CN113436143A - Joint detection method and device based on artificial intelligence and electronic equipment - Google Patents
Joint detection method and device based on artificial intelligence and electronic equipment Download PDFInfo
- Publication number
- CN113436143A CN113436143A CN202110565098.5A CN202110565098A CN113436143A CN 113436143 A CN113436143 A CN 113436143A CN 202110565098 A CN202110565098 A CN 202110565098A CN 113436143 A CN113436143 A CN 113436143A
- Authority
- CN
- China
- Prior art keywords
- joint
- joints
- metacarpophalangeal
- bone
- candidate
- 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
- 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
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
-
- 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
- G06T2207/10116—X-ray image
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30004—Biomedical image processing
- G06T2207/30008—Bone
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Biophysics (AREA)
- Molecular Biology (AREA)
- Biomedical Technology (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Computational Linguistics (AREA)
- Software Systems (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Radiology & Medical Imaging (AREA)
- Quality & Reliability (AREA)
- Medical Informatics (AREA)
- Image Analysis (AREA)
Abstract
The application provides a joint detection method, a joint detection device, electronic equipment and a computer-readable storage medium based on artificial intelligence; the method comprises the following steps: determining candidate skeletal joints in a digitized X-ray (DR) image, the DR image comprising a skeletal image of a limb; and processing the candidate bone joints to obtain target bone joints. Through the embodiment of the application, the accuracy rate of joint detection can be improved.
Description
Technical Field
The present application relates to artificial intelligence technology, and in particular, to a joint detection method and apparatus based on artificial intelligence, an electronic device, and a computer-readable storage medium.
Background
The target detection can be applied to various scenes and is a hot research problem of artificial intelligence. Prior Art
The target detection is mainly aimed at the detection of natural images.
Digital Radiography (DR) images may be used for bone age assessment; specifically, the bone age corresponding to the bone joint can be determined based on the existing bone age evaluation criteria by detecting the bone joint in the DR image. The detection of the bone joints in the DR image belongs to an application scene of target detection, but the target detection for the DR image is not mature, and the problem of low joint detection accuracy exists.
Disclosure of Invention
The embodiment of the application provides a joint detection method and device based on artificial intelligence, an electronic device and a computer readable storage medium, which can improve the accuracy of joint detection.
The technical scheme of the embodiment of the application is realized as follows:
in a first aspect, an embodiment of the present application provides a joint detection method based on artificial intelligence, including:
determining candidate skeletal joints in a Digital Radiography (DR) image, the DR image comprising a skeletal image of a limb;
and processing the candidate bone joints to obtain target bone joints.
In the above solution, the processing the candidate bone joints includes:
performing at least one of a position detection, a quantity detection, and a class detection on the candidate bone joints.
In the above scheme, the processing the candidate bone joints to obtain a target bone joint includes:
the candidate bone joints comprise metacarpophalangeal joints, and the category of the metacarpophalangeal joints of the candidate bones is detected;
if the number of the metacarpophalangeal joints of the first type is larger than 1, determining the metacarpophalangeal joint of the first type with the maximum confidence coefficient;
and deleting the metacarpophalangeal joints except the metacarpophalangeal joint with the maximum confidence coefficient in the first type of metacarpophalangeal joints from the candidate bone joints to obtain the target bone joint.
In the above scheme, the processing the candidate bone joints to obtain a target bone joint includes:
the candidate bone joints comprise metacarpophalangeal joints, and the number of metacarpophalangeal joints in the candidate bones is detected;
if the number of the metacarpophalangeal joints is smaller than a first threshold value, determining a second class according to the class of the metacarpophalangeal joints in the candidate bones, wherein the second class is a class corresponding to the metacarpophalangeal joints to be supplemented
Searching the metacarpophalangeal joints of the second type from abandoned bone joints;
and adding the metacarpophalangeal joint with the highest confidence level in the second type of metacarpophalangeal joints to the candidate bone joints to obtain the target bone joint.
In the above scheme, the processing the candidate bone joints to obtain a target bone joint includes:
the candidate bone joints comprise metacarpophalangeal joints, and the positions of the metacarpophalangeal joints in the candidate bones are detected;
judging whether the position of the first metacarpophalangeal joint meets a first position relation corresponding to the first metacarpophalangeal joint;
and if the first metacarpophalangeal joint does not meet the first position relation, adjusting the position of the first metacarpophalangeal joint so as to enable the first metacarpophalangeal joint to meet the first position relation.
In the above scheme, the processing the candidate bone joints to obtain a target bone joint includes:
the candidate bone joints comprise wrist joints, and the central point of each wrist joint is calculated;
judging whether a first wrist joint is a target bone joint or not based on the central point position of the first wrist joint;
if the judgment result is yes, the first wrist joint is reserved; and if the judgment result is negative, deleting the first wrist joint.
In the above solution, the determining candidate bone joints in the digital X-ray DR image includes:
and determining the output of the neural network model as the candidate bone joint by taking the DR image as the input of the neural network model.
In the above solution, the determining the output of the neural network model as the candidate bone joint with the DR image as the input of the neural network model includes:
the neural network model comprises a first neural network model, an output of the first neural network model comprising a first region of interest;
and determining the metacarpophalangeal joints corresponding to the first region of interest as the candidate bone joints.
In the above solution, the determining the output of the neural network model as the candidate bone joint with the DR image as the input of the neural network model includes:
the neural network model comprises a second neural network model, an output of the second neural network model comprising a second region of interest;
and determining the wrist joint corresponding to the second region of interest as the candidate bone joint.
In a second aspect, an embodiment of the present application provides an artificial intelligence based joint detection apparatus, including:
a determination module to determine candidate bone joints in a DR image, the DR image comprising a bone image of a limb;
and the processing module is used for processing the candidate bone joints to obtain target bone joints.
In a third aspect, an embodiment of the present application provides an electronic device, including:
a memory for storing executable instructions;
and the processor is used for realizing the joint detection method based on artificial intelligence provided by the embodiment of the application when executing the executable instructions stored in the memory.
