An intelligent assessment and classification method for preoperative DBS in Parkinson's disease based on MRI images

Abstract

The present invention provides a preoperative intelligent assessment and classification method for DBS of Parkinson's disease based on MRI images. The method determines the preoperative intervention position of a target patient based on an initial planning point of a target nucleus; retrieves patient attribute information of the target patient and nucleus volume information of the target nucleus, and determines the offset direction and offset distance corresponding to the target nucleus based on the patient attribute information, the nucleus volume information and the initial planning point; updates the preoperative intervention position, the initial planning point, the offset direction and the offset distance to a three-dimensional magnetic resonance image, obtains a three-dimensional reference image and sends it to a surgical end; when it is determined that the pacing electrode is located at the initial planning point, the tremor site of the target patient is collected in real time to obtain an assessment video of the initial planning point; when it is determined that the tremor frequency in the assessment video does not meet the preset requirements, the placement planning point of the target nucleus is determined according to the electrode offset strategy, the offset direction and the offset distance and sent to the surgical end.

Description

Technical Field

[0001] The present invention relates to data processing technology, and in particular to an intelligent assessment and classification method for Parkinson's disease DBS pre-surgery based on MRI images. Background Art

[0002] Parkinson's disease is a neurodegenerative disease that often causes movement disorders such as tremor, rigidity and bradykinesia. For some patients, deep brain stimulation (DBS) surgery can significantly improve their symptoms. However, preoperative evaluation and planning are crucial. Precise positioning of the implantation site of the stimulating electrodes during surgery is required to ensure that surgical risks are minimized and treatment outcomes are maximized.

[0003] Traditional preoperative evaluation methods often rely on the doctor's experience and lack scientific quantitative analysis, which can easily lead to inaccurate electrode placement, thus affecting the surgical effect. At present, the existing technology does not take into account the individual differences of patients sufficiently and fails to conduct customized evaluations for each patient, which may lead to deviations in the judgment of the surgical location. Secondly, the existing methods lack a dynamic feedback mechanism when determining the electrode placement planning points, and cannot obtain real-time changes in the patient's preoperative state, especially the dynamic changes in tremor frequency, which may cause the final placed electrodes to fail to achieve the expected therapeutic effect. In addition, the existing technology also lacks a scientific basis for adjusting the stimulation intensity and cannot accurately match the actual needs of patients.

[0004] Therefore, how to conduct customized assessments based on the actual MRI images of each patient and then determine the electrode placement points in order to reduce the time for physicians to determine the location of the nucleus and improve the efficiency of diagnosis and treatment has become an urgent problem to be solved. Summary of the invention

[0005] The present invention provides an intelligent assessment and classification method for Parkinson's disease DBS preoperatively based on MRI images. Customized assessment can be performed according to the actual MRI images of each patient, and then the electrode placement points can be determined, so as to reduce the time for doctors to judge the location of the nucleus and improve the efficiency of diagnosis and treatment.

[0006] The first aspect of the present invention provides a method for intelligent assessment and classification of Parkinson's disease DBS preoperatively based on MRI images, comprising:

[0007] Acquire a three-dimensional magnetic resonance image of a target patient, locate a target nucleus in the three-dimensional magnetic resonance image, and determine a preoperative intervention position of the target patient based on an initial planning point of the target nucleus;

[0008] Retrieving patient attribute information of a target patient and nucleus volume information of a target nucleus, and determining an offset direction and an offset distance corresponding to the target nucleus based on the patient attribute information, the nucleus volume information and the initial planning point;

[0009] The preoperative intervention position, the initial planning point, the offset direction and the offset distance are updated to the three-dimensional magnetic resonance image, and a three-dimensional reference image is obtained and sent to the surgical end. When it is determined that the pacing electrode is located at the initial planning point, the tremor site of the target patient is collected in real time to obtain an evaluation video of the initial planning point;

[0010] When it is determined that the tremor frequency in the evaluation video does not meet the preset requirements, the placement planning point of the target nucleus is determined according to the electrode offset strategy, the offset direction and the offset distance and sent to the surgical end.

[0011] Optionally, in a possible implementation manner of the first aspect, acquiring a three-dimensional magnetic resonance image of a target patient, locating a target nucleus in the three-dimensional magnetic resonance image, and determining a preoperative intervention position of the target patient based on an initial planning point of the target nucleus, includes:

[0012] Acquire a three-dimensional magnetic resonance image of a target patient, and locate a target nucleus in the three-dimensional magnetic resonance image;

[0013] Determine the center point of the three-dimensional magnetic resonance image, and perform coordinate processing on the three-dimensional magnetic resonance image based on the center point to obtain a three-dimensional coordinate system;

[0014] Acquiring the coordinates corresponding to the center point of the target nucleus as the initial planning point, and counting the pixel coordinates of the intervention site in the three-dimensional magnetic resonance image to obtain an intervention coordinate set corresponding to the intervention site;

[0015] The pixel coordinates in the intervention coordinate set that are closest to the initial planning point are selected as the preoperative intervention position of the target patient.

[0016] Optionally, in a possible implementation manner of the first aspect, the retrieving patient attribute information of the target patient and the nucleus volume information of the target nucleus, and determining the offset direction and offset distance corresponding to the target nucleus based on the patient attribute information, the nucleus volume information and the initial planning point, includes:

[0017] Retrieving patient attribute information of a target patient, wherein the patient attribute information includes age information, height information, and weight information, and retrieving nucleus volume information of a target nucleus;

[0018] Retrieving similar patients in a historical surgery database based on the patient attribute information, and obtaining historical planning points and historical placement points of the similar patients;

[0019] Calculating according to the historical planning points and the historical placement points to obtain an offset vector, and determining an offset direction corresponding to the target nucleus based on the offset vector;

[0020] Based on the ratio of the nucleus volume information to the reference volume information, an offset coefficient is obtained, and a reference offset distance corresponding to the reference volume information is retrieved;

[0021] The offset distance corresponding to the target nucleus is obtained according to the product of the reference offset distance and the offset coefficient.

[0022] Optionally, in a possible implementation manner of the first aspect, when determining that the tremor frequency in the evaluation video does not meet a preset requirement, determining, according to an electrode offset strategy, the offset direction, and the offset distance, a placement planning point of the target nucleus and sending it to a surgical end includes:

[0023] Obtaining the tremor frequency of the tremor part in the evaluation video, and when it is determined that the tremor frequency in the evaluation video is greater than a preset tremor frequency, counting the number of patients of the same type corresponding to each offset direction as the offset number;

[0024] Sort the offset directions in descending order based on the offset quantity to obtain a partial order direction sequence;

[0025] Selecting the first offset direction in the partial order direction sequence as the electrode movement direction, and determining the electrode offset point according to the electrode movement direction and the offset distance;

[0026] When it is determined that the pacing electrode is located at the electrode offset point, the tremor position of the target patient is collected in real time to obtain an offset video of the electrode offset point;

[0027] When it is determined that the tremor frequency in the offset video is greater than a preset tremor frequency, the partial order direction sequence is deleted and updated based on the electrode movement direction;

[0028] Repeat the above steps of obtaining the offset video until the tremor frequency in the offset video is less than or equal to the preset tremor frequency, and then send the corresponding electrode offset point as the placement planning point to the surgical end.

[0029] Optionally, in a possible implementation of the first aspect, the method further includes:

[0030] Obtaining the maximum horizontal coordinate, the minimum horizontal coordinate, the maximum vertical coordinate, the minimum vertical coordinate, the maximum vertical coordinate and the minimum vertical coordinate in the target nucleus;

[0031] Obtaining a first transverse length according to a difference between the maximum transverse coordinate and the minimum transverse coordinate of the target nucleus;

[0032] Obtaining a first longitudinal length based on a difference between the maximum longitudinal coordinate and the minimum longitudinal coordinate of the target nucleus;

[0033] Obtaining a first vertical length according to a difference between the maximum vertical coordinate and the minimum vertical coordinate of the target nucleus;

[0034] Selecting the maximum value among the first transverse length, the first longitudinal length and the first vertical length as the actual dovetail length of the target nucleus;

[0035] Extracting dovetail pixel points in the target nucleus according to the dovetail pixel value, and counting the number of the dovetail pixel points to obtain the actual dovetail number;

[0036] Amplifying the reference nucleus based on the offset coefficient to obtain a standard nucleus, and obtaining a standard dovetail length and a standard dovetail quantity of the standard nucleus;

[0037] Obtaining a first strength adjustment coefficient based on a ratio of the standard dovetail length to the actual dovetail length, and obtaining a second strength adjustment coefficient based on a ratio of the standard dovetail quantity to the actual dovetail quantity;

[0038] The preset stimulation intensity is adjusted based on the first intensity adjustment coefficient and the second intensity adjustment coefficient to obtain an actual stimulation intensity.

