System for evaluating difficult cannulation of ercp, electronic device and storage medium

Abstract

The application discloses an ERCP difficult intubation evaluation system, an electronic device and a storage medium, and comprises an acquisition module, an identification module and an evaluation module. The acquisition module is used for acquiring a target video containing a target ERCP operation to be evaluated. The identification module is used for performing identification processing on the target video to obtain target operation information in the target ERCP operation process. The operation information comprises a starting time of each intubation and an ending time of the intubation and the number of intubations. The evaluation module is used for evaluating the target ERCP operation according to the target operation information to obtain an evaluation result. The evaluation result is used for representing whether the target ERCP operation is a difficult intubation operation. According to the application, the evaluation of whether the ERCP operation belongs to the difficult intubation can be automatically completed, the subjective experience judgment of an operator is not needed, and the accuracy and objectivity of the ERCP difficult intubation evaluation result are effectively improved.

Description

Technical Field

[0001] This invention relates to the field of medical technology assistance, and more particularly to an assessment system, electronic device and storage medium for difficult ERCP cannulation. Background Technology

[0002] Endoscopic retrograde cholangiopancreatography (ERCP) is an important endoscopic technique for the diagnosis and treatment of biliary and pancreatic diseases. Selective bile duct cannulation is one of the key steps to a successful ERCP procedure. Clinical practice shows that the failure rate of traditional selective cannulation techniques can reach 5-35%. Cannulation failure or difficult cannulation not only affects the efficiency of the procedure but also increases the cannulation time. As the cannulation time increases, the number of cannulation attempts increases, and the guidewire is repeatedly misplaced into the pancreatic duct or repeatedly visualized by the pancreatic duct, the risk of complications such as post-ERCP pancreatitis (PEP) and perforation increases significantly. PEP is the most common complication of ERCP, with an incidence rate of up to 10% and a mortality rate of 0.6%-1.1%, which greatly limits the clinical application and promotion of ERCP.

[0003] Current guidelines typically define difficult selective bile duct cannulation as one of the following: cannulation time exceeding 5 minutes, cannulation attempts exceeding 5 times, guidewire misplacement into the pancreatic duct more than once, or pancreatic duct visualization. However, these standards still have the following shortcomings in actual clinical application: First, cannulation time and number of attempts usually rely on manual recording, which is highly subjective and prone to omissions, errors, or inconsistencies in the starting point; second, different operators and different centers have different understandings of the measurement points such as the start of cannulation or the completion of a single cannulation attempt, affecting the consistency of difficult cannulation judgment; third, the existing difficult cannulation thresholds are mainly based on empirical standards, lacking objective and unified judgment criteria, making it difficult to accurately guide clinical operations.

[0004] Therefore, there is an urgent need to provide a technical solution that can improve the objectivity and consistency of ERCP cannulation assessment and solve the judgment bias problem caused by the existing reliance on manually recorded indicators. Summary of the Invention

[0005] The purpose of this invention is to provide an assessment system, electronic device, and storage medium for difficult ERCP cannulation, which can objectively assess ERCP procedures to accurately guide clinical operations.

[0006] In a first aspect, embodiments of the present invention provide an assessment system for difficult ERCP cannulation, comprising: The acquisition module is used to acquire target videos containing the target ERCP operation to be evaluated; The recognition module is used to recognize and process the target video to obtain target operation information during the target ERCP operation process. The operation information includes the start time of each intubation to the end time of the current intubation and the number of intubations. An evaluation module is used to evaluate the target ERCP operation based on the target operation information and obtain an evaluation result. The evaluation result is used to characterize whether the target ERCP operation is a difficult intubation operation.

[0007] In some embodiments, the identification module includes a preprocessing unit and an identification unit; The preprocessing unit is used to decode the target video to obtain continuous image frames, and extract from the continuous image frames a first image containing the duodenal papilla, a second image containing the incision knife, a third image containing the uninserted state, and a fourth image containing the intubated state. The identification unit is used to identify the intubation status of the target ERCP operation based on the first image, the second image, the third image, and the fourth image, and to obtain the intubation start time to the end time of each intubation and the number of intubations during the target ERCP operation.

[0008] In some embodiments, the evaluation system for difficult ERCP cannulation further includes: a first construction module and a first training module; The first construction module is used to construct a first training dataset, which includes intraoperative images under multiple ERCP operations, and segmented images in the intraoperative images that include the duodenal papilla, incision knife, unintubated state and intubated state, and are segmented and labeled. The first training module is used to take the intraoperative image as input and the segmented image as output to train the deep learning model to be trained until convergence, so as to obtain the trained segmentation model. The preprocessing unit is specifically used to: call the segmentation model to segment the continuous image frames to obtain a first image containing the duodenal papilla, a second image containing the incision knife, a third image containing the uninserted state, and a fourth image containing the intubated state.

[0009] In some embodiments, the evaluation system for difficult ERCP cannulation further includes: a second construction module and a second training module; The second construction module is used to construct a second training dataset. The second training dataset includes a set of historical images corresponding to multiple historical ERCP operations, and historical operation information corresponding to each set of historical ERCP operations. The set of historical images includes images of the duodenal papilla, images of the cutting knife, images of the unintubated state, and images of the intubated state from the historical video of the historical ERCP operation. The historical operation information includes the intubation start time to the end time of each intubation and the number of intubations. The second training module is used to take the historical image set as input, and the historical operation information corresponding to the historical image set as output, to train the deep learning model to be trained until convergence, so as to obtain the trained recognition model. The recognition unit is specifically used to: call the recognition model to perform recognition processing on the first image, the second image, the third image, and the fourth image to obtain the intubation start time to the end time of each intubation and the number of intubations during the target ERCP operation.

[0010] In some embodiments, the evaluation module includes a first computing unit and an evaluation unit; The first calculation unit is used to calculate the intubation duration of the target ERCP operation based on the intubation start time to the intubation end time of each intubation in the target ERCP operation. The evaluation unit is used to determine whether the intubation duration and the number of intubations meet the difficult intubation criteria based on the duration threshold and the number of intubations threshold under the difficult intubation criteria. If so, the evaluation result is that the target ERCP operation is a difficult intubation operation; otherwise, the evaluation result is that the target ERCP operation is not a difficult intubation operation.

