Puncture assessment method and system

Abstract

The embodiment of the invention provides a puncture assessment method and system. The method can comprise the steps of obtaining a configuration file corresponding to a target puncture process; the configuration file can comprise an event detection rule and a link assessment rule corresponding to each link in the target puncture process. The method can further comprise the step of obtaining sensing data collected by the sensing device in the process that the assessment object executes the target puncture process. The method can also comprise the step of performing event detection on the perception data based on an event detection rule corresponding to each link in the configuration file so as to determine target perception data corresponding to each link. The method further comprises the step of determining an assessment result corresponding to each link based on the link assessment rule corresponding to the link and the target sensing data.

Description

Technical Field

[0001] This application relates to the field of medical skills assessment technology, and in particular to a method and system for puncture assessment. Background Technology

[0002] In recent years, medical skills training and assessment systems have become increasingly digitized. For example, neural network models can be introduced to assist in scoring clinical procedures of medical skills. However, current scoring systems mainly construct different datasets and end-to-end algorithms for different operational steps of medical skills, lacking an assessment of the overall process of medical skills. Furthermore, different datasets require extensive annotation by examiners. In addition, current scoring systems can only be applied to a single, specific procedure. For example, different scoring systems need to be constructed for different types of punctures in puncture assessments.

[0003] Therefore, a method and system for puncture assessment is provided, which can automate the assessment of different types of puncture procedures, thereby reducing the burden on human examiners or even replacing them. Summary of the Invention

[0004] One embodiment of this specification provides a method for puncture assessment. The method may include acquiring a configuration file corresponding to the target puncture procedure. The configuration file may include event detection rules and assessment rules for each stage of the target puncture procedure. The method may further include acquiring sensing data collected by a sensing device during the target puncture procedure performed by the assessment subject. The method may further include performing event detection on the sensing data based on the event detection rules for each stage in the configuration file to determine the target sensing data for each stage. The method may further include determining the assessment result for each stage based on the stage assessment rules and the target sensing data.

[0005] This specification provides a system for puncture assessment in one embodiment. The method may include an acquisition module, a determination module, and an assessment module. The acquisition module can be used to acquire a configuration file corresponding to the target puncture procedure. The configuration file may include event detection rules and assessment rules for each step in the target puncture procedure. The acquisition module can also be used to acquire sensing data collected by sensing devices during the target puncture procedure performed by the assessment subject. The determination module can be used to perform event detection on the sensing data based on the event detection rules for each step in the configuration file to determine the target sensing data for each step. The assessment module can be used to determine the assessment result for each step based on the corresponding assessment rules and target sensing data.

[0006] One embodiment of this specification provides a computer-readable storage medium that stores computer instructions. When a computer reads the computer instructions from the storage medium, the computer executes a puncture test method. Attached Figure Description

[0007] This specification will be further described by way of exemplary embodiments, which will be described in detail with reference to the accompanying drawings. These embodiments are not limiting; in these embodiments, the same reference numerals denote the same structures, wherein: Figure 1 These are schematic diagrams illustrating application scenarios of the puncture assessment system according to some embodiments of this specification; Figure 2 This is a block diagram of a puncture assessment system according to some embodiments of this application; Figure 3 This is a flowchart illustrating an exemplary procedure for puncture assessment according to some embodiments of this specification; Figure 4 These are schematic diagrams of exemplary user interfaces shown according to some embodiments of this specification; Figure 5 This is a flowchart illustrating an exemplary process for determining target perception data corresponding to some embodiments of this specification; Figure 6 This is a schematic diagram of an exemplary process 500 for determining target perception data according to some embodiments of this specification; Figure 7 This is a flowchart of an exemplary process for determining the assessment results corresponding to a certain step, as shown in some embodiments of this specification; Figure 8 This is a schematic diagram of an exemplary process for determining the assessment results corresponding to a certain step, as shown in some embodiments of this specification. Figure 9 This is a schematic diagram of an exemplary process for parallel scoring according to some embodiments of this specification; Figure 10 This is a schematic diagram of an exemplary process for determining the assessment results corresponding to a certain step, as shown in some embodiments of this specification. Figure 11 This is a schematic diagram of an exemplary process for determining the assessment results corresponding to a certain step, as shown in some embodiments of this specification. Figure 12 This is a schematic diagram of an exemplary process for determining the assessment results corresponding to a certain step, as shown in some embodiments of this specification. Detailed Implementation

[0008] To more clearly illustrate the technical solutions of the embodiments in this specification, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are merely some examples or embodiments of this specification. For those skilled in the art, these drawings can be applied to other similar scenarios without creative effort. Unless obvious from the context or otherwise specified, the same reference numerals in the drawings represent the same structures or operations.

[0009] It should be understood that the terms “system,” “device,” “unit,” and / or “module” used herein are one way to distinguish different components, elements, parts, sections, or assemblies at different levels. However, if other terms can achieve the same purpose, they may be replaced by other expressions.

[0010] As indicated in this specification and claims, unless the context clearly indicates otherwise, the words "a," "an," "an," and / or "the" do not specifically refer to the singular and may also include the plural. Generally speaking, the terms "comprising" and "including" only indicate the inclusion of expressly identified steps and elements, which do not constitute an exclusive list, and the method or apparatus may also include other steps or elements.

[0011] Flowcharts are used in this specification to illustrate the operations performed by the system according to embodiments of this specification. It should be understood that the preceding or following operations are not necessarily performed in exact order. Instead, the steps can be processed in reverse order or simultaneously. Furthermore, other operations can be added to these processes, or one or more steps can be removed from them.

[0012] Figure 1 This is a schematic diagram illustrating an application scenario of the puncture assessment system 100 according to some embodiments of this specification. The puncture assessment system 100 can be used to conduct puncture assessments on test subjects.

[0013] like Figure 1 As shown, in some embodiments, the puncture assessment system 100 may include a puncture device 110, a network 120, a terminal device 130, a processing device 140, a storage device 150, and a sensing device 160. Multiple components in the puncture assessment system 100 can be interconnected via the network 120. For example, the puncture device 110 and the terminal device 130 can be connected or communicate via the network 120. As another example, the puncture device 110 and the processing device 140 can be connected or communicate via the network 120. In some embodiments, the connections between components in the puncture assessment system 100 can be varied. For example, the terminal device 130 can be directly connected to the processing device 140.

[0014] The puncture device 110 refers to a device used to insert (or intervene) into the interior (e.g., tissue, cavity, organ, etc.) of a target object 170 to perform a medical task. For example, the medical task may include aspirating fluid, obtaining tissue samples, establishing a channel, injecting medication, or any combination thereof. The target object refers to the object to be punctured. In some embodiments, the target object may include a biological object (e.g., a patient or a part thereof) and / or a non-biological object (e.g., a phantom).

[0015] Exemplary puncture devices may include puncture needles (e.g., lumbar puncture needles, thoracentesis needles, abdominal puncture needles, bone marrow aspiration needles, etc.), syringe needles, biopsy needles (e.g., aspiration needles, cutting needles, etc.), or any combination thereof. In some embodiments, the puncture device 110 may be a puncture device that has been digitally modified for puncture assessment. For example, the puncture device 110 may be equipped with one or more sensors for sensing the six degrees of freedom of pose and state variables of the puncture device 110. Exemplary state variables may include whether the needle core of the puncture needle has been withdrawn, whether the puncture needle is in contact with a specific area, whether the puncture needle is connected to an external instrument, whether liquid is flowing through the puncture needle, the relative position of the syringe piston, or any combination thereof.

[0016] In some embodiments, the puncture assessment system 100 further includes auxiliary devices. An auxiliary device is a device used to assist the puncture device 110 in performing puncture operations and / or carrying out medical tasks. For example, the auxiliary device may include a guidance and positioning device (e.g., an imaging device), puncture accessories, etc. The imaging device can be used to scan a target object within a detection area or scanning area to obtain scan data of the target object. For example, the imaging device may include a single-modal scanner and / or a multi-modal scanner. A single-modal scanner may include, for example, an ultrasound scanner, an X-ray scanner, a computed tomography (CT) scanner, a magnetic resonance imaging (MRI) scanner, an ultrasound examination instrument, a positron emission tomography (PET) scanner, an optical coherence tomography (OCT) scanner, an ultrasound (US) scanner, an intravascular ultrasound (IVUS) scanner, a near-infrared spectroscopy (NIRS) scanner, a far-infrared (FIR) scanner, etc., or any combination thereof. Multimodal scanners may include, for example, X-ray imaging-magnetic resonance imaging (X-MRI) scanners, positron emission tomography-X-ray imaging (PET-X-ray) scanners, single-photon emission computed tomography-magnetic resonance imaging (SPECT-MRI) scanners, positron emission tomography-computed tomography (PET-CT) scanners, digital subtraction angiography-magnetic resonance imaging (DSA-MRI) scanners, etc. The scanners described above are for illustrative purposes only and are not intended to limit the scope of this specification.