[0039] Optionally, in a possible implementation manner of the first aspect, adjusting the preset stimulation intensity based on the first intensity adjustment coefficient and the second intensity adjustment coefficient to obtain the actual stimulation intensity includes:

[0040] Obtaining a first adjustment value according to the product of the first strength adjustment coefficient and the length weight value;

[0041] Obtaining a second adjustment value based on the product of the second intensity adjustment coefficient and the quantity weight value;

[0042] Adjusting the preset stimulation intensity according to the first adjustment value and the second adjustment value to obtain an actual stimulation intensity;

[0043] The actual stimulus intensity is obtained by the following formula:

[0044] in, is the actual stimulus intensity, To preset the stimulation intensity, is the standard dovetail length, is the actual dovetail length, is the length weight value, is the standard dovetail quantity, is the actual number of dovetails, is the quantity weight value.

[0045] Optionally, in a possible implementation of the first aspect, the method further includes:

[0046] When it is determined that the partial order direction sequence does not have the offset direction, a central abscissa is obtained based on an average value of the maximum abscissa and the minimum abscissa and the value, a central ordinate is obtained based on an average value of the maximum ordinate and the minimum ordinate and the value, and a central ordinate is obtained based on an average value of the maximum ordinate and the minimum ordinate and the value;

[0047] Determining a construction center point of the target nucleus according to the central abscissa, the central ordinate and the central ordinate;

[0048] Selecting the maximum value among the first transverse length, the first longitudinal length and the first vertical length as the constructed diameter;

[0049] Based on the construction center point and the construction diameter, determining a construction sphere corresponding to the target nucleus;

[0050] A spherical coordinate system is constructed with the center of the constructed sphere as the coordinate origin, and the constructed sphere is segmented based on three mutually perpendicular planes in the spherical coordinate system to obtain eight segmented regions;

[0051] Acquire the segmented area where the electrode offset point is located as the exclusion area, and take the remaining segmented areas as the pending areas;

[0052] The pending areas are selected according to the excluded areas to obtain an offset priority sequence.

[0053] Optionally, in a possible implementation manner of the first aspect, the selecting the to-be-determined area according to the exclusion area to obtain an offset priority sequence includes:

[0054] Acquire the tremor frequency of the electrode offset point corresponding to the exclusion area as the exclusion tremor frequency, and select the exclusion area corresponding to the maximum exclusion tremor frequency as the first exclusion area;

[0055] Obtaining the center point of the first exclusion zone as the exclusion midpoint, and obtaining the center point of the pending area as the pending midpoint;

[0056] A priority distance is obtained by performing calculation according to the excluded midpoint and the to-be-selected midpoint, and the to-be-determined areas are sorted in descending order based on the priority distance to obtain an offset priority sequence.

[0057] Optionally, in a possible implementation of the first aspect, the method further includes:

[0058] receiving the input stimulation intensity sent by the surgical end, and when determining that the actual stimulation intensity is greater than the input stimulation intensity, obtaining a first intensity difference based on a difference between the actual stimulation intensity and the input stimulation intensity;

[0059] Based on the ratio of the first intensity difference to the constant value, a first stimulation ratio is obtained, and according to the product of the first stimulation ratio and the stimulation intensity, a first stimulation coefficient is obtained;

[0060] When it is determined that the actual stimulation intensity is less than the input stimulation intensity, obtaining a second intensity difference based on a difference between the input stimulation intensity and the actual stimulation intensity;

[0061] Based on the ratio of the second intensity difference to the constant value, a second stimulation ratio is obtained, and according to the product of the second stimulation ratio and the stimulation intensity, a second stimulation coefficient is obtained;

[0062] An increased adjusted length weight and a decreased adjusted length weight are obtained based on the first stimulation coefficient and the second stimulation coefficient.

[0063] Optionally, in a possible implementation of the first aspect, the method further includes:

[0064] receiving a postoperative tremor video sent by a patient terminal corresponding to the target patient, and a tremor label corresponding to the postoperative tremor video, wherein the tremor label includes resting tremor and action tremor;

[0065] Determine a postoperative tremor video corresponding to the resting tremor as a resting adjustment video, and obtain a tremor frequency corresponding to the resting adjustment video as a postoperative resting tremor frequency;

[0066] Retrieving a preset resting tremor frequency, and obtaining a resting tremor adjustment coefficient according to a ratio of the postoperative resting tremor frequency to the preset resting tremor frequency;

[0067] The actual stimulation intensity is adjusted according to the resting tremor adjustment coefficient to obtain the resting stimulation intensity corresponding to the resting tremor;

[0068] Determine a postoperative tremor video corresponding to the action tremor as an action adjustment video, and obtain a tremor frequency corresponding to the action adjustment video as a postoperative action tremor frequency;

[0069] Retrieving a preset action tremor frequency, and obtaining an action tremor adjustment coefficient according to a ratio of the postoperative action tremor frequency to the preset action tremor frequency;

[0070] The actual stimulation intensity is adjusted according to the action tremor adjustment coefficient to obtain the action stimulation intensity corresponding to the action tremor.

[0071] According to a third aspect of the present invention, there is provided an electronic device, comprising: a memory, a processor and a computer program, wherein the computer program is stored in the memory, and the processor runs the computer program to execute the first aspect of the present invention and various methods that may be involved in the first aspect.

[0072] According to a fourth aspect of the present invention, a storage medium is provided, in which a computer program is stored. When the computer program is executed by a processor, it is used to implement the first aspect of the present invention and various methods that may be involved in the first aspect.

[0073] The beneficial effects of the present invention are as follows:

[0074] 1. The present invention can dynamically and real-time evaluate the tremor condition and adjust the electrode placement planning points by comprehensively considering the patient's attribute information, nucleus volume information and electrode offset strategy. Through in-depth analysis and processing of MRI images, the positioning of the target nucleus and the planning guidance of the electrode placement position can be achieved, and a personalized stimulation intensity adjustment plan can be provided to provide a position reference for physicians. Among them, the present invention can accurately locate the preoperative intervention position by acquiring a three-dimensional MRI image of the target patient and combining the initial planning point of the target nucleus. Among them, the MRI image can be coordinate-processed, the pixel points related to the intervention site can be counted, and the pixel coordinates closest to the initial planning point can be selected as the intervention position, which can significantly improve the accuracy of electrode placement.

[0075] 2. The present invention can plan the electrode placement position in a personalized manner. Specifically, the present invention can retrieve similar patient data in the historical surgery library based on the patient's specific attribute information and the volume information of the target nucleus, and obtain the offset direction and offset distance based on calculation, so that the electrode placement plan is more in line with the patient's actual situation. In addition, the patient's preoperative tremor frequency can be taken into consideration through real-time tremor video analysis, thereby achieving more accurate electrode placement planning. Through personalized evaluation, the surgical effect can be effectively improved to meet the actual diagnosis and treatment needs of different patients.

[0076] 3. The present invention can dynamically adjust the stimulation intensity of the electrode so as to achieve the best therapeutic effect. The stimulation intensity can be adjusted in real time by analyzing the tremor frequency in the postoperative video and combining it with the preset tremor frequency to ensure the optimization of the stimulation effect. It not only significantly improves the real-time feedback capability of electrode placement, but also provides a scientific stimulation intensity adjustment scheme based on the ratio calculation between the standard and the actual value, so that it can better adapt to the actual situation of the patient. BRIEF DESCRIPTION OF THE DRAWINGS

[0077] Figure 1A flow chart of a method for intelligent assessment and classification of Parkinson's disease DBS preoperatively based on MRI images provided by the present invention;

[0078] Figure 2 A schematic diagram of the hardware structure of an electronic device provided by the present invention. DETAILED DESCRIPTION

[0079] The technical solution of the present invention is described in detail with specific embodiments below. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described in detail in some embodiments.

[0080] like Figure 1 As shown, the present invention provides a pre-operation intelligent assessment and classification method for Parkinson's disease DBS based on MRI images, comprising:

[0081] S1, obtaining a three-dimensional magnetic resonance image of a target patient, locating a target nucleus in the three-dimensional magnetic resonance image, and determining a preoperative intervention position of the target patient based on an initial planning point of the target nucleus.

