Method and device for planning electrode implantation point during brain surface pulsation and storage medium

Abstract

The invention provides a method and a device for planning an electrode implantation point during brain surface pulsation, and a storage medium. The method comprises the following steps: acquiring continuous multi-frame blood vessel images which are acquired in real time according to a time sequence during brain surface pulsation; processing a target blood vessel image in the continuous multi-frame blood vessel images to obtain a blood vessel segmentation map; determining at least one target implantation point on the blood vessel segmentation map according to the dispersion arrangement rule of the implantation points, and generating a tracking image containing the target implantation point; determining real-time tracking trajectory data of the target implantation point based on the tracking image and the continuous multi-frame blood vessel image; based on the real-time tracking trajectory data, determining a real-time pulse period of the brain blood vessel of the implantation area and a prediction trajectory result of the target implantation point; and planning an implantation strategy of the electrode according to the real-time pulsation period and the predicted trajectory result. According to the method, the implantation strategy of the electrode can be planned in real time, so that the implantation accuracy and safety of the electrode can be ensured according to the real-time condition of the patient in the operation process.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of electrode implantation, and in particular to a method and device for planning an electrode implantation point during brain surface pulsation, and a storage medium. BACKGROUND

[0002] In the field of invasive brain-computer interface, the planning of an electrode implantation point is a key step in the invasive brain-computer interface. If the planned implantation point is safe and accurate, it can not only provide an accurate position during implantation, but also bring great convenience for subsequent operations after the electrode is implanted. In current implantation point planning methods, the planning point is mostly planned manually. In the surgery, the planning point is selected by the human eye, and the planning point is adjusted according to the pulsation. Compared with the automatic planning method, the method depends on the experience and operation level of the doctor. SUMMARY

[0003] In view of the above technical problems in the prior art, the present application provides a method and device for planning an electrode implantation point during brain surface pulsation, and a storage medium, which can plan the implantation strategy of the electrode in real time, such as the implantation time and implantation position, to ensure the implantation accuracy and safety of the electrode according to the real-time situation of the patient during the surgery.

[0004] The present application provides a method for planning an electrode implantation point during brain surface pulsation, which comprises the following steps: acquiring continuous multiple frames of blood vessel images collected in real time in time sequence during brain surface pulsation; processing a target blood vessel image in the continuous multiple frames of blood vessel images to obtain a blood vessel segmentation map; determining at least one target implantation point on the blood vessel segmentation map according to a scattered arrangement rule of the implantation point, and generating a tracking image containing the target implantation point; determining real-time tracking trajectory data of the target implantation point based on the tracking image and the continuous multiple frames of blood vessel images; determining a real-time pulsation period of a brain blood vessel of an implantation region and a predicted trajectory result of the target implantation point based on the real-time tracking trajectory data; planning an implantation strategy of the electrode according to the real-time pulsation period and the predicted trajectory result.

[0005] In some embodiments, the predicted trajectory result is determined by the following method: predicting a trajectory of the target implantation point in the future according to the real-time tracking trajectory data of the target implantation point by using a target model; wherein the target model at least uses a Kalman filtering algorithm; updating parameters of the target model in real time according to the predicted trajectory of the target implantation point and the real-time tracking trajectory data; generate the predicted trajectory result after an error between the predicted trajectory of the target implantation point and the real-time tracking trajectory data is within a preset threshold.

[0006] In some embodiments, the real-time pulsation cycle is determined by the following method: determine a wave crest and a wave trough of a motion trajectory of the target implantation point according to the real-time tracking trajectory data; determine a real-time pulsation cycle of a cerebral blood vessel of an implantation region according to the wave crest and the wave trough of the motion trajectory of the target implantation point.

[0007] In some embodiments, the target implantation point is determined on the blood vessel segmentation map according to the implantation point dispersion arrangement rule, specifically comprising: determine a plurality of implantable points on the blood vessel segmentation map according to the implantation point dispersion arrangement rule; divide the blood vessel segmentation map into a plurality of planning regions based on the plurality of implantable points; assign a target implantation point to at least one of the planning regions from the plurality of implantable points.

[0008] In some embodiments, the target implantation point is assigned to at least one of the planning regions from the plurality of implantable points, specifically comprising: determine a number of target implantation points of the planning region according to a number of implantable points in the planning region, a total number of implantable points on the blood vessel segmentation map, and a total number of implanted electrodes.

[0009] In some embodiments, the tracking image is obtained by combining the target blood vessel image with the target implantation point, and the plurality of continuous blood vessel images include a plurality of continuous to-be-registered images sequentially acquired after the target blood vessel image is acquired; determine the real-time tracking trajectory data of the target implantation point based on the tracking image and the plurality of continuous blood vessel images, specifically comprising: perform feature matching between the plurality of continuous to-be-registered images and the tracking image in sequence until positions of the target implantation point on the plurality of to-be-registered images are determined respectively; determine the real-time tracking trajectory data based on the tracking image and the positions of the target implantation point on the plurality of to-be-registered images.