[0011] In some embodiments, the evaluation module further includes: an acquisition unit, a second calculation unit, and a determination unit; The acquisition unit is used to acquire multiple sets of historical intubation information. Each set of historical intubation information includes operation information of multiple historical ERCP operations and historical clinical outcomes of whether complications occurred for each historical ERCP operation. The operation information of all historical ERCP operations in each set of historical intubation information is the same. The second calculation unit is used to calculate the probability of complications in the corresponding clinical outcome under different operation information based on the number of historical ERCP operations in each set of historical intubation information and the number of complications in the historical clinical outcomes corresponding to all historical ERCP operations. The determining unit is used to calculate the similarity between any two different operation information, and when the probability of complications in the clinical outcome corresponding to the two different operation information with the highest similarity is the largest difference, the intubation duration and number of intubations in the operation information with the higher probability of complications in the clinical outcome are determined as the duration threshold and number of intubations threshold under the difficult intubation judgment condition.

[0012] In some embodiments, the ERCP difficult cannulation assessment system further includes: an alarm module; The alarm module is used to trigger an alarm mechanism to remind the relevant ERCP operator when the evaluation result indicates that the target ERCP operation is a difficult intubation operation.

[0013] In some embodiments, the ERCP difficult cannulation assessment system further includes: a detection module and a transmission module; The detection module is used to detect, when the evaluation result indicates that the target ERCP operation is a difficult intubation operation, whether the probability of complications in the clinical outcome corresponding to the adjustment operation information of increasing the number of intubations or increasing the intubation time is lower than the probability of complications in the clinical outcome corresponding to the difficult intubation operation, and obtain the detection result. The sending module is used to send the adjustment operation information and the probability of complications in the corresponding clinical outcome to the relevant ERCP operator when the test result is determined to be yes.

[0014] Secondly, embodiments of the present invention provide an electronic device, which includes a processor, a memory, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it performs the following steps: Obtain the target video containing the target ERCP operation to be evaluated; The target video is processed to obtain target operation information during the target ERCP operation. The operation information includes the start time of each intubation to the end time of the current intubation and the number of intubations. Based on the target operation information, the target ERCP operation is evaluated to obtain an evaluation result, which is used to characterize whether the target ERCP operation is a difficult intubation operation.

[0015] Thirdly, embodiments of the present invention provide a computer-readable storage medium storing a computer program, which, when executed by a processor, performs the following steps: Obtain the target video containing the target ERCP operation to be evaluated; The target video is processed to obtain target operation information during the target ERCP operation. The operation information includes the start time of each intubation to the end time of the current intubation and the number of intubations. Based on the target operation information, the target ERCP operation is evaluated to obtain an evaluation result, which is used to characterize whether the target ERCP operation is a difficult intubation operation.

[0016] This invention provides an assessment system, electronic device, and storage medium for difficult ERCP cannulation. The system identifies video of the target ERCP operation to extract target operation information, including the start time of each cannulation to the end time of the current cannulation and the number of cannulations. This eliminates the need for manual recording and judgment, effectively avoiding problems such as subjective bias and inconsistent node judgment caused by manual recording. At the same time, based on objective target operation information, the system assesses the target ERCP operation to determine whether it is a difficult cannulation operation, thus effectively improving the accuracy and objectivity of the assessment results for difficult ERCP cannulation. Attached Figure Description

[0017] Figure 1 This is a schematic diagram of a structural system for evaluating difficult ERCP cannulation provided in an embodiment of the present invention; Figure 2 This is a schematic diagram of a first image including the major duodenal papilla provided in an embodiment of the present invention; Figure 3 This is a schematic diagram of a second image including a cutting blade provided in an embodiment of the present invention; Figure 4a This is a schematic diagram of a third image including a non-intubated state provided in an embodiment of the present invention; Figure 4b This is a schematic diagram of a fourth image including the cannulation state provided in an embodiment of the present invention; Figure 5 This is a schematic flowchart of an ERCP cannulation difficulty assessment method provided in an embodiment of the present invention; Figure 6 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention; Figure 7 This is another structural schematic diagram of the electronic device provided in the embodiment of the present invention. Detailed Implementation

[0018] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0019] It should be understood that the steps described in the method embodiments of this disclosure may be performed in different orders and / or in parallel. Furthermore, the method embodiments may include additional steps and / or omit the steps shown. The scope of this disclosure is not limited in this respect.

[0020] The term "comprising" and its variations as used herein are open-ended inclusions, meaning "including but not limited to". The term "based on" means "at least partially based on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments". Definitions of other terms will be given in the description below.

[0021] Among related techniques, endoscopic retrograde cholangiopancreatography (ERCP) is an important endoscopic technique for the diagnosis and treatment of biliary and pancreatic diseases. Selective bile duct cannulation is one of the key steps to successful ERCP procedures. Clinical practice shows that the failure rate of traditional selective cannulation techniques can reach 5-35%. Cannulation failure or difficult cannulation not only affects surgical efficiency but also increases cannulation time. As cannulation time prolongs, the number of cannulation attempts increases, and the guidewire repeatedly enters the pancreatic duct or is repeatedly visualized, the risk of complications such as post-ERCP pancreatitis (PEP) and perforation increases significantly. PEP is the most common complication of ERCP, with an incidence rate of up to 10% and a mortality rate of 0.6%-1.1%, which greatly limits the clinical application and promotion of ERCP.

[0022] Current guidelines typically define difficult selective bile duct cannulation as one of the following: cannulation time exceeding 5 minutes, cannulation attempts exceeding 5 times, guidewire misplacement into the pancreatic duct more than once, or pancreatic duct visualization. However, these standards still have the following shortcomings in actual clinical application: First, cannulation time and number of attempts usually rely on manual recording, which is highly subjective and prone to omissions, errors, or inconsistencies in the starting point; second, different operators and different centers have different understandings of the measurement points such as the start of cannulation or the completion of a single cannulation attempt, affecting the consistency of difficult cannulation judgment; third, the existing difficult cannulation thresholds are mainly based on empirical standards, lacking objective and unified judgment criteria, making it difficult to accurately guide clinical operations.

[0023] Therefore, there is an urgent need to provide a technical solution that can improve the objectivity and consistency of ERCP cannulation assessment and solve the judgment bias problem caused by the existing reliance on manually recorded indicators.

[0024] To address the technical problems existing in related technologies, embodiments of the present invention provide an evaluation system for difficult ERCP cannulation. Please refer to [link to relevant documentation]. Figure 1 , Figure 1 This is a schematic diagram of a structural system for evaluating difficult ERCP cannulation provided in an embodiment of the present invention, as shown below. Figure 1 As shown, the ERCP difficult cannulation evaluation system provided in this embodiment includes: an acquisition module, an identification module, and an evaluation module; The acquisition module is used to acquire target videos containing the target ERCP operation to be evaluated.