[0082] It should be noted that the nucleus image corresponding to the current person can be identified through MRI images, wherein the nucleus imaging corresponding to people with Parkinson's disease and normal people is different. The nuclei in the brain magnetic resonance imaging of normal people have a dovetail shape, while the nucleus images of people with Parkinson's disease may not have a dovetail shape or the dovetail shape is shorter. At the same time, the nucleus positions and sizes of different people are also different. Therefore, a three-dimensional magnetic resonance image of the target patient can be obtained to quickly identify the information corresponding to the nucleus, so as to facilitate the subsequent timely determination of the preoperative access position according to the target nucleus, thereby improving the accuracy of the subsequent surgical position.

[0083] It can be understood that the target patient is the patient currently undergoing preoperative position analysis, such as patient A, the three-dimensional magnetic resonance image is an MRI image, that is, a magnetic resonance imaging, the target nucleus is the corresponding nucleus imaging in the three-dimensional magnetic resonance image, that is, the nucleus that inhibits dopamine secretion, the initial planning point is the position point of the initial planning analysis, that is, the center point of the target nucleus, and the preoperative intervention position is the planned position for brain diagnosis and treatment before surgery, that is, the position where the electrode is placed after the skull drilling.

[0084] It is not difficult to understand that Parkinson's patients usually have uncontrollable hand tremors. Therefore, when diagnosing and treating patients, it is usually necessary to insert a brain pacemaker into the brain nucleus so that the target nucleus can be treated through the stimulation of the brain pacemaker, inhibiting the secretion of dopamine, so as to reduce the patient's tremors. Before the brain pacemaker is intervened, the intervention position needs to be determined and the physician needs to be guided. By selecting the appropriate intervention position, the abnormal effects on the patient can be reduced, avoiding large-area damage in the subsequent diagnosis and treatment process, so as to improve the diagnosis and treatment effect on the patient.

[0085] It is worth mentioning that MRI is magnetic resonance imaging, which is an inspection technology that uses the magnetic resonance phenomenon to obtain electromagnetic signals from the human body and reconstruct human body information. Parkinson's disease is a neurodegenerative disease, which is mainly manifested by the progressive destruction of dopaminergic neurons in the substantia nigra. This change will cause the signal of the substantia nigra nucleus 1 to become lower, and the "swallow tail sign" cannot be observed on MRI images. Therefore, the disappearance of the "swallow tail sign" can be used as an important medical sign of Parkinson's disease.

[0086] In some embodiments, a specific implementation of step S1 (obtaining a three-dimensional magnetic resonance image of a target patient, locating a target nucleus in the three-dimensional magnetic resonance image, and determining a preoperative intervention position of the target patient based on an initial planning point of the target nucleus) includes:

[0087] S11, obtaining a three-dimensional magnetic resonance image of a target patient, and locating a target nucleus in the three-dimensional magnetic resonance image.

[0088] It is understandable that after the patient undergoes MRI examination, the server can quickly receive the three-dimensional MRI image corresponding to the target patient, and then identify the target nucleus in the three-dimensional MRI image, so as to subsequently analyze the identified target nucleus, thereby improving the accuracy of the preoperative intervention position and facilitating improving the diagnosis and treatment effect on the patient.

[0089] S12, determining a center point of the three-dimensional magnetic resonance image, and performing coordinate processing on the three-dimensional magnetic resonance image based on the center point to obtain a three-dimensional coordinate system.

[0090] It is understandable that the center point of the three-dimensional magnetic resonance image can be obtained through existing image recognition technology, such as OpenCV, so as to construct a three-dimensional coordinate system based on the center point, thereby facilitating the coordinate processing of the three-dimensional magnetic resonance image, and further, facilitating the subsequent determination of various position information through the three-dimensional coordinate system, thereby improving the efficiency of determining the preoperative intervention position.

[0091] The three-dimensional coordinate system is a coordinate system constructed with the center point of the three-dimensional magnetic resonance image as the coordinate origin.

[0092] S13, obtaining the coordinates corresponding to the center point of the target nucleus as the initial planning point, and counting the pixel coordinates of the intervention site in the three-dimensional magnetic resonance image to obtain an intervention coordinate set corresponding to the intervention site.

[0093] It can be understood that the initial planning point is the coordinate position corresponding to the center point of the target nucleus, the intervention site is the site where the electrode needs to be placed, such as the brain, the pixel point coordinates are the position coordinates of the pixel points of the intervention site in the three-dimensional magnetic resonance image, and the intervention coordinate set is the set of all pixel point coordinates corresponding to the intervention site.

[0094] Through the above implementation, the present invention can obtain an intervention coordinate set, so as to subsequently determine the preoperative intervention position through the intervention coordinate set.

[0095] S14, selecting the pixel point coordinates in the intervention coordinate set that are closest to the initial planning point as the preoperative intervention position of the target patient.

[0096] It can be understood that the intervention coordinate set contains multiple pixel point coordinates. In order to reduce the side effects caused by electrode placement in subsequent actual surgery, the pixel point coordinates in the intervention coordinate set that are closest to the initial planning point can be used as the preoperative intervention position of the target patient, so that the electrode placement distance is shortest and the side effects on the brain are minimized.

[0097] S2, retrieve the patient attribute information of the target patient and the nucleus volume information of the target nucleus, and determine the offset direction and offset distance corresponding to the target nucleus based on the patient attribute information, the nucleus volume information and the initial planning point.

[0098] It should be noted that in the existing technology, personnel usually determine the position of electrode placement based on the patient's shaking frequency. For example, when placing the electrode, the initial position of the electrode will be moved based on the personnel's experience, and the movement direction and position are determined by the physician himself. When it is determined that the patient's hand tremor frequency changes from high to low, the physician will subjectively determine that the position is a more appropriate position. The present invention can retrieve the diagnosis and treatment data of historically treated patients with similar attribute information in the database based on the attribute information of the current target patient, such as gender, age, height, weight, etc., so as to update the corresponding treatment direction in the three-dimensional image of the current target patient, so as to facilitate the subsequent rapid determination of the offset direction and offset distance corresponding to the target nucleus, thereby improving the accuracy and timeliness of the electrode placement and reducing the time for trial movement in multiple directions.

[0099] It can be understood that the patient attribute information is the physical sign information corresponding to the target patient, such as gender, age, height and weight, etc. The nucleus volume information is the volume size of the target nucleus, the offset direction is the moving direction of the electrode pointed out by the initial planning point, and the offset distance is the distance of the moving electrode.

[0100] It is not difficult to understand that, due to the small size of the nucleus, in order to achieve a better treatment effect and reduce the patient's tremor frequency, the position of the initial planning point can be appropriately offset and adjusted.

[0101] In some embodiments, a specific implementation of step S2 (the step of retrieving the patient attribute information of the target patient and the nucleus volume information of the target nucleus, and determining the offset direction and offset distance corresponding to the target nucleus based on the patient attribute information, the nucleus volume information and the initial planning point) includes:

[0102] S21, retrieve the patient attribute information of the target patient, wherein the patient attribute information includes age information, height information and weight information, and retrieve the nucleus volume information of the target nucleus.

[0103] It can be understood that the patient attribute information includes age information, height information and weight information, wherein the age information is the age of the target patient, the height information is the height of the target patient, and the weight information is the corresponding weight of the target patient. At the same time, the nucleus volume size corresponding to the target nucleus is obtained, so that similar historical patients can be selected according to the obtained patient attribute information and nucleus volume information, thereby determining the offset direction and offset distance.

[0104] S22, based on the patient attribute information, retrieve similar patients in the historical surgery database to obtain historical planning points and historical placement points of the similar patients.

[0105] It can be understood that the historical surgery library is an information database containing historical diagnoses and treatments, similar patients are people similar to the target patients in the historical surgery library, historical planning points are the initial planning points corresponding to similar patients, and historical placement points are the final electrode placement positions corresponding to similar patients in the historical surgery library.

[0106] S23, performing calculation according to the historical planning points and the historical placement points to obtain an offset vector, and determining an offset direction corresponding to the target nucleus based on the offset vector.

[0107] It can be understood that the corresponding offset vector can be obtained by pointing the historical planning point to the historical placement point. Since the offset vector has a corresponding direction, the offset direction corresponding to the target nucleus can be determined, so that the corresponding offset direction can be subsequently updated to the three-dimensional magnetic resonance image corresponding to the target patient, which is convenient for the server to perform automatic offset later, thereby determining the appropriate preoperative intervention position.

[0108] S24, obtaining an offset coefficient based on the ratio of the nucleus volume information to the reference volume information, and retrieving a reference offset distance corresponding to the reference volume information.

