the scope of the invention, as claimed, but is merely representative of selected embodiments of the invention. 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 invention.
It should be noted that: like reference numbers and letters refer to like items in the following figures, and thus, once an item is defined in one figure, it need not be further defined and explained in subsequent figures. Meanwhile, in the description of the present invention, the terms "first", "second", and the like are used only for distinguishing the description, and are not to be construed as indicating or implying relative importance.
Example 1
As shown in fig. 1, the present embodiment provides a method for adjusting a rehabilitation regimen in real time, which includes step S1, step S2, step S3, step S4 and step S5.
Step S1, acquiring first information, wherein the first information is medical record information of a magnetic resonance image containing a stroke focus;
the medical record information acquisition device comprises a medical record acquisition module, a storage device and a magnetic resonance imaging module, wherein the medical record acquisition module is used for acquiring a medical record of a cerebral apoplexy patient, and the medical record acquisition module is used for acquiring a medical record of the cerebral apoplexy patient.
Step S2, sending the first information to a clustering model for classification to obtain medical record information of at least one category;
the focus images are clustered through the clustering model, and the focus images are classified according to the focus positions and the focus range of the patient, so that the classification accuracy can be improved, and more accurate data can be provided for determining a rehabilitation training scheme later.
Step S3, sending all the medical record information of the categories to a first rehabilitation training scheme distribution model for processing to obtain a first rehabilitation training scheme corresponding to the medical record information of each category;
and step S4, acquiring second information, wherein the second information comprises magnetic resonance imaging information of real-time lesion change in the rehabilitation training process of the patient.
The method can be understood that after the focus images are classified, iterative optimization is performed on the rehabilitation training scheme based on the particle swarm optimization algorithm to obtain the optimal rehabilitation training scheme, training is performed based on the optimal rehabilitation training scheme, focus image information is monitored in real time, change images of the focus in the training process are obtained, and the change images are uploaded to the storage device.
It is understood that all images in this application are images obtained by magnetic resonance imaging, or images obtained by processing images obtained by magnetic resonance imaging.
The understandable patient can acquire the magnetic resonance image of focus in real time after the rehabilitation training, and will the magnetic resonance image is uploaded, the magnetic resonance image can have portable magnetic resonance image to generate the instrument and acquire, then compare the image before and after training, and then can judge whether rehabilitation training is effective.
And step S5, sending the second information to the trained neural network model for processing to obtain a redistributed second rehabilitation training scheme, wherein the neural network model is a model for adjusting parameters of the neural network model based on the second information and determining the second rehabilitation training scheme.
The method comprises the steps of monitoring the focus of a stroke patient after rehabilitation training in real time by adopting a magnetic resonance imaging mode, judging the change condition of the focus of the stroke patient after rehabilitation training, and redistributing a rehabilitation training scheme based on the change condition of the focus.
It can be understood that the rehabilitation effect is graded, and whether the first rehabilitation training scheme meets the requirements or not is judged according to the rehabilitation grade obtained through grading, if the first rehabilitation training scheme does not meet the requirements, the scheme is redistributed based on the neural network model, and the situation that the expected rehabilitation effect cannot be obtained all the time when the first rehabilitation training scheme is used is avoided, so that a large amount of time and cost are wasted.
In a specific embodiment of the present disclosure, the step S2 includes a step S21, a step S22, a step S23, a step S24, and a step S25.
Step S21, sending the magnetic resonance image of the cerebral apoplexy focus to a target detection model for target detection to obtain focus image information of a patient;
step S22, obtaining the focus range and the focus position in the focus image information of each patient based on the focus image information of the patient;
it can be understood that the present application determines which position the patient's lesion image is located and the size of the patient's lesion image by performing target detection on the magnetic resonance image of the patient's lesion, and then determines the category of the lesion based on the location of the lesion image and the size of the lesion image.
