Medical operation table image monitoring intelligent feedback system and method based on artificial intelligence

Abstract

The invention discloses a medical operation table image monitoring intelligent feedback system and method based on artificial intelligence, and belongs to the technical field of medical equipment. An image sensor is used for shooting an operation table image and recording the definition of the image, and illumination equipment is used for illuminating the operation table and providing an illumination function; adjusting an illumination intensity parameter of the illumination equipment, and selecting one function option to execute an operation instruction of the illumination equipment during adjustment; establishing a behavior capture matrix of the simulation experiment, and constructing a judgment function to endow each matrix element in the behavior capture matrix with a numerical value; the similarity probability between the behavior capture matrixes is analyzed, and artificial intelligence first-time calibration of the behavior capture matrixes is achieved; taking a behavior capture matrix of artificial intelligence secondary calibration analysis as an optimization feedback target of a current simulation experiment based on a first calibration result and the definition of an operation table image; the equipment operation efficiency of the medical operation table can be optimized, the operation environment of the medical operation table is improved in an artificial intelligence mode, and the hands of workers are liberated.

Description

Technical Field

[0001] The present invention relates to the technical field of medical equipment, and in particular to an intelligent feedback system and method for medical operating table image monitoring based on artificial intelligence. Background Art

[0002] In modern medical surgery, the medical operating table is a core device, and its intelligence level is crucial to the accuracy and safety of the surgery. The improvement of the intelligence level of the medical operating table is inseparable from the application of technologies such as artificial intelligence, big data, and the Internet of Things. For example, the image sensor is the "eye" during the operation, and its performance directly affects the accuracy of the operation and the doctor's judgment. However, the clarity of the image sensors equipped on many medical operating tables still requires manual setting of parameters, which makes it difficult for doctors to obtain clear and accurate image information during the operation, thus affecting the smooth progress of the operation. At the same time, considering that the lighting systems of many medical operating tables for surgery still use traditional lighting methods and lack intelligent adjustment functions, the image feedback effect of the image sensor is also affected. In view of this, traditional medical operating tables for surgery are difficult to meet the needs of more intelligent surgery. Summary of the invention

[0003] The purpose of the present invention is to provide an artificial intelligence-based medical operating table image monitoring intelligent feedback system and method to solve the problems raised in the above-mentioned background technology.

[0004] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0005] An intelligent feedback system for medical operating table image monitoring based on artificial intelligence, the system comprises: an equipment terminal module, a function preprocessing module, a parameter source preprocessing module, and an artificial intelligence calibration analysis module connected in sequence;

[0006] The equipment terminal module includes an image sensor and a lighting device installed on the medical sensor; the image sensor is installed at different positions on the medical operating table, and is used to shoot the operating table image of the simulated surgical process and record the clarity of the operating table image; the lighting device is used to illuminate the medical operating table and provide lighting for the simulated surgical process;

[0007] The functional preprocessing module is used to adjust the light intensity parameters of the lighting equipment on the medical operating table in the simulation experiment. After each adjustment of the light intensity parameters, the image sensors at each position correspondingly capture an image of the operating table. The adjustment includes: adjusting the light intensity parameters of all lighting equipment based on the initialization adjustment amplitude ratio, selecting a function option to execute the operation instruction of the light intensity parameters of the lighting equipment each time the adjustment is made, and recording the behavior of each adjustment by adjusting the behavior label;

[0008] The parameter source preprocessing module establishes a behavior capture matrix for the simulation experiment based on the adjusted behavior labels; constructs a judgment function based on the behavior capture matrix, and assigns a value to each matrix element in the behavior capture matrix;

[0009] The artificial intelligence calibration and analysis module is used to combine the Boolean matrix logic operation principle to analyze the similarity probability between behavior capture matrices and perform artificial intelligence initial calibration on the behavior capture matrix; after the operation instruction of the illumination intensity parameter of the lighting equipment is executed, it is used to record the clarity of the corresponding image of the operating table at each position to form a simulated sensory sample cluster, and based on the initial calibration result, perform artificial intelligence secondary calibration analysis, and use the secondary calibrated behavior capture matrix as the optimization feedback target of the current simulation experiment.

[0010] Further, the function preprocessing module includes a function option configuration unit and a behavior label generation unit which are sequentially connected;

[0011] The function option configuration unit is used to uniformly preset the percentage coefficient of increase or decrease of the light intensity parameter of each lighting device to form an initialization adjustment amplitude ratio, and the percentage coefficient forms a function option in the form of a code instruction, one percentage coefficient corresponds to one function option, and each percentage coefficient increases or decreases in sequence according to an arithmetic difference, wherein the increasing order represents the code instruction sequence for increasing the light intensity parameter of the lighting device according to the percentage coefficient corresponding to the function option, and the decreasing order represents the code instruction sequence for decreasing the light intensity parameter of the lighting device according to the percentage coefficient corresponding to the function option;

[0012] The behavior label generating unit is used to obtain the number of lighting devices of the medical operating table, and in the simulation experiment, record the function options selected when executing the operation instructions of the light intensity parameters of the lighting devices to generate the adjustment behavior label.