[0025] In this embodiment, the acquisition module may be a hardware interface or software unit for acquiring or receiving video data generated during ERCP surgery. The acquisition module is mainly used to transmit the acquired continuous image data to the recognition module for processing.

[0026] In practical applications, the acquisition module provided in this embodiment can directly acquire real-time video streams from the endoscope host via a wired connection, or read recorded historical video files from the hospital's image library or local storage device.

[0027] It should be noted that the target video provided in this embodiment can be a real-time video file or a historical video file. The specific video file type can be set according to actual application needs and is not specifically limited here. Furthermore, since this embodiment mainly evaluates ERCP operations, any video containing objects involved in the ERCP operation can be used as the target video of this application.

[0028] The recognition module is used to recognize and process the target video to obtain target operation information during the target ERCP operation process. The operation information includes the start time of each intubation to the end time of the current intubation and the number of intubations.

[0029] In this embodiment, the recognition module provided may be a computing unit with built-in image processing algorithms or deep learning models. It is mainly used to recognize and analyze the input target video, so that after receiving the target video, it can automatically extract the timestamps of key image frames and the number of times a specified event has occurred in the corresponding image frame sequence of the entire target video through a preset algorithm.

[0030] Specifically, this embodiment can determine the start time to end time of each intubation and the number of intubation attempts for each operation by analyzing the spatial relationship and state changes between relevant tissue structures (such as the greater duodenal papilla) and medical devices (such as a scalpel) in the target video. For example, the start time of an intubation operation is marked when the tip of the scalpel contacts the greater duodenal papilla, and the end time of an intubation operation is marked when the guidewire or catheter successfully enters the bile duct and is visualized, or when the intubation operation ends and moves away from the greater duodenal papilla (the end time of the intubation operation is counted whether the intubation is successful or unsuccessful).

[0031] An evaluation module is used to evaluate the target ERCP operation based on the target operation information and obtain an evaluation result. The evaluation result is used to characterize whether the target ERCP operation is a difficult intubation operation.

[0032] In this embodiment, the evaluation module is mainly used to compare and analyze the quantitative information in the above embodiment according to the preset difficult intubation judgment conditions, so as to obtain an objective evaluation conclusion.

[0033] In practical applications, the evaluation module can calculate the intubation duration (excluding the time for non-intubation operations between the start and end times of each intubation) for one or more intubation operations until successful intubation, based on the start time of each intubation and the end time of the current intubation. This intubation duration is then compared to a preset intubation duration threshold, and the number of intubations is also compared to a preset number of intubations threshold. If any indicator or combination of indicators meets the judgment criteria, an evaluation result representing a difficult intubation operation is generated; otherwise, an evaluation result representing a non-difficult intubation operation is generated.

[0034] In summary, this embodiment acquires the target video of the ERCP operation to be evaluated through the acquisition module, and uses image recognition technology through the recognition module to analyze the target video content frame by frame, automatically capturing the features of the intubation action, and calculating the target operation information including the start time of each intubation, the end time of each intubation, and the number of intubation attempts during the period. This can eliminate the errors and subjective biases of manual timing, and improve the objectivity and accuracy of intubation time and number statistics. At the same time, the evaluation module matches this objectively quantified target operation information with preset difficult intubation standards, which can automatically generate objective evaluation results. This effectively eliminates the differences in the understanding of difficult intubation standards among different doctors, improves the consistency and reliability of evaluation results, and enables timely warnings during the operation to avoid complications such as pancreatitis and perforation.

[0035] In some embodiments, in order to accurately quantify the intubation start time to the intubation end time and the number of intubation attempts during each intubation attempt in the target video, the recognition module provided in this embodiment may include a preprocessing unit and a recognition unit; The preprocessing unit is used to decode the target video to obtain continuous image frames, and extract from the continuous image frames a first image containing the duodenal papilla, a second image containing the incision knife, a third image containing the uninserted state, and a fourth image containing the intubated state.

[0036] In this embodiment, the preprocessing unit is mainly used to convert continuous time-series video data into a continuous sequence of image frames. Specifically, the preprocessing unit provided in this embodiment can call a video decoding algorithm to decode the target video into continuous image frames according to a preset frame rate or keyframe strategy.

[0037] At the same time, the preprocessing unit also needs to perform image filtering and classification operations, that is, extract four types of key images from consecutive image frames based on image content features: the first image containing the duodenal papilla, the second image containing the incision knife, the third image containing the unintubated state, and the fourth image containing the intubated state.

[0038] For example, the preprocessing unit provided in this embodiment can call the trained segmentation model to identify and segment each frame of image, so as to identify the duodenal papilla region and the incision knife region, and then determine whether the image content features of the current frame image belong to the intubation state based on the relative position relationship or morphological features of the two, and complete the classification and extraction.

[0039] In practical applications, the extraction criteria for the first image can be set according to actual needs. For example, it can be a frame where the opening of the major duodenal papilla is fully visible, or a frame with a complete outline, as long as the specific tissue structure can be determined. This application does not impose any special limitations on this. The specific extracted first image can be found in [reference needed]. Figure 2 , Figure 2 This is a schematic diagram of a first image containing the major duodenal papilla provided in an embodiment of the present invention.

[0040] Meanwhile, in the second image, the incision blade can be in different positions, such as extending a duct or contacting tissue structures. This second image is mainly used to determine the relative positional relationship between the incision blade and the greater duodenal papilla. When extracting the second image, if both the greater duodenal papilla and the incision blade are present in the image, that frame can be simultaneously labeled as the first image and the second image. For details of the extracted second image, please refer to [link to relevant documentation]. Figure 3 , Figure 3 This is a schematic diagram of a second image including a cutting knife provided in an embodiment of the present invention.

[0041] The third image, representing the state before intubation, is a frame indicating that the cutting blade has not yet initiated an effective intubation attempt. In this state, the tip of the cutting blade may be positioned on the surface of the major duodenal papilla, ready to make contact, but no insertion action has been performed. In practical applications, the preprocessing unit can distinguish the third image from other state images by analyzing features such as the relative distance and angle between the cutting blade tip and the opening of the major duodenal papilla, as well as whether an insertion action has occurred. For details of the extracted third image, please refer to [link to relevant documentation]. Figure 4a , Figure 4a This is a schematic diagram of a third image showing a state without intubation, provided in an embodiment of the present invention.