In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium storing executable instructions for implementing the joint detection method based on artificial intelligence provided in the embodiment of the present application when executed by a processor.
The joint detection method based on artificial intelligence provided by the embodiment of the application determines candidate bone joints in a DR image, wherein the DR image comprises a bone image of limbs; and processing the candidate bone joints to obtain target bone joints. In the embodiment of the application, the candidate bone joints are processed, so that the bone joints which are not detected can be added to the target bone joints, the bone joints which are re-detected can be deleted from the candidate bone joints, the bone joints which are mistakenly detected are corrected, and the accuracy of joint detection is improved. Because the process of the joint detection method based on artificial intelligence is completed by the electronic equipment, compared with the joint search by manpower according to DR images in the related art, the time for determining the target bone joint is greatly shortened.
Drawings
FIG. 1 is a schematic diagram of an architecture of an artificial intelligence based joint detection system provided by an embodiment of the present application;
FIG. 2 is a schematic structural diagram of a server applying an artificial intelligence-based joint detection method according to an embodiment of the present application;
FIG. 3 is a schematic view of an alternative process flow of the joint detection method based on artificial intelligence provided by the embodiment of the present application;
FIG. 4 is a schematic view of an alternative process flow for processing the candidate bone joint to obtain a target bone joint according to an embodiment of the present application;
FIG. 5 is a schematic view of an alternative process flow for processing the candidate bone joint to obtain a target bone joint according to an embodiment of the present application;
FIG. 6 is a schematic view of another alternative processing flow for processing the candidate bone joint to obtain a target bone joint according to the embodiment of the present application;
FIG. 7 is a schematic flow chart illustrating yet another alternative process for processing the candidate bone joint to obtain a target bone joint according to an embodiment of the present disclosure;
fig. 8 is a schematic diagram of a candidate bone joint provided by an embodiment of the present application.
Detailed Description
In order to make the objectives, technical solutions and advantages of the present application clearer, the present application will be described in further detail with reference to the attached drawings, the described embodiments should not be considered as limiting the present application, and all other embodiments obtained by a person of ordinary skill in the art without creative efforts shall fall within the protection scope of the present application.
In the following description, reference is made to "some embodiments" which describe a subset of all possible embodiments, but it is understood that "some embodiments" may be the same subset or different subsets of all possible embodiments, and may be combined with each other without conflict.
In the following description, references to the terms "first", "second", and the like, are only to distinguish similar objects and do not denote a particular order, but rather the terms "first", "second", and the like may be used interchangeably with the order specified, where permissible, to enable embodiments of the present application described herein to be practiced otherwise than as specifically illustrated or described herein.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein is for the purpose of describing embodiments of the present application only and is not intended to be limiting of the application.
Before further detailed description of the embodiments of the present application, terms and expressions referred to in the embodiments of the present application will be described, and the terms and expressions referred to in the embodiments of the present application will be used for the following explanation.
1) Artificial Intelligence (AI) is a theory, method and technique and application system that uses a digital computer or a machine controlled by a digital computer to simulate, extend and expand human Intelligence, perceive the environment, acquire knowledge and use the knowledge to obtain the best results.
2) Region Of Interest (ROI): in machine vision and image processing, a region to be processed is outlined in a square, circle, ellipse, or the like from a processed image is called a region of interest. The region of interest is obtained by various operators (operators) and functions commonly used in machine vision software such as Halcon, OpenCV, Matlab and the like, and the image is processed in the next step.
3) The DR system, i.e. a direct digital radiography system, is composed of an electronic cassette, a scan controller, a system controller, an image monitor, etc., and directly converts X-ray photons into a digital image through the electronic cassette, which is a direct digital radiography in a broad sense. In the narrow sense, direct digital radiography (ddr) generally refers to digital radiography using a direct image conversion technique of a flat panel detector, and is a real direct digital X-ray radiography system. Mainly divided into an amorphous silicon flat plate DR, an amorphous selenium flat plate DR and a CCD DR according to the type of the detector; the frame structure is divided into a suspension DR and a column (UC arm) DR.
In the related art, a neural network model can be used for target detection on natural images (such as images shot by a camera and other imaging devices); however, when the target detection (such as joint detection) is performed on the DR image by using the neural network model, due to the special attribute of the DR image, when the target detection is performed by using the neural network model, the detection accuracy is poor, such as missing detection, erroneous detection or re-detection. The missing detection may mean that the number of detected target objects is less than the number of actual target objects; the recheck (also referred to as repeat detection) may refer to detecting multiple or multiple times for the same target object; the misdetection may be that the detected object is not the target object, or that the position of the detected target object does not coincide with the actual position of the target object.
Aiming at the problem of poor joint detection accuracy of the joint detection method provided by the related technology, the embodiment of the application provides a joint detection method based on artificial intelligence, a device, electronic equipment and a computer readable storage medium, which can solve the problem of poor joint detection accuracy, and is a joint detection method based on a neural network model, wherein the neural network model is trained by using joint features in a historical DR image, so that candidate bone joints in a new DR image can be determined based on the trained neural network model; processing the determined candidate bone joint (such as screening of omission, error detection and reinspection) to obtain a target bone joint; the accuracy of joint detection can be improved.
An exemplary application of the electronic device provided in the embodiment of the present application is described below, and the electronic device provided in the embodiment of the present application may be implemented as a server. In the following, an exemplary application will be explained when the electronic device is implemented as a server.
The server may be an independent physical server, a server cluster or a distributed system formed by a plurality of physical servers, or a cloud server providing cloud computing services. The terminal may be, but is not limited to, a smart phone, a tablet computer, a laptop computer, a desktop computer, a smart speaker, a smart watch, and the like. The terminal and the server may be directly or indirectly connected through wired or wireless communication, and the embodiment of the present application is not limited herein.