[0109] It can be understood that the reference volume information is the standard volume size for judging the nuclear mass, which can be artificially pre-determined, the offset coefficient is the offset degree coefficient value of the electrode placement position, that is, the ratio of the nuclear mass volume information to the reference volume information, and the reference offset distance is the reference distance for position movement, which corresponds to the reference volume information and can be artificially pre-set.

[0110] S25, obtaining an offset distance corresponding to the target nucleus according to the product of the reference offset distance and the offset coefficient.

[0111] It can be understood that by multiplying the reference offset distance and the offset coefficient, the distance required to be moved corresponding to the target nucleus can be obtained, which is convenient for guiding the physician to move, thereby reducing the time for determining the electrode placement position.

[0112] S3, updating the preoperative intervention position, the initial planning point, the offset direction and the offset distance to the three-dimensional magnetic resonance image, obtaining a three-dimensional reference image and sending it to the surgical end, and when it is determined that the pacing electrode is located at the initial planning point, collecting the tremor site of the target patient in real time to obtain an evaluation video of the initial planning point.

[0113] It should be noted that after the offset direction and offset distance are determined, the preoperative intervention position and initial planning point, the offset direction and offset distance can be updated in the three-dimensional magnetic resonance image to obtain a three-dimensional reference reference to guide the physician to place the electrode according to the three-dimensional reference reference. When it is determined that the pacing electrode is located at the initial planning point, it means that the pacing electrode has been placed in the corresponding intervention site. Therefore, the tremor site of the target patient can be collected for subsequent analysis of the evaluation video, so that the position can be adjusted according to the offset direction and offset distance, which is convenient for guiding the physician's viewing and movement and improving the efficiency of diagnosis and treatment.

[0114] It can be understood that the three-dimensional reference figure is a three-dimensional image of the reference placement position, that is, a three-dimensional magnetic resonance image with the preoperative intervention position, initial planning point, offset direction and offset distance. The surgical end is the information terminal of the physician performing the operation, such as a tablet. The pacing electrode is the electrode corresponding to the brain pacemaker. The tremor site is the site where the tremor occurs, such as the patient's hand. The evaluation video is a captured video of the tremor site corresponding to the initial planning point when the pacing electrode is located at the initial planning point, which is used to judge the patient's diagnosis and treatment. When the tremor frequency is lower than a certain level, it means that the position is more suitable and can have a therapeutic effect. Otherwise, it means that the initial planning point needs to be moved.

[0115] S4, when it is determined that the tremor frequency in the evaluation video does not meet the preset requirements, the placement planning point of the target nucleus is determined according to the electrode offset strategy, the offset direction and the offset distance and sent to the surgical end.

[0116] It should be noted that when the tremor frequency in the evaluation video does not meet the preset requirements, for example, the tremor frequency is high and not lower than the preset reference frequency, the initial planning point can be moved to obtain the placement planning point and send it to the surgical end to provide offset guidance to the surgical physicians and improve the efficiency of determining the placement planning point.

[0117] The preset requirement is a pre-set judgment requirement, for example, it may be a requirement that the vibration frequency is lower than the reference frequency.

[0118] In some embodiments, the specific implementation of step S4 (determining the placement planning point of the target nucleus and sending it to the surgical end according to the electrode offset strategy, the offset direction and the offset distance when the tremor frequency in the evaluation video does not meet the preset requirements) includes:

[0119] S41, obtaining the tremor frequency of the tremor part in the evaluation video, and when it is determined that the tremor frequency in the evaluation video is greater than a preset tremor frequency, counting the number of patients of the same type corresponding to each offset direction as the offset number.

[0120] It can be understood that the preset tremor frequency is a pre-set tremor frequency. When the tremor frequency in the evaluation video is greater than the preset tremor frequency, it means that the vibration frequency of the current target patient is high and the treatment effect has not been achieved. Therefore, the number of similar patients corresponding to each offset direction can be counted to obtain the offset number, so that the multiple offset directions can be arranged according to the offset number in the future, so that the position can be moved according to the arranged offset direction, which greatly reduces the time for determining the appropriate placement of planning points due to random movement.

[0121] The offset number is the number of patients of the same type corresponding to the offset direction. For example, when there are 3 patients of the same type whose corresponding offset directions are directly above, the number of offsets corresponding to directly above is 3.

[0122] S42: Sort the offset directions in descending order based on the offset quantity to obtain a partial order direction sequence.

[0123] It can be understood that, when the number of offsets is larger, it can be explained that the probability that a more suitable placement planning point can be obtained in the current direction is greater. Then, the offset directions can be arranged in descending order according to the number of offsets to obtain a partial order direction sequence.

[0124] The partial order direction sequence is a descending sequence in the offset direction.

[0125] S43, selecting the first offset direction in the partial order direction sequence as the electrode movement direction, and determining the electrode offset point according to the electrode movement direction and the offset distance.

[0126] It can be understood that the electrode movement direction is the direction of moving the pacing electrode, that is, the first offset direction in the offset direction sequence, and the electrode offset point is the position point of the pacing electrode after movement.

[0127] It is not difficult to understand that the electrode offset point can be determined by taking the initial planning point as the starting point and moving the offset distance along the electrode moving direction.

[0128] S44, when it is determined that the pacing electrode is located at the electrode offset point, the tremor position of the target patient is acquired in real time to obtain an offset video of the electrode offset point.

[0129] It can be understood that when it is determined that the pacing electrode is located at the electrode offset point, the tremor site of the current target patient can be collected in real time to obtain an offset video of the electrode offset point. For example, a one-minute video can be collected to subsequently determine the tremor frequency of the tremor site in the offset video, so as to facilitate timely determination of the placement planning point corresponding to the pacing electrode.

[0130] The offset video is a video captured of the tremor site corresponding to the electrode offset point where the pacing electrode is located.

[0131] S45, when it is determined that the tremor frequency in the offset video is greater than the preset tremor frequency, the partial order direction sequence is deleted and updated based on the electrode movement direction.

[0132] It can be understood that when it is determined that the tremor frequency in the offset video is greater than the preset tremor frequency, it can be explained that the electrode offset point after the current movement cannot achieve the therapeutic effect, so the corresponding electrode movement direction can be deleted in the partial order direction sequence, so that the remaining offset directions can be selected subsequently to determine the electrode placement position point.

[0133] S46, repeat the above steps of obtaining the offset video until the tremor frequency in the offset video is less than or equal to the preset tremor frequency, and send the corresponding electrode offset point as a placement planning point to the surgical end.

[0134] It can be understood that by repeating the above-mentioned steps of determining the tremor frequency in the offset video until the tremor frequency is less than or equal to the preset tremor frequency, it can be said that the current electrode offset point can achieve the therapeutic effect, and then the corresponding electrode offset point can be used as a placement planning point and sent to the surgical end to guide the surgical staff to view it intuitively.

[0135] It should be noted that, since the severity of the disease of different patients is inconsistent, the stimulation intensity of the corresponding pacing electrode can be customized by analyzing the nucleus swallowtail sign to achieve the best effect and save personnel adjustment time. Therefore, in some embodiments, it also includes:

[0136] A1, obtaining the maximum horizontal coordinate, the minimum horizontal coordinate, the maximum vertical coordinate, the minimum vertical coordinate, the maximum vertical coordinate and the minimum vertical coordinate in the target nucleus.

[0137] It can be understood that the maximum horizontal coordinate is the maximum value of the horizontal coordinate of the target nucleus in the three-dimensional magnetic resonance image, the minimum horizontal coordinate is the minimum value of the horizontal coordinate of the target nucleus in the three-dimensional magnetic resonance image, the maximum vertical coordinate is the maximum value of the vertical coordinate of the target nucleus in the three-dimensional magnetic resonance image, the minimum vertical coordinate is the minimum value of the vertical coordinate of the target nucleus in the three-dimensional magnetic resonance image, the maximum vertical coordinate is the maximum value of the vertical coordinate of the target nucleus in the three-dimensional magnetic resonance image, and the minimum vertical coordinate is the minimum value of the vertical coordinate of the target nucleus in the three-dimensional magnetic resonance image.

[0138] Through the above implementation, the present invention can obtain the position range corresponding to the target nucleus, so as to subsequently obtain the corresponding dovetail length, thereby analyzing the stimulation intensity, inhibiting the secretion of dopamine, and reducing the patient's tremor behavior.

[0139] A2, obtaining a first transverse length according to the difference between the maximum transverse coordinate and the minimum transverse coordinate of the target nucleus.