Step S23, numbering the focus range and focus position in the focus image information of the patient to obtain the numbering information of each focus image information;
it can be understood that the range and position of the focus of the lesion are respectively labeled, the focus is further divided in detail, the focuses in different ranges and different positions are numbered in a one-to-one correspondence manner, and the type of the focus to which the focus belongs can be determined.
S24, clustering the first number information based on a clustering algorithm of distance classes to obtain at least one cluster;
and step S25, calculating to obtain a threshold range corresponding to each clustering category based on the Lauda criterion, and classifying the medical record information of the patient according to the threshold range to obtain the medical record information of at least one category.
The medical record information of at least one category is obtained by clustering the number information, determining the size range of the focus of each category and the position range of the focus of each category, classifying the focus images through different ranges, and mapping the medical record information of each focus image based on the focus images of different categories one by one, so that the medical record information of the patient can be classified quickly and effectively, and a rehabilitation training scheme can be formulated in a targeted manner.
In a specific embodiment of the present disclosure, the step S3 includes a step S31, a step S32, a step S33, and a step S34.
Step S31, initializing preset first rehabilitation training scheme information, wherein each preset first rehabilitation training scheme information is used as a single individual to be placed in a particle swarm to obtain initialized first rehabilitation training scheme information;
step S32, calculating the fitness value of each preset first rehabilitation training scheme information and all the categories of medical record information;
it can be understood that the fitness value in the present application refers to a numerical value obtained by performing a dimensionless quantization on an effect generated by rehabilitation on patients with medical record information of each category based on each rehabilitation training scheme and performing the effect on the patient based on each rehabilitation training scheme, where the fitness value may represent the effect generated by rehabilitation training on the patient based on each rehabilitation training scheme, and the larger the numerical value is, the better the effect is.
Step S33, comparing the fitness value with a preset fitness threshold value, and if the fitness value is larger than the preset fitness threshold value, enabling the fitness value to be the latest fitness threshold value;
and step S34, repeating the previous step until the maximum fitness value corresponding to each rehabilitation training scheme is determined, and taking the first rehabilitation training scheme corresponding to each maximum fitness value as the first rehabilitation training scheme corresponding to the medical record information of each category.
It can be understood that the above steps are to determine the training scheme with the best rehabilitation effect corresponding to the medical record of each category through the particle swarm optimization algorithm, and to use the training scheme with the best rehabilitation effect corresponding to the medical record of each category as the rehabilitation training scheme for the patient with the medical record of that category, so that the first training scheme determination is performed on the existing medical record by referring to the history scheme information, thereby reducing trial and error cost, reducing scheme adjustment times, and ensuring high efficiency and high quality of rehabilitation.
In a specific embodiment of the present disclosure, the step S5 includes a step S51, a step S52, a step S53, and a step S54.
Step S51, sending the second information to a rehabilitation characteristic comparison module for comparison to obtain rehabilitation effect characteristics corresponding to the second information;
step S52, sending the rehabilitation effect characteristics corresponding to the second information to a grade judgment module for judgment to obtain the rehabilitation effect grade of the stroke patient;
step S53, mapping the rehabilitation effect grade of the stroke patient and the first rehabilitation training scheme one by one to obtain the rehabilitation evaluation grade corresponding to each first rehabilitation training scheme;
and step S54, respectively comparing the rehabilitation evaluation grade corresponding to each first rehabilitation training scheme with a preset grade, and sending the first rehabilitation training scheme with the evaluation grade smaller than the preset grade to the trained neural network model for redistribution to obtain a second rehabilitation scheme.
It can be understood that the invention firstly obtains the rehabilitation effect characteristic corresponding to the second information by comparing the magnetic resonance images before and after the rehabilitation training, and judges whether the rehabilitation effect characteristic is recovering or aggravating the state of an illness, if so, immediately adjusts the rehabilitation training scheme, if so, grades the rehabilitation effect characteristic, judges whether the grade of the rehabilitation effect characteristic meets the preset grade requirement, if less than the preset grade requirement, redistributes the scheme by using the trained neural network model, and the trained neural network model is the model based on the scheme characteristic not meeting the requirement, and redistributes the rehabilitation training scheme.