[0013] Further, the parameter source preprocessing module includes a behavior capture matrix unit and a judgment assignment unit connected in sequence;

[0014] The behavior capture matrix unit establishes a behavior capture matrix of the simulation experiment based on the adjusted behavior label, and uses the serial numbers of the function options as the row numbers of the behavior capture matrix, and the serial numbers of the lighting devices as the column numbers of the behavior capture matrix, so that the total number of rows of the behavior capture matrix is ​​the total number of function options, and the total number of columns of the behavior capture matrix is ​​the total number of lighting devices;

[0015] The judgment assignment unit constructs a judgment function based on the behavior capture matrix, and the operating logic of the judgment function is: if there is a matrix element in a behavior capture matrix that is the same as a matrix element in another behavior capture matrix, then the matrix element in one behavior capture matrix and the matrix element in the other behavior capture matrix are both set to 1, otherwise they are set to 0.

[0016] Further, the artificial intelligence calibration and analysis module includes a primary calibration and analysis unit and a secondary calibration and analysis unit connected in sequence;

[0017] The first calibration analysis unit analyzes the similarity probability between the behavior capture matrices based on the judgment function and the Boolean matrix logic operation principle, presets a similarity probability threshold, and if the similarity probability is greater than or equal to the similarity probability threshold, the behavior capture matrix is ​​first calibrated;

[0018] The secondary calibration analysis unit is used to retrieve the clarity of the operating table image taken by the image sensor at each position in the simulation experiment after the operation instruction of the light intensity parameter of the lighting equipment is executed; arrange the clarity in order from small to large according to the position sequence number to form a simulated sensory sample cluster; based on the first calibration result, perform secondary calibration analysis to calculate the intra-cluster distance of the simulated sensory sample cluster; from all the results of the first calibration, secondary screen out the behavior capture matrix corresponding to the smallest intra-cluster distance, and use the secondary screened behavior capture matrix as the optimization feedback target.

[0019] The medical operating table image monitoring intelligent feedback method based on artificial intelligence comprises the following steps:

[0020] Step S1: installing image sensors at different positions on the medical operating table, and one image sensor is installed at each position, the image sensor is used to capture the image of the operating table during the simulated surgical process and record the clarity of the image of the operating table; the medical operating table is equipped with a lighting device, the lighting device is used to illuminate the medical operating table and provide lighting for the simulated surgical process;

[0021] Step S2: In the simulation experiment, the light intensity parameters of all lighting devices are adjusted based on the initial adjustment amplitude ratio, and a function option is selected each time to execute the operation instruction of the light intensity parameters of the lighting devices, and each adjustment behavior is recorded by adjusting the behavior label;

[0022] Step S3: Based on the adjusted behavior labels, a behavior capture matrix of the simulation experiment is established; based on the behavior capture matrix, a judgment function is constructed, and a value is assigned to each matrix element in the behavior capture matrix;

[0023] Step S4: combining the Boolean matrix logic operation principle, analyzing the similarity probability between the behavior capture matrices, and performing the first artificial intelligence calibration on the behavior capture matrices;

[0024] Step S5: After the operation instruction of the illumination intensity parameter of the lighting equipment is executed, the clarity of the corresponding image of the operating table at each position is recorded to form a simulated sensory sample cluster; and based on the first calibration result, an artificial intelligence secondary calibration analysis is performed, and the secondary calibrated behavior capture matrix is ​​used as the optimization feedback target of the current simulation experiment.

[0025] Furthermore, the specific implementation process of step S1 includes:

[0026] The image sensors arranged at different positions on the medical operating table are used to capture the operating table images simulating the surgical process, and the clarity of the operating table images is recorded, wherein one image sensor is arranged at one position;

[0027] In the simulation experiment, the light intensity parameters of the lighting equipment on the medical operating table were adjusted. After each adjustment of the light intensity parameters, the image sensors at various positions correspondingly captured an image of the operating table.

[0028] Furthermore, the specific implementation process of step S2 includes:

[0029] The initialization adjustment amplitude ratio is a uniformly preset percentage coefficient for increasing or decreasing the light intensity parameter of each lighting device, and the percentage coefficient forms a function option in the form of a code instruction, one percentage coefficient corresponds to one function option, and each percentage coefficient increases or decreases in sequence according to an arithmetic difference, wherein the increasing order represents the code instruction sequence for increasing the light intensity parameter of the lighting device according to the percentage coefficient corresponding to the function option, and the decreasing order represents the code instruction sequence for decreasing the light intensity parameter of the lighting device according to the percentage coefficient corresponding to the function option;

[0030] Get the number of lighting devices on the medical operating table and record the e-th lighting device as L e ; Uniformly encode the function options, and record the ath function option as F a ;

[0031] In the xth simulation experiment, record the execution of lighting equipment L e When operating the light intensity parameter, select function option F a , and generate an adjustment behavior label, denoted as [F a , L e ] x .