[0140] It can be understood that the first transverse length is the transverse length corresponding to the target nucleus, that is, the difference between the maximum transverse coordinate and the minimum transverse coordinate of the target nucleus.

[0141] A3, obtaining a first longitudinal length based on the difference between the maximum longitudinal coordinate and the minimum longitudinal coordinate of the target nucleus.

[0142] It can be understood that the first longitudinal length is the longitudinal length corresponding to the target nucleus, that is, the difference between the maximum longitudinal coordinate and the minimum longitudinal coordinate of the target nucleus.

[0143] A4, obtaining a first vertical length according to the difference between the maximum vertical coordinate and the minimum vertical coordinate of the target nucleus.

[0144] It can be understood that the first vertical length is the vertical length corresponding to the target nucleus, that is, the difference between the maximum vertical coordinate and the minimum vertical coordinate of the target nucleus.

[0145] A5: Select the maximum value among the first horizontal length, the first longitudinal length and the first vertical length as the actual dovetail length of the target nucleus.

[0146] It can be understood that the actual dovetail length is the dovetail length corresponding to the target nucleus, that is, the maximum value among the first transverse length, the first longitudinal length and the first vertical length.

[0147] Through the above implementation, the present invention can obtain the actual dovetail length of the target nucleus, so as to compare it with the standard dovetail length later, thereby analyzing and determining the actual stimulation intensity.

[0148] A6, extracting dovetail pixel points in the target nucleus according to the dovetail pixel value, and counting the number of the dovetail pixel points to obtain the actual dovetail number.

[0149] It can be understood that the dovetail pixel value is the pixel value corresponding to the dovetail sign, the dovetail pixel point is the pixel point corresponding to the dovetail sign in the target nucleus, and the actual dovetail number is the number of dovetail pixel points.

[0150] A7, amplifying the reference nucleus based on the offset coefficient to obtain a standard nucleus, and obtaining a standard dovetail length and a standard dovetail quantity of the standard nucleus.

[0151] It can be understood that the reference nucleus is a nucleus of a preset reference size, the standard nucleus is a nucleus of a standard size amplified by an offset coefficient, the standard dovetail length is the dovetail length corresponding to the standard nucleus, and the standard dovetail quantity is the quantity of standard dovetails.

[0152] It is not difficult to understand that there can be multiple dovetails on each nucleus, for example, 2. By obtaining the standard number of dovetails, the abnormal condition of the patient can be determined. The fewer the number of dovetails, the more serious the corresponding condition.

[0153] A8, obtaining a first strength adjustment coefficient based on the ratio of the standard dovetail length to the actual dovetail length, and obtaining a second strength adjustment coefficient based on the ratio of the standard dovetail quantity to the actual dovetail quantity.

[0154] It can be understood that the first strength adjustment coefficient is the adjustment coefficient value corresponding to the dovetail length, that is, the ratio of the standard dovetail length to the actual dovetail length, and the second strength adjustment coefficient is the adjustment coefficient value corresponding to the dovetail number, that is, the ratio of the standard dovetail number to the actual dovetail number.

[0155] A9. Adjust the preset stimulation intensity based on the first intensity adjustment coefficient and the second intensity adjustment coefficient to obtain an actual stimulation intensity.

[0156] It can be understood that the preset stimulation intensity is a pre-set electrode stimulation intensity, and the actual stimulation intensity is a stimulation intensity determined based on the actual condition of the patient.

[0157] Through the above implementation, the preset stimulation intensity is adjusted so that the actual stimulation intensity obtained is more suitable for the patient, thereby improving the diagnosis and treatment effect.

[0158] In some embodiments, a specific implementation of step A9 (adjusting the preset stimulation intensity based on the first intensity adjustment coefficient and the second intensity adjustment coefficient to obtain the actual stimulation intensity) includes:

[0159] A91: Obtain a first adjustment value according to the product of the first strength adjustment coefficient and the length weight value.

[0160] It can be understood that the length weight value is the weight of the influence of the dovetail length factor on the stimulation intensity, which can be preset, and the first adjustment value is the product of the first intensity adjustment coefficient and the length weight value.

[0161] A92: Obtain a second adjustment value based on the product of the second intensity adjustment coefficient and the quantity weight value.

[0162] It can be understood that the quantity weight value is the weight of the influence of the dovetail quantity factor on the stimulation intensity, which can be preset manually, and the second adjustment value is the product of the second intensity adjustment coefficient and the quantity weight value.

[0163] A93: Adjust the preset stimulation intensity according to the first adjustment value and the second adjustment value to obtain an actual stimulation intensity.

[0164] It is understandable that the preset stimulation intensity is adjusted by the first adjustment value and the second adjustment value, so as to obtain the actual stimulation intensity so as to meet the diagnosis and treatment of the patient's condition and improve the diagnosis and treatment effect.

[0165] A94, the actual stimulus intensity is obtained by the following formula,

[0166] in, is the actual stimulus intensity, To preset the stimulation intensity, is the standard dovetail length, is the actual dovetail length, is the length weight value, is the standard dovetail quantity, is the actual number of dovetails, is the quantity weight value.

[0167] It can be understood that when the actual dovetail length is shorter, that is The smaller the first intensity adjustment coefficient is, The larger the actual dovetail number, the The smaller the value, the second strength adjustment coefficient The larger the dovetail length, the greater the actual stimulation intensity. This indicates that when the dovetail is smaller and the number is smaller, the more serious the condition is, and a stronger stimulation is needed to inhibit the secretion of dopamine and achieve a therapeutic effect. On the contrary, when the actual dovetail length is longer, that is, The larger the first intensity adjustment coefficient is, the The smaller the actual dovetail number, the smaller the The more the second intensity adjustment coefficient is, the The smaller it is, the smaller the actual stimulation intensity is. It can be shown that when the swallowtails are longer and more numerous, the condition is less serious, and the condition can be diagnosed and treated without the need for stronger stimulation intensity.

[0168] In some embodiments, it also includes:

[0169] B1, when it is determined that the partial order direction sequence does not have the offset direction, the central horizontal coordinate is obtained based on the average value of the maximum horizontal coordinate and the minimum horizontal coordinate and the value, the central vertical coordinate is obtained based on the average value of the maximum vertical coordinate and the minimum vertical coordinate and the value, and the central vertical coordinate is obtained based on the average value of the maximum vertical coordinate and the minimum vertical coordinate and the value.

[0170] It can be understood that when the tremor frequencies of the offset videos collected corresponding to all the offset directions selected in the partial order direction sequence do not meet the preset requirements, all the offset directions in the partial order direction sequence will be deleted. When there is no offset direction, the nucleus can be divided into regions and sorted, so that the corresponding regions can be selected in turn for position movement, which is convenient for the subsequent determination of the electrode placement position points.

[0171] The central abscissa, central ordinate and central ordinate can be obtained through the maximum abscissa, minimum abscissa, maximum ordinate, minimum ordinate, maximum ordinate and minimum ordinate to facilitate subsequent area division.

[0172] B2, determining the construction center point of the target nucleus according to the central horizontal coordinate, the central vertical coordinate and the central vertical coordinate.

[0173] It can be understood that the construction center point is the center position point of the target nucleus, that is, the center horizontal coordinate, the center vertical coordinate and the center vertical coordinate are combined to determine and store the coordinates of the construction center point.

[0174] B3, selecting the maximum value among the first horizontal length, the first longitudinal length and the first vertical length as the constructed diameter.

[0175] It can be understood that the maximum value among the first horizontal length, the first longitudinal length and the first vertical length is selected as the construction diameter so that the sphere constructed subsequently can completely wrap the nucleus, thereby facilitating the subsequent division.

[0176] The construction diameter is the diameter value of the constructed sphere.

[0177] B4, determining a construction sphere corresponding to the target nucleus based on the construction center point and the construction diameter.

[0178] It can be understood that a construction sphere is generated according to the construction diameter and with the construction center point as the center of the construction sphere, so as to wrap the irregular nuclei, facilitate the subsequent division of the regular construction sphere, and further realize the division of the nuclei.

[0179] B5, constructing a spherical coordinate system with the center of the constructed sphere as the coordinate origin, and segmenting the constructed sphere based on three mutually perpendicular planes in the spherical coordinate system to obtain 8 segmented areas.

[0180] It can be understood that the spherical coordinate system is a coordinate system for coordinate processing of the constructed sphere, that is, a coordinate system established with the new point of the constructed sphere as the coordinate origin, and then the constructed sphere can be segmented according to the three mutually perpendicular planes in the spherical coordinate system, thereby obtaining 8 segmented areas, which is convenient for the subsequent offset movement of the direction of the segmented area to determine the electrode placement position point.