The so-called artificial intelligence cloud Service is also generally called AIaaS (AI as a Service, chinese). The method is a service mode of an artificial intelligence platform, and particularly, the AIaaS platform splits several types of common AI services and provides independent or packaged services at a cloud. This service model is similar to the one opened in an AI theme mall: all developers can access one or more artificial intelligence services provided by the platform by means of an API (application programming interface), and part of the qualified developers can also use an AI framework and an AI infrastructure provided by the platform to deploy and operate and maintain the self-dedicated cloud artificial intelligence services
Referring to fig. 1, fig. 1 is a schematic diagram of an architecture of an artificial intelligence-based joint detection system provided in an embodiment of the present application, which may be used to determine a target bone joint in a DR image. In the joint detection system, the terminal 400 is connected to the server 200 through the network 300, the network 300 may be a wide area network or a local area network, or a combination of the two, in response to receiving a joint detection request of the terminal 400, the function of the joint detection system may be implemented based on each module in the server 200, in the process that a user uses a client, the terminal 400 reports collected DR images and bone joint images in the DR images to the database 600 as training sample data, the training sample data is data from different individuals reported by each terminal, the server 200 trains a neural network model based on the obtained training data, and in response to receiving the joint detection request of the terminal 400 by the server 200, the determining module 2551 in the server 200 determines candidate bone joints in the DR images; the processing module 2552 processes the candidate bone joints to obtain target bone joints.
As an example, the terminal 400 may install and run a related application. The application refers to a program corresponding to the server and providing local service for the client. Here, the local service may include, but is not limited to: displaying the DR image and sending the DR image to a server. The terminal in the embodiment of the present application may include, but is not limited to, any electronic product based on an intelligent operating system, which can perform human-computer interaction with a user through an input device such as a keyboard, a virtual keyboard, a touch pad, a touch screen, and a voice control device, such as a smart phone, a tablet computer, a personal computer, and the like. Smart operating systems include, but are not limited to, any operating system that enriches device functionality by providing various mobile applications to a mobile device, such as: android, IOS, and the like.
It is understood that the artificial intelligence based joint detection system architecture of fig. 1 is only a partial exemplary implementation in the embodiments of the present application, which include, but are not limited to, the artificial intelligence based joint detection system architecture shown in fig. 1.
Referring to fig. 2, fig. 2 is a schematic structural diagram of a server 200 applying an artificial intelligence-based joint detection method according to an embodiment of the present application, where the server 200 shown in fig. 2 includes: at least one processor 210, memory 250, and at least one network interface 220. The various components in server 200 are coupled together by a bus system 240. It is understood that the bus system 240 is used to enable communications among the components. The bus system 240 includes a power bus, a control bus, and a status signal bus in addition to a data bus. For clarity of illustration, however, the various buses are labeled as bus system 240 in fig. 2.
The Processor 210 may be an integrated circuit chip having Signal processing capabilities, such as a general purpose Processor, a Digital Signal Processor (DSP), or other programmable logic device, discrete gate or transistor logic device, discrete hardware components, or the like, wherein the general purpose Processor may be a microprocessor or any conventional Processor, or the like.
The memory 250 may be removable, non-removable, or a combination thereof. Exemplary hardware devices include solid state memory, hard disk drives, optical disk drives, and the like. Memory 250 optionally includes one or more storage devices physically located remotely from processor 210.
In some embodiments, memory 250 is capable of storing data, examples of which include programs, modules, and data structures, or a subset or superset thereof, to support various operations, as exemplified below.
An operating system 251 including system programs for processing various basic system services and performing hardware-related tasks, such as a framework layer, a core library layer, a driver layer, etc., for implementing various basic services and processing hardware-based tasks;
a network communication module 252 for communicating to other computing devices via one or more (wired or wireless) network interfaces 220, exemplary network interfaces 220 including: bluetooth, wireless compatibility authentication (WiFi), and Universal Serial Bus (USB), among others.
In some embodiments, the artificial intelligence based information recommendation device provided by the embodiments of the present application may be implemented in software, and fig. 2 illustrates an artificial intelligence based joint detection device 255 stored in a memory 250, which includes a plurality of modules of a joint detection system, where the modules may be software in the form of programs and plug-ins, and include the following software modules: a determination module 2551 and a processing module 2552, which are logical and thus can be arbitrarily combined or further split according to the implemented functions, which will be described below.
The joint detection method based on artificial intelligence provided by the embodiment of the present application will be described in conjunction with an exemplary application and implementation of the joint detection system provided by the embodiment of the present application, and the joint detection system includes a training phase and an application phase.
First, an application of the model in the joint detection method based on artificial intelligence provided in the embodiment of the present application is explained. Referring to fig. 3, fig. 3 is a schematic view of an alternative processing flow of the joint detection method based on artificial intelligence according to the embodiment of the present application, which will be described with reference to steps S101-S102 shown in fig. 3.
Step S101, candidate bone joints in a DR image are determined, wherein the DR image comprises a bone image of a limb.
In some embodiments, first, an artificial intelligence based joint detection apparatus acquires a DR image. The DR image may include a skeletal image of a limb; the limb may be a hand or foot, etc. Taking the limb as a hand as an example, the skeleton image included in the DR image may be an image in which the fingers are open upward, or an image in which the fingers are open downward. To improve the accuracy of determining candidate bone joints, the DR image may be preprocessed before determining candidate bone joints in the DR image; as an example, the preprocessing the DR image may be at least one of adjusting a contrast of the DR image, denoising the DR image, and normalizing the DR image.
Then, the joint detection device based on artificial intelligence determines candidate bone joints in the DR image, and the regions corresponding to the candidate bone joints can also be called regions of interest. The region of interest may be a region delineated in a square, circle, ellipse, or the like from the DR image.
In some embodiments, taking as an example that the DR image includes a skeletal image of a hand, the regions of interest may include a first region of interest corresponding to a metacarpophalangeal joint and a second region of interest corresponding to a wrist joint.