In a specific embodiment of the present disclosure, the step S51 includes steps S511, S512, S513, and 5414.
Step S511, converting the second information into a single-channel gray-scale image, and extracting a focus edge contour in the single-channel gray-scale image;
step S512, determining third information based on the focus edge contour, wherein the third information comprises range information of the focus after the rehabilitation training and range information position information of the focus after the rehabilitation training;
step S513, comparing the third information with corresponding information in the first information to obtain the change area information of the focus, wherein the corresponding information in the first information is the range information of the focus and the position information of the focus in the medical record information;
step S514, judging whether the change area of the focus is positioned in the focus area of the medical record, if the change area of the focus is positioned in the focus area of the medical record, marking the change area as a first characteristic, and if the change area of the focus is positioned outside the focus area in the medical record, marking the change area as a second characteristic.
It can be understood that the invention performs grey-scale image channel extraction on the second information, extracts the focus edge contour in the single-channel grey-scale image, and further judges the range information of the focus based on the focus edge contour, and further judges whether the range information of the focus after the rehabilitation training changes, if so, the focus is changed or changed, or the position of the focus is changed or not, and further obtains the change characteristic, so as to judge whether the rehabilitation training achieves the due effect.
In a specific embodiment of the present disclosure, the step S54 includes steps S541, S542, S543, and S544.
Step S541, acquiring a historical first rehabilitation training scheme and a historical rehabilitation evaluation grade;
step S542, reallocating a historical first rehabilitation training scheme with a historical rehabilitation evaluation grade smaller than a preset grade on the basis of a neural network, wherein the reallocating is that a scheme different from the historical first rehabilitation training scheme is selected from a plurality of rehabilitation training schemes of the same focus to obtain a historical second rehabilitation training scheme;
step S543, judging whether the rehabilitation evaluation grade corresponding to the historical second rehabilitation training scheme is larger than a preset grade or not to obtain a judgment result;
and S544, if the judgment result is that the rehabilitation evaluation grade corresponding to the historical second rehabilitation training scheme is smaller than or equal to the preset grade, adjusting the distribution coefficient in the neural network model, and redistributing the historical second rehabilitation training scheme until the rehabilitation evaluation grade corresponding to the historical second rehabilitation training scheme is larger than the preset grade.
The first rehabilitation training scheme is redistributed through the neural network model, all the evaluation levels of the second rehabilitation training schemes are traversed, and the historical second rehabilitation training schemes with the levels larger than the second level are used as final schemes by adjusting the distribution coefficients in the neural network model, so that the trained neural network model is obtained.
Example 2
As shown in fig. 2, the present embodiment provides a device for real-time adjustment of a rehabilitation regimen, which includes a first obtaining unit 701, a classifying unit 702, a first distributing unit 703, a second obtaining unit 704, and a second distributing unit 705.
A first obtaining unit 701, configured to obtain first information, where the first information is medical record information of a magnetic resonance image including a stroke focus;
the classification unit 702 is configured to send the first information to a clustering model for classification, so as to obtain medical record information of at least one category;
the first allocation unit 703 is configured to send all categories of medical record information to the first rehabilitation training scheme allocation model for processing, so as to obtain a first rehabilitation training scheme corresponding to each category of medical record information;
a second obtaining unit 704, configured to obtain second information, where the second information includes magnetic resonance imaging information of a real-time lesion change in a rehabilitation training process of a patient;
the second allocating unit 705 is configured to send the second information to the trained neural network model for processing, so as to obtain a second re-allocated rehabilitation training scheme, where the neural network model is a model that adjusts parameters of the neural network model based on the second information and determines the second rehabilitation training scheme.
In a specific embodiment of the present disclosure, the classifying unit 702 includes a first processing sub-unit 7021, a second processing sub-unit 7022, a third processing sub-unit 7023, a first clustering sub-unit 7024, and a second clustering sub-unit 7025.