[0017] Exemplary puncture accessories may include syringes, catheters, drainage tubes, guidewires, connecting tubes, three-way valves, etc., or any combination thereof. Syringes can be used to create negative pressure to aspirate fluid or inject medication. Catheters or drainage tubes can be inserted into the target body after a successful puncture for continuous drainage of fluids (e.g., pleural effusion, ascites, bile, abscess). Guidewires can be used to guide catheters or drainage tubes to the target location on the target body. Connecting tubes or three-way valves can be used to connect different components.

[0018] Network 120 may include any suitable network capable of facilitating information and / or data exchange within the puncture assessment system 100. In some embodiments, at least one component of the puncture assessment system 100 (e.g., puncture device 110, terminal device 130, processing device 140, storage device 150, sensing device 160) may exchange information and / or data with at least one other component of the puncture assessment system 100 via network 120. For example, processing device 140 may acquire sensing data collected by sensing device 160 during the target puncture procedure performed by the assessment subject via network 120. Network 120 may include public networks (e.g., the Internet), private networks (e.g., local area networks (LANs)), wired networks, wireless networks (e.g., 802.11 networks, Wi-Fi networks), Frame Relay networks, virtual private networks (VPNs), satellite networks, telephone networks, routers, hubs, switches, fiber optic networks, telecommunications networks, intranets, wireless local area networks (WLANs), metropolitan area networks (MANs), public switched telephone networks (PSTNs), Bluetooth™ networks, ZigBee™ networks, near field communication (NFC) networks, etc., or any combination thereof. In some embodiments, network 120 may include at least one network access point. For example, network 120 may include wired and / or wireless network access points, such as base stations and / or internet switching points, through which at least one component of system 100 may connect to network 120 to exchange data and / or information.

[0019] Terminal device 130 can communicate and / or connect to puncture device 110, processing device 140, storage device 150, and / or sensing device 160. For example, a user can interact with sensing device 160 through terminal device 130 to control one or more components of sensing device 160. In some embodiments, terminal device 130 may include mobile device 130-1, tablet computer 130-2, laptop computer 130-3, etc., or any combination thereof. For example, mobile device 130-1 may include a mobile control handle, personal digital assistant (PDA), smartphone, etc., or any combination thereof.

[0020] Processing device 140 can process data and / or information obtained from puncture device 110, terminal device 130, storage device 150, sensing device 160, or other components of puncture assessment system 100. For example, processing device 140 can acquire a configuration file corresponding to the target puncture process. The configuration file may include event detection rules and assessment rules for each stage of the target puncture process. As another example, processing device 140 can acquire sensing data collected by sensing device 160 during the target puncture process performed by the assessment subject. Furthermore, processing device 140 can perform event detection on the sensing data based on the event detection rules for each stage in the configuration file to determine the target sensing data for each stage. Finally, for each stage, processing device 140 can determine the assessment result for that stage based on the stage assessment rules and the target sensing data.

[0021] In some embodiments, processing device 140 may be a single server or a group of servers. The server group may be centralized or distributed. In some embodiments, processing device 140 may be local or remote. For example, processing device 140 may access information and / or data from puncture device 110, processing device 140, storage device 150, and / or sensing device 160 via network 120. Alternatively, processing device 140 may be directly connected to puncture device 110, processing device 140, storage device 150, and / or sensing device 160 to access information and / or data. In some embodiments, processing device 140 may be implemented on a cloud platform. For example, the cloud platform may include private cloud, public cloud, hybrid cloud, community cloud, distributed cloud, inter-cloud cloud, multi-cloud, etc., or any combination thereof.

[0022] In some embodiments, the processing device 140 may include one or more processors (e.g., a single-chip processor or a multi-chip processor). By way of example only, the processing device 140 may include a central processing unit (CPU), an application-specific integrated circuit (ASIC), an application-specific instruction set processor (ASIP), a graphics processing unit (GPU), a physical processing unit (PPU), a digital signal processor (DSP), a field-programmable gate array (FPGA), a programmable logic device (PLD), a controller, a microcontroller unit, a reduced instruction set computer (RISC), a microprocessor, or any combination thereof. In some embodiments, the processing device 140 may be part of the puncture device 110 or the terminal device 130.

[0023] Storage device 150 can store data, instructions, and / or any other information. For example, storage device 150 can store configuration files corresponding to the target puncture procedure, sensing data collected by sensing device 160 during the target puncture procedure performed by the test subject, target sensing data corresponding to each stage, and test results corresponding to each stage. In some embodiments, storage device 150 can store data obtained from puncture device 110, processing device 140, storage device 150, and / or sensing device 160. In some embodiments, storage device 150 can store data and / or instructions used by processing device 140 to perform or use in order to complete the exemplary methods described herein. In some embodiments, storage device 150 may include mass storage, removable storage, volatile read-write storage, read-only storage (ROM), or any combination thereof. In some embodiments, storage device 150 can be implemented on a cloud platform.

[0024] In some embodiments, storage device 150 may be connected to network 120 to communicate with at least one other component of puncture testing system 100 (e.g., puncture device 110, processing device 140, storage device 150, and / or sensing device 160). At least one component of puncture testing system 100 may access data stored in storage device 150 via network 120. In some embodiments, storage device 150 may be part of processing device 140.

[0025] Sensing device 160 can be used to collect sensory data during the target puncture procedure performed by the test subject. For example, sensing device 160 may include a single-modal sensing device and a multi-modal sensing device. "Modality" can be understood as a form of information expression or a sensory channel. An exemplary single-modal sensing device may include an image sensor (also called a vision sensor), a sound sensor, a motion sensor, a position sensor, a state sensor, etc., or any combination thereof. The image sensor may be configured to collect image data during the target puncture procedure performed by the test subject; the sound sensor may be configured to collect voice signals during the same procedure; the motion sensor may be configured to collect motion data of the puncture device 110 and / or the test subject (or a portion thereof); the position sensor may be configured to collect position data of the puncture device 110 and / or the test subject (or a portion thereof); and the state sensor may be configured to collect state data of the puncture device 110 (or a portion thereof). For example, the image sensor may include a front-facing camera to simulate the traditional examiner's frontal observation perspective and provide third-party video information.

[0026] Exemplary multimodal sensing devices may include Mixed Reality (MR) head-mounted displays (HMDs), digitally modified puncture devices, multimodal sensors, etc. For example, an MR HMD may include image sensors (e.g., RGB cameras, infrared cameras, depth cameras, etc.), sound sensors (e.g., microphones, headphones, etc.), and motion sensors. As an example only, an MR HMD can acquire image data and voice signals during the target puncture procedure performed by the test subject, and transmit them to the test subject in a high-fidelity manner via video see-through (VST) or optical see-through (OST), without affecting the test subject's vision and operation. Simultaneously, according to a preset algorithm, the MR HMD can sense the test subject's hand information (including root pose information, joint pose information, etc.) and head information (e.g., head pose information, etc.) during the target puncture procedure. The pose information may include 6-DOF three-dimensional position and rotational posture information. In some embodiments, the sensing device 160 may be a standalone device or integrated into another device. For example, the sound sensor may be part of the puncture device 110 or the terminal device 130.

[0027] In some embodiments, all components involving pose information in the puncture assessment system 100 can be converted to a unified virtual world coordinate system. For example, the puncture device 110, the sensing device 160, and the target object 170 can be uniformly converted to the same virtual world coordinate system.

[0028] It should be noted that the above description is provided for illustrative purposes only and is not intended to limit the scope of this specification. Various changes and modifications can be made by those skilled in the art based on the content of this specification. Features, structures, methods, and other features of the exemplary embodiments described herein can be combined in various ways to obtain other and / or alternative exemplary embodiments. For example, storage device 150 may be a data storage device including a cloud computing platform (e.g., public cloud, private cloud, community cloud, and hybrid cloud). However, these changes and modifications will not depart from the scope of this specification.

[0029] Figure 2 This is a block diagram of a puncture assessment system 200 according to some embodiments of this application.