And inputting the DR image into a first neural network model by using the joint detection device based on artificial intelligence aiming at the first region of interest, and detecting the metacarpophalangeal joints of the hand by using the first neural network model to obtain the first region of interest corresponding to the metacarpophalangeal joints. As an example, the DR image is an input of a first neural network model, the first region of interest is an output of the first neural network model, and a metacarpophalangeal joint corresponding to the first region of interest is the candidate bone joint. As an example, when detecting a metacarpophalangeal joint of a hand, 3 metacarpals, 8 phalanges, 1 ulna and 1 radius may be detected, and a range of the detected metacarpophalangeal joint is outlined in a rectangle or other shape, and an area within the outlined range is the first region of interest. In specific implementation, the number of the metacarpophalangeal bones is not limited to 13 in the above example, or may be other numbers, and the embodiment of the present application is not limited.
In some embodiments, the first neural network model may also be referred to as a target detection model, which may be, for example, a fast-RCNN target detection model. The artificial intelligence based joint detection apparatus may also train the first neural network model prior to determining the region of interest in the DR image. As an example, an artificial intelligence based joint detection apparatus generates a first set of training samples for training the first neural network model; the first training sample set may be dicom images of the hand, which are normalized by the maximum and/or minimum values to obtain png format images. Labeling all sample images in the first training sample set, such as labeling a surrounding frame (namely an interested area) of a metacarpophalangeal joint; the metacarpophalangeal joints in the sample image can also be identified, and if the first metacarpophalangeal joint is identified as 1, the second metacarpophalangeal joint is identified as 2, and the like, the first metacarpophalangeal joint and the second metacarpophalangeal joint can be divided based on the positions of the fingers where the metacarpophalangeal joints are located and the metacarpophalangeal joints in the fingers. As an example, the size of the anchor box (anchor size) in the fast-RCNN object detection model may be set according to actual conditions, and as an example, the size of the anchor box may be set to 8 × 8 pixels, or 16 × 16 pixels, or 32 × 32 pixels, or 64 × 64 pixels, etc.,
thus, the first neural network model is trained through the known images of the metacarpophalangeal joints and the interested areas corresponding to the metacarpophalangeal joints, so that the first neural network model can determine the first interested areas corresponding to the metacarpophalangeal joints according to the images of the metacarpophalangeal joints in the new skeleton images; as an example, the first neural network model can determine the type, confidence, and the like of the metacarpophalangeal joints from the images of the metacarpophalangeal joints in the new bone image. The confidence coefficient is used for representing the credibility of the first region of interest obtained based on the first neural network model, and the higher the confidence coefficient is, the higher the credibility of the first region of interest is indicated. To improve the accuracy of the first neural network model, a large number of bone images of different age groups may be included in the first set of training samples.
And aiming at a second region of interest, inputting the DR image into a second neural network model by using the joint detection device based on artificial intelligence, and segmenting the wrist joint in the skeleton image by using the second neural network model to obtain a second region of interest corresponding to the wrist joint. As an example, the DR image is an input of a second neural network model, the first region of interest is an output of the second neural network model, and the wrist joint corresponding to the second region of interest is the candidate bone joint. As an example, when detecting a wrist joint of a hand, 7 pieces of carpal bones may be segmented; if the background (mask) of 7 carpal bones except the pisiform bones is used as a true value (group truth) of segmentation, and the wrist DR image of the hand is used as the input of the second neural network model, the second region of interest corresponding to the wrist joint can be output. When a second region of interest is determined, firstly, a contour line of the wrist joint is drawn, and then a region in the first minimum enclosing frame in the shape corresponding to the contour line is determined as the second region of interest; as an example, the first shape may be a rectangle. In specific implementation, the number of wrist joints is not limited to the 7 pieces illustrated above, or may be another number, and the embodiment of the present application is not limited.
In some embodiments, the second neural network model may also be referred to as a semantic segmentation model, which may be, for example, a deplaybv 3 semantic segmentation model. The joint detection apparatus based on artificial intelligence may also train a second neural network model prior to determining the region of interest in the DR image. As an example, an artificial intelligence-based joint detection apparatus generates a second set of training samples for training the second neural network model; the second training sample set may be dicom images of the hand, which are normalized by the maximum and/or minimum values to obtain png format images. Labeling all sample images in the second training sample set, such as labeling a bounding box (i.e., a region of interest) of the wrist joint; wrist joints in the sample image may also be identified, and if a first type of wrist joint is identified as a, a second type of wrist joint is identified as B, etc., the first type of wrist joint and the second type of wrist joint may be divided based on the position of the wrist joint. In this way, the second neural network model is trained through the known wrist joint image and the wrist joint corresponding region of interest, so that the second neural network model can determine a second region of interest corresponding to the wrist joint according to the wrist joint image in the new bone image; the second region of interest may also become a mask for the wrist joint; as an example, the first neural network model can be based on an image of the wrist joint in the new bone image, and can also determine the category, confidence, and the like of the wrist joint. And the confidence coefficient is used for representing the credibility of the second region of interest obtained based on the second neural network model, and the higher the confidence coefficient is, the higher the credibility of the second region of interest is indicated. To improve the accuracy of the second neural network model, a large number of bone images of different age groups may be included in the second set of training samples.
In some embodiments, the first set of training samples and the second set of training samples may be the same set of training samples or may be different sets of training samples. The same training sample set may mean that the samples in the first training sample set and the second training sample set are identical; different sets of training samples may mean that the samples in the first set of training samples and the second set of training samples are not identical or are not identical.
And step S102, processing the candidate bone joints to obtain target bone joints.
In some embodiments, the artificial intelligence based joint detection apparatus may perform at least one of position detection, quantity detection, and class detection on the candidate bone joints to obtain the target bone joint.
The following describes an alternative process for obtaining a target bone joint, with respect to bone joints including a metacarpophalangeal joint and a wrist joint, respectively.
Aiming at skeletal joints including metacarpophalangeal joints:
in some embodiments, an alternative process flow of processing the candidate bone joints to obtain the target bone joint, as shown in fig. 4, includes:
step S102a, detecting the category of the metacarpophalangeal joint of the candidate bones.