The first processing subunit 7021 is configured to send the magnetic resonance image of the stroke lesion to a target detection model for target detection, so as to obtain lesion image information of the patient;
a second processing subunit 7022, configured to obtain a lesion range and a lesion position in the lesion image information of each patient based on the lesion image information of the patient;
a third processing subunit 7023, configured to number a lesion range and a lesion position in the lesion image information of the patient, to obtain number information of each lesion image information;
a first clustering subunit 7024, configured to cluster the first number information based on a distance-class clustering algorithm to obtain at least one clustered cluster;
the second clustering subunit 7025 is configured to obtain a threshold range corresponding to each clustering category through calculation based on the ralida criterion, and classify medical record information of the patient according to the threshold range to obtain medical record information of at least one category.
In a specific embodiment of the present disclosure, the first allocating unit 703 includes a fourth processing subunit 7031, a calculating subunit 7032, a first comparing subunit 7033, and an iterating subunit 7034.
A fourth processing subunit 7031, configured to perform initialization processing on preset first rehabilitation training scheme information, where each preset first rehabilitation training scheme information is placed in a particle swarm as a single individual, so as to obtain initialized first rehabilitation training scheme information;
a calculating subunit 7032, configured to calculate fitness values of each of the preset first rehabilitation training regimen information and the medical record information of all categories;
a first comparing subunit 7033, configured to compare the fitness value with a preset fitness threshold, and if the fitness value is greater than the preset fitness threshold, the fitness value is the latest fitness threshold;
an iteration subunit 7034, configured to repeat the previous iteration step until the maximum fitness value corresponding to each rehabilitation training scheme is determined, and use the first rehabilitation training scheme corresponding to each maximum fitness value as the first rehabilitation training scheme corresponding to the medical record information of each category.
In an embodiment of the present disclosure, the second allocating unit 705 includes a second comparing sub-unit 7051, a first determining sub-unit 7052, a fifth processing sub-unit 7053, and a second determining sub-unit 7054.
The second comparing subunit 7051 is configured to send the second information to the rehabilitation characteristic comparing module for comparison, so as to obtain a rehabilitation effect characteristic corresponding to the second information;
the first judging subunit 7052 is configured to send the rehabilitation effect characteristic corresponding to the second information to the level judging module for judgment, so as to obtain a rehabilitation effect level of the stroke patient;
a fifth processing subunit 7053, configured to be the sixth processing subunit, and configured to perform one-to-one mapping on the rehabilitation effect level of the stroke patient and the first rehabilitation training schemes to obtain a rehabilitation evaluation level corresponding to each first rehabilitation training scheme;
a second judging subunit 7054, configured to compare the rehabilitation evaluation level corresponding to each first rehabilitation training scheme with a preset level, and send the first rehabilitation training scheme with the evaluation level smaller than the preset level to the trained neural network model for redistribution, so as to obtain a second rehabilitation scheme.
In an embodiment of the present disclosure, the second comparing sub-unit 7051 includes a sixth processing sub-unit 70511, a seventh processing sub-unit 70512, a third comparing sub-unit 70513, and a third determining sub-unit 70514.
A sixth processing subunit 70511, configured to convert the second information into a single-channel grayscale map, and extract a lesion edge contour in the single-channel grayscale map;
a seventh processing subunit 70512, configured to determine third information based on the lesion edge contour, where the third information includes range information of a lesion after rehabilitation training and range information position information of the lesion after rehabilitation training;
a third comparing subunit 70513, configured to compare the third information with corresponding information in the first information to obtain change area information of the lesion, where the corresponding information in the first information is range information of the lesion and position information of the lesion in the medical record information;
a third determining subunit 70514, configured to determine whether the change area of the lesion is located in a lesion area of a medical record, mark the change area as a first feature if the change area of the lesion is located in the lesion area of the medical record, and mark the change area as a second feature if the change area of the lesion is located outside the lesion area in the medical record.