[0181] The segmented area is the area after the constructed sphere is segmented.

[0182] B6, obtaining the segmented area where the electrode offset point is located as the exclusion area, and taking the remaining segmented areas as the pending areas.

[0183] It can be understood that the excluded area is the segmented area where the electrode offset point is located, that is, the area where no motion detection is required, and the pending area is the segmented area that needs to be selected for motion.

[0184] Through the above implementation, the present invention can determine the pending area, so that the pending area can be selected later, so that the initial planning point is moved into the pending area, so that the electrode placement point can be determined in time.

[0185] B7, selecting the pending area according to the excluded area to obtain an offset priority sequence.

[0186] It can be understood that, excluding the excluded areas, the pending areas are selected in sequence to obtain an offset priority sequence.

[0187] The offset priority sequence is a sequence of regions that are prioritized for position offset, that is, a sequence of regions after sorting the pending regions.

[0188] In some embodiments, a specific implementation of step B7 (selecting the to-be-determined area according to the excluded area to obtain an offset priority sequence) includes:

[0189] B71, obtaining the tremor frequency of the electrode offset point corresponding to the exclusion area as the exclusion tremor frequency, and selecting the exclusion area corresponding to the largest exclusion tremor frequency as the first exclusion area.

[0190] It can be understood that the excluded tremor frequency is the tremor frequency of the electrode offset point corresponding to the excluded area, and the first excluded area is the excluded area corresponding to the maximum excluded tremor frequency.

[0191] B72, obtaining the center point of the first exclusion zone as the exclusion midpoint, and obtaining the center point of the pending area as the selection midpoint.

[0192] It can be understood that the exclusion midpoint is the center point of the first exclusion zone, and the to-be-selected midpoint is the center point of the to-be-determined zone.

[0193] Through the above implementation, the present invention can obtain the excluded midpoints and the midpoints to be selected, so as to subsequently calculate the distances between the excluded midpoints and the midpoints to be selected, thereby obtaining the priority distances, which is convenient for arranging the pending areas.

[0194] B73, performing calculation according to the excluded midpoint and the midpoint to be selected to obtain a priority distance, and sorting the to-be-determined areas in descending order based on the priority distance to obtain an offset priority sequence.

[0195] It can be understood that the priority distance is the distance for determining the priority of the center point to be selected, that is, excluding the distance between the midpoint and the center point to be selected, and the offset priority sequence is the sequence of areas for priority position movement, that is, the to-be-determined areas are sorted in descending order according to the priority distance, and the to-be-determined areas that are farther away from the excluded areas are arranged in front, so that the electrode offset points can be determined in the to-be-determined areas in the sequence in turn, thereby determining the electrode placement position point.

[0196] It is not difficult to understand that since the electrode offset points in the exclusion area cannot achieve the diagnosis and treatment effect, it is necessary to preferentially select and determine the pending area that is far away from the current electrode offset point so that the electrode placement point can be quickly determined.

[0197] It should be noted that, since the electrode stimulation intensity determined by the server needs to be continuously trained in order to determine a more appropriate stimulation intensity, the personnel can also automatically determine it during the real-time training process, so that the server can adjust the current electrode stimulation intensity according to the stimulation intensity actively input by the personnel. Therefore, it also includes:

[0198] C1, receiving the input stimulation intensity sent by the surgical end, and when determining that the actual stimulation intensity is greater than the input stimulation intensity, obtaining a first intensity difference based on the difference between the actual stimulation intensity and the input stimulation intensity.

[0199] It can be understood that the input stimulation intensity is the electrode stimulation intensity actively input by the surgical end, and the first intensity difference is the difference between the actual stimulation intensity and the input stimulation intensity.

[0200] Through the above implementation, the present invention can obtain the first intensity difference, so as to subsequently adjust the weight value for calculating the actual stimulation intensity according to the first intensity difference, so that the actual stimulation intensity obtained subsequently is more consistent with the patient's condition.

[0201] C2, obtaining a first stimulation ratio based on the ratio of the first intensity difference to a constant value, and obtaining a first stimulation coefficient according to the product of the first stimulation ratio and the stimulation intensity.

[0202] It can be understood that the constant value is a numerical value for calculating the adjustment weight, which can be preset manually. The first stimulation ratio is the ratio of the first intensity difference and the constant value. When the first intensity difference is larger, the first stimulation ratio is larger. The first stimulation coefficient is the product of the first stimulation ratio and the stimulation intensity.

[0203] C3: When it is determined that the actual stimulation intensity is less than the input stimulation intensity, a second intensity difference is obtained based on the difference between the input stimulation intensity and the actual stimulation intensity.

[0204] It can be understood that when it is determined that the actual stimulation intensity is less than the input stimulation intensity, it can be explained that the currently calculated actual stimulation intensity is small. Therefore, the weight value needs to be increased. Furthermore, the second intensity difference can be obtained by the difference between the input stimulation intensity and the actual stimulation intensity, so that the weight value can be increased subsequently.

[0205] The second intensity difference is the difference between the input stimulation intensity and the actual stimulation intensity.

[0206] C4, obtaining a second stimulation ratio based on the ratio of the second intensity difference to a constant value, and obtaining a second stimulation coefficient according to the product of the second stimulation ratio and the stimulation intensity.

[0207] It can be understood that the second stimulation ratio is the ratio of the second intensity difference to the constant value, and the second stimulation coefficient is the product of the second stimulation ratio and the stimulation intensity.

[0208] C5, obtaining an increased adjusted length weight and a decreased adjusted length weight based on the first stimulation coefficient and the second stimulation coefficient.

[0209] The increased adjusted length weight and decreased adjusted length weight are obtained by the following formula:

[0210] in, To increase the adjusted length weight value, is the input stimulus intensity, is a constant value, is the stimulus weight, To reduce the adjusted length weight.

[0211] It can be understood that the length weight value is calculated according to the first stimulation coefficient and the second stimulation coefficient to obtain the adjusted length weight, so as to subsequently improve the accuracy of the actual stimulation intensity.

[0212] Among them, when the input stimulus intensity is greater than the actual stimulus intensity and the difference is greater, the first intensity difference The larger the input stimulus intensity is, the larger the length weight needs to be, and the larger the length weight will be. Therefore, the increased adjusted length weight will also be larger. Conversely, when the input stimulus intensity is greater than the actual stimulus intensity and the difference is smaller, the first intensity difference is The smaller it is, the smaller the length weight needs to be increased.

[0213] Similarly, when the input stimulus intensity is less than the actual stimulus intensity and the difference is greater, the second intensity difference The larger the input stimulus intensity is, the larger the length weight needs to be reduced. As a result, the reduced adjusted length weight will also become smaller. Conversely, when the input stimulus intensity is less than the actual stimulus intensity and the difference is smaller, the second intensity difference is The smaller it is, the smaller the length weight needs to be reduced.

[0214] In some embodiments, it also includes:

[0215] D1, receiving a postoperative tremor video sent by a patient terminal corresponding to the target patient, and a tremor label corresponding to the postoperative tremor video, wherein the tremor label includes resting tremor and action tremor.

[0216] It can be understood that the patient end is the information terminal corresponding to the target patient, such as the patient's mobile phone, the postoperative tremor video is a recorded video of the tremor after the operation, such as a one-minute video of hand vibration, and the tremor label is a state label of vibration, including static tremor and action tremor, among which static tremor is the tremor generated when the person does not have any autonomous movement, and action tremor is the tremor generated when the patient performs an action, such as a tremor in the hand when picking up something.

[0217] D2, determining the postoperative tremor video corresponding to the resting tremor as the resting adjustment video, and obtaining the tremor frequency corresponding to the resting adjustment video as the postoperative resting tremor frequency.

[0218] It can be understood that the postoperative tremor video corresponding to the resting tremor can be used as the resting adjustment video, and the tremor frequency corresponding to the resting adjustment video can be used as the postoperative resting tremor frequency.

[0219] It is not difficult to understand that by obtaining the postoperative resting tremor frequency, the stimulation intensity can be adjusted promptly according to the patient's recovery condition.

[0220] D3, calling a preset resting tremor frequency, and obtaining a resting tremor adjustment coefficient according to a ratio of the postoperative resting tremor frequency to the preset resting tremor frequency.

[0221] It can be understood that the preset resting tremor frequency is the preset frequency of the resting tremor, which can be preset manually, and the resting tremor adjustment coefficient is the coefficient value for adjusting the stimulation intensity of the resting tremor, that is, the ratio of the postoperative resting tremor frequency to the preset resting tremor frequency.