[0032] Furthermore, the specific implementation process of step S3 includes:

[0033] Based on the adjustment behavior label [F a , L e ] x , establish the behavior capture matrix of the simulation experiment, and set the function options F a The serial number a is used as the row number of the behavior capture matrix, and the lighting device L e The serial number e of the behavior capture matrix is ​​used as the column number of the behavior capture matrix, and the matrix element corresponding to the ath row and the eth column of the behavior capture matrix is ​​recorded as F a |L e , and the behavior capture matrix generated by the xth simulation experiment is recorded as R x (A, E), where A represents the total number of rows of the behavior capture matrix, i.e., the total number of function options, and E represents the total number of columns of the behavior capture matrix, i.e., the total number of lighting devices;

[0034] Based on the behavior capture matrix, the behavior capture matrix R x (A, E) is the data reference center, and the judgment function is constructed:

[0035]

[0036] The operation logic of the judgment function is that there is a behavior capture matrix R y The matrix element F in (A, E) a |L e and the behavior capture matrix R x The matrix element F in (A, E) a |L e The same, let the behavior capture matrix R y The matrix element F in (A, E) a |L e and the behavior capture matrix R x The matrix element F in (A, E) a |L e All are 1, otherwise 0;

[0037] Furthermore, the specific implementation process of step S4 includes:

[0038] Based on the judgment function and the Boolean matrix logic operation principle, the behavior capture matrix R is analyzed. y (A, E) and the behavior capture matrix R x The similarity probability between (A, E) is as follows:

[0039] Calculate the behavior capture matrix R y (A, E) and the behavior capture matrix R x The similarity probability between (A, E) is as follows:

[0040]

[0041] Where, SP xy Represents the behavior capture matrix R y (A, E) and the behavior capture matrix R x The similarity probability between (A, E), y represents the number of simulation experiments, and y<x; NUM[R y (A, E)∩R x (A, E)] represents the behavior capture matrix R y (A, E) and the behavior capture matrix R x The number of 1s in the result of the Boolean matrix and logic operation between (A, E), NUM[R y (A, E)∪R x (A, E)] represents the behavior capture matrix R y (A, E) and the behavior capture matrix R x The number of 1s contained in the Boolean matrix or logic operation result between (A, E);

[0042] Preset similarity probability threshold, if similarity probability SP xy If it is greater than or equal to the similarity probability threshold, the behavior is first calibrated as the capture matrix R y (A, E);

[0043] According to the above method, when there are more identical matrix elements in different behavior capture matrices, more numerical values ​​1 are included after the Boolean logic operation, and thus the operating parameters of the lighting devices recorded in the two different behavior capture matrices are more similar.

[0044] Furthermore, the specific implementation process of step S5 includes:

[0045] Get the number of positions of the medical operating table and record the rth position as S r ;

[0046] In the simulation experiment, when the lighting device L e After the operation instruction of the light intensity parameter is executed, the clarity of the operating table image taken by the image sensor at each position is retrieved, and the clarity of the image of the operating table taken by the image sensor at each position is set. r The clarity of the operating table image obtained in the yth simulation experiment is recorded as D y (S r ); Arrange the clarity in ascending order according to the position number to form a simulated sensory sample cluster, recorded as SC y ={D y (S r )|r∈[1,R]}, where R represents the total number of directions;

[0047] Based on the first calibration results, a second calibration analysis is performed:

[0048] Computational simulation of sensory sample cluster SC y The intra-cluster distance

[0049] Among all the results of the first calibration, the minimum intra-cluster distance min{CD y}The corresponding behavior capture matrix R y (A, E), and the secondary screening behavior capture matrix R y (A, E) is the behavior capture matrix R x (A, E) The corresponding optimized feedback target of the xth simulation experiment;

[0050] According to the above method, for the simulated sensory sample cluster, the smaller the intra-cluster distance is, the closer the image clarity is at all directions and angles of the medical operating table, and thus the more uniform the environmental conditions of the medical operating table are, the better the image effect is.