[0030] like Figure 2As shown, in some embodiments, the puncture assessment system 200 may include an acquisition module 210, a determination module 220, and an assessment module 230. In some embodiments, the functions corresponding to the puncture assessment system 200 may be implemented by the processing device 140.

[0031] The acquisition module 210 can be used to acquire the configuration file corresponding to the target puncture procedure. The configuration file may include event detection rules and procedure assessment rules for each step in the target puncture procedure. For more information on acquiring the configuration file, please refer to step 310 and its related description.

[0032] The acquisition module 210 can also be used to acquire sensing data collected by the sensing device during the target puncture process performed by the assessment object. For more information on acquiring sensing data, please refer to step 320 and its related description.

[0033] The determination module 220 can be used to perform event detection on the perceived data based on the event detection rules corresponding to each stage in the configuration file, so as to determine the target perceived data corresponding to each stage. For more information on determining the target perceived data corresponding to each stage, please refer to step 330 and its related description.

[0034] The assessment module 230 can be used to determine the assessment result for each stage based on the corresponding stage assessment rules and target perception data. For more information on determining the assessment result for each stage, please refer to step 240 and its related description.

[0035] It should be understood that Figure 2 The puncture testing system 200 and its modules shown can be implemented in various ways, for example, by hardware, software, or a combination of both. The system and its modules described herein can be implemented not only by hardware circuits such as very large-scale integrated circuits or gate arrays, semiconductors such as logic chips or transistors, or programmable hardware devices such as field-programmable gate arrays or programmable logic devices, but also by software, for example, executed by various types of processors, or by a combination of the aforementioned hardware circuits and software (e.g., firmware).

[0036] It should be noted that the above description of the puncture assessment system 200 and its modules is for convenience only and should not be construed as limiting this specification to the scope of the embodiments described. It is understood that those skilled in the art, after understanding the principles of the system, may arbitrarily combine the various modules or construct subsystems connected to other modules without departing from these principles. For example, the acquisition module 210 may include a configuration file acquisition unit and a sensory data acquisition unit. The configuration file acquisition unit can be used to acquire the configuration file corresponding to the target puncture procedure, and the sensory data acquisition unit can be used to acquire the sensory data collected by the sensing device during the target puncture procedure performed by the assessment subject.

[0037] Figure 3 This is a flowchart of an exemplary process 300 for puncture assessment according to some embodiments of this specification. In some embodiments, process 300 may be executed by processing device 140 or puncture assessment system 200. For example, process 300 may be stored in a storage device (e.g., storage unit of processing device 140, storage device 150) in the form of a program or instructions, and executed by the processor or... Figure 2 When the module shown executes a program or instructions, it can implement process 300. In some embodiments, process 300 may be completed using one or more additional operations not described below, and / or not through one or more operations discussed below. Additionally, as Figure 3 The order of operations shown is not restrictive.

[0038] Step 310: Obtain the configuration file corresponding to the target puncture procedure. In some embodiments, step 310 may be performed by the processing device 140 or the puncture assessment system 200 (e.g., the acquisition module 210).

[0039] The target puncture procedure refers to the puncture procedure that the test subject needs to follow when undergoing puncture assessment.

[0040] The assessment subjects refer to those who need to undergo puncture assessment. For example, the assessment subjects may be doctors taking clinical skills exams such as the medical licensing exam, or students learning clinical skills such as puncture.

[0041] The puncture procedure may include clinical procedures such as bone marrow aspiration, lumbar puncture, thoracentesis, and paracentesis. In some embodiments, the puncture procedure may include multiple steps. For example, multiple steps may include a preparation step, a pre-treatment step, a puncture step, and a post-treatment step. In some embodiments, according to different levels, multiple steps may further include primary steps, secondary steps, or lower-level steps. As an example only, a primary step may include a preparation step, a puncture step, and a post-treatment step. The secondary steps of the preparation step may include material preparation, target subject preparation, and assessment subject preparation. The secondary steps of the pre-treatment step may include patient positioning and puncture site selection, disinfection, puncture preparation, and anesthesia. The secondary steps of the puncture step may include puncture, post-puncture procedures, needle removal, and post-puncture site treatment.

[0042] In some embodiments, different puncture procedures may have the same steps. For example, several steps in a bone marrow aspiration procedure and several steps in a lumbar puncture procedure are the same. In some embodiments, different puncture procedures may have different steps. For example, several steps in a bone marrow aspiration procedure and several steps in a lumbar puncture procedure are different.

[0043] In some embodiments, the puncture procedure can be manually broken down into multiple steps. For example, users (e.g., examiners, teachers, etc.) can break down the puncture procedure into multiple steps according to assessment criteria documents (e.g., the "Basic Clinical Skills Operation Scoring Standards (Trial Version)" document).

[0044] In some embodiments, the processing device 140 can automatically break down the puncture procedure into multiple stages. For example, the processing device 140 can input an assessment criteria file into a splitting model, which can output text (e.g., structured text in JSON format) including multiple stages. The splitting model can be a machine learning model. In some embodiments, the processing device 140 can train an initial splitting model based on multiple sets of training samples to determine the splitting model. Each set of training samples can include a sample assessment criteria file (as training data) and the corresponding sample splitting results (as labels).

[0045] In some embodiments, the target puncture procedure may include the entire puncture procedure or a portion thereof. For example, if the entire puncture procedure includes a preparation step, a pretreatment step, a puncture step, and a posttreatment step, the target puncture procedure may include a preparation step, a pretreatment step, a puncture step, and a posttreatment step. Alternatively, the target puncture procedure may include only a pretreatment step and a puncture step.

[0046] A configuration file is a reference document that defines the relevant standards or rules for assessment. In some embodiments, the configuration file may include event detection rules and assessment rules for each stage of the target puncture process. Event detection rules are rules used to detect characteristic events. Stage assessment rules are rules used to determine the assessment results for each stage.

[0047] Feature events are events used to determine the stage in the target puncture procedure for the assessment subject. If a feature event is detected, it can be determined that the assessment subject is in the stage corresponding to that feature event. Depending on the data modality corresponding to the feature event, feature events can include feature events based on voice detection, feature events based on position and motion trajectory detection, feature events based on state-type sensor judgment, feature events based on image intelligent analysis, feature events based on video intelligent analysis, etc., or any combination thereof.

[0048] In some embodiments, each stage may correspond to one or more feature events. For example, the target object preparation stage may correspond only to feature events based on voice detection. As another example, the item preparation stage may correspond to feature events based on voice detection and feature events based on position and motion trajectory detection. In some embodiments, when a stage corresponds to multiple feature events, the processing device 140 can detect the multiple feature events in parallel. That is, the processing device 140 can simultaneously determine multiple feature events. As an example only, the feature events of each stage in the bone marrow aspiration procedure may be as shown in Table 1.

[0049] Table 1. Characteristic events at each stage of the bone marrow aspiration procedure

[0050] Event detection rules can include characteristic events and their corresponding detection rules. If an event that matches the detection rule is detected, it is considered that a characteristic event has been detected. In some embodiments, the detection rule corresponding to a characteristic event includes detection parameters and their value ranges, used to detect whether the characteristic event has occurred. For example, the detection parameter for a characteristic event corresponding to the item preparation stage can be the distance between the item and the treatment table, with a corresponding value range of less than a distance threshold, such as 5 cm, 10 cm, 15 cm, 20 cm, etc. In some embodiments, some event detection rules are related to various stages in the entire target puncture procedure, including those related to the overall performance of the subject in the target puncture procedure (such as aseptic technique, time management, and injury awareness).

[0051] The assessment rules for each stage can include each stage, its corresponding assessment parameters and their value ranges, and scoring rules. Assessment parameters are the parameters that need to be evaluated during the assessment, and their corresponding value ranges are the reference ranges within which the assessment scope lies. Scoring rules are the rules for assigning scores based on the values ​​of the assessment parameters. For example, if the assessment parameter is within its value range, 1 point can be obtained; otherwise, 0 points can only be obtained. Assessment parameters, their value ranges, and scoring rules can be used to determine the assessment result (e.g., score) for each stage.

[0052] In some embodiments, the processing device 140 can present multiple candidate steps to the user through a user interface. In response to the user's selection command, the processing device 140 can determine the steps included in the target puncture procedure from the multiple candidate steps, and generate a configuration file corresponding to the target puncture procedure based on the steps and their corresponding preset event detection rules and preset step assessment rules.

[0053] A user interface refers to an interface used for human-computer interaction. In some embodiments, the user interface may include a candidate stage area and a process configuration area. The candidate stage area can be used to present multiple candidate stages to the user. The process configuration area can be used to configure and present the target puncture procedure.

