Medical puncture robot

Abstract

The application provides a medical puncture robot, which comprises a positioning device and an eyeball puncture device connected in communication, and the positioning device comprises: an acquisition module for acquiring an initial needle insertion position of a target eyeball; a first control module for controlling the eyeball puncture device to insert an initial puncture needle at the initial needle insertion position of the target eyeball and record a needle insertion posture of the initial puncture needle; a determination module for determining a target needle insertion position of the target eyeball according to a bleeding area of the target eyeball after the initial puncture needle is inserted; a second control module for controlling the eyeball puncture device to insert a target puncture needle at the target needle insertion position of the target eyeball according to the needle insertion posture to complete eyeball puncture; and the diameter of the initial puncture needle is greater than that of the target puncture needle. The puncture needle can be inserted into the eyeball for puncture, thereby avoiding the problem that the puncture needle cannot be accurately inserted into a puncture point when the area of the eyeball is very small or the bending resistance of the puncture needle is very low, and the puncture effect is improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of medical devices, in particular to a medical puncture robot. BACKGROUND

[0002] Ocular puncture refers to using a thin needle to enter the intraocular cavity through the conjunctiva or cornea. Traditional puncture technology mainly directly punctures through manual operation of the puncture needle.

[0003] However, when the ocular area is very small or the puncture needle has very low bending resistance, the operator cannot accurately insert the puncture needle into the puncture point, resulting in poor puncture effect. SUMMARY

[0004] Therefore, the purpose of the present application is to provide a medical puncture robot which can insert a puncture needle into an ocular for puncture, thereby avoiding the problem that the puncture needle cannot be accurately inserted into the puncture point when the ocular area is very small or the puncture needle has very low bending resistance, and improving the puncture effect.

[0005] In a first aspect, the embodiments of the present application provide a medical puncture robot, which comprises a positioning device and an ocular puncture device in communication connection, wherein the positioning device comprises:

[0006] an acquisition module configured to acquire an initial needle insertion position of a target ocular, wherein the initial needle insertion position is determined according to an ocular image of the target ocular;

[0007] a first control module configured to control the ocular puncture device to insert an initial puncture needle at the initial needle insertion position of the target ocular until the initial puncture needle reaches a first preset area of the target ocular, and to record a needle insertion posture of the initial puncture needle;

[0008] a determination module configured to determine a target needle insertion position of the target ocular according to a bleeding area of the target ocular after the initial puncture needle is inserted;

[0009] a second control module configured to control the ocular puncture device to insert a target puncture needle at the target needle insertion position of the target ocular according to the needle insertion posture until the target puncture needle reaches a second preset area of the target ocular to complete ocular puncture, wherein a diameter of the initial puncture needle is greater than a diameter of the target puncture needle.

[0010] In a possible implementation, the acquisition module comprises:

[0011] an acquisition unit configured to acquire a first ocular image of the target ocular and a second ocular image obtained by performing edge extraction on the first ocular image;

[0012] The determining unit is configured to determine a position meeting a preset needle insertion condition in a region between an outer sclera contour and an inner sclera contour in the second eyeball image, to obtain an initial needle insertion position of the target eyeball.

[0013] In a possible implementation, the acquisition unit is specifically configured to:

[0014] acquire initial second eyeball images corresponding to the first eyeball image in multiple preset scales;

[0015] calculate a weight corresponding to each initial second eyeball image according to a preset scale corresponding to the initial second eyeball image;

[0016] perform weighted summation on all initial second eyeball images according to the weight corresponding to each initial second eyeball image, to obtain a target second eyeball image.

[0017] In a possible implementation, when the acquisition unit performs the acquisition of the initial second eyeball images corresponding to the first eyeball image in multiple scales, the acquisition unit is specifically configured to:

[0018] perform convolution on the first eyeball image through a Gaussian kernel of each preset scale, to obtain a convolution image in each preset scale;

[0019] perform edge extraction on the convolution image in each preset scale, to obtain an initial second eyeball image in each preset scale.

[0020] In a possible implementation, when the acquisition unit performs the calculation of the weight corresponding to each initial second eyeball image according to the preset scale corresponding to the initial second eyeball image, the acquisition unit is specifically configured to:

[0021] sort all initial second eyeball images according to the corresponding preset scale in ascending order, to obtain a serial number corresponding to each initial second eyeball image;

[0022] calculate the weight corresponding to each initial second eyeball image according to the serial number corresponding to the initial second eyeball image and the number of preset scales.