[0051] Compared with the prior art, the beneficial effects achieved by the present invention are as follows: in the medical operating table image monitoring intelligent feedback system and method based on artificial intelligence provided by the present invention, the operating table image is captured by an image sensor and the clarity of the image is recorded, and the operating table is illuminated by a lighting device and a lighting function is provided; the light intensity parameter of the lighting device is adjusted, and a function option is selected during the adjustment to execute the operating instructions of the lighting device; a behavior capture matrix of a simulation experiment is established, and a judgment function is constructed to assign numerical values ​​to each matrix element in the behavior capture matrix; the similarity probability between the behavior capture matrices is analyzed to achieve the first artificial intelligence calibration of the behavior capture matrix; based on the first calibration result and the clarity of the operating table image, the behavior capture matrix analyzed by the artificial intelligence secondary calibration is used as the optimization feedback target of the current simulation experiment; the present invention can optimize the equipment operation efficiency of the medical operating table, improve the surgical environment of the medical operating table through artificial intelligence, and free the hands of the staff. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] The accompanying drawings are used to provide further understanding of the present invention and constitute a part of the specification. They are used to explain the present invention together with the embodiments of the present invention and do not constitute a limitation of the present invention.

[0053] Figure 1 It is a structural schematic diagram of the medical operating table image monitoring intelligent feedback system based on artificial intelligence of the present invention. DETAILED DESCRIPTION

[0054] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0055] In the first embodiment of the present invention: an intelligent feedback system for medical operating table image monitoring based on artificial intelligence is provided, the system comprising: an equipment terminal module, a function preprocessing module, a parameter source preprocessing module, and an artificial intelligence calibration analysis module connected in sequence;

[0056] The equipment terminal module includes an image sensor and a lighting device installed on the medical sensor; the image sensor is installed at different positions on the medical operating table, and is used to shoot the operating table image of the simulated surgical process and record the clarity of the operating table image; the lighting device is used to illuminate the medical operating table and provide lighting for the simulated surgical process;

[0057] The function preprocessing module is used to adjust the light intensity parameters of the lighting equipment on the medical operating table in the simulation experiment. After each adjustment of the light intensity parameters, the image sensors at various positions correspondingly capture an image of the operating table. The adjustment includes: adjusting the light intensity parameters of all lighting equipment based on the initial adjustment amplitude ratio, selecting a function option to execute the operation instruction of the light intensity parameters of the lighting equipment each time the adjustment is made, and recording each adjustment behavior by adjusting the behavior label;

[0058] Preferably, the function preprocessing module includes a function option configuration unit and a behavior label generation unit connected in sequence;

[0059] A function option configuration unit, used for uniformly presetting the percentage coefficient of increase or decrease of the light intensity parameter of each lighting device to form an initialization adjustment amplitude ratio, wherein the percentage coefficient forms a function option in the form of a code instruction, one percentage coefficient corresponds to one function option, and each percentage coefficient increases or decreases in sequence according to an arithmetic difference, wherein the increasing order represents the code instruction sequence for increasing the light intensity parameter of the lighting device according to the percentage coefficient corresponding to the function option, and the decreasing order represents the code instruction sequence for decreasing the light intensity parameter of the lighting device according to the percentage coefficient corresponding to the function option;

[0060] A behavior label generating unit is used to obtain the number of lighting devices of the medical operating table, and in a simulation experiment, record the function options selected when executing the operation instructions of the light intensity parameters of the lighting devices to generate an adjustment behavior label;

[0061] The parameter source preprocessing module establishes the behavior capture matrix of the simulation experiment based on the adjusted behavior labels; constructs the judgment function based on the behavior capture matrix and assigns values ​​to each matrix element in the behavior capture matrix;

[0062] Preferably, the parameter source preprocessing module includes a behavior capture matrix unit and a judgment assignment unit connected in sequence;

[0063] The behavior capture matrix unit establishes the behavior capture matrix of the simulation experiment based on the adjusted behavior labels, and uses the serial numbers of the function options as the row numbers of the behavior capture matrix, and the serial numbers of the lighting devices as the column numbers of the behavior capture matrix. Then, the total number of rows of the behavior capture matrix is ​​the total number of function options, and the total number of columns of the behavior capture matrix is ​​the total number of lighting devices.

[0064] The judgment assignment unit constructs a judgment function based on the behavior capture matrix. The operation logic of the judgment function is: if a matrix element in a behavior capture matrix is ​​the same as a matrix element in another behavior capture matrix, then the matrix element in one behavior capture matrix and the matrix element in another behavior capture matrix are both set to 1, otherwise they are set to 0;

[0065] The AI ​​calibration and analysis module is used to analyze the similarity probability between behavior capture matrices in combination with the Boolean matrix logic operation principle, and to perform the AI ​​first calibration on the behavior capture matrix; after the operation instruction of the illumination intensity parameter of the lighting equipment is executed, it is used to record the clarity of the corresponding image of the operating table at each position to form a simulated sensory sample cluster, and based on the first calibration result, perform AI second calibration analysis, and use the second calibrated behavior capture matrix as the optimization feedback target of the current simulation experiment;