[0042] The fourth image in the intubation state can be an image frame representing that the cutting blade has successfully passed through the opening of the major duodenal papilla, or that the intubation operation is in progress. In the intubation state, the tip of the cutting blade can be submerged in the major duodenal papilla. In practical applications, the recognition unit can determine that an intubation operation is in progress by detecting the appearance of the fourth image. Specifically, the fourth image provided in this embodiment can include images of the intubation attempt process, or it can include four images when the intubation is successful. Whether the fourth image represents a successful intubation state can be determined by the morphological features corresponding to successful intubation, or the relative positional relationship between the cutting blade and the major duodenal papilla. For details of the extracted fourth image, please refer to [link to relevant documentation]. Figure 4b , Figure 4b This is a schematic diagram of a fourth image including the cannulation state provided in an embodiment of the present invention.

[0043] As an optional embodiment, in order to accurately identify the first image, the second image, the third image, and the fourth image, the ERCP difficult intubation evaluation system provided in this embodiment may further include: a first construction module and a first training module; The first construction module is used to construct a first training dataset, which includes intraoperative images under multiple ERCP operations, and segmented images in the intraoperative images that include the duodenal papilla, incision knife, unintubated state and intubated state, and are segmented and labeled.

[0044] In this embodiment, the first training dataset may include intraoperative images acquired during multiple historical ERCP procedures. These intraoperative images may be extracted from consecutive time-series video frames from different patients and surgical scenarios. For each intraoperative image, this embodiment may also have multiple experts in the field segment and label it to obtain a segmented and labeled image. This segmented image clearly identifies the duodenal papilla region, the incision area, the unintubated area, and the intubated area.

[0045] The first training module is used to train the deep learning model to be trained until convergence by taking the intraoperative image as input and the segmented image as output, thereby obtaining the trained segmentation model.

[0046] In this embodiment, the deep learning model to be trained can be a deep learning model based on a convolutional neural network (CNN) architecture. During the training process, the first training module performs a large number of iterative training sessions, enabling the model to learn the mapping rules from the original image to specific tissue structures and state categories, thereby enabling the trained segmentation model to accurately identify, label, and segment images.

[0047] After obtaining the trained segmentation model, the preprocessing unit provided in this embodiment can be specifically used to: call the segmentation model to segment the continuous image frames to obtain a first image containing the duodenal papilla, a second image containing the incision knife, a third image containing the uninserted state, and a fourth image containing the intubated state.

[0048] In this embodiment, by calling the trained segmentation model, the preprocessing unit can automatically separate the first image containing the duodenal papilla, the second image containing the incision knife, the third image containing the unintubated state, and the fourth image containing the intubated state from the complex background, thereby facilitating the subsequent recognition unit to perform intubation status judgment, time statistics, and intubation count statistics.

[0049] In this way, by using the trained segmentation model to identify and segment continuous image frames, the subjective errors and inefficiencies of manual image selection can be avoided. This enables the stable and consistent extraction of key images containing the duodenal papilla, the cutting knife, and different intubation states from complex and varied target videos, thus ensuring accurate statistics on subsequent intubation time and number of intubations.

[0050] The identification unit is used to identify the intubation status of the target ERCP operation based on the first image, the second image, the third image, and the fourth image, and to obtain the intubation start time to the end time of each intubation and the number of intubations during the target ERCP operation.

[0051] In this embodiment, the recognition unit may determine whether the image content features of the current frame image are the start of intubation operation, intubation attempt operation, and successful intubation operation based on the relative positional relationship or morphological features of the incision knife and the duodenal papilla in the first image, second image, third image, and fourth image, thereby determining the intubation start time to the end time of the current intubation and the number of intubations in the target ERCP operation process.

[0052] As another optional embodiment, in order to improve the recognition accuracy and recognition efficiency of the recognition unit, the ERCP difficult cannulation evaluation system provided in this embodiment may further include: a second construction module and a second training module; The second construction module is used to construct a second training dataset. The second training dataset includes a set of historical images corresponding to multiple historical ERCP operations, and historical operation information corresponding to each set of historical ERCP operations. The set of historical images includes images of the duodenal papilla, images of the incision knife, images of the unintubated state, and images of the intubated state from the historical video of the historical ERCP operation. The historical operation information includes the start time of each intubation to the end time of the current intubation and the number of intubations.

[0053] In this embodiment, the historical image set may include images extracted from continuous time-series historical video frames, including images of the duodenal papilla, incision knife, unintubated state, and intubated state, as input data for model training; the historical operation information records the time node when intubation started for each operation, the time node when intubation ended for each operation (including the end time nodes corresponding to operation failure and operation success), and the number of intubation attempts, as the output target for model training.

[0054] The second training module is used to take the historical image set as input and the historical operation information corresponding to the historical image set as output to train the deep learning model to be trained until convergence, so as to obtain the trained recognition model.

[0055] In this embodiment, the second training module is mainly used to use the historical image set as input data for model training, and the corresponding historical operation information (such as the start time of each intubation to the end time of the current intubation, and the number of intubations) as the output target for model training, and to iteratively train the deep learning model to be trained. Specifically, the backpropagation algorithm can be used during the training process to minimize the loss function between the predicted operation information and the true historical operation information until the model converges.

[0056] It should be noted that the deep learning model to be trained can be selected according to actual needs, such as convolutional neural networks (CNN) or recurrent neural networks (RNN), or a combination of the two. No specific network architecture is limited here.

[0057] After obtaining the trained recognition model, the recognition unit provided in this embodiment can be specifically used to: call the recognition model to perform recognition processing on the first image, the second image, the third image and the fourth image to obtain the intubation start time to the end time of the current intubation and the number of intubations in the target ERCP operation process.

[0058] In this embodiment, the trained recognition model is integrated into the recognition unit of the evaluation system. During ERCP operation, the model can be called in real time to analyze continuous frame images, which can automatically determine the start and end of each intubation action. This allows for accurate statistics on intubation duration and number of intubations, solving the problem of strong subjectivity caused by manual statistics and thus improving the accuracy of intubation status recognition and intubation count statistics.

[0059] In some embodiments, in order to objectively evaluate the target operation information of the target ERCP operation, the evaluation module provided in this embodiment may include a first calculation unit and an evaluation unit; The first calculation unit is used to calculate the intubation duration of the target ERCP operation based on the intubation start time to the intubation end time of each intubation operation.

[0060] In this embodiment, the first calculation unit can extract the timestamp data corresponding to the start time of each intubation to the end time of the current intubation, and then obtain the time interval between the two through subtraction, and determine the time interval as the intubation duration.