[0222] D4, adjusting the actual stimulation intensity according to the resting tremor adjustment coefficient to obtain the resting stimulation intensity corresponding to the resting tremor.

[0223] The resting stimulus intensity corresponding to resting tremor was calculated by the following formula:

[0224] in, is the postoperative resting tremor frequency, To preset the static vibration frequency, is the static stimulus intensity.

[0225] It can be understood that the actual stimulation intensity is adjusted by adjusting the resting tremor adjustment coefficient to obtain the resting stimulation intensity corresponding to the resting tremor, so that the stimulation intensity can be adjusted in time later to meet the patient's recovery condition.

[0226] Among them, when the postoperative resting tremor frequency Greater than the preset resting vibration frequency When the postoperative tremor frequency is high, it means that the patient's tremor frequency is abnormal, so the stimulation intensity needs to be increased. Less than the preset resting vibration frequency , it means that the patient's tremor frequency has decreased after surgery and the current stimulation intensity is high, so the stimulation intensity needs to be reduced.

[0227] It is worth mentioning that since the preset resting tremor frequency is a pre-set baseline frequency that can improve the patient's vibration frequency, and the lower the postoperative resting tremor frequency is, the better the treatment effect of the patient is, which means that the current stimulation intensity can effectively improve the patient's tremor behavior. Furthermore, when the postoperative resting tremor frequency is less than the preset resting tremor frequency, and the greater the difference between the postoperative resting tremor frequency and the preset resting tremor frequency, the more the current stimulation intensity is in line with the diagnosis and treatment of the patient, and the lower the degree of reduction in the actual stimulation intensity. Conversely, under the condition that the postoperative resting tremor frequency is less than the preset resting tremor frequency, the smaller the difference between the postoperative resting tremor frequency and the preset resting tremor frequency is, the greater the difference between the current stimulation intensity and the stimulation intensity for better reducing the tremor frequency, and the greater the degree of adjustment that needs to be reduced.

[0228] It is not difficult to understand that by making targeted adjustments to the stimulation intensity according to the tremor conditions under different states, the treatment intensity suitable for the patient's current condition can be determined more quickly and accurately to improve the treatment effect.

[0229] D5, determining the postoperative tremor video corresponding to the action tremor as the action adjustment video, and obtaining the tremor frequency corresponding to the action adjustment video as the postoperative action tremor frequency.

[0230] It can be understood that the postoperative tremor video corresponding to the action tremor can be used as the action adjustment video, and the tremor frequency corresponding to the action adjustment video can be used as the postoperative action tremor frequency.

[0231] It is not difficult to understand that by obtaining the frequency of postoperative action tremor, the stimulation intensity can be adjusted promptly according to the patient's recovery condition.

[0232] D6, calling a preset action tremor frequency, and obtaining an action tremor adjustment coefficient according to a ratio of the postoperative action tremor frequency to the preset action tremor frequency.

[0233] It can be understood that the preset action tremor frequency is the preset frequency of the action tremor, which can be preset manually, and the action tremor adjustment coefficient is the coefficient value for adjusting the stimulation intensity of the action tremor, that is, the ratio of the postoperative action tremor frequency to the preset action tremor frequency.

[0234] D7, adjusting the actual stimulation intensity according to the action tremor adjustment coefficient to obtain the action stimulation intensity corresponding to the action tremor.

[0235] The action stimulus intensity corresponding to action tremor is calculated by the following formula:

[0236] in, is the frequency of postoperative action tremor, To preset the action vibration frequency, To stimulate the intensity of the action.

[0237] It can be understood that the actual stimulation intensity is adjusted by the action tremor adjustment coefficient to obtain the action stimulation intensity corresponding to the action tremor, so that the stimulation intensity can be adjusted in time later to make it suitable for the patient's recovery condition.

[0238] Among them, when the frequency of postoperative action tremor Greater than the preset action vibration frequency When the postoperative tremor frequency is high, it means that the patient's tremor frequency is abnormal, so the stimulation intensity needs to be increased. Less than the preset action vibration frequency , it means that the patient's tremor frequency has decreased after surgery and the current stimulation intensity is high, so the stimulation intensity needs to be reduced.

[0239] It is worth mentioning that the implementation method is the same as the above step D4, which will not be repeated here, that is, after the operation tremor frequency Less than the preset action vibration frequency In the case of postoperative action tremor frequency The smaller the value, the smaller the degree of adjustment of the current actual stimulation intensity. The closer to the preset action vibration frequency , the greater the degree of adjustment of the current actual stimulus intensity.

[0240] It is not difficult to understand that by making targeted adjustments to the stimulation intensity according to the tremor conditions under different states, the treatment intensity suitable for the patient's current condition can be determined more quickly and accurately to improve the treatment effect.

[0241] See also Figure 2, is a schematic diagram of the hardware structure of an electronic device provided by an embodiment of the present invention, the electronic device 20 includes: a processor 21, a memory 22 and a computer program; wherein

[0242] The memory 22 is used to store the computer program, and the memory may also be a flash memory. The computer program is, for example, an application program, a functional module, etc. for implementing the above method.

[0243] The processor 21 is used to execute the computer program stored in the memory to implement each step performed by the device in the above method. For details, please refer to the relevant description in the above method embodiment.

[0244] Optionally, the memory 22 may be independent or integrated with the processor 21 .

[0245] When the memory 22 is a device independent of the processor 21, the device may further include:

[0246] The bus 23 is used to connect the memory 22 and the processor 21 .

[0247] The present invention also provides a readable storage medium, in which a computer program is stored. When the computer program is executed by a processor, it is used to implement the methods provided by the various embodiments described above.

[0248] Among them, the readable storage medium can be a computer storage medium or a communication medium. The communication medium includes any medium that facilitates the transmission of a computer program from one place to another. The computer storage medium can be any available medium that can be accessed by a general-purpose or special-purpose computer. For example, a readable storage medium is coupled to a processor so that the processor can read information from the readable storage medium and write information to the readable storage medium. Of course, the readable storage medium can also be a component of the processor. The processor and the readable storage medium can be located in an application-specific integrated circuit (Application Specific Integrated Circuits, referred to as: ASIC). In addition, the ASIC can be located in a user device. Of course, the processor and the readable storage medium can also exist in a communication device as discrete components. The readable storage medium can be a read-only memory (ROM), a random access memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, and an optical data storage device, etc.

[0249] The present invention also provides a program product, which includes an execution instruction, which is stored in a readable storage medium. At least one processor of a device can read the execution instruction from the readable storage medium, and at least one processor executes the execution instruction so that the device implements the methods provided in the above various embodiments.

[0250] In the embodiments of the above-mentioned devices, it should be understood that the processor may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), etc. The general-purpose processor may be a microprocessor or any conventional processor. The steps of the method disclosed in the present invention may be directly implemented as being executed by a hardware processor, or may be executed by a combination of hardware and software modules in the processor.

[0251] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein with equivalents. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for intelligent assessment and classification of Parkinson's disease DBS preoperatively based on MRI images, characterized in that: include: Acquire a three-dimensional magnetic resonance image of a target patient, locate a target nucleus in the three-dimensional magnetic resonance image, and determine a preoperative intervention position of the target patient based on an initial planning point of the target nucleus; Retrieving patient attribute information of a target patient and nucleus volume information of a target nucleus, and determining an offset direction and an offset distance corresponding to the target nucleus based on the patient attribute information, the nucleus volume information and the initial planning point; The preoperative intervention position, the initial planning point, the offset direction and the offset distance are updated to the three-dimensional magnetic resonance image, and a three-dimensional reference image is obtained and sent to the surgical end. When it is determined that the pacing electrode is located at the initial planning point, the tremor site of the target patient is collected in real time to obtain an evaluation video of the initial planning point; When it is determined that the tremor frequency in the evaluation video does not meet the preset requirements, the placement planning point of the target nucleus is determined according to the electrode offset strategy, the offset direction and the offset distance and sent to the surgical end.

2. The method according to claim 1, characterized in that The step of acquiring a three-dimensional magnetic resonance image of a target patient, locating a target nucleus in the three-dimensional magnetic resonance image, and determining a preoperative intervention position of the target patient based on an initial planning point of the target nucleus includes: Acquire a three-dimensional magnetic resonance image of a target patient, and locate a target nucleus in the three-dimensional magnetic resonance image; Determine the center point of the three-dimensional magnetic resonance image, and perform coordinate processing on the three-dimensional magnetic resonance image based on the center point to obtain a three-dimensional coordinate system; Acquiring the coordinates corresponding to the center point of the target nucleus as the initial planning point, and counting the pixel coordinates of the intervention site in the three-dimensional magnetic resonance image to obtain an intervention coordinate set corresponding to the intervention site; The pixel coordinates in the intervention coordinate set that are closest to the initial planning point are selected as the preoperative intervention position of the target patient.