[0066] Preferably, the artificial intelligence calibration analysis module includes a primary calibration analysis unit and a secondary calibration analysis unit connected in sequence;

[0067] The first calibration analysis unit analyzes the similarity probability between the behavior capture matrices based on the judgment function and the Boolean matrix logic operation principle, and presets a similarity probability threshold. If the similarity probability is greater than or equal to the similarity probability threshold, the behavior capture matrix is ​​first calibrated;

[0068] The secondary calibration and analysis unit is used to retrieve the clarity of the operating table image taken by the image sensor at each position in the simulation experiment after the operation instruction of the light intensity parameter of the lighting equipment is executed; arrange the clarity in order from small to large according to the position number to form a simulated sensory sample cluster; based on the first calibration result, perform secondary calibration analysis to calculate the intra-cluster distance of the simulated sensory sample cluster; from all the results of the first calibration, screen out the behavior capture matrix corresponding to the smallest intra-cluster distance for the second time, and use the second screened behavior capture matrix as the optimization feedback target.

[0069] See also Figure 1 In the second embodiment, a medical operating table image monitoring intelligent feedback method based on artificial intelligence is provided, and the method comprises the following steps:

[0070] Step S1: image sensors are installed at different positions on the medical operating table, and one image sensor is installed at each position, the image sensor is used to capture the image of the operating table during the simulated surgical process and record the clarity of the image of the operating table; a lighting device is installed on the medical operating table, the lighting device is used to illuminate the medical operating table and provide lighting for the simulated surgical process;

[0071] Exemplarily, an image sensor disposed at different positions on the medical operating table is used to capture an image of the operating table simulating the surgical process, and the clarity of the image of the operating table is recorded, wherein one image sensor is disposed at one position;

[0072] In the simulation experiment, the light intensity parameters of the lighting equipment on the medical operating table are adjusted. After each adjustment of the light intensity parameters, the image sensors at various positions correspondingly capture an image of the operating table.

[0073] Step S2: In the simulation experiment, the light intensity parameters of all lighting devices are adjusted based on the initial adjustment amplitude ratio, and a function option is selected each time to execute the operation instruction of the light intensity parameters of the lighting devices, and each adjustment behavior is recorded by adjusting the behavior label;

[0074] Exemplarily, the initialization adjustment amplitude ratio is a uniformly preset percentage coefficient of increase or decrease of the light intensity parameter of each lighting device, the percentage coefficient forms a function option in the form of a code instruction, one percentage coefficient corresponds to one function option, and each percentage coefficient increases or decreases in sequence according to an arithmetic difference, wherein the increasing order represents the code instruction sequence for increasing the light intensity parameter of the lighting device according to the percentage coefficient corresponding to the function option, and the decreasing order represents the code instruction sequence for decreasing the light intensity parameter of the lighting device according to the percentage coefficient corresponding to the function option;

[0075] Get the number of lighting devices on the medical operating table and record the e-th lighting device as L e ; Unify the coding of the function options, and record the ath function option as F a ;

[0076] In the xth simulation experiment, record the execution of lighting equipment L e When operating the light intensity parameter, select function option F a , and generate an adjustment behavior label, denoted as [F a , L e ] x ;

[0077] Step S3: Based on the adjusted behavior labels, a behavior capture matrix of the simulation experiment is established; based on the behavior capture matrix, a judgment function is constructed, and a value is assigned to each matrix element in the behavior capture matrix;

[0078] For example, based on adjusting the behavior label [F a , L e ] x , establish the behavior capture matrix of the simulation experiment, and set the function options F a The serial number a is used as the row number of the behavior capture matrix, and the lighting device L e The serial number e is used as the column number of the behavior capture matrix, and the matrix element corresponding to the ath row and the eth column of the behavior capture matrix is ​​recorded as F a |L e , and the behavior capture matrix generated by the xth simulation experiment is recorded as R x (A, E), where A represents the total number of rows of the behavior capture matrix, i.e., the total number of function options, and E represents the total number of columns of the behavior capture matrix, i.e., the total number of lighting devices;

[0079] Based on the behavior capture matrix, the behavior capture matrix R x (A, E) is the data reference center, and the judgment function is constructed:

[0080]

[0081] The operation logic of the judgment function is that there is a behavior capture matrix R y The matrix element F in (A, E) a |L e and the behavior capture matrix R x The matrix element F in (A, E) a |L e The same, let the behavior capture matrix R y The matrix element F in (A, E) a |L e and the behavior capture matrix R x The matrix element F in (A, E) a |L e All are 1, otherwise 0;

[0082] Step S4: combining the Boolean matrix logic operation principle, analyzing the similarity probability between the behavior capture matrices, and performing the first artificial intelligence calibration on the behavior capture matrices;