[0010] In some embodiments, the implantation strategy of the electrode is planned according to the real-time pulsation cycle and the predicted trajectory result, specifically comprising: determine a second wave crest time when the real-time pulsation cycle and the predicted trajectory result match at a first wave crest time, wherein the second wave crest time is a next wave crest time of the first wave crest time; control the electrode to be implanted to a target implantation point at the second wave peak moment.

[0011] In some embodiments, the target blood vessel image in the continuous multiple frames of blood vessel images is processed to obtain a blood vessel segmentation map, specifically including: The target blood vessel image is preprocessed to obtain a preprocessed image. The preprocessed image is subjected to coarse extraction processing to obtain a first extraction map. The preprocessed image is subjected to fine extraction processing to obtain a second extraction map. The first extraction map and the second extraction map are fused to obtain a blood vessel segmentation map.

[0012] The embodiments of the present application also provide a device for planning an electrode implantation point during brain surface pulsation, comprising: An acquisition module is configured to acquire continuous multiple frames of blood vessel images collected in time sequence in real time during brain surface pulsation. A processing module is configured to process a target blood vessel image in the continuous multiple frames of blood vessel images to obtain a blood vessel segmentation map. A determination module is configured to determine at least one target implantation point on the blood vessel segmentation map according to a scattered arrangement rule of implantation points, and generate a tracking image containing the target implantation point; determine real-time tracking trajectory data of the target implantation point based on the tracking image and the continuous multiple frames of blood vessel images; and determine a real-time pulsation period of a brain blood vessel of an implantation region and a predicted trajectory result of the target implantation point based on the real-time tracking trajectory data. A planning module is configured to plan an implantation strategy of an electrode according to the real-time pulsation period and the predicted trajectory result.

[0013] The embodiments of the present application also provide a computer readable storage medium storing a computer program, which, when executed by a processor, implements the steps of the planning method of an electrode implantation point during brain surface pulsation according to any of the above embodiments.

[0014] Compared with the prior art, the embodiments of the present application have the beneficial effects that: by using the continuous multiple frames of blood vessel images collected in time sequence in real time during brain surface pulsation, the blood vessel segmentation map and the tracking image are obtained based on the real-time acquired blood vessel images, so as to obtain the real-time tracking trajectory data of the target implantation point, and the real-time pulsation period and the predicted trajectory result determined according to the real-time tracking trajectory data can be used to plan the implantation strategy of the electrode in real time, such as the implantation time and the implantation position, so as to ensure the implantation accuracy and safety of the electrode according to the real-time situation of the patient during the operation process, and compared with the scheme of relying on the experience and operation level of the doctor for implantation, the implantation efficiency is effectively improved. BRIEF DESCRIPTION OF DRAWINGS

[0015] In drawings that are not necessarily drawn to scale, the same reference numerals may describe similar parts in different views. The drawings generally illustrate various embodiments by way of example rather than limitation and are used, together with the description and claims, to illustrate the disclosed embodiments. Where appropriate, the same reference numerals are used in all drawings to refer to the same or similar parts. Such embodiments are illustrative and not intended to be exhaustive or exclusive embodiments of the apparatus or method.

[0016] Figure 1 This is a first flowchart of the planning method in an embodiment of this application; Figure 2 This is a schematic diagram of the blood vessel segmentation diagram of the planning method in the embodiments of this application; Figure 3 This is a schematic diagram of the tracking image of the planning method in the embodiments of this application; Figure 4 This is a second flowchart of the planning method in an embodiment of this application; Figure 5 This is a third flowchart of the planning method in an embodiment of this application; Figure 6 This is a schematic diagram of the planning method of this application, showing implantable points on a vascular segmentation map; Figure 7 This is the fourth flowchart of the planning method in the embodiments of this application; Figure 8 This is the fifth flowchart of the planning method in the embodiments of this application; Figure 9 This is a schematic diagram of the first extraction diagram of the planning method in an embodiment of this application; Figure 10 This is a schematic diagram of the second extraction diagram of the planning method in an embodiment of this application; Figure 11 This is a structural block diagram of the device for planning electrode implantation points during brain surface pulsation, as described in an embodiment of this application. Detailed Implementation

[0017] It should be understood that various modifications can be made to the embodiments described herein. Therefore, the above description should not be considered as limiting, but merely as an example of embodiments. Other modifications within the scope and spirit of this application will be apparent to those skilled in the art.

[0018] The accompanying drawings, which are included in and form part of this specification, illustrate embodiments of the present application and, together with the general description of the present application given above and the detailed description of the embodiments given below, serve to explain the principles of the present application.

[0019] These and other features of this application will become apparent from the following description of preferred forms of embodiments given as non-limiting examples, with reference to the accompanying drawings.

[0020] It should also be understood that, while the present application has been described in terms of certain embodiments, the skilled person will readily ascertain many other ways of making the present application.

[0021] The above and other aspects, features, and advantages of the present application will become more apparent from the following detailed description, taken in conjunction with the accompanying drawings, which illustrate

[0022] Specific embodiments of the present application are described hereinbelow, with reference to the drawings; however, it should be understood that the embodiments described are merely examples of the present application, which can be practiced in various ways. Well-known and / or repetitive functions and structures are not described in detail to avoid obscuring the present application unnecessarily. Therefore, specific structural and functional details disclosed herein are not intended to limit the present application, but merely as a basis for the claims and a representative basis for teaching one skilled in the art to variously employ the present application in virtually any appropriate detailed structure.