3. The method according to claim 2, characterized in that The retrieving the patient attribute information of the target patient and the nucleus volume information of the target nucleus, and determining the offset direction and offset distance corresponding to the target nucleus based on the patient attribute information, the nucleus volume information and the initial planning point, includes: Retrieving patient attribute information of a target patient, wherein the patient attribute information includes age information, height information, and weight information, and retrieving nucleus volume information of a target nucleus; Retrieving similar patients in a historical surgery database based on the patient attribute information, and obtaining historical planning points and historical placement points of the similar patients; Calculating according to the historical planning points and the historical placement points to obtain an offset vector, and determining an offset direction corresponding to the target nucleus based on the offset vector; Based on the ratio of the nucleus volume information to the reference volume information, an offset coefficient is obtained, and a reference offset distance corresponding to the reference volume information is retrieved; The offset distance corresponding to the target nucleus is obtained according to the product of the reference offset distance and the offset coefficient.

4. The method according to claim 3, characterized in that: When it is determined that the tremor frequency in the evaluation video does not meet the preset requirement, determining the placement planning point of the target nucleus according to the electrode offset strategy, the offset direction and the offset distance and sending it to the surgical end, includes: Obtaining the tremor frequency of the tremor part in the evaluation video, and when it is determined that the tremor frequency in the evaluation video is greater than a preset tremor frequency, counting the number of patients of the same type corresponding to each offset direction as the offset number; Sort the offset directions in descending order based on the offset quantity to obtain a partial order direction sequence; Selecting the first offset direction in the partial order direction sequence as the electrode movement direction, and determining the electrode offset point according to the electrode movement direction and the offset distance; When it is determined that the pacing electrode is located at the electrode offset point, the tremor position of the target patient is collected in real time to obtain an offset video of the electrode offset point; When it is determined that the tremor frequency in the offset video is greater than a preset tremor frequency, the partial order direction sequence is deleted and updated based on the electrode movement direction; Repeat the above steps of obtaining the offset video until the tremor frequency in the offset video is less than or equal to the preset tremor frequency, and then send the corresponding electrode offset point to the surgical end as the placement planning point.

5. The method according to claim 4, characterized in that Also includes: Obtaining the maximum horizontal coordinate, the minimum horizontal coordinate, the maximum vertical coordinate, the minimum vertical coordinate, the maximum vertical coordinate and the minimum vertical coordinate in the target nucleus; Obtaining a first transverse length according to a difference between the maximum transverse coordinate and the minimum transverse coordinate of the target nucleus; Obtaining a first longitudinal length based on a difference between the maximum longitudinal coordinate and the minimum longitudinal coordinate of the target nucleus; Obtaining a first vertical length according to a difference between the maximum vertical coordinate and the minimum vertical coordinate of the target nucleus; Selecting the maximum value among the first transverse length, the first longitudinal length and the first vertical length as the actual dovetail length of the target nucleus; Extracting dovetail pixel points in the target nucleus according to the dovetail pixel value, and counting the number of the dovetail pixel points to obtain the actual dovetail number; Amplifying the reference nucleus based on the offset coefficient to obtain a standard nucleus, and obtaining a standard dovetail length and a standard dovetail quantity of the standard nucleus; Obtaining a first strength adjustment coefficient based on a ratio of the standard dovetail length to the actual dovetail length, and obtaining a second strength adjustment coefficient based on a ratio of the standard dovetail quantity to the actual dovetail quantity; The preset stimulation intensity is adjusted based on the first intensity adjustment coefficient and the second intensity adjustment coefficient to obtain an actual stimulation intensity.

6. The method according to claim 5, characterized in that The step of adjusting the preset stimulation intensity based on the first intensity adjustment coefficient and the second intensity adjustment coefficient to obtain the actual stimulation intensity includes: Obtaining a first adjustment value according to the product of the first strength adjustment coefficient and the length weight value; Obtaining a second adjustment value based on the product of the second intensity adjustment coefficient and the quantity weight value; Adjusting the preset stimulation intensity according to the first adjustment value and the second adjustment value to obtain an actual stimulation intensity; The actual stimulus intensity is obtained by the following formula: in, is the actual stimulus intensity, To preset the stimulation intensity, is the standard dovetail length, is the actual dovetail length, is the length weight value, is the standard dovetail quantity, is the actual number of dovetails, is the quantity weight value.

7. The method according to claim 5, characterized in that Also includes: When it is determined that the partial order direction sequence does not have the offset direction, a central abscissa is obtained based on an average value of the maximum abscissa and the minimum abscissa and the value, a central ordinate is obtained based on an average value of the maximum ordinate and the minimum ordinate and the value, and a central ordinate is obtained based on an average value of the maximum ordinate and the minimum ordinate and the value; Determining a construction center point of the target nucleus according to the central abscissa, the central ordinate and the central ordinate; Selecting the maximum value among the first transverse length, the first longitudinal length and the first vertical length as the constructed diameter; Based on the construction center point and the construction diameter, determining a construction sphere corresponding to the target nucleus; A spherical coordinate system is constructed with the center of the constructed sphere as the coordinate origin, and the constructed sphere is segmented based on three mutually perpendicular planes in the spherical coordinate system to obtain eight segmented regions; Acquire the segmented area where the electrode offset point is located as the exclusion area, and take the remaining segmented areas as the pending areas; The pending areas are selected according to the excluded areas to obtain an offset priority sequence.

8. The method according to claim 7, characterized in that The selecting and processing the pending area according to the excluded area to obtain an offset priority sequence includes: Acquire the tremor frequency of the electrode offset point corresponding to the exclusion area as the exclusion tremor frequency, and select the exclusion area corresponding to the maximum exclusion tremor frequency as the first exclusion area; Obtaining the center point of the first exclusion zone as the exclusion midpoint, and obtaining the center point of the pending area as the pending midpoint; A priority distance is obtained by performing calculation according to the excluded midpoint and the to-be-selected midpoint, and the to-be-determined areas are sorted in descending order based on the priority distance to obtain an offset priority sequence.

9. The method according to claim 6, characterized in that Also includes: receiving the input stimulation intensity sent by the surgical end, and when determining that the actual stimulation intensity is greater than the input stimulation intensity, obtaining a first intensity difference based on a difference between the actual stimulation intensity and the input stimulation intensity; Based on the ratio of the first intensity difference to the constant value, a first stimulation ratio is obtained, and according to the product of the first stimulation ratio and the stimulation intensity, a first stimulation coefficient is obtained; When it is determined that the actual stimulation intensity is less than the input stimulation intensity, obtaining a second intensity difference based on a difference between the input stimulation intensity and the actual stimulation intensity; Based on the ratio of the second intensity difference to the constant value, a second stimulation ratio is obtained, and according to the product of the second stimulation ratio and the stimulation intensity, a second stimulation coefficient is obtained; An increased adjusted length weight and a decreased adjusted length weight are obtained based on the first stimulation coefficient and the second stimulation coefficient.

10. The method according to claim 6, characterized in that Also includes: receiving a postoperative tremor video sent by a patient terminal corresponding to the target patient, and a tremor label corresponding to the postoperative tremor video, wherein the tremor label includes resting tremor and action tremor; Determine a postoperative tremor video corresponding to the resting tremor as a resting adjustment video, and obtain a tremor frequency corresponding to the resting adjustment video as a postoperative resting tremor frequency; Retrieving a preset resting tremor frequency, and obtaining a resting tremor adjustment coefficient according to a ratio of the postoperative resting tremor frequency to the preset resting tremor frequency; The actual stimulation intensity is adjusted according to the resting tremor adjustment coefficient to obtain the resting stimulation intensity corresponding to the resting tremor; Determine a postoperative tremor video corresponding to the action tremor as an action adjustment video, and obtain a tremor frequency corresponding to the action adjustment video as a postoperative action tremor frequency; Retrieving a preset action tremor frequency, and obtaining an action tremor adjustment coefficient according to a ratio of the postoperative action tremor frequency to the preset action tremor frequency; The actual stimulation intensity is adjusted according to the action tremor adjustment coefficient to obtain the action stimulation intensity corresponding to the action tremor.

Images