In one embodiment of the present disclosure, the third processing unit 704 includes an obtaining sub-unit 70541, an eighth processing sub-unit 70542, a fourth determining sub-unit 70543, and a fifth determining sub-unit 70544.
An obtaining subunit 70541, configured to obtain a historical first rehabilitation training scenario and a historical rehabilitation evaluation level;
an eighth processing subunit 70542, configured to reallocate the historical first rehabilitation training scenario of which the historical rehabilitation evaluation level is smaller than the preset level based on the neural network, where the reallocation is to select a scenario different from the historical first rehabilitation training scenario among multiple rehabilitation training scenarios of the same lesion, so as to obtain a historical second rehabilitation training scenario;
a fourth judging subunit 70543, configured to judge whether the rehabilitation evaluation level corresponding to the historical second rehabilitation training scenario is greater than a preset level, so as to obtain a judgment result;
a fifth determining subunit 70544, if the determination result is that the rehabilitation evaluation level corresponding to the historical second rehabilitation training regimen is less than or equal to the preset level, adjusting the distribution coefficient in the neural network model, and reallocating the historical second rehabilitation training regimen until the rehabilitation evaluation level corresponding to the historical second rehabilitation training regimen is greater than the preset level.
It should be noted that, regarding the apparatus in the above embodiment, the specific manner in which each module performs the operation has been described in detail in the embodiment related to the method, and will not be elaborated herein.
Example 3
Corresponding to the above method embodiment, the present disclosure further provides a device for adjusting a rehabilitation program in real time, and the device for adjusting a rehabilitation program in real time described below and the method for adjusting a rehabilitation program in real time described above may be referred to correspondingly.
Fig. 3 is a block diagram illustrating a device 800 for real-time adjustment of a rehabilitation regimen according to an exemplary embodiment. As shown in fig. 3, the apparatus 800 for real-time adjustment of a rehabilitation regimen may include: a processor 801, a memory 802. The device 800 for real-time adjustment of a rehabilitation regimen may further include one or more of a multimedia component 803, an I/O interface 804, and a communication component 805.
The processor 801 is configured to control the overall operation of the apparatus 800 for real-time adjustment of a rehabilitation program, so as to complete all or part of the steps of the method for real-time adjustment of a rehabilitation program. The memory 802 is used to store various types of data to support the operation of the device 800 for adjusting a rehabilitation regimen in real-time, which data may include, for example, instructions for any application or method operating on the device 800 for adjusting a rehabilitation regimen in real-time, as well as application-related data, such as contact data, messages sent or received, pictures, audio, video, and the like. The Memory 802 may be implemented by any type of volatile or non-volatile Memory device or combination thereof, such as Static Random Access Memory (SRAM), Electrically Erasable Programmable Read-Only Memory (EEPROM), Erasable Programmable Read-Only Memory (EPROM), Programmable Read-Only Memory (PROM), Read-Only Memory (ROM), magnetic Memory, flash Memory, magnetic disk or optical disk. The multimedia components 803 may include screen and audio components. Wherein the screen may be, for example, a touch screen and the audio component is used for outputting and/or inputting audio signals. For example, the audio component may include a microphone for receiving external audio signals. The received audio signal may further be stored in the memory 802 or transmitted through the communication component 805. The audio assembly also includes at least one speaker for outputting audio signals. The I/O interface 804 provides an interface between the processor 801 and other interface modules, such as a keyboard, mouse, buttons, and the like. These buttons may be virtual buttons or physical buttons. The communication component 805 is used for wired or wireless communication between the device 800 for real-time adjustment of the rehabilitation regimen and other devices. Wireless communication, such as Wi-Fi, bluetooth, Near Field Communication (NFC), 2G, 3G, or 4G, or a combination of one or more of them, so that the corresponding communication component 805 may include: Wi-Fi module, bluetooth module, NFC module.
In an exemplary embodiment, the Device 800 for adjusting the rehabilitation program in real time may be implemented by one or more Application Specific Integrated Circuits (ASICs), Digital Signal Processors (DSPs), Digital Signal Processing Devices (DSPDs), Programmable Logic Devices (PLDs), Field Programmable Gate Arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic components for performing one of the above-described methods for adjusting the rehabilitation program in real time.