[0054] Candidate stages refer to the stages in the puncture procedure that can be assessed. For example, the processing device 140 can identify multiple stages of the puncture procedure as candidate stages based on the breakdown results. In some embodiments, candidate stages can be presented on a user interface (e.g., a candidate stage area) for the user to select. The user can be the same as the assessment subject, i.e., the assessment subject selects the stages included in the target puncture procedure. Alternatively, the user can be different from the assessment subject; for example, the user is an examiner or teacher. That is, an object other than the assessment subject selects the stages included in the target puncture procedure for the assessment subject.

[0055] A selection command is an instruction used to select a segment from the candidate segments in the target puncture procedure. In some embodiments, the selection command can be entered by moving a candidate segment to the procedure configuration area in the user interface. For example, a user can drag and drop a candidate segment from the candidate segment area to the procedure configuration area in the user interface to enter the selection command. Alternatively, a user can enter the selection command in the procedure configuration area of ​​the user interface using an interactive device (e.g., a keyboard, microphone, etc.).

[0056] For example only, Figure 4 This is a schematic diagram of an exemplary user interface 400 according to some embodiments of this specification. For example... Figure 4As shown, the user interface 400 includes a process configuration area 410 and a candidate stage area 420. The candidate stage area 420 presents multiple candidate stages to the user, such as a preparation stage 422, a pre-processing stage 424, a puncture stage 426, and a post-processing stage 428. The user can drag and drop candidate stages (e.g., pre-processing stage 424 and puncture stage 426) from the candidate stage area 420 to the process configuration area 410 to input a selection command. Accordingly, in response to the user's selection command, it can be determined that the target puncture process includes pre-processing stage 424 and puncture stage 426.

[0057] In some embodiments, the configuration file may also include information about the relationships between the steps of the target puncture procedure. This relationship information may include sequential relationships and independence relationships. A sequential relationship refers to the order in which steps are executed (e.g., a dependency relationship). For example, if there is a sequential relationship between step A and step B (e.g., step A is a dependent step of step B), and step A is not executed when step B is executed, then step A is considered missed, and any subsequent execution of step A is considered invalid. As an example only, an anesthesia procedure includes anesthesia preparation steps (e.g., draping the anesthesia drape) and anesthesia steps that have a sequential relationship. If the subject executes the anesthesia step without executing the anesthesia preparation step, even if the anesthesia preparation step is executed during the anesthesia step, the anesthesia preparation step is still considered not executed. Alternatively, the assessment of the sequential relationship between the anesthesia preparation step and the anesthesia step will not receive any points.

[0058] An independent relationship refers to a situation where there is no sequential relationship between the execution of steps (e.g., a dependency relationship). For example, the preparation step includes preparing materials, preparing the target, and preparing the assessment subject. The assessment subject can perform any one of these steps first.

[0059] Relationship information can be determined based on preset relationships between stages in the target puncture procedure, or by user-inputted stage connection instructions. Stage connection instructions are used to set the relationship information between stages included in the target puncture procedure. In some embodiments, stage connection instructions can be input by establishing connections between stages. For example, the user establishes a connection between two stages in the procedure configuration area.

[0060] In some embodiments, the processing device 140 can create or update a tree-like flowchart or a directed acyclic graph (DAG) corresponding to the target puncture procedure on a user interface based on selection instructions and link connection instructions. A tree-like flowchart is a diagram that combines the hierarchical characteristics of a tree structure with the process-oriented nature of a flowchart. A directed acyclic graph (DAG) is a graph with direction and does not fall into loops. Tree-like flowcharts or DAGs can visually represent the sequential relationships of links in the target puncture procedure.

[0061] For example only, please continue reading. Figure 4 A connection A can be established between the pre-processing stage 424 and the puncture stage 426 to input the connection instruction, thereby creating a tree flowchart corresponding to the target puncture process. The arrow direction of the connection A indicates that there is a sequential relationship (e.g., a prerequisite dependency relationship) between the pre-processing stage 424 and the puncture stage 426.

[0062] In some embodiments, the processing device 140 can generate a configuration file corresponding to the target puncture procedure based on the user-selected stage and its corresponding preset event detection rules and preset stage assessment rules. For example, the processing device 140 can select preset event detection rules and preset stage assessment rules corresponding to the user-selected stage from a rule base, thereby generating a configuration file corresponding to the target puncture procedure. The rule base refers to a database that pre-stores preset event detection rules and preset stage assessment rules corresponding to candidate stages. For example, preset event detection rules and preset stage assessment rules can be determined based on historical puncture assessment data and stored in the rule base.

[0063] The configuration file can be dynamically loaded through user commands, thereby binding the candidate stages and candidate data in the rule base, ensuring the flexibility and versatility of the configuration file.

[0064] For example, the processing device 140 can select preset event detection rules and preset stage assessment rules corresponding to the stage selected by the user from the rule base, and present these rules to the user through a user interface. Furthermore, the processing device 140 can generate a configuration file corresponding to the target puncture procedure based on the stage, preset event detection rules, preset stage assessment rules, and user-inputted rule update instructions. Rule update instructions can be used to update the preset event detection rules and / or preset stage assessment rules. As an example only, rule update instructions may include instructions to delete or add feature events corresponding to the stage, instructions to adjust detection parameters and / or their value ranges in the preset event detection rules, instructions to adjust assessment parameters and / or their value ranges in the preset stage assessment rules, or any combination thereof.

[0065] By introducing rule update instructions, the rationality of the configuration file can be checked and personalized, improving the adaptability and accuracy of the configuration file to the target puncture procedure, thereby improving the accuracy of the scoring.

[0066] Step 320: Acquire sensing data collected by the sensing device during the target puncture procedure performed by the assessment subject. In some embodiments, step 320 may be performed by the processing device 140 or the puncture assessment system 200 (e.g., acquisition module 210).

[0067] Sensing devices are devices used to collect sensing data. For example, sensing devices can include single-modal sensing devices and multi-modal sensing devices (e.g., MR HMDs). More information about sensing devices can be found at [link to relevant documentation]. Figure 2 And its related descriptions.

[0068] Sensing data refers to data collected by sensing devices during the target puncture procedure performed by the test subject. For example, sensing data may include image data (pictures or videos), voice data, sensor data (position, movement trajectory, status, etc.), or any combination thereof. In some embodiments, multimodal sensing data can be collected simultaneously using multiple sensing devices.

[0069] In some embodiments, the processing device 140 (e.g., the acquisition module 210) can acquire sensing data from a sensing device (e.g., sensing device 160) or a storage device (e.g., storage device 150, a database, or external storage) that stores the sensing data.

[0070] Step 330: Based on the event detection rules corresponding to each stage in the configuration file, perform event detection on the perceived data to determine the target perceived data corresponding to each stage. In some embodiments, this step 330 may be performed by the processing device 140 or the puncture assessment system 200 (e.g., the determination module 220).

[0071] Feature event detection refers to detecting feature events to determine whether an operation corresponding to the perceived data has entered, ended, or is in the process of entering a certain stage. For example, for the item preparation stage, the detection parameter for the feature event is the distance between the item and the treatment table, and the value of the detection parameter is less than 10 centimeters. The processing device 140 can determine the actual distance between the item and the treatment table based on the perceived data (e.g., image data). If the actual distance between the item and the treatment table is less than 10 centimeters, the processing device 140 detects the feature event and indicates that the item preparation is complete.

[0072] Therefore, the processing device 140 can perform event detection on the sensing data collected at different times based on the event detection rules corresponding to each stage in the configuration file, in order to determine the specific stage corresponding to the sensing data at different times, and thus divide the sensing data into stages. For example, when a start feature event entering stage A and an end feature event ending stage A are detected, the processing device 140 can determine the target sensing data for stage A from the sensing data based on the start feature event and the end feature event. The target sensing data is the sensing data whose collection time is located between the first collection time and the second collection time. The first collection time refers to the collection time of the first subset of sensing data corresponding to the start feature event, and the second collection time refers to the collection time of the second subset of sensing data corresponding to the end feature event.

[0073] Target perception data refers to the perception data corresponding to a specific stage. For example, if the perception data for 0-1 minutes is determined to be the perception data for the item preparation stage, the processing device 140 can define the 0-1 minute perception data as the target perception data for the item preparation stage.