[0061] The evaluation unit is used to determine whether the intubation duration and the number of intubations meet the difficult intubation criteria based on the duration threshold and the number of intubations threshold under the difficult intubation criteria. If so, the evaluation result is that the target ERCP operation is a difficult intubation operation; otherwise, the evaluation result is that the target ERCP operation is not a difficult intubation operation.

[0062] It should be noted that the criteria for determining difficult intubation mainly include pre-set duration thresholds and number of intubations thresholds, such as a duration threshold of 5 minutes and a number of intubations threshold of 5 times; or optimized thresholds derived from historical clinical data analysis, without specifying the specific values ​​here.

[0063] In practical applications, the evaluation unit mainly compares the intubation duration output by the first calculation unit with the duration threshold, and simultaneously compares the number of intubations output by the recognition module with the number of intubations threshold. If the intubation duration is greater than or equal to the duration threshold, and / or the number of intubations is greater than or equal to the number of intubations threshold, the difficult intubation criteria are met, and an evaluation result representing a difficult intubation operation is output. Conversely, if one or both of these indicators fail to reach the corresponding threshold, an evaluation result representing a non-difficult intubation operation is output.

[0064] Thus, by adopting this embodiment, the identified time points and number of intubations can be automatically converted into quantitative indicators and compared with pre-selected standardized thresholds. This can solve the problems of large subjective errors and inconsistent standards in traditional manual recording, thereby achieving the goal of objective and standardized evaluation of difficult ERCP intubations.

[0065] As an optional embodiment, in order to obtain an objective condition for determining difficult intubation, the evaluation module provided in this embodiment may further include: an acquisition unit, a second calculation unit, and a determination unit; The acquisition unit is used to acquire multiple sets of historical intubation information. Each set of historical intubation information includes operation information of multiple historical ERCP operations and historical clinical outcomes of whether complications occurred for each historical ERCP operation. The operation information of all historical ERCP operations in each set of historical intubation information is the same.

[0066] In this embodiment, the acquisition unit can collect and organize historical ERCP operation data from a medical database or historical case database. It should be noted that each set of historical intubation information provided in this embodiment corresponds to a specific operational scenario, under which the same operational information is used, namely, the same intubation duration and the same number of intubations. Therefore, each set of historical intubation information provided in this embodiment can contain multiple instances of ERCP operations performed under different operational scenarios, and the corresponding historical clinical outcome for each instance. Similarly, multiple sets of historical intubation information provided in this embodiment can contain instances of ERCP operations performed under various different operational information and scenarios, and the corresponding historical clinical outcome for each instance. The clinical outcome can include the occurrence or absence of complications, where complications can include postoperative pancreatitis (PEP), perforation, or bleeding, etc.

[0067] The second calculation unit is used to calculate the probability of complications in the corresponding clinical outcome under different operation information based on the number of historical ERCP operations in each set of historical intubation information and the number of complications in the historical clinical outcomes corresponding to all historical ERCP operations.

[0068] In this embodiment, the second calculation unit can traverse each historical intubation information set, count the total number of historical ERCP operations within the set, and further count the number of historical clinical outcomes marked as having complications. Then, based on these two values, it calculates the average probability of complications occurring in the clinical outcome under the same operation information. For example, if the specified operation information is an intubation time of 3 minutes and 3 intubations, the historical intubation information set contains 100 historical operations, of which 15 resulted in PEP, then the probability of complications corresponding to the specified operation information can be calculated to be 15%, meaning that if the specified operation information is used, the probability of complications occurring is 15%.

[0069] The determining unit is used to calculate the similarity between any two different operation information, and when the probability of complications in the clinical outcome corresponding to the two different operation information with the highest similarity is the largest difference, the intubation duration and number of intubations in the operation information with the higher probability of complications in the clinical outcome are determined as the duration threshold and number of intubations threshold under the difficult intubation judgment condition.

[0070] In this embodiment, the determining unit is mainly used to identify the critical point of operation information where the risk of complications increases significantly among a large number of operation information combinations. In practical applications, this embodiment can first calculate the similarity between any two different operation information pairs. The similarity provided in this embodiment can be determined based on the numerical characteristics of the operation information (such as time difference, frequency difference). The higher the similarity, the closer the two operation scenarios are. Subsequently, among multiple operation information pairs with the highest similarity or exceeding the similarity threshold, the pair with the largest difference in the probability of complications is identified. Such combinations with high similarity and large differences in the probability of complications usually indicate an inflection point region where the risk of complications increases sharply. If the operation information corresponding to any ERCP operation is in this inflection point region, it indicates that the risk of complications corresponding to the ERCP operation will increase significantly. At this time, a reminder message can be output to remind relevant medical personnel to pay attention.

[0071] In some embodiments, if the target operation information corresponding to the target ERCP operation is determined to be a difficult intubation operation, the ERCP difficult intubation assessment system provided in this embodiment may further include: an alarm module, which is used to trigger an alarm mechanism to remind the corresponding ERCP operator when the assessment result indicates that the target ERCP operation is a difficult intubation operation.

[0072] The alarm module can communicate with the evaluation module to receive the evaluation results output by the evaluation module. When the evaluation result output by the evaluation module indicates that the target ERCP operation is a difficult intubation operation, the alarm module will activate a preset alarm mechanism. Specifically, the alarm mechanism provided in this embodiment can be set according to actual application needs. For example, it can be an audible prompt, such as a buzzer alarm or voice broadcast, or a visual prompt, such as a pop-up warning on the display screen, flashing colors in a specific area, or color changes of indicator lights. As long as it can convey risk warning information to the ERCP operator, the specific form of the alarm mechanism is not limited here.

[0073] Thus, by using this embodiment, timely alerts can be issued to ERCP operators at critical moments when the risk of complications increases significantly, helping doctors to adjust surgical strategies in a timely manner and reduce the probability of postoperative complications.

[0074] As an optional embodiment, in order to help doctors adjust surgical strategies in a timely manner and reduce the probability of postoperative complications, the ERCP difficult cannulation assessment system provided in this embodiment may further include: a detection module and a transmission module; The detection module is used to detect, when the evaluation result indicates that the target ERCP operation is a difficult intubation operation, whether the probability of complications in the clinical outcome corresponding to the adjustment operation information of increasing the number of intubations or increasing the intubation time is lower than the probability of complications in the clinical outcome corresponding to the difficult intubation operation, and obtain the detection result.