[0023] The specification can use phrases such as "in one embodiment", "in another embodiment", "in yet another embodiment", or "in other embodiments", which can refer to one or more of the same or different embodiments under the present application.

[0024] The embodiments of the present application provide a method for planning an electrode implantation point during brain surface pulsation, which can be applied to a planning platform for an electrode implantation point, a planning device for an electrode implantation point, and the like.

[0025] As shown in FIG. 1, the method for planning an electrode implantation point during brain surface pulsation includes steps S101 to S106. Figure 1

[0026] Step S101: Obtain continuous multiple frames of blood vessel images collected in real time in time sequence during brain surface pulsation.

[0027] The blood vessels corresponding to the blood vessel images can specifically be cerebral blood vessels under the pia mater, and the implantation region where the electrode is to be implanted is near the cerebral blood vessels under the pia mater. It should be noted that the cerebral blood vessels under the pia mater are different from the regularity of heart rate and pulse during pulsation, and the brain surface pulsation is caused by the combined action of respiration and blood vessels, which may have occasional irregularities. Therefore, the cerebral blood vessels under the pia mater pulsate differently according to the real-time situation of the patient, and the continuous multiple frames of blood vessel images collected in real time can ensure the real-time planning of the electrode implantation point during the operation, i.e., the electrode implantation can be combined with the implementation of the patient.

[0028] Specifically, the continuous multiple frames of blood vessel images can be collected by a micro-vision system during brain surface pulsation, and of course other image collection devices can also be used for blood vessel image collection, which is not specifically limited in the present application. ​

[0029] Step S102: processing the target blood vessel image in the continuous multiple frames of blood vessel images to obtain a blood vessel segmentation map.

[0030] As shown in Figure 2 , Figure 2 The blood vessel segmentation map is shown, specifically a binary map after blood vessel segmentation, wherein the white area is the implantation area and the black color is the blood vessel.

[0031] Step S103: determining at least one target implantation point on the blood vessel segmentation map according to a scattered arrangement rule of the implantation point and generating a tracking image containing the target implantation point.

[0032] As shown in Figure 3 , Figure 3 The tracking image is shown, wherein the blue dots in the figure are the target implantation points, the blue numbers near the blue dots are the numbers of the target implantation points, and the 32 target implantation points shown in the figure are only examples. When implanting the electrode, one or more of them can be selected for electrode implantation.

[0033] The scattered arrangement rule of the implantation point can be understood as meeting the electrode size itself, the spacing between electrodes, the safety distance of the electrode from the blood vessel, etc., and the purpose is to ensure that the position of the implantation point can guarantee the safe implantation of the electrode.

[0034] The above-mentioned tracking image can be presented on the blood vessel segmentation map combined with the target implantation point, or presented on the target blood vessel image combined with the target implantation point. In order to achieve the purpose of optimizing the display effect, Figure 3 The tracking image shown in the middle is presented on the target blood vessel image combined with the target implantation point.

[0035] Step S104: determining real-time tracking trajectory data of the target implantation point based on the tracking image and the continuous multiple frames of blood vessel images.

[0036] In the case of multiple target implantation points, real-time tracking trajectory data can be determined for each target implantation point. The real-time tracking trajectory data can be understood as determining the position of the target implantation point on each blood vessel image, thereby obtaining the total trajectory data of the implantation point on the continuous multiple frames of blood vessel images.

[0037] Step S105: determining the real-time pulsation cycle of the brain blood vessel of the implantation area and the predicted trajectory result of the target implantation point based on the real-time tracking trajectory data.

[0038] The real-time pulsation cycle is obtained according to the continuous multiple frames of blood vessel images collected in real time when the brain surface pulsates, and the pulsation cycle has real-time performance. The pulsation cycle of the cerebral blood vessel under the dura mater may have occasional irregularities due to individual differences of patients. Therefore, the determined real-time pulsation cycle can ensure the targeted implantation for the patient and further ensure the implantation accuracy and safety for different patients.

[0039] The predicted trajectory result of the target implantation point can be understood as a predicted trajectory result of the target implantation point, which can be specifically calculated by a model.

[0040] Step S106: planning an implantation strategy of the electrode according to the real-time pulsation cycle and the predicted trajectory result.

[0041] The implantation strategy can include an implantation time, an implantation position, and the like, so that the electrode can be accurately implanted based on the implantation strategy. The object that executes the implantation strategy can be a surgical robot or a doctor, and the present application does not make a specific limitation thereon, and the implantation strategy determined can be accurately executed. When the execution object is a surgical robot, the surgical robot can be in place in advance based on the predicted trajectory result, so as to ensure the accuracy and the degree of automation of the implantation surgery.

[0042] When the electrode to be implanted is multiple, the position of each electrode to be implanted can be determined in the multiple target implantation points, and each electrode can be implanted into the position of the corresponding target implantation point in sequence.

[0043] The method can provide a good guarantee for obtaining an accurate implantation strategy through real-time tracking of the target implantation point when the brain surface pulsates and the predicted trajectory result, and the efficiency in the implantation process is improved.