[0074] In some embodiments, the event detection rules corresponding to each stage can define the target sensing device and its detection standard corresponding to the feature event in the stage. For example, when the feature event corresponds to a feature event based on speech detection, the target sensing device corresponding to the feature event is a sound sensor, and the detection standard corresponding to the feature event also corresponds to speech perception data.

[0075] In some embodiments, for each stage, the processing device 140 can determine whether the sensing data contains a subset of sensing data corresponding to the feature events of the stage. The subset of sensing data may be collected by the target sensing device corresponding to the feature events, and its content conforms to the corresponding detection criteria. In response to determining that the sensing data contains a subset of sensing data corresponding to the feature events of the stage, the processing device 140 can use the subset of sensing data as the target sensing data corresponding to the stage. For more information on determining the target sensing data, see [link to relevant documentation]. Figure 5 And its related descriptions.

[0076] Step 340: For each stage, determine the corresponding assessment result based on the stage assessment rules and target perception data. In some embodiments, this step 330 may be performed by the processing device 140 or the puncture assessment system 200 (e.g., assessment module 230).

[0077] Assessment results can indicate the extent to which the assessed individual has completed a given process. For example, assessment results may include a score for each process.

[0078] The evaluation rules for each stage can include a primary evaluation criterion related to the execution order of stages. This primary criterion defines the sequence of stages. For example, when a stage has dependent stages, if a dependent stage is not executed when the current stage is executed, the dependent stage is considered missed, and any subsequent execution of the dependent stage is considered invalid. The evaluation rules can also include a secondary evaluation criterion related to the quality of stage execution. For example, the secondary criterion defines the execution time, duration, and specifications of a specific characteristic event within the stage, used to evaluate the completion rate of the characteristic event. Some stages have only a secondary evaluation criterion; these stages are called independent stages. Some stages can have both a primary and a secondary evaluation criterion; these stages are called non-independent stages.

[0079] In some embodiments, for an independent stage without a first assessment standard, the processing device 140 may determine the assessment result for that stage individually or determine the assessment result in parallel with any other stage.

[0080] For example only, see Figure 9 , Figure 9 This is a schematic diagram of an exemplary parallel scoring process 900 according to some embodiments of this specification.

[0081] like Figure 9 As shown, the item preparation stage and the target object preparation stage are both independent stages (without dependencies). Therefore, the processing device 140 can determine the evaluation results of the item preparation stage and the target object preparation stage in parallel.

[0082] For the item preparation and target preparation stages, the corresponding second assessment criteria include a dictionary of keywords for the items to be checked, which must be verbally stated. A score is awarded for either the item preparation or target preparation stage when all keywords in the dictionary are mentioned (no points are awarded for omissions during item inspection). For example, speech recognition can be performed on the corresponding voice inputs "A" and "B" to determine if they contain keywords from the dictionary. Simultaneously, feature event detection and assessment can be conducted through image and video analysis. For example, for the "mask and hat wearing" and "hand disinfection" stages, image and video analysis can be used. Mask and hat wearing is captured by cameras in the examination room at fixed time intervals and transmitted to the cloud for detection. When the examinee's human posture skeleton and the content of the mask and hat are detected, the relative position of the mask / hat and the head and neck within the skeleton is determined to determine whether the mask / hat is worn correctly at a given time. Regarding hand disinfection, a video stream of several seconds will be recorded and transmitted to the cloud when hands overlap for a certain degree and for a certain duration. Behavioral recognition models such as SlowFast and I3D will be used for confirmation to determine whether handwashing was performed at a given time.

[0083] In some embodiments, the processing device 140 can determine whether the assessment rules corresponding to a stage include a first assessment criterion related to the stage sequence and a second assessment criterion related to the stage execution quality. If the assessment rules include a first assessment criterion related to the stage sequence and a second assessment criterion related to the stage execution quality, the processing device 140 can acquire target perception data corresponding to the stage's dependent stages. The processing device 140 can determine a first assessment result corresponding to the first assessment criterion based on the acquisition time of the target perception data corresponding to the stage and the target perception data corresponding to the dependent stages, and determine a second assessment result corresponding to the second assessment criterion based on the target perception data. For more information on determining the assessment results corresponding to a stage, see [link to relevant documentation]. Figure 7 And its related descriptions.

[0084] According to the embodiments of this specification, a configuration file corresponding to the target puncture procedure can be pre-determined before the assessment of the target puncture procedure begins. The configuration file includes event detection rules and assessment rules for each stage of the target puncture procedure. During or after the assessment of the target puncture procedure, sensing data collected by the sensing device during the assessment of the subject performing the target puncture procedure can be acquired. Based on the event detection rules corresponding to each stage in the configuration file, event detection is performed on the sensing data to determine the target sensing data for each stage. Furthermore, for each stage, based on the stage assessment rules and the target sensing data, the assessment result for that stage is determined, thereby achieving automated assessment, reducing the burden on human examiners, and ultimately replacing human examiners.

[0085] It should be noted that the above description of process 300 is for illustrative purposes only and does not limit the scope of this specification. Those skilled in the art can make various modifications and changes to process 300 under the guidance of this specification. However, these modifications and changes remain within the scope of this specification.

[0086] Figure 5 This is a flowchart of an exemplary process 500 for determining target perception data corresponding to a certain step, as shown in some embodiments of this specification. In some embodiments, process 500 may be executed by processing device 140 or puncture assessment system 200. For example, process 500 may be stored in a storage device (e.g., storage unit of processing device 140, storage device 150) in the form of a program or instructions, and executed by the processor or... Figure 2 When the module shown executes a program or instructions, it can implement process 500. In some embodiments, process 500 may be completed using one or more additional operations not described below, and / or not through one or more operations discussed below. Additionally, as Figure 5 The order of operations shown is not restrictive. In some embodiments, Figure 3 The target perception data corresponding to the determination step described in operation 330 can be obtained according to process 500.

[0087] Step 510: Determine whether the sensed data contains a subset of sensed data corresponding to the characteristic events of the segment. In some embodiments, this step 510 may be performed by the processing device 140 or the puncture assessment system 200 (e.g., the determination module 220).

[0088] A subset of the perceived data can be collected by the target sensing device corresponding to the feature event, and its content conforms to the corresponding detection standard.

[0089] In some embodiments, the processing device 140 can perform parallel detection of different feature events in different stages to determine whether the perceived data contains a subset of perceived data corresponding to each feature event in each stage.

[0090] In some embodiments, the processing device 140 can determine a first subset of sensing data corresponding to the start feature events of a stage and a second subset of sensing data corresponding to the end feature events of a stage from the sensing data. The processing device 140 can filter candidate sensing data from the sensing data whose acquisition time falls within a target acquisition period. The target acquisition period can be between a first acquisition time corresponding to the first subset of sensing data and a second acquisition time corresponding to the second subset of sensing data. The processing device 140 can determine whether the candidate sensing data contains a subset of sensing data corresponding to other feature events of the stage, i.e., detect other feature events of the stage.

[0091] A start feature event refers to a feature event that enters a stage. An end feature event refers to a feature event that ends a stage or indicates that a stage has been completed. In some embodiments, the processing device 140 can determine the start and end feature events based on their respective event detection rules. By detecting the start and end feature events of a stage first, the target acquisition period corresponding to the stage can be quickly identified; the detection of other feature events in that stage can be performed directly based on the sensing data corresponding to the target acquisition period, rather than based on all sensing data. In this way, the amount of data processing can be reduced and the event detection efficiency can be improved.

[0092] Step 520: In response to determining that the sensing data contains a subset of sensing data corresponding to the feature events of the segment, the subset of sensing data is used as the target sensing data corresponding to the segment. In some embodiments, this step 510 may be performed by the processing device 140 or the puncture assessment system 200 (e.g., the determination module 220).

[0093] After determining that the sensing data contains a subset of the sensing data corresponding to the characteristic events of the process, the processing device 140 can use the subset of sensing data as the target sensing data corresponding to the process.

[0094] For example only, see Figure 6 , Figure 6 This is a schematic diagram of an exemplary process 600 for determining target perception data according to some embodiments of this specification. For example... Figure 6 As shown, the sensing data may include sensing data 610 and sensing data 620, and the target sensing device corresponding to the feature events in link A and link B is the sensing device that collects sensing data 610.