In another exemplary embodiment, a computer readable storage medium comprising program instructions which, when executed by a processor, implement the steps of the above-described method of real-time adjustment of a rehabilitation regimen is also provided. For example, the computer readable storage medium may be the memory 802 described above comprising program instructions executable by the processor 801 of the device 800 for real-time adjustment of a rehabilitation protocol to perform the method for real-time adjustment of a rehabilitation protocol described above.
Example 4
Corresponding to the above method embodiment, the disclosed embodiment further provides a readable storage medium, and a readable storage medium described below and a method for adjusting a rehabilitation regimen in real time described above may be referred to correspondingly.
A readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method of real-time adjustment of a rehabilitation protocol of the above-mentioned method embodiment.
The readable storage medium may be a usb disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and various other readable storage media capable of storing program codes.
The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
The above description is only for the specific embodiments of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art can easily conceive of the changes or substitutions within the technical scope of the present invention, and all the changes or substitutions should be covered within the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.
Claims (10)
1. A method of adjusting a rehabilitation regimen in real-time, comprising:
acquiring first information, wherein the first information is medical record information of a magnetic resonance image containing a stroke focus;
sending the first information to a clustering model for classification to obtain medical record information of at least one category;
sending all the categories of medical record information to a first rehabilitation training scheme distribution model for processing to obtain a first rehabilitation training scheme corresponding to the medical record information of each category;
acquiring second information, wherein the second information comprises magnetic resonance imaging information of real-time lesion change in the rehabilitation training process of a patient;
and sending the second information to the trained neural network model for processing to obtain a redistributed second rehabilitation training scheme, wherein the neural network model is a model for adjusting parameters of the neural network model based on the second information and determining the second rehabilitation training scheme.
2. The method of claim 1, wherein sending the first information to a clustering model for classification to obtain medical record information of at least one category comprises:
sending the magnetic resonance image of the cerebral apoplexy focus to a target detection model for target detection to obtain focus image information of a patient;
acquiring a focus range and a focus position in focus image information of each patient based on the focus image information of the patient;
numbering the focus range and the focus position in the focus image information of the patient to obtain the numbering information of each focus image information;
clustering the first number information based on a clustering algorithm of distance classes to obtain at least one cluster family;
and calculating to obtain a threshold range corresponding to each clustering category based on a Lauda criterion, and classifying the medical record information of the patient according to the threshold range to obtain the medical record information of at least one category.
3. The method for adjusting a rehabilitation regimen in real time according to claim 1, wherein the step of sending all the categories of medical record information to the first rehabilitation regimen allocation model for processing to obtain the first rehabilitation regimen corresponding to the medical record information of each category comprises:
initializing preset first rehabilitation training scheme information, wherein each preset first rehabilitation training scheme information is used as a single individual to be placed in a particle swarm to obtain initialized first rehabilitation training scheme information;
calculating the fitness value of each preset first rehabilitation training scheme information and the medical record information of all categories;
comparing the fitness value with a preset fitness threshold, and if the fitness value is greater than the preset fitness threshold, enabling the fitness value to be the latest fitness threshold;
and repeating the iteration of the previous step until the maximum fitness value corresponding to each rehabilitation training scheme is determined, and taking the first rehabilitation training scheme corresponding to each maximum fitness value as the first rehabilitation training scheme corresponding to the medical record information of each category.