[0044] The calculation of the real-time pulsation cycle and the predicted trajectory result can achieve real-time performance of 30 frames per second, so that the purpose of accurately planning the implantation strategy of the electrode according to the real-time pulsation cycle and the predicted trajectory result in the surgery can be achieved.

[0045] The present application realizes the blood vessel segmentation map and the tracking image based on the blood vessel images obtained in real time by collecting the continuous multiple frames of blood vessel images in real time in time sequence when the brain surface pulsates, so as to obtain the real-time tracking trajectory data of the target implantation point. According to the real-time pulsation cycle and the predicted trajectory result determined according to the real-time tracking trajectory data, the implantation strategy of the electrode, such as the implantation time and the implantation position, can be planned in real time, so as to ensure the implantation accuracy of the electrode according to the real-time situation of the patient in the surgery. Compared with the scheme that relies on the experience and operation level of the doctor for implantation, the implantation efficiency is effectively improved.

[0046] In some embodiments, as Figure 4As shown, the predicted trajectory result is determined by the following steps S201 to S203.

[0047] Step S201: predicting a trajectory of the target implantation point in the future by using a target model according to real-time tracking trajectory data of the target implantation point; wherein the target model at least adopts Kalman filtering algorithm.

[0048] Step S202: updating parameters of the target model in real time according to the predicted trajectory of the target implantation point and the real-time tracking trajectory data.

[0049] Step S203: generating the predicted trajectory result when an error between the predicted trajectory of the target implantation point and the real-time tracking trajectory data is within a preset threshold.

[0050] In this way, the target model can be used to accurately predict the trajectory of the target implantation point, and after adjusting the parameters of the target model according to the predicted trajectory and the real-time tracking trajectory, the predicted trajectory result meeting the implantation requirements can be generated when the error meets the preset threshold, thereby improving the real-time and effectiveness of the predicted trajectory result calculation.

[0051] The target model at least adopts Kalman filtering algorithm, which can dynamically adjust parameters in combination with real-time tracking trajectory data, thereby improving the accuracy of the predicted trajectory of the target implantation point output by the target model. It should be noted that since Kalman filtering algorithm requires certain prior knowledge, the result of the initial target model may not be accurate, and the accuracy of the output result will increase significantly after the target model is predicted for a period of time. When the prediction error is within the preset threshold, it is determined that the implantation requirements are met, and the implantation strategy of the electrode can be accurately planned based on the real-time beating cycle and the obtained predicted trajectory result.

[0052] In some embodiments, as shown, Figure 5 As shown, the real-time beating cycle is determined by the following steps S301 to S302.

[0053] Step S301: determining a wave crest and a wave trough of a motion trajectory of the target implantation point according to the real-time tracking trajectory data.

[0054] Step S302: determining a real-time beating cycle of a brain blood vessel of an implantation region according to the wave crest and the wave trough of the motion trajectory of the target implantation point.

[0055] In this way, after the wave crest and the wave trough of the motion trajectory of the target implantation point are determined based on the obtained real-time tracking trajectory data, the real-time beating cycle of the brain blood vessel of the implantation region can be accurately calculated, which can plan a more accurate implantation strategy for the implantation surgery and improve the safety of the patient and the postoperative recovery effect.

[0056] It can be understood that in the case of multiple target implant points determined on the tracking image, the real-time pulsation period can be determined based on the wave crest and wave trough of the motion trajectory of one of the target implant points. Specifically, in the multiple target implant points, one is determined as the position of the electrode to be implanted this time, and the real-time pulsation period can be determined based on the wave crest and wave trough of the motion trajectory of the target implant point.

[0057] Before determining the wave crest and wave trough of the motion trajectory of the target implant point according to the real-time tracking trajectory data, data preprocessing can be performed on the tracking trajectory data, which can include but is not limited to filtering, interpolation, smoothing, etc., the purpose of which is to eliminate noise and smooth the trajectory, and then the wave crest and wave trough are calculated respectively, and the real-time pulsation period of the cerebral blood vessel is determined by the wave crest and wave trough.

[0058] After obtaining the wave crest and wave trough of the motion trajectory of the target implant point, a data statistical method can be used to obtain the real-time pulsation period, such as a histogram statistical method, which is not limited in this application, as long as it can accurately calculate the real-time pulsation period.

[0059] In some embodiments, the step S103 of determining at least one target implant point on the blood vessel segmentation map according to the implant point dispersion arrangement rule specifically includes: determining a plurality of implantable points on the blood vessel segmentation map according to the implant point dispersion arrangement rule; dividing the blood vessel segmentation map into a plurality of planning regions based on the plurality of implantable points; assigning a target implant point to at least one of the planning regions from the plurality of implantable points.

[0060] In this way, a plurality of implantable points can be determined first, and then a plurality of planning regions divided based on the plurality of implantable points are assigned target implant points for each planning region, improving the reliability of determining target implant points from the plurality of implantable points and meeting the arrangement requirements for the implant point of the electrode.

[0061] The implant point dispersion arrangement rule described above is related to at least one of the following: electrode diameter, electrode spacing, and distance between electrode and blood vessel.