[0095] The processing device 140 can determine, from the sensing data 610, a first subset 612 of the starting feature events corresponding to stage A and a second subset 614 of the ending feature events corresponding to stage A. The processing device 140 can determine that the target acquisition period for stage A is between the first acquisition time (0 minutes) corresponding to the first subset 612 and the second acquisition time (5 minutes) corresponding to the second subset 614. Further, the processing device 140 can filter candidate sensing data 652 from the sensing data 610 whose acquisition time falls within the target acquisition period; and filter candidate sensing data 662 from the sensing data 620 whose acquisition time falls within the target acquisition period. The processing device 140 can determine the subsets of sensing data corresponding to other feature events of the stage from the candidate sensing data 652 and 662. The processing device 140 can use the first subset 612, the second subset 614, and the subsets of sensing data corresponding to other detected feature events as target sensing data. Alternatively, the processing device 140 can directly determine the candidate sensing data 652 and 662 as target sensing data.

[0096] The processing device 140 can determine, from the sensing data 610, a first subset 614 of the starting feature events corresponding to stage B and a second subset 616 of the ending feature events corresponding to stage B. The processing device 140 can determine that the second target acquisition period corresponding to stage B is between the first acquisition time (5 minutes) corresponding to the first subset 614 and the second acquisition time (25 minutes) corresponding to the second subset 616. Further, the processing device 140 can filter candidate sensing data 654 from the sensing data 610, and candidate sensing data 664 from the sensing data 620, whose acquisition time falls within the second target acquisition period. The processing device 140 can determine, from the candidate sensing data 654, a subset 615 of sensing data corresponding to other feature events of the stage (corresponding to a time period of 10-12 minutes), and a subset of sensing data corresponding to other feature events of the stage that are not included in the candidate sensing data 664. Therefore, the processing device 140 can determine the first sensing data subset 614, the second sensing data subset 616, and the sensing data subset 615 as target sensing data.

[0097] Figure 7 This is a flowchart of an exemplary process 700 for determining the assessment result corresponding to a certain step, as shown in some embodiments of this specification. In some embodiments, process 700 may be executed by processing device 140 or puncture assessment system 200. For example, process 700 may be stored in a storage device (e.g., storage unit of processing device 140, storage device 150) in the form of a program or instructions, and executed by the processor or... Figure 2When the module shown executes a program or instructions, it can implement process 700. In some embodiments, process 700 may be completed using one or more additional operations not described below, and / or not through one or more operations discussed below. Additionally, as Figure 7 The order of operations shown is not restrictive. In some embodiments, Figure 3 The assessment results corresponding to the determination step described in operation 340 can be obtained according to process 700.

[0098] Step 710: In response to the fact that the assessment rules for the process include a first assessment criterion related to the sequence of processes and a second assessment criterion related to the quality of process execution, target perception data corresponding to the dependent processes of the process is obtained. In some embodiments, this step 710 may be performed by the processing device 140 or the puncture assessment system 200 (e.g., assessment module 230).

[0099] The sequence of steps refers to the order in which different steps are executed. For example, when a step has dependent steps, it must be executed after the dependent steps have been executed. In this case, the evaluation rules for that step can include a first evaluation criterion related to the sequence of steps and a second evaluation criterion related to the quality of step execution. Conversely, when a step has no dependent steps, it is independent. In this case, the evaluation rules for that step can include only the second evaluation criterion related to the quality of step execution.

[0100] The target perception data corresponding to the dependent link refers to the data in the perception data corresponding to the dependent link. The method for obtaining the target perception data corresponding to the dependent link can be the same as or similar to the method for obtaining the target perception data. For more information, please refer to [link to relevant documentation]. Figure 5 and 6 And its related descriptions.

[0101] Step 720: Based on the acquisition time of the target perception data and the target perception data corresponding to the dependent link, determine the first assessment result corresponding to the first assessment standard. In some embodiments, this step 720 may be performed by the processing device 140 or the puncture assessment system 200 (e.g., assessment module 230).

[0102] For example, processing device 140 can compare the acquisition times of the target perception data and the target perception data corresponding to the dependent link. If the acquisition time of the target perception data is earlier than or simultaneous with the acquisition time of the target perception data corresponding to the dependent link, processing device 140 can determine that the dependent link is executed before the dependent link is executed, and determine the first assessment result as failing or receiving no score. If the acquisition time of the target perception data is later than the acquisition time of the target perception data corresponding to the dependent link, processing device 140 can determine that the dependent link is executed after the dependent link is executed, and determine the first assessment result as passing or receiving a score.

[0103] Step 730: Based on the target perception data, determine the second assessment result corresponding to the second assessment standard. In some embodiments, this step 730 may be performed by the processing device 140 or the puncture assessment system 200 (e.g., assessment module 230).

[0104] In some embodiments, the processing device 140 can determine whether the target perception data meets the second assessment criterion, thereby determining the second assessment result corresponding to the second assessment criterion. For example, when it is determined that the target perception data meets the second assessment criterion, the processing device 140 can determine that the second assessment result is a pass or a score. As another example, when it is determined that the target perception data does not meet the second assessment criterion, the processing device 140 can determine that the second assessment result is a fail or a score.

[0105] In some embodiments, the feature events included in a process may be dependent on each other. Accordingly, the second evaluation criterion may include a third evaluation criterion related to the order of feature events and a fourth evaluation criterion related to the quality of feature event execution.

[0106] In response to the second evaluation criterion including a third evaluation criterion related to the sequence of feature events and a fourth evaluation criterion related to the execution quality of feature events, the processing device 140 can determine the subset of perceived data corresponding to each feature event in the target perceived data. More information on how to determine the subset of perceived data corresponding to a feature event can be found in [link to relevant documentation]. Figure 5 The processing device 140 can determine the third assessment result corresponding to the third assessment standard based on the acquisition time of the sensory data subset corresponding to each feature event. The method for determining the third assessment result can be the same as or similar to the method for determining the first assessment result, and will not be elaborated here. Furthermore, for each feature event, the processing device 140 can determine the fourth assessment result corresponding to the fourth assessment standard based on its corresponding sensory data subset. For example, the fourth assessment standard may include assessment parameters, value ranges, scoring rules, etc., corresponding to each feature event in the process. The processing device 140 can score the sensory data subset corresponding to each feature event according to the fourth assessment standard. For example, the feature event corresponding to hand disinfection is the hand crossing event in video data, and its corresponding assessment parameter is the duration of hand crossing, with a score awarded when the crossing duration exceeds 30 seconds. The processing device 140 can determine the actual duration of the hand crossing of the assessment subject based on the video data (i.e., the sensory data subset) capturing the hand disinfection scene. If the actual duration exceeds 30 seconds, the processing device 140 can determine the fourth assessment result as pass or score. If the actual duration does not exceed 30 seconds, the processing device 140 can determine that the fourth assessment result is a failure or no score.

[0107] In some embodiments, for a standalone stage, only the second assessment result needs to be determined.

[0108] For example only, see Figure 8 , Figure 8 This is a schematic diagram of an exemplary process 800 for determining the assessment result corresponding to a certain step, as shown in some embodiments of this specification. Figure 8 As shown, it can be determined whether the assessment rules corresponding to step 810 include a first assessment standard 820 related to the step sequence and a second assessment standard 825 related to the step execution quality. If it includes the first assessment standard 820 and the second assessment standard 825, the first assessment result 830 corresponding to the first assessment standard 820 and the second assessment result 835 corresponding to the second assessment standard 825 can be determined. If it does not include the first assessment standard 820, only the second assessment result 835 corresponding to the second assessment standard 825 can be determined.

[0109] When determining the second assessment result 835 corresponding to the second assessment criterion 825, it can be determined whether the second assessment criterion includes a third assessment criterion 8252 related to the sequence of characteristic events and a fourth assessment criterion 8254 related to the performance quality of characteristic events. If it includes both the third and fourth assessment criterions 8252, the third assessment result 8352 corresponding to the third assessment criterion 8252 and the fourth assessment result 8354 corresponding to the fourth assessment criterion 8254 can be determined. If it does not include the third assessment criterion 8252, only the fourth assessment result 8354 corresponding to the fourth assessment criterion 8254 can be determined.

[0110] For example, see Figure 10 , Figure 10 This is a schematic diagram of a procedure 1000 for evaluating a puncture procedure, as shown in some embodiments of this specification. For example... Figure 10 As shown, the puncture procedure can include the puncture stage, post-puncture procedures, and needle removal and post-puncture site treatment. The assessment standard for the puncture stage is: "The operator uses their left thumb and index finger to fix the puncture site (4'), and holds the bone marrow aspiration needle in their right hand to insert it perpendicularly to the bone surface (4'). After the needle tip contacts the bone, the operator rotates the needle left and right along its long axis and advances it forward, slowly inserting it into the bone (4'), so that the needle is firmly fixed inside the bone (4')." Therefore, there are requirements for the position of the left hand, the angle of needle insertion, the technique of inserting the needle into the bone, and the final fixation state.