[0083] For example, based on the judgment function and combined with the Boolean matrix logic operation principle, the behavior capture matrix R is analyzed. y (A, E) and the behavior capture matrix R xThe similarity probability between (A, E) is as follows:

[0084] Calculate the behavior capture matrix R y (A, E) and the behavior capture matrix R x The similarity probability between (A, E) is as follows:

[0085]

[0086] Where, SP xy Represents the behavior capture matrix R y (A, E) and the behavior capture matrix R x The similarity probability between (A, E), y represents the number of simulation experiments, and y<x; NUM[R y (A, E)∩R x (A, E)] represents the behavior capture matrix R y (A, E) and the behavior capture matrix R x The number of 1s in the result of the Boolean matrix and logic operation between (A, E), NUM[R y (A, E)∪R x (A, E)] represents the behavior capture matrix R y (A, E) and the behavior capture matrix R x The number of 1s contained in the Boolean matrix or logic operation result between (A, E);

[0087] Preset similarity probability threshold, if similarity probability SP xy If it is greater than or equal to the similarity probability threshold, the behavior is first calibrated as the capture matrix R y (A, E);

[0088] Step S5: After the operation instruction of the illumination intensity parameter of the lighting device is executed, the clarity of the corresponding image of the operating table at each position is recorded to form a simulated sensory sample cluster; and based on the first calibration result, an artificial intelligence secondary calibration analysis is performed, and the secondary calibrated behavior capture matrix is ​​used as the optimization feedback target of the current simulation experiment;

[0089] Exemplarily, the number of positions of the medical operating table is obtained, and the rth position is recorded as S r ;

[0090] In the simulation experiment, when the lighting device L e After the operation instruction of the light intensity parameter is executed, the clarity of the operating table image taken by the image sensor at each position is retrieved, and the clarity of the image of the operating table taken by the image sensor at each position is set. r The clarity of the operating table image obtained in the yth simulation experiment is recorded as D y (S r); Arrange the clarity in ascending order according to the position number to form a simulated sensory sample cluster, recorded as SC y ={D y (S r )|r∈[1,R]}, where R represents the total number of directions;

[0091] Based on the first calibration results, a second calibration analysis is performed:

[0092] Computational simulation of sensory sample cluster SC y The intra-cluster distance

[0093] Among all the results of the first calibration, the minimum intra-cluster distance min{CD y}The corresponding behavior capture matrix R y (A, E), and the secondary screening behavior capture matrix R y (A, E) is the behavior capture matrix R x (A, E) The corresponding optimized feedback target of the xth simulation experiment.

[0094] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.

[0095] Finally, it should be noted that the above is only a preferred embodiment of the present invention and is not intended to limit the present invention. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art can still modify the technical solutions described in the aforementioned embodiments or replace some of the technical features therein by equivalents. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. An intelligent feedback method for medical operating table image monitoring based on artificial intelligence, characterized in that: The method comprises the following steps: Step S1: installing image sensors at different positions on the medical operating table, and one image sensor is installed at each position, the image sensor is used to capture the image of the operating table during the simulated surgical process and record the clarity of the image of the operating table; the medical operating table is equipped with a lighting device, the lighting device is used to illuminate the medical operating table and provide lighting for the simulated surgical process; Step S2: In the simulation experiment, the light intensity parameters of all lighting devices are adjusted based on the initial adjustment amplitude ratio, and a function option is selected each time to execute the operation instruction of the light intensity parameters of the lighting devices, and each adjustment behavior is recorded by adjusting the behavior label; Step S3: Based on the adjusted behavior labels, a behavior capture matrix of the simulation experiment is established; based on the behavior capture matrix, a judgment function is constructed, and a value is assigned to each matrix element in the behavior capture matrix; Step S4: combining the Boolean matrix logic operation principle, analyzing the similarity probability between the behavior capture matrices, and performing the first artificial intelligence calibration on the behavior capture matrices; Step S5: After the operation instruction of the illumination intensity parameter of the lighting equipment is executed, the clarity of the corresponding image of the operating table at each position is recorded to form a simulated sensory sample cluster; and based on the first calibration result, an artificial intelligence secondary calibration analysis is performed, and the secondary calibrated behavior capture matrix is ​​used as the optimization feedback target of the current simulation experiment.

2. The medical operating table image monitoring intelligent feedback method based on artificial intelligence according to claim 1 is characterized in that: The specific implementation process of step S1 includes: The image sensors arranged at different positions on the medical operating table are used to capture the operating table images simulating the surgical process, and the clarity of the operating table images is recorded, wherein one image sensor is arranged at one position; In the simulation experiment, the light intensity parameters of the lighting equipment on the medical operating table were adjusted. After each adjustment of the light intensity parameters, the image sensors at various positions correspondingly captured an image of the operating table.