[0075] In this embodiment, the detection module can pre-build a risk prediction model based on a set of historical intubation information to simulate and generate various adjustment operation information, such as increasing the current number of intubations by one or extending the intubation time threshold by a certain duration (e.g., 30 seconds). Simultaneously, it calculates the probability of complications corresponding to these adjustment operation information and compares the calculated probabilities with the complication probabilities corresponding to the current difficult intubation operation. If the complication probability corresponding to the adjustment operation information is lower than the complication probability corresponding to the current difficult intubation operation, the detection module outputs a positive detection result; otherwise, it outputs a negative detection result.

[0076] The sending module is used to send the adjustment operation information and the probability of complications in the corresponding clinical outcome to the relevant ERCP operator when the test result is determined to be yes.

[0077] In this embodiment, the sending module is used to receive the test results output by the detection module and related adjustment operation information. When the test results indicate that there is a better path (i.e., the probability of complications corresponding to the adjusted operation information is lower), the sending module sends the adjustment operation information and the probability of complications of the expected clinical outcome corresponding to the adjustment operation information as prompt information to the terminal device of the corresponding ERCP operator, such as the ERCP operator's display screen, mobile tablet or wearable device.

[0078] It should be noted that the sending module provided in this embodiment can send the optimal adjustment operation information (the adjustment operation information with the lowest probability of complications) to the terminal device of the corresponding ERCP operator after receiving multiple adjustment operation information, thereby minimizing the probability of postoperative complications and assisting doctors in making better decisions in complex clinical situations.

[0079] Thus, by employing the embodiments of the present invention, after identifying difficult intubation procedures, not only can risk warnings be provided, but also the probability of complications under different adjustment strategies can be analyzed, and optimal adjustment suggestions can be proactively pushed to ERCP operators, which can effectively reduce the risk of postoperative complications.

[0080] This concludes the description of the evaluation system for difficult ERCP cannulation provided in the embodiments of the present invention.

[0081] In practice, the above modules and / or units can be implemented as independent entities or combined in any way to be implemented as the same or several entities.

[0082] As an optional embodiment, to address the same technical problem, this embodiment also provides an evaluation method for difficult ERCP cannulation; please refer to [link to relevant documentation]. Figure 5 , Figure 5 This is a flowchart illustrating an evaluation method for difficult ERCP cannulation provided in an embodiment of the present invention, as shown below. Figure 5 As shown, the method may include the following steps: Step 501: Obtain the target video containing the target ERCP operation to be evaluated.

[0083] Step 502: The target video is processed for recognition to obtain target operation information during the target ERCP operation. The operation information includes the start time of each intubation to the end time of the current intubation and the number of intubations.

[0084] Step 503: Based on the target operation information, evaluate the target ERCP operation to obtain an evaluation result. The evaluation result is used to characterize whether the target ERCP operation is a difficult intubation operation.

[0085] It should be noted that when implementing the ERCP difficult cannulation evaluation method provided in this embodiment, each method step can be carried out according to the scheme in the above system embodiment, and the technical effects that can be achieved can also be referred to the above system embodiment, which will not be repeated here.

[0086] Additionally, please see Figure 6 , Figure 6 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention. The electronic device can be a mobile terminal such as a smartphone, tablet computer, or other similar device. Figure 6 As shown, the electronic device 600 includes a processor 601 and a memory 602. The processor 601 and the memory 602 are electrically connected.

[0087] The processor 601 is the control center of the electronic device 600. It connects various parts of the electronic device through various interfaces and lines. By running or loading the application program stored in the memory 602 and calling the data stored in the memory 602, it performs various functions of the electronic device 600 and processes data, thereby monitoring the electronic device 600 as a whole.

[0088] In this embodiment, the processor 601 in the electronic device 600 loads the instructions corresponding to the processes of one or more applications into the memory 602 according to the following steps, and the processor 601 runs the applications stored in the memory 602, thereby realizing any step in the ERCP difficult cannulation evaluation method provided in the above embodiment.

[0089] The electronic device 600 can implement the steps in any embodiment of the ERCP difficult cannulation evaluation method provided in the embodiments of the present invention. Therefore, it can achieve the beneficial effects that any ERCP difficult cannulation evaluation method provided in the embodiments of the present invention can achieve, as detailed in the preceding embodiments, and will not be repeated here.

[0090] Please see Figure 7 , Figure 7 This is another structural schematic diagram of the electronic device provided in the embodiments of the present invention, such as... Figure 7 As shown, Figure 7 A specific structural block diagram of an electronic device provided in an embodiment of the present invention is shown. This electronic device can be used to implement the ERCP difficult cannulation evaluation method provided in the above embodiments. The electronic device 700 can be a mobile terminal such as a smartphone or laptop computer.

[0091] RF circuit 710 is used to receive and transmit electromagnetic waves, converting electromagnetic waves into electrical signals and vice versa, thereby enabling communication with communication networks or other devices. RF circuit 710 may include various existing circuit elements used to perform these functions, such as antennas, radio frequency transceivers, digital signal processors, encryption / decryption chips, subscriber identity modules (SIM cards), memory, etc. RF circuit 710 can communicate with various networks such as the Internet, corporate intranets, and wireless networks, or communicate with other devices via wireless networks. The aforementioned wireless networks may include cellular telephone networks, wireless local area networks (WLANs), or metropolitan area networks (MANs). The aforementioned wireless networks may use various communication standards, protocols, and technologies, including but not limited to Global System for Mobile Communication (GSM), Enhanced Data GSM Environment (EDGE), Wideband Code Division Multiple Access (WCDMA), Code Division Multiple Access (CDMA), Time Division Multiple Access (TDMA), Wireless Fidelity (Wi-Fi) (such as IEEE 802.11a, IEEE 802.11b, IEEE 802.11g, and / or IEEE 802.11n), Voice over Internet Protocol (VoIP), Worldwide Interoperability for Microwave Access (Wi-Max), other protocols for email, instant messaging, and short messages, and any other suitable communication protocols, including those that have not yet been developed.

[0092] The memory 720 can be used to store software programs and modules, such as the program instructions / modules corresponding to the ERCP difficult intubation evaluation method in the above embodiment. The processor 780 executes various functional applications and evaluates ERCP difficult intubation by running the software programs and modules stored in the memory 720.

[0093] Memory 720 may include high-speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, memory 720 may further include memory remotely located relative to processor 780, which can be connected to electronic device 700 via a network. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.