[0111] The processing device 140 can define the initiation characteristic event of the puncture process as "the handheld puncture needle entering the spatial volume range of the puncture point on the phantom," that is, it detects whether the puncture needle (e.g., the puncture device 110) is not stationary and is held by hand, and considers the entry into the puncture process as the puncture needle's three-dimensional position approaching the phantom puncture point. The three-dimensional position of the puncture needle can be tracked in real time, and the stationary position of the phantom puncture point can be initially registered and detected in real time using a positioning method. To analyze the insertion angle and rotational posture into the bone during the puncture process, the left-hand fixed puncture point can be determined as the starting point of the puncture process, using hand tracking and gesture detection system information for judgment, and the state signal of the puncture needle sensor can be determined as the ending point of the puncture process, extracting the sequence information of the puncture needle's six-degree-of-freedom pose data and time trajectory. The processing device 140 can determine whether the puncture needle is perpendicular to the bone plane based on the sequence information, and whether it rotates around the long axis during its advancement. The puncture is considered complete when the base of the puncture needle contacts a specific area of ​​the phantom (e.g., the phantom itself). At this point, the relative position of the puncture needle with respect to the phantom and the puncture point can be determined to see if the puncture is in place and enters the bone.

[0112] The needle insertion process can be described using the needle trajectory. The needle trajectory can be represented as follows: ,in Representing the puncture needle pose in a virtual world coordinate system Homogeneous matrix for The corresponding timestamp. During the needle insertion process, the angle between the vector of the long axis of the puncture needle along the needle tip and the negative normal vector is always less than a certain threshold (keeping the needle inserted perpendicularly), which can be expressed by formula (1): (1) in, for The extracted three-dimensional position, Let be the outward normal vector of the plane of the anterior superior iliac spine at the target puncture point of the phantom. During needle insertion, the absolute value of the frame-by-frame rotation along the positive and negative directions of the long axis is greater than a specific threshold (left and right rotation into the bone), which can be expressed by formulas (2) and (3): (2) (3) in, and These are specific thresholds for left and right rotation, A function used to determine and The difference between the rotations is represented by the Euler angle of the positive rotation of the major axis of the puncture needle, and the function value is 0 when it is a negative rotation. Function meaning and Similarly, the needle position at the end of the insertion process ( ) and the initial needle position ( The difference vector is in the same direction as the negative normal direction, and the projection of this displacement onto the negative normal direction is the same as a specific value ( The absolute value of the difference is less than a certain threshold. It can be expressed by formula (4): (4) The evaluation criteria for the post-puncture procedure are: "Remove the needle core, connect a dry syringe (10cm or 20cm), aspirate bone marrow fluid with appropriate force (4'), drop 0.2ml of bone marrow fluid onto a glass slide for the assistant to immediately prepare a bone marrow smear (4'), and reinsert the needle core after the bone marrow fluid aspiration is complete (4')." Sensors on the intelligently modified (digitally modified) puncture needle can be used to detect various characteristic events in the post-puncture procedure, including removing the needle core, connecting the syringe, aspirating fluid, disconnecting the syringe, reinserting the needle core, and transferring the bone marrow fluid for oral smear preparation. Removing the needle core is the initial characteristic event of the post-puncture procedure. If the puncture procedure is not considered complete (e.g., the needle is not fully inserted), the detection of this event (removing the needle core) will also indicate that the puncture procedure is finished. If the state changes and sequence of the various sensors meet the requirements, it is determined that each step has been executed and in the correct order. When the state of the fluid aspirator sensor is valid, it is determined that bone marrow fluid has been successfully aspirated.

[0113] The assessment criteria for the needle removal and post-puncture site treatment are as follows: "After removing the puncture needle, disinfect the puncture site again with povidone-iodine, apply sterile gauze to the puncture site (4'), press for 1-2 minutes (more than 5 minutes for those with low platelet counts), and after confirming that the puncture site is no longer bleeding, apply pressure with adhesive tape (4')." The phantom contact sensor on the puncture needle base can be used to track the puncture needle leaving the phantom puncture point range as the initial characteristic event for the needle removal and post-puncture site treatment. Then, the disinfection event is detected, the pressing action is detected using hand tracking, and finally, the image classification model is used to determine whether the bandaging and tape fixation are completed.

[0114] The scoring method for disinfection events in the post-needle removal and puncture site treatment process is basically the same as that for the disinfection process itself, but extensive disinfection is not required; simply picking up a sterile cotton ball and placing it within the puncture site area is sufficient. The scoring for the disinfection process can be as follows: Figure 11 As shown. The overall process of disinfection will not be repeated here, as it is similar to the above. The disinfection mode is executed by capturing the hand trajectory during a single disinfection process. Confirmed. Among them, This can be considered as the three-dimensional positional information of the fingertip. It allows us to determine the center point of the puncture site volume and the radial distances between points. and angle Check whether the radial distance increases overall (allowing for small fluctuations), which can be expressed by formula (5): (5) in, The proportional threshold is used to adjust the allowable retraction ratio.

[0115] Furthermore, it can be determined whether the angle change is continuous (without jumps), which can be expressed by formula (6): (6) in, A threshold for determining whether an angle change is continuous.

[0116] Then, the velocity vector can be decomposed to calculate the radial velocity. and tangential velocity Verification speed ratio: ,Right now Finally, if the distance between the center point of the trajectory and the puncture point is less than a certain specific value, and the trajectory conforms to the property of a gradually expanding spiral, then the disinfection is deemed satisfactory. Repeat this process three times, calculating the maximum radial distance for each iteration. The distance must decrease progressively, and the final value must be greater than a specific value for the repeated disinfection to be deemed satisfactory.

[0117] In some embodiments, neural networks can be used to score whether a disinfection trajectory is acceptable. For example, by collecting a large amount of disinfection trajectory data and corresponding video data, medical examination examiners can be recruited to annotate the video data, obtaining a dataset of (trajectory, score), and an RNN-based temporal data classification neural network can be trained using this dataset. During runtime, the RNN-based temporal data classification neural network can be used to score whether a disinfection trajectory is acceptable.

[0118] For example, see Figure 12 , Figure 12 This is a schematic diagram of a scoring process 1200 for an exemplary anesthesia procedure according to some embodiments of this specification. The anesthesia procedure is an operation that requires relatively complex judgment of the trajectory. For example... Figure 12 As shown, trajectory data is extracted based on state time detection and entry / exit marker times. The syringe trajectory and state are... .in, To track the position trajectory of the needle obtained by the syringe. The piston position data was obtained using a piston position sensor modified from a syringe. This was to ensure the anesthesia mode met the requirement of "injecting a wheal first, then administering medication while simultaneously advancing the needle and aspirating, gradually anesthetizing the periosteum." The trajectory needs to meet the characteristics of a stepped progression, at the start of the injection. A section needs to be shortened to better represent hitting Pichu, and then... The plateau phase of the trajectory exhibits a pattern of first increasing and then decreasing, reflecting the requirement of no blood aspiration before drug administration. Finally, the anesthesia reaches the periosteum, which needs to be calculated. The distance from the periosteum and the preset threshold are used to determine the effectiveness of the anesthetic endpoint.

[0119] An end-to-end trajectory regression network model can be used for scoring. The data construction and training of the trajectory regression network model can be similar to those for disinfection scoring. For example, a large amount of syringe trajectory and status data and corresponding video stream data can be collected, medical examination examiners can be recruited to score and label the collected data, and then a sequence data regression network model can be trained to perform regression scoring estimation on the collected trajectory data.

[0120] According to the embodiments of this specification, by introducing a first assessment criterion related to the sequence of steps, the sequentiality between different steps in the target puncture procedure can be evaluated, improving the accuracy of scoring. Furthermore, by introducing sequential requirements between different steps (characteristic events) within a step, the sequentiality within the step is evaluated, further improving the accuracy of scoring.

[0121] In some embodiments of this specification, (1) the configuration file corresponding to the target puncture procedure is predetermined before the assessment of the target puncture procedure begins; during the assessment of the target puncture procedure, the assessment result corresponding to the step is determined based on the configuration file and the collected target perception data, thereby realizing automated assessment, reducing the burden on human examiners and replacing human examiners; (2) by using multimodal perception data, different types of information can be provided, thereby improving the comprehensiveness and richness of information, and thus improving the accuracy of subsequent feature event detection and scoring; (3) by using a first assessment standard related to the step sequence and a second assessment standard related to the step execution quality, the execution sequence and execution quality of the steps can be evaluated from multiple angles at the same time, thereby improving the accuracy of the assessment.