In some embodiments, the joint detection apparatus based on artificial intelligence is able to determine the category and confidence level, etc. of the metacarpophalangeal joint in addition to the image of the metacarpophalangeal joint in the new bone image according to the first neural network model. Wherein, the category of the metacarpophalangeal joints can be distinguished or identified based on the position of the metacarpophalangeal bones; for example, the metacarpophalangeal joint located at the lowest position of the thumb is a metacarpophalangeal joint of the first kind, and is marked as 1; the metacarpophalangeal joint located at the lowest part of the little finger is the thirteenth metacarpophalangeal joint, which is marked as 13. The joint detection device based on artificial intelligence can detect which of the categories of the candidate bone metacarpophalangeal joints are included.
Step S102b, if the number of metacarpophalangeal joints of the first type is greater than 1, determining a metacarpophalangeal joint with the highest confidence level among the metacarpophalangeal joints of the first type.
In some embodiments, the first type of metacarpophalangeal joint may be any one of the candidate metacarpophalangeal joints. If the number of the metacarpophalangeal joints of the first type is more than 1, the retest of one metacarpophalangeal joint is performed. In the scene, the joint detection device based on artificial intelligence compares the confidence coefficient of the first metacarpophalangeal joint and determines the metacarpophalangeal joint with the highest confidence coefficient in the first metacarpophalangeal joint.
Step S102c, deleting, from the candidate bone joints, the metacarpophalangeal joints of the first type except the metacarpophalangeal joint with the highest confidence level to obtain the target bone joint.
In some embodiments, the joint detection device based on artificial intelligence determines the first metacarpophalangeal joint with the highest confidence as the target bone joint, and deletes the metacarpophalangeal joints except the metacarpophalangeal joint with the highest confidence in the first metacarpophalangeal joints.
In other embodiments, an alternative process flow for processing the candidate bone joints to obtain the target bone joint is shown in fig. 5, and includes:
step S102d, detecting the number of metacarpophalangeal joints of the candidate bones.
In some embodiments, the artificial intelligence based joint detection apparatus detects the number of metacarpophalangeal joints of the candidate bones.
Step S102e, if the number of the metacarpophalangeal joints is smaller than a first threshold, determining a second class according to the class of the metacarpophalangeal joints in the candidate bones, where the second class is a class corresponding to the metacarpophalangeal joint to be supplemented.
In some embodiments, the first threshold may be preset, and the first threshold may be the number of metacarpophalangeal joints of the target skeletal joint. If the number of the metacarpophalangeal joints is smaller than the first threshold value, the detected number of the metacarpophalangeal joints is smaller than the actual number of the metacarpophalangeal joints in the target bone joints, and the phenomenon of missing detection occurs.
In this scenario, the joint detection apparatus based on artificial intelligence may determine a second class corresponding to the metacarpophalangeal joint to be supplemented according to the category of the metacarpophalangeal joint in the candidate bone. For example, if the target bone joint includes 13 metacarpophalangeal joints of 1-13 types, and the candidate metacarpophalangeal joints include 1-12 metacarpophalangeal joints, the metacarpophalangeal joint to be supplemented is determined to be 13 th type.
Step S102f, searching the metacarpophalangeal joints of the second type from the abandoned bone joints.
In some embodiments, in step S101, the joint detection apparatus based on artificial intelligence may discard a part of bone joints with low confidence when determining candidate bone joints in the DR image, which is referred to as discarding bone joints in this embodiment. As an example, a confidence threshold may be set, bone joints with confidence less than the confidence threshold are discarded bone joints, bone joints with confidence greater than the confidence threshold are candidate bone joints; as an example, the confidence threshold may be flexibly set according to actual situations, such as 0.5. And if the number of the metacarpophalangeal joints in the candidate bone joints is smaller than a first threshold value, searching a second metacarpophalangeal joint in the abandoned bone joints by using the joint detection device based on artificial intelligence.
And step S102g, adding the metacarpophalangeal joint with the highest confidence level in the second type of metacarpophalangeal joints to the candidate bone joints to obtain the target bone joint.
In some embodiments, if the abandoned bone joints include two or more second metacarpophalangeal joints, the joint detection device based on artificial intelligence determines the metacarpophalangeal joint with the highest confidence level in the second metacarpophalangeal joints, and adds the second metacarpophalangeal joint with the highest confidence level to the candidate bone joints to obtain the target bone joint.
In still other embodiments, the candidate bone joints are processed to obtain yet another alternative process flow of the target bone joint, as shown in fig. 6, which includes:
step S102h, detecting the position of the metacarpophalangeal joint of the candidate bone.
In some embodiments, an artificial intelligence based joint detection device detects the location of the metacarpophalangeal joints of the candidate bones. As an example, the metacarpophalangeal joint may be located near the radius in the thumb, near the tip of the finger in the thumb, near the wrist in the pause, near the ulna in the little thumb, and the like.
In step S102i, it is determined whether the position of the first metacarpophalangeal joint satisfies the first positional relationship corresponding to the first metacarpophalangeal joint.
In some embodiments, the joint detection device based on artificial intelligence determines whether the position of the first metacarpophalangeal joint satisfies a first position relationship corresponding to the first metacarpophalangeal joint. Wherein, the first position relation corresponding to the first metacarpophalangeal joint can be obtained according to prior knowledge or common knowledge. For example, the middle finger is located between the thumb and the fifth phalange, the distal phalange of the middle finger is located at the top, the distal, middle and proximal ends of each phalange are fixed, the ulna and radius are located substantially parallel and located at the lowest position of the whole palm, the joints of the wrist are arranged in a fixed order, the carpal region is located between the metacarpal bones of the fingers and the ulna and the radius, and the like.
Step S102j, if the first metacarpophalangeal joint does not satisfy the first positional relationship, adjusting the position of the first metacarpophalangeal joint so that the first metacarpophalangeal joint satisfies the first positional relationship.