[0062] The planning region described above can be encoded according to the rules of rows and columns. When there is a blood vessel obstruction in the middle of a large region, it will be separated according to a small region, so as to improve the dispersity of the implantable points. Specifically, a clustering method can be used to divide a plurality of planning regions, for example, a plurality of implantable points close to each other are divided into a region, and after obtaining the clustering result, the region of the implantable points belonging to a class can be divided into a region.

[0063] As shown in FIG. 8, the target implant point is determined on the blood vessel segmentation map, and the target implant point is determined according to the implant point dispersion arrangement rule. Figure 6 The target implant point is determined on the blood vessel segmentation map, and the target implant point is determined according to the implant point dispersion arrangement rule. Figure 6To present a schematic diagram of implantable points on a blood vessel segmentation map, a green box represents a surgical area, and a plurality of implantable points (green dots) are presented on the blood vessel segmentation map. The red number near the implantable point is the code of the planning area corresponding to the implantable point. For example, Figure 6 The planning areas shown in the middle have 22 planning areas, of which the planning area numbered 1 has 1 implantable point, the planning area numbered 2 has 1 implantable point, the planning area numbered 3 has 1 implantable point, the planning area numbered 4 has 4 implantable points, and so on, which will not be repeated here.

[0064] After assigning the target implantable point, there can be no target implantable point in some planning areas, or there can be one or more target implantable points, which are not specifically limited by the present application.

[0065] In some embodiments, the assigning of the target implantable point for at least one of the planning areas from the plurality of implantable points specifically includes: The number of target implantable points of the planning area is determined according to the number of implantable points in the planning area, the total number of implantable points on the blood vessel segmentation map, and the total number of implanted electrodes.

[0066] The number of target implantable points of each planning area can be calculated using the following formula: ; Wherein, The number of implantable points in the planning area; The total number of implantable points on the blood vessel segmentation map; The total number of implanted electrodes.

[0067] All planning areas can be sorted in descending order according to the number of implantable points in each planning area, and the number of target implantable points of each planning area is calculated in turn based on this order.

[0068] After determining the number of target implantable points of the planning area, a target implantable point can be selected from the plurality of implantable points in the planning area according to the distance from the blood vessel. For example, Figure 6 The planning area numbered 19 in the middle has 3 implantable points, and after determining that the planning area numbered 19 has 1 target implantable point, one of the 3 implantable points can be selected as the target implantable point according to the distance from the blood vessel, for example, the implantable point farthest from the blood vessel is determined as the target implantable point.

[0069] In some embodiments, the tracking image is obtained by combining the target blood vessel image with the target implantable point, and the plurality of continuous blood vessel images include a plurality of continuous images to be registered in time sequence after the target blood vessel image is acquired. For example, Figure 7As shown, the step S104 of determining the real-time tracking trajectory data of the target implantation point based on the tracking image and the continuous multiple frames of vessel images specifically comprises steps S401-S402.

[0070] Step S401: sequentially perform feature matching between the continuous multiple frames of the to-be-registered images and the tracking image until the positions of the target implantation points on the multiple to-be-registered images are determined.

[0071] Step S402: determine the real-time tracking trajectory data based on the tracking image and the positions of the target implantation points on each to-be-registered image.

[0072] In this way, after obtaining the tracking image, the positions of the target implantation points on the multiple to-be-registered images can be determined by sequentially registering the other vessel images with the tracking image, so that the accurate real-time tracking trajectory data can be obtained after registration.

[0073] The target vessel image in the continuous multiple frames of vessel images can be understood as a starting image. After the tracking image is calculated based on the starting image, there is no need to calculate the vessel images of subsequent frames, but the positions of the target implantation points on the vessel images of the subsequent frames can be obtained by sequentially performing feature matching between the vessel images of the subsequent frames and the tracking image. There is no need to calculate the target implantation point trajectory data in all vessel images, thereby reducing the calculation amount, and the accurate real-time tracking trajectory data can be obtained through feature matching.

[0074] The feature matching can adopt a conventional feature point-based matching method such as SIFT (Scale-Invariant Feature Transform), SURF (Speeded-Up Robust Features), or a deep learning method. Preferably, a deep learning model with a Transformer architecture can be used for tracking of the target implantation point.

[0075] In some embodiments, as shown, Figure 8 As shown, the step S106 of planning an implantation strategy of the electrode according to the real-time beating cycle and the predicted trajectory result specifically comprises steps S501-S502.

[0076] Step S501: in the case where the real-time beating cycle and the predicted trajectory result match at a first wave peak time, a second wave peak time is determined; the second wave peak time is a next wave peak time of the first wave peak time.

[0077] Step S502: control the electrode to be implanted into the target implantation point at the second wave peak time.

[0078] Therefore, in the case that the real-time beating cycle and the predicted trajectory result match at the first peak time, it can be determined that the output result of the target model after the parameter adjustment has reached the implantation requirement, and the electrode can be implanted at the next peak time, thereby meeting the accuracy of the electrode implantation.

[0079] Specifically, the second peak time can be determined by the following formula: ; Wherein, T1 is the first peak time; T2 is the valley time after the first peak time; and T3 is the second peak time.