[0122] The basic concepts have been described above. Obviously, for those skilled in the art, the detailed disclosure above is merely illustrative and does not constitute a limitation of this specification. Although not explicitly stated herein, those skilled in the art may make various modifications, improvements, and corrections to this specification. Such modifications, improvements, and corrections are suggested in this specification and therefore remain within the spirit and scope of the exemplary embodiments described herein.

[0123] Furthermore, this specification uses specific terms to describe embodiments thereof. For example, "an embodiment," "one embodiment," and / or "some embodiments" refer to a particular feature, structure, or characteristic associated with at least one embodiment of this specification. Therefore, it should be emphasized and noted that references to "an embodiment," "one embodiment," or "an alternative embodiment" in different locations throughout this specification do not necessarily refer to the same embodiment. Moreover, certain features, structures, or characteristics in one or more embodiments of this specification can be appropriately combined.

[0124] Furthermore, unless expressly stated in the claims, the order of processing elements and sequences, the use of numbers and letters, or other names described in this specification are not intended to limit the order of the processes and methods described herein. Although various examples have been discussed in the foregoing disclosure of some embodiments of the invention that are currently considered useful, it should be understood that such details are for illustrative purposes only, and the appended claims are not limited to the disclosed embodiments; rather, the claims are intended to cover all modifications and equivalent combinations that conform to the spirit and scope of the embodiments described herein. For example, while the system components described above can be implemented using hardware devices, they can also be implemented solely using software solutions, such as installing the described system on existing servers or mobile devices.

[0125] Similarly, it should be noted that, in order to simplify the description disclosed herein and thus aid in the understanding of one or more embodiments of the invention, the foregoing description of embodiments in this specification may sometimes combine multiple features into a single embodiment, drawing, or description thereof. However, this method of disclosure does not imply that the subject matter of this specification requires more features than those mentioned in the claims. In fact, the embodiments contain fewer features than all the features of a single embodiment disclosed above.

[0126] In some embodiments, numbers describing the quantity of components and attributes are used. It should be understood that such numbers used in the description of embodiments are modified in some examples with the terms "approximately," "approximately," or "generally." Unless otherwise stated, "approximately," "approximately," or "generally" indicates that the numbers are allowed to vary by ±20%. Accordingly, in some embodiments, the numerical parameters used in the specification and claims are approximate values, which may be changed depending on the characteristics required by individual embodiments. In some embodiments, numerical parameters should take into account specified significant digits and employ a general method of digit reservation. Although the numerical ranges and parameters used to confirm their breadth of range in some embodiments of this specification are approximate values, in specific embodiments, such values ​​are set as precisely as feasible.

[0127] For each patent, patent application, patent application publication, and other material such as articles, books, specifications, publications, and documents referenced in this specification, the entire contents of which are incorporated herein by reference. This excludes historical application documents that are inconsistent with or conflict with the content of this specification, as well as documents that limit the broadest scope of the claims in this specification (currently or subsequently appended to this specification). It should be noted that in the event of any inconsistency or conflict between the descriptions, definitions, and / or terminology used in the supplementary materials to this specification and the content of this specification, the descriptions, definitions, and / or terminology used in this specification shall prevail.

[0128] Finally, it should be understood that the embodiments described in this specification are merely illustrative of the principles of the embodiments described herein. Other variations may also fall within the scope of this specification. Therefore, alternative configurations of the embodiments described herein are intended to be illustrative rather than limiting, and should be considered consistent with the teachings of this specification. Accordingly, the embodiments described herein are not limited to those explicitly introduced and described herein.

Claims

1. A method for puncture assessment, comprising: Obtain the configuration file corresponding to the target puncture procedure, wherein the configuration file includes event detection rules and procedure assessment rules corresponding to each step of the target puncture procedure; Acquire sensing data collected by the sensing device during the target puncture procedure performed by the assessment subject; Based on the event detection rules corresponding to each stage in the configuration file, event detection is performed on the perceived data to determine the target perceived data corresponding to each stage. as well as For each step, the assessment result corresponding to that step is determined based on the assessment rules for that step and the target perception data.

2. The method according to claim 1, characterized in that, The configuration file corresponding to the target puncture procedure is generated through the following steps: Multiple candidate stages are presented to the user through the user interface; In response to the user's input selection instruction, the steps included in the target puncture procedure are determined from the plurality of candidate steps; as well as Based on the aforementioned steps and their corresponding preset event detection rules and preset step assessment rules, a configuration file corresponding to the target puncture process is generated.

3. The method according to claim 2, characterized in that, The configuration file further includes information about the relationships between the steps of the target puncture procedure, and this relationship information is determined based on the step connection instructions input by the user. The selection command is entered by moving the selected step to the process configuration area in the user interface. The link connection command is input by establishing a connection between the links.

4. The method according to claim 2, characterized in that, Based on the aforementioned steps and their corresponding preset event detection rules and preset step assessment rules, a configuration file corresponding to the target puncture procedure is generated, including: Through the user interface, the preset event detection rules and preset assessment rules corresponding to the stage are presented to the user. Based on the aforementioned steps, the preset event detection rules, the preset step assessment rules, and the rule update instructions input by the user, a configuration file corresponding to the target puncture procedure is generated.

5. The method according to claim 1, characterized in that, The event detection rules corresponding to each stage define the target sensing devices and their detection standards for the feature events in that stage. The step of performing event detection on the perceived data to determine the target perceived data corresponding to each stage includes: For each of the aforementioned steps, Determine whether the perceived data contains a subset of perceived data corresponding to the feature event of the process, wherein the subset of perceived data is collected by the target sensing device corresponding to the feature event and its content conforms to the corresponding detection standard; In response to determining that the perceived data contains a subset of perceived data corresponding to the feature events of the link, the subset of perceived data is used as the target perceived data corresponding to the link.

6. The method according to claim 5, characterized in that, Determining whether the perceived data contains a subset of perceived data corresponding to the feature events of the aforementioned process includes: In the perceived data, a first subset of perceived data corresponding to the starting feature event and a second subset of perceived data corresponding to the ending feature event are determined; From the sensed data, candidate sensed data whose collection time is within the target collection period are selected, wherein the target collection period is between the first collection time corresponding to the first subset of sensed data and the second collection time corresponding to the second subset of sensed data; Determine whether the candidate sensing data contains a subset of sensing data corresponding to other feature events of the process.

7. The method according to claim 1, characterized in that, The determination of the assessment result corresponding to the step based on the step assessment rules and the target perception data includes: The assessment rules for the aforementioned stages include a first assessment standard related to the sequence of stages and a second assessment standard related to the quality of stage execution. Obtain the target perception data corresponding to the dependent links of the aforementioned link; Based on the collection time of the target perception data and the target perception data corresponding to the dependent link, the first assessment result corresponding to the first assessment standard is determined. Based on the target perception data, the second assessment result corresponding to the second assessment standard is determined.

8. The method according to claim 7, characterized in that, Based on the target perception data, the second assessment result corresponding to the second assessment standard is determined, including: In response to the second assessment criterion including a third assessment criterion related to the sequence of characteristic events and a fourth assessment criterion related to the quality of performance of characteristic events, Determine the subset of perception data in the target perception data that corresponds to each feature event of the process; Based on the collection time of the perceptual data subset corresponding to each feature event, the third assessment result corresponding to the third assessment standard is determined. For each of the aforementioned feature events, a fourth assessment result corresponding to the fourth assessment criterion is determined based on its corresponding subset of perceived data.

9. A system for puncture assessment, characterized in that, It includes an acquisition module, a determination module, and an assessment module; The acquisition module is used to acquire the configuration file corresponding to the target puncture process. The configuration file includes event detection rules and process assessment rules for each step in the target puncture process. The acquisition module is also used to acquire sensing data collected by the sensing device during the target puncture procedure performed by the assessment object; The determining module is used to perform event detection on the perceived data based on the event detection rules corresponding to each link in the configuration file, so as to determine the target perceived data corresponding to each link; as well as The assessment module is used to determine the assessment result for each step based on the assessment rules for that step and the target perception data.

10. A computer-readable storage medium storing computer instructions, wherein when a computer reads the computer instructions in the storage medium, the computer executes the puncture test method as described in any one of claims 1 to 8.

Images