In some embodiments, the first metacarpophalangeal joint does not satisfy the first positional relationship, which may be based on the joint detection device of artificial intelligence identifying that the first metacarpophalangeal joint is not at a first position, the first position being a position in the palm corresponding to the first metacarpophalangeal joint acquired based on prior knowledge or common sense; in this case, it is considered that the error detection has occurred, and the type of the metacarpophalangeal joint corresponding to the first position may be considered to be incorrect. For example, if the first metacarpophalangeal joint is the joint of the thumb near the wrist, the first positional relationship is that the first metacarpophalangeal joint is located above the radius; however, if the joint detection device based on artificial intelligence recognizes that the first metacarpophalangeal joint is above the ulna, the display of the position of the first metacarpophalangeal joint is represented as an error, and the position of the first metacarpophalangeal joint is adjusted to be above the radius.
For skeletal joints including wrist joints:
in some embodiments, the candidate bone joints are processed to obtain a further alternative process flow of the target bone joint, as shown in fig. 7, including:
step S102k, the center point of each wrist joint is calculated.
In some embodiments, the artificial intelligence based joint detection apparatus calculates a center point for each wrist joint. As an example, the number of wrist joints may be 7, and the joint detection apparatus based on artificial intelligence calculates the central points of the 7 wrist joints, respectively.
Step S102l is a step of determining whether or not a first wrist joint is a target bone joint based on the center point position of the first wrist joint.
In some embodiments, the first wrist joint may be any one of the total wrist joints. The joint detection device based on artificial intelligence can judge whether the first wrist joint is a target bone joint or not based on the position of the central point of the first wrist joint by utilizing prior knowledge or common knowledge.
For example, as shown in the schematic diagram of a candidate bone joint shown in fig. 8, a wrist joint includes two partially overlapped wrist joints, as an example, a wrist joint 1 and a wrist joint 2 are partially overlapped, and the center points of the wrist joint 1 and the wrist joint 2 are located above a radius; the wrist joint 1 and the wrist joint 2 are the target bone joints. As an example, the wrist joint 1 and the wrist joint 2 are partially overlapped, and the center points of the wrist joint 1 and the wrist joint 2 are located below the radius or above the ulna; the wrist joint 1 and the wrist joint 2 are not the target bone joint.
Step S102m, if the judgment result is yes, reserving the first wrist joint; and if the judgment result is negative, deleting the first wrist joint.
The joint detection method based on artificial intelligence provided by the embodiment of the application is characterized in that a neural network model for joint detection is trained in advance, wherein the neural network model can comprise a first neural network model and a second neural network model; and taking the DR image as the input of the neural network model to obtain the candidate bone joints in the DR image. The process of determining the candidate bone joints in the DR image is completed by the electronic equipment, and compared with the process of manually searching the joints according to the DR image in the related art, the time for detecting the joints is greatly shortened. In the embodiment of the application, the candidate bone joints obtained based on the neural network model are subjected to processing such as omission, re-inspection and error detection, the omitted bone joints can be added to the target bone joints, the re-inspected bone joints can be deleted from the candidate bone joints, the error-detected bone joints are corrected, and the accuracy of joint detection is improved.
Continuing with the exemplary structure of the artificial intelligence based joint detection apparatus 255 provided by the embodiments of the present application as software modules, in some embodiments, as shown in fig. 2, the software modules stored in the artificial intelligence based joint detection apparatus 255 of the memory 250 may include: a determination module 2551 for determining candidate bone joints in a DR image, the DR image comprising a bone image of a limb; a processing module 2552, configured to process the candidate bone joints to obtain target bone joints.
In some embodiments, the processing module 2552 is configured to perform at least one of position detection, number detection and class detection on the candidate bone joints.
In some embodiments, the candidate bone joints comprise metacarpophalangeal joints, the processing module 2552 is configured to detect a category of the candidate bone metacarpophalangeal joints;
if the number of the first type of metacarpophalangeal joints is larger than 1, determining the metacarpophalangeal joint with the highest confidence level in the first type of metacarpophalangeal joints;
and deleting the metacarpophalangeal joints except the metacarpophalangeal joint with the maximum confidence coefficient in the first type of metacarpophalangeal joints from the candidate bone joints to obtain the target bone joint.
In some embodiments, the candidate bone joints comprise metacarpophalangeal joints, the processing module 2552 is configured to detect a number of metacarpophalangeal joints in the candidate bone;
if the number of the metacarpophalangeal joints is smaller than a first threshold value, determining a second class according to the class of the metacarpophalangeal joints in the candidate bones, wherein the second class is a class corresponding to the metacarpophalangeal joints to be supplemented
Searching the metacarpophalangeal joints of the second type from abandoned bone joints;
and adding the metacarpophalangeal joint with the maximum confidence level value in the second type of metacarpophalangeal joints to the candidate bone joints to obtain the target bone joint.
In some embodiments, the candidate bone joints comprise metacarpophalangeal joints, the processing module 2552 to detect a location of the candidate bone metacarpophalangeal joints;
judging whether the position of the first metacarpophalangeal joint meets a first position relation corresponding to the first metacarpophalangeal joint;
and if the first metacarpophalangeal joint does not meet the first position relation, adjusting the position of the first metacarpophalangeal joint so as to enable the first metacarpophalangeal joint to meet the first position relation.
In some embodiments, the candidate bone joints comprise wrist joints, the processing module 2552 to calculate a center point for each wrist joint;
judging whether a first wrist joint is a target bone joint or not based on the central point position of the first wrist joint;
if the judgment result is yes, the first wrist joint is reserved; and if the judgment result is negative, deleting the first wrist joint.
In some embodiments, the determining module 2551 is configured to determine the output of the neural network model as the candidate bone joint using the DR image as an input of the neural network model.
In some embodiments, the neural network model comprises a first neural network model, an output of the first neural network model comprising a first region of interest;
the determining module 2551 is configured to determine that the metacarpophalangeal joint corresponding to the first region of interest is the candidate bone joint.