4. The method of adjusting a rehabilitation regimen in real-time according to claim 1, wherein sending the second information to the trained neural network model for processing to obtain a redistributed second rehabilitation regimen comprises:
sending the second information to a rehabilitation characteristic comparison module for comparison to obtain rehabilitation effect characteristics corresponding to the second information;
sending the rehabilitation effect characteristics corresponding to the second information to a grade judgment module for judgment to obtain the rehabilitation effect grade of the stroke patient;
mapping the rehabilitation effect grade of the stroke patient and the first rehabilitation training scheme one by one to obtain a rehabilitation evaluation grade corresponding to each first rehabilitation training scheme;
and comparing the rehabilitation evaluation grade corresponding to each first rehabilitation training scheme with a preset grade, and sending the first rehabilitation training scheme with the evaluation grade smaller than the preset grade to the trained neural network model for redistribution to obtain a second rehabilitation scheme.
5. An apparatus for adjusting a rehabilitation regimen in real time, comprising:
the first acquisition unit is used for acquiring first information, wherein the first information is medical record information of a magnetic resonance image containing a stroke focus;
the classification unit is used for sending the first information to a clustering model for classification to obtain medical record information of at least one category;
the first distribution unit is used for sending all the types of medical record information to the first rehabilitation training scheme distribution model for processing to obtain a first rehabilitation training scheme corresponding to the medical record information of each type;
the second acquisition unit is used for acquiring second information, and the second information comprises magnetic resonance imaging information of real-time focus change in the rehabilitation training process of the patient;
and the second distribution unit is used for sending the second information to the trained neural network model for processing to obtain a redistributed second rehabilitation training scheme, and the neural network model is a model for adjusting parameters of the neural network model based on the second information and determining the second rehabilitation training scheme.
6. The device for real-time adjustment of a rehabilitation program according to claim 5, characterized in that it comprises:
the first processing subunit is used for sending the magnetic resonance image of the cerebral apoplexy focus to a target detection model for target detection to obtain focus image information of a patient;
the second processing subunit is used for obtaining the focus range and the focus position in the focus image information of each patient based on the focus image information of the patient;
the third processing subunit is used for numbering the focus range and the focus position in the focus image information of the patient to obtain the numbering information of each focus image information;
the first clustering subunit is used for clustering the first number information based on a distance-class clustering algorithm to obtain at least one clustering block;
and the second clustering subunit is used for calculating to obtain a threshold range corresponding to each clustering category based on the Lauda criterion, and classifying the medical record information of the patient according to the threshold range to obtain the medical record information of at least one category.
7. The device for real-time adjustment of a rehabilitation program according to claim 5, characterized in that it comprises:
the fourth processing subunit is configured to perform initialization processing on preset first rehabilitation training scheme information, where each preset first rehabilitation training scheme information is placed in the particle swarm as a single individual, so as to obtain initialized first rehabilitation training scheme information;
the calculating subunit is configured to calculate fitness values of each preset first rehabilitation training scenario information and the medical record information of all categories;
the first comparison subunit is configured to compare the fitness value with a preset fitness threshold, and if the fitness value is greater than the preset fitness threshold, the fitness value is the latest fitness threshold;
and the iteration subunit is used for repeating the iteration of the previous step until the maximum fitness value corresponding to each rehabilitation training scheme is determined, and taking the first rehabilitation training scheme corresponding to each maximum fitness value as the first rehabilitation training scheme corresponding to the medical record information of each category.
8. The device for real-time adjustment of a rehabilitation program of claim 5, wherein said device comprises:
the second comparison subunit is used for sending the second information to the rehabilitation characteristic comparison module for comparison to obtain rehabilitation effect characteristics corresponding to the second information;
the first judging subunit is used for sending the rehabilitation effect characteristics corresponding to the second information to the grade judging module for judgment to obtain the rehabilitation effect grade of the stroke patient;
the fifth processing subunit is used for the sixth processing subunit, and is used for mapping the rehabilitation effect grade of the stroke patient and the first rehabilitation training scheme one by one to obtain the rehabilitation evaluation grade corresponding to each first rehabilitation training scheme;
and the second judgment subunit is used for comparing the rehabilitation evaluation grade corresponding to each first rehabilitation training scheme with the preset grade respectively, and sending the first rehabilitation training scheme with the evaluation grade smaller than the preset grade to the trained neural network model for redistribution to obtain a second rehabilitation scheme.