[0094] The input unit 730 can be used to receive input digital or character information, and to generate keyboard, mouse, joystick, optical, or trackball signal inputs related to user settings and function control. Specifically, the input unit 730 may include a touch-sensitive surface 731 and other input devices 732. The touch-sensitive surface 731, also known as a touch display screen or touchpad, can collect touch operations performed by the user on or near it (such as operations performed by the user using a finger, stylus, or any suitable object or accessory on or near the touch-sensitive surface 731), and drive the corresponding connection device according to a pre-set program. Optionally, the touch-sensitive surface 731 may include two parts: a touch detection device and a touch controller. The touch detection device detects the user's touch position and the signal generated by the touch operation, and transmits the signal to the touch controller; the touch controller receives touch information from the touch detection device, converts it into touch point coordinates, sends it to the processor 780, and can receive and execute commands sent by the processor 780. In addition, the touch-sensitive surface 731 can be implemented using various types such as resistive, capacitive, infrared, and surface acoustic wave. In addition to the touch-sensitive surface 731, the input unit 730 may also include other input devices 732. Specifically, other input devices 732 may include, but are not limited to, one or more of the following: physical keyboard, function keys (such as volume control buttons, power buttons, etc.), trackball, mouse, joystick, etc.

[0095] Display unit 740 can be used to display information input by the user or information provided to the user, as well as various graphical user interfaces of electronic device 700. These graphical user interfaces can be composed of graphics, text, icons, video, and any combination thereof. Display unit 740 may include display panel 741, optionally configured as LCD (Liquid Crystal Display), OLED (Organic Light-Emitting Diode), or other similar forms. Further, touch-sensitive surface 731 may cover display panel 741. When touch-sensitive surface 731 detects a touch operation on or near it, it transmits the information to processor 780 to determine the type of touch event. Subsequently, processor 780 provides corresponding visual output on display panel 741 according to the type of touch event. Although in the figures, touch-sensitive surface 731 and display panel 741 are implemented as two separate components to achieve input and output functions, in some embodiments, touch-sensitive surface 731 and display panel 741 can be integrated to achieve input and output functions.

[0096] The electronic device 700 may also include at least one sensor 750, such as a light sensor, a motion sensor, and other sensors. Specifically, the light sensor may include an ambient light sensor and a proximity sensor, wherein the ambient light sensor can adjust the brightness of the display panel 741 according to the ambient light level, and the proximity sensor can generate an interruption when the flip is closed or shut down. As a type of motion sensor, a gravity acceleration sensor can detect the magnitude of acceleration in various directions (generally three axes), and can detect the magnitude and direction of gravity when stationary. It can be used for applications that recognize the phone's posture (such as landscape / portrait switching, related games, magnetometer posture calibration), vibration recognition related functions (such as pedometer, tapping), etc. Other sensors that may be configured in the electronic device 700, such as gyroscopes, barometers, hygrometers, thermometers, and infrared sensors, will not be described in detail here.

[0097] Audio circuitry 760, speaker 761, and microphone 762 provide an audio interface between the user and electronic device 700. Audio circuitry 760 converts received audio data into electrical signals and transmits them to speaker 761, where speaker 761 converts them into sound signals for output. Conversely, microphone 762 converts collected sound signals into electrical signals, which are then received by audio circuitry 760, converted back into audio data, and processed by processor 780. The audio data is then transmitted via RF circuitry 710 to, for example, another terminal, or output to memory 720 for further processing. Audio circuitry 760 may also include an earphone jack to facilitate communication between peripheral headphones and electronic device 700.

[0098] Electronic device 700, through transmission module 770 (e.g., Wi-Fi module), can help users receive requests, send information, etc., providing users with wireless broadband internet access. Although transmission module 770 is shown in the figure, it is understood that it is not an essential component of electronic device 700 and can be omitted as needed without changing the essence of the invention.

[0099] The processor 780 is the control center of the electronic device 700. It connects to various parts of the phone via various interfaces and lines, and performs various functions and processes data of the electronic device 700 by running or executing software programs and / or modules stored in the memory 720, and by calling data stored in the memory 720, thereby providing overall monitoring of the electronic device. Optionally, the processor 780 may include one or more processing cores; in some embodiments, the processor 780 may integrate an application processor and a modem processor, wherein the application processor mainly handles the operating system, user interface, and applications, and the modem processor mainly handles wireless communication. It is understood that the modem processor may also not be integrated into the processor 780.

[0100] The electronic device 700 also includes a power supply 790 (such as a battery) that supplies power to various components. In some embodiments, the power supply may be logically connected to the processor 780 through a power management system, thereby enabling functions such as managing charging, discharging, and power consumption through the power management system. The power supply 790 may also include one or more DC or AC power supplies, recharging systems, power fault detection circuits, power converters or inverters, power status indicators, and other arbitrary components.

[0101] Although not shown, the electronic device 700 also includes cameras (such as front-facing cameras and rear-facing cameras), Bluetooth modules, etc., which will not be described in detail here. Specifically, in this embodiment, the display unit of the electronic device is a touch screen display, and the mobile terminal also includes a memory and one or more programs, one or more of which are stored in the memory and configured to be executed by one or more processors to implement any step in the ERCP difficult cannulation evaluation method provided in the above embodiments.

[0102] In practice, each of the above modules can be implemented as an independent entity or can be combined arbitrarily to be implemented as the same or several entities. For the specific implementation of each of the above modules, please refer to the previous embodiments, which will not be repeated here.

[0103] Those skilled in the art will understand that all or part of the steps in the various methods of the above embodiments can be implemented by instructions, or by instructions controlling related hardware. These instructions can be stored in a computer-readable storage medium and loaded and executed by a processor. Therefore, embodiments of the present invention provide a storage medium storing multiple instructions that, when executed by a processor, can implement any step in the ERCP difficult cannulation evaluation method provided in the above embodiments.

[0104] The storage medium may include: read-only memory (ROM), random access memory (RAM), disk or optical disk, etc.

[0105] Since the instructions stored in the storage medium can execute the steps in any embodiment of the ERCP difficult cannulation evaluation method provided in the embodiments of the present invention, the beneficial effects that any ERCP difficult cannulation evaluation method provided in the embodiments of the present invention can achieve can be realized, as detailed in the preceding embodiments, and will not be repeated here.