[0080] The above is to take the peak as the implantation time. In some other embodiments, the valley can be selected as the implantation time. Specifically, in the case that the real-time beating cycle and the predicted trajectory result match at the first valley time, the second valley time can be determined, wherein the second valley time is the next valley time of the first valley time; and the electrode is controlled to be implanted to the target implantation point at the second valley time.

[0081] The above-mentioned matching of the real-time beating cycle and the predicted trajectory result at the first peak time can be understood as that the error between the predicted trajectory result and the real-time beating cycle is within a preset threshold at the first peak time, that is, the real-time beating cycle and the predicted trajectory result are matched.

[0082] In some embodiments, the processing of the target blood vessel image in the continuous multiple frames of blood vessel images in step S102 to obtain a blood vessel segmentation map specifically includes: preprocessing the target blood vessel image to obtain a preprocessed image; coarsely extracting the preprocessed image to obtain a first extraction map; finely extracting the preprocessed image to obtain a second extraction map; fusing the first extraction map and the second extraction map to obtain a blood vessel segmentation map.

[0083] Therefore, by coarsely and finely extracting the preprocessed image respectively, the blood vessel segmentation map obtained by fusing the first extraction map and the second extraction map can more accurately represent the condition of the blood vessels in the target blood vessel image, specifically, the first extraction map can represent the large outline of the blood vessels, and the second extraction map can represent the condition of the small capillary blood vessels.

[0084] As shown in Figure 9 and Figure 10 , the first extraction map is shown in Figure 9 , the second extraction map is shown in Figure 10 , and the blood vessel segmentation map obtained by fusing the first extraction map and the second extraction map is shown in Figure 2 .

[0085] The preprocessing of the target blood vessel image includes, but is not limited to, normalization, image filtering, image enhancement, scaling and the like of the target blood vessel image.

[0086] The rough extraction processing at least includes enhancing contrast of the preprocessed image, binarizing the image after the contrast enhancement, to obtain a first extraction image in which a large outline of the blood vessel can be extracted.

[0087] The fine extraction processing at least includes multiple opening and closing operations, noise reduction, connection strengthening of small blood vessels and the like of the preprocessed image, to obtain a binary image including a segmentation result of capillary vessels, i.e., a second extraction image.

[0088] The embodiment of the present application further provides a brain surface pulsation electrode implantation point planning device 100. As shown in the figure, Figure 11 The brain surface pulsation electrode implantation point planning device 100 includes an acquisition module 101, a processing module 102, a determination module 103 and a planning module 104. The acquisition module 101 is configured to acquire continuous multiple frames of blood vessel images collected in real time in time sequence when the brain surface pulsates. The processing module 102 is configured to process a target blood vessel image in the continuous multiple frames of blood vessel images to obtain a blood vessel segmentation image. The determination module 103 is configured to determine at least one target implantation point on the blood vessel segmentation image according to a scattered arrangement rule of the implantation point, generate a tracking image containing the target implantation point, determine real-time tracking trajectory data of the target implantation point based on the tracking image and the continuous multiple frames of blood vessel images, and determine a real-time pulsation period of a brain blood vessel of an implantation region and a prediction trajectory result of the target implantation point based on the real-time tracking trajectory data. The planning module 104 is configured to plan an implantation strategy of an electrode according to the real-time pulsation period and the prediction trajectory result.

[0089] The present application realizes the blood vessel segmentation image and the tracking image based on the blood vessel images acquired in real time, to obtain the real-time tracking trajectory data of the target implantation point, and according to the real-time pulsation period and the prediction trajectory result determined based on the real-time tracking trajectory data, the implantation strategy of the electrode, such as the implantation time and the implantation position, can be planned in real time, to ensure the implantation accuracy of the electrode according to the real-time situation of the patient during the operation process. Compared with the scheme of relying on the experience and operation level of the doctor for implantation, the implantation efficiency is effectively improved.

[0090] In some embodiments, the determining module 103 is further configured to: predict a future trajectory of the target implantation point according to real-time tracking trajectory data of the target implantation point by using a target model; wherein the target model at least employs a Kalman filtering algorithm; update parameters of the target model in real time according to the predicted trajectory of the target implantation point and the real-time tracking trajectory data; and generate the predicted trajectory result when an error between the predicted trajectory of the target implantation point and the real-time tracking trajectory data is within a preset threshold.

[0091] In some embodiments, the determining module 103 is further configured to: determine a wave crest and a wave trough of a motion trajectory of the target implantation point according to the real-time tracking trajectory data; and determine a real-time pulsation cycle of a cerebral blood vessel of an implantation region according to the wave crest and the wave trough of the motion trajectory of the target implantation point.

[0092] In some embodiments, the determining module 103 is further configured to: determine a plurality of implantable points on the blood vessel segmentation map according to a dispersion arrangement rule of implantation points; divide the blood vessel segmentation map into a plurality of planning regions based on the plurality of implantable points; and assign a target implantation point to at least one of the planning regions from the plurality of implantable points.

[0093] In some embodiments, the determining module 103 is further configured to: determine a number of target implantation points of the planning region according to a number of implantable points in the planning region, a total number of implantable points on the blood vessel segmentation map, and a total number of implanted electrodes.