9. An apparatus for adjusting a rehabilitation regimen in real time, comprising:
a memory for storing a computer program;
a processor for implementing the steps of the method of real-time adjustment of a rehabilitation program according to any one of claims 1 to 4 when executing said computer program.
10. A readable storage medium, characterized by: the readable storage medium has stored thereon a computer program which, when executed by a processor, carries out the steps of the method of real-time adjustment of a rehabilitation protocol according to any one of claims 1 to 4.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210629259.7A CN115019928A (en) | 2022-05-31 | 2022-05-31 | Method, device and equipment for adjusting rehabilitation scheme in real time and readable storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210629259.7A CN115019928A (en) | 2022-05-31 | 2022-05-31 | Method, device and equipment for adjusting rehabilitation scheme in real time and readable storage medium |
Publications (1)
Publication Number | Publication Date |
---|---|
CN115019928A true CN115019928A (en) | 2022-09-06 |
Family
ID=83073557
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202210629259.7A Pending CN115019928A (en) | 2022-05-31 | 2022-05-31 | Method, device and equipment for adjusting rehabilitation scheme in real time and readable storage medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN115019928A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116665871A (en) * | 2023-08-02 | 2023-08-29 | 上海迎智正能文化发展有限公司 | Monitoring scheme optimization method and system based on big data |
-
2022
- 2022-05-31 CN CN202210629259.7A patent/CN115019928A/en active Pending
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116665871A (en) * | 2023-08-02 | 2023-08-29 | 上海迎智正能文化发展有限公司 | Monitoring scheme optimization method and system based on big data |
CN116665871B (en) * | 2023-08-02 | 2023-11-03 | 上海迎智正能文化发展有限公司 | Monitoring scheme optimization method and system based on big data |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109919928B (en) | Medical image detection method and device and storage medium | |
CN110136103B (en) | Medical image interpretation method, device, computer equipment and storage medium | |
WO2021179498A1 (en) | Target detection method, method for training model therefor, apparatus, and electronic device | |
JP5868231B2 (en) | Medical image diagnosis support apparatus, medical image diagnosis support method, and computer program | |
JP2021536057A (en) | Lesion detection and positioning methods, devices, devices, and storage media for medical images | |
US11790279B2 (en) | System and method for class specific deep learning | |
JP2008536208A (en) | Space-time self-organizing map | |
CN113111968B (en) | Image recognition model training method, device, electronic equipment and readable storage medium | |
CN116933046B (en) | Deep learning-based multi-mode health management scheme generation method and system | |
CN109949280B (en) | Image processing method, image processing apparatus, device storage medium, and growth evaluation system | |
CN110175697A (en) | A kind of adverse events Risk Forecast System and method | |
CN112465231B (en) | Method, apparatus and readable storage medium for predicting regional population health status | |
CN111368911B (en) | Image classification method and device and computer readable storage medium | |
Kelly et al. | Automatic prediction of health status using smartphone-derived behavior profiles | |
CN112560723A (en) | Fall detection method and system based on form recognition and speed estimation | |
CN115019928A (en) | Method, device and equipment for adjusting rehabilitation scheme in real time and readable storage medium | |
JP2022502730A (en) | Generate metadata about the trained model | |
CN116311539B (en) | Sleep motion capturing method, device, equipment and storage medium based on millimeter waves | |
McCullough et al. | Convolutional neural network models for automatic preoperative severity assessment in unilateral cleft lip | |
CN109871866B (en) | Model training method, device, equipment and medium for hospital infection prediction | |
TWI816078B (en) | Mining method for sample grouping | |
CN110007764A (en) | A kind of gesture skeleton recognition methods, device, system and storage medium | |
CN111414930A (en) | Deep learning model training method and device, electronic equipment and storage medium | |
KR20220117729A (en) | Method and apparatus for detecting adverse reactions of drugs based on machine learning | |
US20220027726A1 (en) | Pre-processing device, pre-processing method, and pre-processing program |
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 |