[0106] The foregoing has provided a detailed description of an ERCP difficult cannulation evaluation system, electronic device, and storage medium provided in the embodiments of this application. Specific examples have been used to illustrate the principles and implementation methods of this application. The descriptions of the embodiments above are only for the purpose of helping to understand the method and core ideas of this application. Furthermore, those skilled in the art will recognize that, based on the ideas of this application, there will be changes in the specific implementation methods and application scope. Therefore, the content of this specification should not be construed as a limitation of this application. Moreover, those skilled in the art can make several improvements and modifications without departing from the principles of this invention, and these improvements and modifications are also considered to be within the scope of protection of this invention.

Claims

1. An evaluation system for difficult ERCP cannulation, characterized in that, include: The acquisition module is used to acquire target videos containing the target ERCP operation to be evaluated; The recognition module is used to recognize and process the target video to obtain target operation information during the target ERCP operation process. The operation information includes the start time of each intubation to the end time of the current intubation and the number of intubations. An evaluation module is used to evaluate the target ERCP operation based on the target operation information and obtain an evaluation result. The evaluation result is used to characterize whether the target ERCP operation is a difficult intubation operation.

2. The ERCP difficult cannulation assessment system according to claim 1, characterized in that, The identification module includes a preprocessing unit and an identification unit; The preprocessing unit is used to decode the target video to obtain continuous image frames, and extract from the continuous image frames a first image containing the duodenal papilla, a second image containing the incision knife, a third image containing the uninserted state, and a fourth image containing the intubated state. The identification unit is used to identify the intubation status of the target ERCP operation based on the first image, the second image, the third image, and the fourth image, and to obtain the intubation start time to the end time of each intubation and the number of intubations during the target ERCP operation.

3. The ERCP difficult cannulation assessment system according to claim 2, characterized in that, The evaluation system for difficult ERCP cannulation also includes: a first construction module and a first training module; The first construction module is used to construct a first training dataset, which includes intraoperative images under multiple ERCP operations, and segmented images in the intraoperative images that include the duodenal papilla, incision knife, unintubated state and intubated state, and are segmented and labeled. The first training module is used to take the intraoperative image as input and the segmented image as output to train the deep learning model to be trained until convergence, so as to obtain the trained segmentation model. The preprocessing unit is specifically used to: call the segmentation model to segment the continuous image frames to obtain a first image containing the duodenal papilla, a second image containing the incision knife, a third image containing the uninserted state, and a fourth image containing the intubated state.

4. The ERCP difficult cannulation assessment system according to claim 2, characterized in that, The evaluation system for difficult ERCP cannulation also includes: a second construction module and a second training module; The second construction module is used to construct a second training dataset. The second training dataset includes a set of historical images corresponding to multiple historical ERCP operations, and historical operation information corresponding to each set of historical ERCP operations. The set of historical images includes images of the duodenal papilla, images of the cutting knife, images of the unintubated state, and images of the intubated state from the historical video of the historical ERCP operation. The historical operation information includes the intubation start time to the end time of each intubation and the number of intubations. The second training module is used to take the historical image set as input, and the historical operation information corresponding to the historical image set as output, to train the deep learning model to be trained until convergence, so as to obtain the trained recognition model. The recognition unit is specifically used to: call the recognition model to perform recognition processing on the first image, the second image, the third image, and the fourth image to obtain the intubation start time to the end time of each intubation and the number of intubations during the target ERCP operation.

5. The ERCP difficult cannulation assessment system according to claim 1, characterized in that, The evaluation module includes a first calculation unit and an evaluation unit; The first calculation unit is used to calculate the intubation duration of the target ERCP operation based on the intubation start time to the intubation end time of each intubation in the target ERCP operation. The evaluation unit is used to determine whether the intubation duration and the number of intubations meet the difficult intubation criteria based on the duration threshold and the number of intubations threshold under the difficult intubation criteria. If so, the evaluation result is that the target ERCP operation is a difficult intubation operation; otherwise, the evaluation result is that the target ERCP operation is not a difficult intubation operation.

6. The ERCP difficult cannulation assessment system according to claim 5, characterized in that, The evaluation module further includes: an acquisition unit, a second calculation unit, and a determination unit; The acquisition unit is used to acquire multiple sets of historical intubation information. Each set of historical intubation information includes operation information of multiple historical ERCP operations and historical clinical outcomes of whether complications occurred for each historical ERCP operation. The operation information of all historical ERCP operations in each set of historical intubation information is the same. The second calculation unit is used to calculate the probability of complications in the corresponding clinical outcome under different operation information based on the number of historical ERCP operations in each set of historical intubation information and the number of complications in the historical clinical outcomes corresponding to all historical ERCP operations. The determining unit is used to calculate the similarity between any two different operation information, and when the probability of complications in the clinical outcome corresponding to the two different operation information with the highest similarity is the largest difference, the intubation duration and number of intubations in the operation information with the higher probability of complications in the clinical outcome are determined as the duration threshold and number of intubations threshold under the difficult intubation judgment condition.

7. The ERCP difficult cannulation assessment system according to claim 5, characterized in that, The ERCP difficult cannulation assessment system also includes: an alarm module; The alarm module is used to trigger an alarm mechanism to remind the relevant ERCP operator when the evaluation result indicates that the target ERCP operation is a difficult intubation operation.

8. The ERCP difficult cannulation assessment system according to claim 5, characterized in that, The ERCP difficult cannulation evaluation system also includes: a detection module and a transmission module; The detection module is used to detect, when the evaluation result indicates that the target ERCP operation is a difficult intubation operation, whether the probability of complications in the clinical outcome corresponding to the adjustment operation information of increasing the number of intubations or increasing the intubation time is lower than the probability of complications in the clinical outcome corresponding to the difficult intubation operation, and obtain the detection result. The sending module is used to send the adjustment operation information and the probability of complications in the corresponding clinical outcome to the relevant ERCP operator when the test result is determined to be yes.

9. An electronic device, characterized in that, The electronic device includes a processor, a memory, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it performs the following steps: Obtain the target video containing the target ERCP operation to be evaluated; The target video is processed to obtain target operation information during the target ERCP operation. The operation information includes the start time of each intubation to the end time of the current intubation and the number of intubations. Based on the target operation information, the target ERCP operation is evaluated to obtain an evaluation result, which is used to characterize whether the target ERCP operation is a difficult intubation operation.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, performs the following steps: Obtain the target video containing the target ERCP operation to be evaluated; The target video is processed to obtain target operation information during the target ERCP operation. The operation information includes the start time of each intubation to the end time of the current intubation and the number of intubations. Based on the target operation information, the target ERCP operation is evaluated to obtain an evaluation result, which is used to characterize whether the target ERCP operation is a difficult intubation operation.

Images