3. The medical operating table image monitoring intelligent feedback method based on artificial intelligence according to claim 2 is characterized in that: The specific implementation process of step S2 includes: The initialization adjustment amplitude ratio is a uniformly preset percentage coefficient for increasing or decreasing the light intensity parameter of each lighting device, and the percentage coefficient forms a function option in the form of a code instruction, one percentage coefficient corresponds to one function option, and each percentage coefficient increases or decreases in sequence according to an arithmetic difference, wherein the increasing order represents the code instruction sequence for increasing the light intensity parameter of the lighting device according to the percentage coefficient corresponding to the function option, and the decreasing order represents the code instruction sequence for decreasing the light intensity parameter of the lighting device according to the percentage coefficient corresponding to the function option; Get the number of lighting devices on the medical operating table and record the e-th lighting device as L e ; Uniformly encode the function options, and record the ath function option as F a ; In the xth simulation experiment, record the execution of lighting equipment L e When operating the light intensity parameter, select function option F a , and generate an adjustment behavior label, denoted as [F a , L e ] x .

4. The medical operating table image monitoring intelligent feedback method based on artificial intelligence according to claim 3 is characterized in that: The specific implementation process of step S3 includes: Based on the adjustment behavior label [F a , L e ] x , establish the behavior capture matrix of the simulation experiment, and set the function options F a The serial number a is used as the row number of the behavior capture matrix, and the lighting device L e The serial number e of the behavior capture matrix is ​​used as the column number of the behavior capture matrix, and the matrix element corresponding to the ath row and the eth column of the behavior capture matrix is ​​recorded as F a |L e , and the behavior capture matrix generated by the xth simulation experiment is recorded as R x (A, E), where A represents the total number of rows of the behavior capture matrix, i.e., the total number of function options, and E represents the total number of columns of the behavior capture matrix, i.e., the total number of lighting devices; Based on the behavior capture matrix, the behavior capture matrix R x (A, E) is the data reference center, and the judgment function is constructed: The operation logic of the judgment function is that there is a behavior capture matrix R y The matrix element F in (A, E) a |L e and the behavior capture matrix R x The matrix element F in (A, E) a |L e The same, let the behavior capture matrix R y The matrix element F in (A, E) a |L e and the behavior capture matrix R x The matrix element F in (A, E) a |L e 1 if both are true, otherwise 0.

5. The medical operating table image monitoring intelligent feedback method based on artificial intelligence according to claim 4 is characterized in that: The specific implementation process of step S4 includes: Based on the judgment function and the Boolean matrix logic operation principle, the behavior capture matrix R is analyzed. y (A, E) and the behavior capture matrix R x The similarity probability between (A, E) is as follows: Calculate the behavior capture matrix R y (A, E) and the behavior capture matrix R x The similarity probability between (A, E) is as follows: Where, SP xy Represents the behavior capture matrix R y (A, E) and the behavior capture matrix R x The similarity probability between (A, E), y represents the number of simulation experiments, and y<x; NUM[R y (A, E)∩R x (A, E)] represents the behavior capture matrix R y (A, E) and the behavior capture matrix R x The number of 1s in the result of the Boolean matrix and logic operation between (A, E), NUM[R y (A, E)∪R x (A, E)] represents the behavior capture matrix R y (A, E) and the behavior capture matrix R x The number of 1s contained in the Boolean matrix or logic operation result between (A, E); Preset similarity probability threshold, if similarity probability SP xy If it is greater than or equal to the similarity probability threshold, the behavior is first calibrated as the capture matrix R y (A, E).

6. The medical operating table image monitoring intelligent feedback method based on artificial intelligence according to claim 5 is characterized in that: The specific implementation process of step S5 includes: Get the number of positions of the medical operating table and record the rth position as S r ; In the simulation experiment, when the lighting device L e After the operation instruction of the light intensity parameter is executed, the clarity of the operating table image taken by the image sensor at each position is retrieved, and the clarity of the image of the operating table taken by the image sensor at each position is set. r The clarity of the operating table image obtained in the yth simulation experiment is recorded as D y (S r ); Arrange the clarity in ascending order according to the position number to form a simulated sensory sample cluster, recorded as SC y ={D y (S r )|r∈[1,R]}, where R represents the total number of directions; Based on the first calibration results, a second calibration analysis is performed: Computational simulation of sensory sample cluster SC y The intra-cluster distance Among all the results of the first calibration, the minimum intra-cluster distance min{CD y }The corresponding behavior capture matrix R y (A, E), and the secondary screening behavior capture matrix R y (A, E) is the behavior capture matrix R x (A, E) The corresponding optimized feedback target of the xth simulation experiment.