[0094] In some embodiments, the tracking image is obtained by combining the target blood vessel image with the target implantation point, and the plurality of continuous frames of to-be-registered images are sequentially acquired after the target blood vessel image is acquired. The determining module 103 is further configured to: sequentially perform feature matching between the plurality of continuous frames of to-be-registered images and the tracking image until positions of the target implantation point on the plurality of to-be-registered images are determined; and determine the real-time tracking trajectory data based on the tracking image and the positions of the target implantation point on the plurality of to-be-registered images.

[0095] In some embodiments, the planning module 104 is further configured to: determine a second wave crest time when the real-time pulsation cycle and the predicted trajectory result match at a first wave crest time; wherein the second wave crest time is a next wave crest time of the first wave crest time; and control the electrode to be implanted into the target implantation point at the second wave crest time.

[0096] In some embodiments, the processing module 102 is further configured to: pre-process the target blood vessel image to obtain a pre-processed image; perform coarse extraction processing on the pre-processed image to obtain a first extraction image; perform fine extraction processing on the pre-processed image to obtain a second extraction image; and fuse the first extraction image and the second extraction image to obtain a blood vessel segmentation image.

[0097] The embodiments of the present application further provide a computer readable storage medium, which stores a computer program. The computer program is executed by a processor to implement the steps of the method for planning an electrode implantation point in a brain surface beat.

[0098] It should be noted that, according to various units in various embodiments of the present application, the units can be implemented as computer executable instructions stored on a memory, which are executed by a processor to implement corresponding steps; or can be implemented as hardware with corresponding logic computing capability; or can be implemented as a combination of software and hardware (firmware). In some embodiments, the processor can be implemented as any one of an FPGA, an ASIC, a DSP chip, a SOC (System on Chip), an MPU (such as but not limited to Cortex), etc. The processor can be communicatively coupled to the memory and configured to execute computer executable instructions stored therein. The memory can include a read-only memory (ROM), a flash memory, a random access memory (RAM), such as a synchronous DRAM (SDRAM) or a Rambus DRAM, a static storage memory (for example, a flash memory, a static random access memory), etc., which stores computer executable instructions in any format. The computer executable instructions can be accessed by the processor, read from the ROM or any other suitable storage location, and loaded into the RAM for execution by the processor to implement the wireless communication method according to various embodiments of the present application.

[0099] It should be noted that, in various components of the system of the present application, the components are logically divided according to the functions to be implemented, but the present application is not limited thereto, and the various components can be re-divided or combined as needed, for example, some components can be combined into a single component, or some components can be further divided into more sub-components.

[0100] Various component embodiments of the present application can be implemented in hardware, or as software modules running in one or more processors, or combinations thereof. Skilled persons will appreciate that a microprocessor or digital signal processor (DSP) can be used in practice to implement some or all of the functionality of some or all of the components in a system according to embodiments of the present application. The present application can also be implemented as a program of apparatus (e.g. a computer program and a computer program product) for performing part or all of the methods described herein. Such a program of the present application can be stored on a computer readable medium, or can be in the form of one or more signals. Such signals can be downloaded from an Internet website, or provided on a carrier medium, or in any other form. Furthermore, the present application can be implemented by means of hardware comprising several distinct elements, and by means of a suitably programmed computer. In the unitary claim enumerating several apparatus, several of these apparatus can be embodied by one and the same item of hardware. The use of the words "first", "second", and "third", etc. do not imply any order but such words are to be interpreted as names.

[0101] Moreover, although example embodiments have been described herein, it should be understood that the scope of the application includes any and all modifications, omissions, combinations (e.g., of aspects across various embodiments), adaptations and / or alterations based on the present disclosure. The elements of the claims are to be construed in the broadest reasonable manner, and not limited to the examples described herein or by the specification. The specification and drawings are to be regarded as illustrative only, and any example is to be construed as not excluding any other example or suitable modification that could be made by a skilled person.

[0102] The above description is intended to be illustrative, and not restrictive. For example, the above-described examples (or one or more aspects thereof) can be used in combination with each other. Other examples can be used in addition to those described above, such as one of ordinary skill in the art would understand upon reading the above description. Additionally, in the specific description of embodiments above, various features can be grouped together or divided up for the purpose of streamlining the disclosure. This should not be interpreted as a requirement that the claimed subject matter must include such grouped or divided features. Rather, the subject matter described herein includes all possible combinations of features that can be claimed in any one or more of the claims. The claims are hereby incorporated into this detailed description, with each claim standing on its own as a separate embodiment, which can be combined with any one or more other claims. The scope of the application should be determined with reference to the appended claims, along with the full scope of equivalents to which such claims are entitled. The claims are not limited to the embodiments described above by any means.

[0103] The above examples are only exemplary embodiments of the present application, and are not intended to limit the present application, and the protection scope of the present application is defined by the claims. Those skilled in the art can make various modifications or equivalent replacements to the present application within the spirit and protection scope of the present application, and such modifications or equivalent replacements are also considered to fall within the protection scope of the present application.