In some embodiments, the neural network model comprises a second neural network model, an output of the second neural network model comprising a second region of interest;
the determining module 2551 is configured to determine that the wrist joint corresponding to the second region of interest is the candidate bone joint.
It should be noted that the description of the apparatus in the embodiment of the present application is similar to the description of the method embodiment, and has similar beneficial effects to the method embodiment, and therefore, the description is not repeated. The inexhaustible technical details of the artificial intelligence based joint detection device provided by the embodiment of the application can be understood from the description of any one of the drawings in fig. 1 to 8.
Embodiments of the present application provide a computer-readable storage medium storing executable instructions, which when executed by a processor, cause the processor to perform the artificial intelligence based joint detection method provided by embodiments of the present application.
In some embodiments, the computer-readable storage medium may be memory such as FRAM, ROM, PROM, EPROM, EEPROM, flash, magnetic surface memory, optical disk, or CD-ROM; or may be various devices including one or any combination of the above memories.
In some embodiments, executable instructions may be written in any form of programming language (including compiled or interpreted languages), in the form of programs, software modules, scripts or code, and may be deployed in any form, including as a stand-alone program or as a module, component, subroutine, or other unit suitable for use in a computing environment.
By way of example, executable instructions may be deployed to be executed on one computing device or on multiple computing devices at one site or distributed across multiple sites and interconnected by a communication network.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
It should be understood that, in the various embodiments of the present application, the size of the serial number of each implementation process does not mean the execution sequence, and the execution sequence of each process should be determined by its function and inherent logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.
The above description is only an example of the present application, and is not intended to limit the scope of the present application. Any modification, equivalent replacement, and improvement made within the spirit and scope of the present application are included in the protection scope of the present application.
Claims (12)
1. An artificial intelligence based joint detection method, characterized in that the method comprises:
determining candidate skeletal joints in a digitized X-ray DR image, the DR image comprising a skeletal image of a limb;
and processing the candidate bone joints to obtain target bone joints.
2. The method of claim 1, wherein said processing said candidate bone joints comprises:
performing at least one of a position detection, a quantity detection, and a class detection on the candidate bone joints.
3. The method of claim 1 or 2, wherein said processing said candidate bone joints to obtain a target bone joint comprises:
the candidate bone joints comprise metacarpophalangeal joints, and the category of the metacarpophalangeal joints of the candidate bones is detected;
if the number of the first type of metacarpophalangeal joints is larger than 1, determining the metacarpophalangeal joint with the highest confidence level in the first type of metacarpophalangeal joints;
and deleting the metacarpophalangeal joints except the metacarpophalangeal joint with the maximum confidence coefficient in the first type of metacarpophalangeal joints from the candidate bone joints to obtain the target bone joint.
4. The method of claim 1 or 2, wherein said processing said candidate bone joints to obtain a target bone joint comprises:
the candidate bone joints comprise metacarpophalangeal joints, and the number of metacarpophalangeal joints in the candidate bones is detected;
if the number of the metacarpophalangeal joints is smaller than a first threshold value, determining a second class according to the class of the metacarpophalangeal joints in the candidate bones, wherein the second class is a class corresponding to the metacarpophalangeal joints to be supplemented
Searching the metacarpophalangeal joints of the second type from abandoned bone joints;
and adding the metacarpophalangeal joint with the maximum confidence level value in the second type of metacarpophalangeal joints to the candidate bone joints to obtain the target bone joint.
5. The method of claim 1 or 2, wherein said processing said candidate bone joints to obtain a target bone joint comprises:
the candidate bone joints comprise metacarpophalangeal joints, and the positions of the metacarpophalangeal joints in the candidate bones are detected;
judging whether the position of the first metacarpophalangeal joint meets a first position relation corresponding to the first metacarpophalangeal joint;
and if the first metacarpophalangeal joint does not meet the first position relation, adjusting the position of the first metacarpophalangeal joint so as to enable the first metacarpophalangeal joint to meet the first position relation.
6. The method of claim 1 or 2, wherein said processing said candidate bone joints to obtain a target bone joint comprises:
the candidate bone joints comprise wrist joints, and the central point of each wrist joint is calculated;
judging whether a first wrist joint is a target bone joint or not based on the central point position of the first wrist joint;
if the judgment result is yes, the first wrist joint is reserved; and if the judgment result is negative, deleting the first wrist joint.
7. The method of claim 1, wherein said determining candidate bone joints in a digitized X-ray DR image comprises:
and determining the output of the neural network model as the candidate bone joint by taking the DR image as the input of the neural network model.
8. The method of claim 7, wherein said determining an output of a neural network model as said candidate bone joint using said DR image as an input to said neural network model comprises:
the neural network model comprises a first neural network model, an output of the first neural network model comprising a first region of interest;
and determining the metacarpophalangeal joints corresponding to the first region of interest as the candidate bone joints.
9. The method of claim 7 or 8, wherein the determining the output of the neural network model as the candidate bone joint using the DR image as an input of the neural network model comprises:
the neural network model comprises a second neural network model, an output of the second neural network model comprising a second region of interest;
and determining the wrist joint corresponding to the second region of interest as the candidate bone joint.
10. An artificial intelligence based joint detection apparatus, the apparatus comprising:
a determination module to determine candidate bone joints in a digitized X-ray DR image, the DR image comprising a bone image of a limb;
and the processing module is used for processing the candidate bone joints to obtain target bone joints.
11. An electronic device, comprising:
a memory for storing executable instructions;
a processor for implementing the artificial intelligence based joint detection method of any one of claims 1 to 9 when executing executable instructions stored in the memory.