7. An artificial intelligence-based medical operating table image monitoring intelligent feedback system, which executes the artificial intelligence-based medical operating table image monitoring intelligent feedback method according to any one of claims 1 to 6, characterized in that: The system includes a device terminal module, a function preprocessing module, a parameter source preprocessing module, and an artificial intelligence calibration analysis module which are connected in sequence; The equipment terminal module includes an image sensor and a lighting device installed on the medical sensor; the image sensor is installed at different positions on the medical operating table, and is used to shoot the operating table image of the simulated surgical process and record the clarity of the operating table image; the lighting device is used to illuminate the medical operating table and provide lighting for the simulated surgical process; The functional preprocessing module is used to adjust the light intensity parameters of the lighting equipment on the medical operating table in the simulation experiment. After each adjustment of the light intensity parameters, the image sensors at each position correspondingly capture an image of the operating table. The adjustment includes: adjusting the light intensity parameters of all lighting equipment based on the initialization adjustment amplitude ratio, selecting a function option to execute the operation instruction of the light intensity parameters of the lighting equipment each time the adjustment is made, and recording the behavior of each adjustment by adjusting the behavior label; The parameter source preprocessing module establishes a behavior capture matrix for the simulation experiment based on the adjusted behavior labels; constructs a judgment function based on the behavior capture matrix, and assigns a value to each matrix element in the behavior capture matrix; The artificial intelligence calibration and analysis module is used to combine the Boolean matrix logic operation principle to analyze the similarity probability between behavior capture matrices and perform artificial intelligence initial calibration on the behavior capture matrix; after the operation instruction of the illumination intensity parameter of the lighting equipment is executed, it is used to record the clarity of the corresponding image of the operating table at each position to form a simulated sensory sample cluster, and based on the initial calibration result, perform artificial intelligence secondary calibration analysis, and use the secondary calibrated behavior capture matrix as the optimization feedback target of the current simulation experiment.

8. The medical operating table image monitoring intelligent feedback system based on artificial intelligence according to claim 7 is characterized by: The function preprocessing module includes a function option configuration unit and a behavior label generation unit connected in sequence; The function option configuration unit is used to uniformly preset the percentage coefficient of increase or decrease of the light intensity parameter of each lighting device to form an initialization adjustment amplitude ratio, and the percentage coefficient forms a function option in the form of a code instruction, one percentage coefficient corresponds to one function option, and each percentage coefficient increases or decreases in sequence according to an arithmetic difference, wherein the increasing order represents the code instruction sequence for increasing the light intensity parameter of the lighting device according to the percentage coefficient corresponding to the function option, and the decreasing order represents the code instruction sequence for decreasing the light intensity parameter of the lighting device according to the percentage coefficient corresponding to the function option; The behavior label generating unit is used to obtain the number of lighting devices of the medical operating table, and in the simulation experiment, record the function options selected when executing the operation instructions of the light intensity parameters of the lighting devices to generate the adjustment behavior label.

9. The medical operating table image monitoring intelligent feedback system based on artificial intelligence according to claim 7 is characterized by: The parameter source preprocessing module includes a behavior capture matrix unit and a judgment assignment unit connected in sequence; The behavior capture matrix unit establishes a behavior capture matrix of the simulation experiment based on the adjusted behavior label, and uses the serial numbers of the function options as the row numbers of the behavior capture matrix, and the serial numbers of the lighting devices as the column numbers of the behavior capture matrix, so that the total number of rows of the behavior capture matrix is ​​the total number of function options, and the total number of columns of the behavior capture matrix is ​​the total number of lighting devices; The judgment assignment unit constructs a judgment function based on the behavior capture matrix, and the operating logic of the judgment function is: if there is a matrix element in a behavior capture matrix that is the same as a matrix element in another behavior capture matrix, then the matrix element in one behavior capture matrix and the matrix element in the other behavior capture matrix are both set to 1, otherwise they are set to 0.

10. The medical operating table image monitoring intelligent feedback system based on artificial intelligence according to claim 7, characterized in that: The artificial intelligence calibration and analysis module includes a primary calibration and analysis unit and a secondary calibration and analysis unit which are sequentially connected; The first calibration analysis unit analyzes the similarity probability between the behavior capture matrices based on the judgment function and the Boolean matrix logic operation principle, presets a similarity probability threshold, and if the similarity probability is greater than or equal to the similarity probability threshold, the behavior capture matrix is ​​first calibrated; The secondary calibration analysis unit is used to retrieve the clarity of the operating table image taken by the image sensor at each position after the operation instruction of the illumination intensity parameter of the lighting device is executed in the simulation experiment; arrange the clarity in the order of the position number from small to large to form a simulated sensory sample cluster; perform secondary calibration analysis based on the first calibration result to calculate the intra-cluster distance of the simulated sensory sample cluster; Among all the results of the first calibration, the behavior capture matrix corresponding to the smallest intra-cluster distance is screened out for the second time, and the second-screened behavior capture matrix is ​​used as the optimization feedback target.

Images