Claims

1. A method of planning an electrode implant site for brain surface pulsation, characterized by, The method comprises the following steps: acquiring a plurality of continuous frames of blood vessel images collected in real time in time sequence when the brain is pulsating; processing a target blood vessel image in the plurality of continuous frames of blood vessel images to obtain a blood vessel segmentation image; determining at least one target implantation point on the blood vessel segmentation image according to a dispersion arrangement rule of implantation points, and generating a tracking image containing the target implantation point; determining real-time tracking trajectory data of the target implantation point based on the tracking image and the plurality of continuous frames of blood vessel images; determining a real-time pulsation cycle of a brain blood vessel of an implantation region and a predicted trajectory result of the target implantation point based on the real-time tracking trajectory data; planning an implantation strategy of an electrode according to the real-time pulsation cycle and the predicted trajectory result.

2. The method of planning brain surface pulsatile electrode implantation sites according to claim 1, wherein, The predicted trajectory result is determined by the following method: predicting a trajectory of the target implantation point in the future according to real-time tracking trajectory data of the target implantation point by using a target model; wherein the target model at least uses a Kalman filtering algorithm; updating parameters of the target model in real time according to the predicted trajectory of the target implantation point and the real-time tracking trajectory data; generating the predicted trajectory result after an error between the predicted trajectory of the target implantation point and the real-time tracking trajectory data is within a preset threshold.

3. The method of planning brain surface pulsatile electrode implantation points according to claim 1 or 2, characterized in that, The real-time pulsation cycle is determined by the following method: determining a wave crest and a wave trough of a motion trajectory of the target implantation point according to the real-time tracking trajectory data; determining a real-time pulsation cycle of a brain blood vessel of an implantation region according to the wave crest and the wave trough of the motion trajectory of the target implantation point.

4. The method of planning brain surface pulsatile electrode implantation points according to claim 1, wherein, The at least one target implantation point is determined on the blood vessel segmentation image according to a dispersion arrangement rule of implantation points, and specifically comprises the following steps: determining a plurality of implantable points on the blood vessel segmentation image according to the dispersion arrangement rule of implantation points; dividing the blood vessel segmentation image into a plurality of planning regions based on the plurality of implantable points; allocating a target implantation point for at least one of the planning regions among the plurality of implantable points.

5. The method of planning brain surface pulsatile electrode implantation points according to claim 4, wherein, The target implantation point for at least one of the planning regions is allocated among the plurality of implantable points, and specifically comprises the following steps: determining a number of target implantation points of the planning region according to a number of implantable points in the planning region, a total number of implantable points on the blood vessel segmentation image, and a total number of electrodes to be implanted.

6. The method of planning brain surface pulsatile electrode implantation points according to claim 1 or 2, wherein, The tracking image is obtained by combining the target blood vessel image with the target implantation point, and the plurality of continuous frames of blood vessel images contain a plurality of continuous frames of to-be-registered images collected in time sequence after the target blood vessel image is collected; The real-time tracking trajectory data of the target implantation point is determined based on the tracking image and the plurality of continuous frames of blood vessel images, and specifically comprises the following steps: performing feature matching between the plurality of continuous frames of to-be-registered images and the tracking image in sequence until positions of the target implantation points on the plurality of to-be-registered images are determined; determining the real-time tracking trajectory data based on the tracking image and the positions of the target implantation points on the to-be-registered images.

7. The method of planning brain surface pulsatile electrode implantation points according to claim 1, wherein, The implantation strategy of the electrode is planned according to the real-time pulsation cycle and the predicted trajectory result, and specifically comprises the following steps: In a case where the real-time beating cycle and the predicted trajectory result match at the first wave peak time, a second wave peak time is determined, wherein the second wave peak time is a next wave peak time of the first wave peak time; The electrode is controlled to be implanted to a target implantation point at the second wave peak time.

8. The method of planning brain surface pulsatile electrode implantation points according to claim 1, wherein, The target blood vessel image in the continuous multiple frames of blood vessel images is processed to obtain a blood vessel segmentation map, specifically including: The target blood vessel image is preprocessed to obtain a preprocessed image; The preprocessed image is coarsely extracted to obtain a first extraction map; The preprocessed image is finely extracted to obtain a second extraction map; The first extraction map and the second extraction map are fused to obtain the blood vessel segmentation map.

9. A device for planning electrode implantation sites for brain surface pulsations, characterized by It includes: An acquisition module is configured to acquire continuous multiple frames of blood vessel images collected in time sequence in real time when the brain surface beats; A processing module is configured to process a target blood vessel image in the continuous multiple frames of blood vessel images to obtain a blood vessel segmentation map; A determination module is configured to determine at least one target implantation point on the blood vessel segmentation map according to a dispersion arrangement rule of implantation points, and generate a tracking image containing the target implantation point; determine real-time tracking trajectory data of the target implantation point based on the tracking image and the continuous multiple frames of blood vessel images; And determine a real-time beating cycle of a brain blood vessel of an implantation region and a predicted trajectory result of the target implantation point based on the real-time tracking trajectory data; A planning module is configured to plan an implantation strategy of an electrode according to the real-time beating cycle and the predicted trajectory result.

10. A computer readable storage medium storing a computer program, characterized in that, The computer program is executed by the processor to realize the steps of the method for planning an electrode implantation point when the brain surface beats according to any one of claims 1 to 8.

Images