12. A computer-readable storage medium storing executable instructions for implementing the artificial intelligence based joint detection method of any one of claims 1 to 9 when executed by a processor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110565098.5A CN113436143A (en) | 2021-05-24 | 2021-05-24 | Joint detection method and device based on artificial intelligence and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110565098.5A CN113436143A (en) | 2021-05-24 | 2021-05-24 | Joint detection method and device based on artificial intelligence and electronic equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113436143A true CN113436143A (en) | 2021-09-24 |
Family
ID=77802682
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110565098.5A Pending CN113436143A (en) | 2021-05-24 | 2021-05-24 | Joint detection method and device based on artificial intelligence and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113436143A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115007765A (en) * | 2022-08-03 | 2022-09-06 | 山东迪格重工机械有限公司 | Stamping machine tool anti-pinch automatic control method based on infrared ray |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20080319448A1 (en) * | 2006-12-12 | 2008-12-25 | Perception Raisonnement Action En Medecine | System and method for determining an optimal type and position of an implant |
| US20180204481A1 (en) * | 2017-01-18 | 2018-07-19 | Behzad Nejat | Method of creating and distributing digital data sets to improve performance of physical activities |
| CN108334899A (en) * | 2018-01-28 | 2018-07-27 | 浙江大学 | Quantify the bone age assessment method of information integration based on hand bone X-ray bone and joint |
| CN110689551A (en) * | 2019-10-14 | 2020-01-14 | 慧影医疗科技（北京）有限公司 | Method and device for limb bone segmentation, electronic equipment and readable storage medium |
| CN110838121A (en) * | 2018-08-15 | 2020-02-25 | 辽宁开普医疗***有限公司 | Child hand bone joint identification method for assisting bone age identification |
| CN111985414A (en) * | 2020-08-21 | 2020-11-24 | 成都数字天空科技有限公司 | Method and device for determining position of joint point |
| CN112052787A (en) * | 2020-09-03 | 2020-12-08 | 腾讯科技（深圳）有限公司 | Target detection method and device based on artificial intelligence and electronic equipment |
-
2021
- 2021-05-24 CN CN202110565098.5A patent/CN113436143A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20080319448A1 (en) * | 2006-12-12 | 2008-12-25 | Perception Raisonnement Action En Medecine | System and method for determining an optimal type and position of an implant |
| US20180204481A1 (en) * | 2017-01-18 | 2018-07-19 | Behzad Nejat | Method of creating and distributing digital data sets to improve performance of physical activities |
| CN108334899A (en) * | 2018-01-28 | 2018-07-27 | 浙江大学 | Quantify the bone age assessment method of information integration based on hand bone X-ray bone and joint |
| CN110838121A (en) * | 2018-08-15 | 2020-02-25 | 辽宁开普医疗***有限公司 | Child hand bone joint identification method for assisting bone age identification |
| CN110689551A (en) * | 2019-10-14 | 2020-01-14 | 慧影医疗科技（北京）有限公司 | Method and device for limb bone segmentation, electronic equipment and readable storage medium |
| CN111985414A (en) * | 2020-08-21 | 2020-11-24 | 成都数字天空科技有限公司 | Method and device for determining position of joint point |
| CN112052787A (en) * | 2020-09-03 | 2020-12-08 | 腾讯科技（深圳）有限公司 | Target detection method and device based on artificial intelligence and electronic equipment |
Non-Patent Citations (2)
| Title |
|---|
| DONGHYUN KIM ET.AL: "Expert System for Mandibular Condyle Detection and Osteoarthritis Classification in Panoramic Imaging Using R-CNN and CNN", 《 APPLIED SCIENCES》 * |
| 刘鸣谦 等: "基于多维度特征融合的深度学习骨龄评估模型", 《第二军医大学学报》 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115007765A (en) * | 2022-08-03 | 2022-09-06 | 山东迪格重工机械有限公司 | Stamping machine tool anti-pinch automatic control method based on infrared ray |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| EP3961500A1 (en) | Medical image detection method based on deep learning, and related device | |
| KR102014385B1 (en) | Method and apparatus for learning surgical image and recognizing surgical action based on learning | |
| CN102854983B (en) | A kind of man-machine interaction method based on gesture identification | |
| JP2022505775A (en) | Image classification model training methods, image processing methods and their equipment, and computer programs | |
| JP2022518939A (en) | Detection model training methods, equipment, computer devices and computer programs | |
| CN109741309A (en) | A kind of stone age prediction technique and device based on depth Recurrent networks | |
| CN111414946B (en) | Artificial intelligence-based medical image noise data identification method and related device | |
| CN110796018B (en) | Hand motion recognition method based on depth image and color image | |
| CN110827236B (en) | Brain tissue layering method, device and computer equipment based on neural network | |
| CN110084192B (en) | Rapid dynamic gesture recognition system and method based on target detection | |
| WO2023134071A1 (en) | Person re-identification method and apparatus, electronic device and storage medium | |
| CN107066081B (en) | Interactive control method and device of virtual reality system and virtual reality equipment | |
| US20230290174A1 (en) | Weakly supervised semantic parsing | |
| McCullough et al. | Convolutional neural network models for automatic preoperative severity assessment in unilateral cleft lip | |
| CN108521820B (en) | Coarse to fine hand detection method using deep neural network | |
| CN113436143A (en) | Joint detection method and device based on artificial intelligence and electronic equipment | |
| CN113781462A (en) | Human body disability detection method, device, equipment and storage medium | |
| CN110728172B (en) | Point cloud-based face key point detection method, device and system and storage medium | |
| CN116453226A (en) | Human body posture recognition method and device based on artificial intelligence and related equipment | |
| CN113436144A (en) | Joint rating method and device based on artificial intelligence and electronic equipment | |
| CN113436145A (en) | Bone age determination method and device based on artificial intelligence and electronic equipment | |
| Soroni et al. | Hand Gesture Based Virtual Blackboard Using Webcam | |
| CN113570616B (en) | Image processing method, image processing device, electronic equipment and computer readable storage medium | |
| Kardawi et al. | A Comparative Analysis of Deep Learning Models for Detection of Knee Osteoarthritis Disease through Mobile Apps | |
| US10893391B1 (en) | Tracking and monitoring system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210924 |