[0023] In a possible implementation, when the acquisition unit performs the calculation of the weight corresponding to each initial second eyeball image according to the serial number corresponding to the initial second eyeball image and the number of preset scales, the acquisition unit is specifically configured to:

[0024] substitute the serial number corresponding to each initial second eyeball image and the number of preset scales into the following formula, to obtain the weight corresponding to each initial second eyeball image;

[0025]

[0026] wherein ω i is a weight corresponding to the initial second eye image of the sequence number i, and n is a number of preset scales.

[0027] In a possible implementation, the determining unit, when determining the outer scleral contour and the inner scleral contour in the second eye image, is specifically configured to:

[0028] For each first circle in the second eye image, the number of pixel points on all circles in the first eye image that meet the equation of the first circle is counted to obtain a score corresponding to the first circle;

[0029] The first circle with the highest score is determined as the outer scleral contour of the target eye;

[0030] A concentric circle of the first circle with the highest score in the second eye image is determined as a second circle;

[0031] The second circle with the largest radius is determined as the inner scleral contour of the target eye.

[0032] In a possible implementation, the determining module is specifically configured to:

[0033] The center point of the hemorrhage area is determined as the target needle insertion position of the target eye.

[0034] In a possible implementation, the second control module is specifically configured to:

[0035] The current position of the target puncture needle is obtained.

[0036] It is determined whether the current position is the target needle insertion position.

[0037] If the current position is the target needle insertion position, the eye puncture device is controlled to insert the target puncture needle in the needle insertion posture.

[0038] In a possible implementation, the second control module is further configured to:

[0039] If the current position is not the target needle insertion position, a moving speed of the target puncture needle corresponding to the current position is obtained, and it is determined whether the target puncture needle can reach the target needle insertion position according to the current position and the moving speed.

[0040] If the target puncture needle cannot reach the target needle insertion position, the puncture path of the target puncture needle is adjusted so that the target puncture needle can reach the target needle insertion position.

[0041] The medical puncture robot provided by the embodiment of the present application comprises a positioning device and an eyeball puncture device which are communicatively connected, and the positioning device comprises: an acquisition module, configured to acquire an initial needle insertion position of a target eyeball; the initial needle insertion position is determined according to an eyeball image of the target eyeball; a first control module, configured to control the eyeball puncture device to insert an initial puncture needle at the initial needle insertion position of the target eyeball until the initial puncture needle reaches a first preset area of the target eyeball and then withdraws; and record a needle insertion posture of the initial puncture needle; a determination module, configured to determine a target needle insertion position of the target eyeball according to a bleeding area of the target eyeball after the initial puncture needle is inserted; and a second control module, configured to control the eyeball puncture device to insert a target puncture needle at the target needle insertion position of the target eyeball according to the needle insertion posture until the target puncture needle reaches a second preset area of the target eyeball and then completes eyeball puncture; the diameter of the initial puncture needle is greater than the diameter of the target puncture needle. The medical puncture robot is used to first insert a puncture needle with a larger diameter into a target eyeball, and then determine a needle insertion position of a puncture needle with a smaller diameter according to a bleeding area of the puncture needle with the larger diameter, so that the puncture needle with the smaller diameter is inserted into the target eyeball along a needle insertion path of the puncture needle with the larger diameter to perform puncture, thereby avoiding the problem that the puncture needle cannot be accurately inserted into a puncture point when the eyeball area is very small or the puncture needle has very low bending resistance, and improving the puncture effect. BRIEF DESCRIPTION OF DRAWINGS

[0042] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following will briefly introduce the drawings needed to be used in the embodiments. It should be understood that the following drawings only show some embodiments of the present application, and therefore should not be regarded as a limitation on the scope. For those skilled in the art, other related drawings can also be obtained without creative labor.

[0043] Figure 1 A structure schematic diagram of a medical puncture robot provided by the embodiment of the present application is shown;

[0044] Figure 2 A structure schematic diagram of an acquisition module provided by the embodiment of the present application is shown;

[0045] Figure 3 A flowchart of acquiring a second eyeball image provided by the embodiment of the present application is shown;

[0046] Figure 4 A flowchart of determining a sclera outer contour and a sclera inner contour in a second eyeball image provided by the embodiment of the present application is shown. DETAILED DESCRIPTION

[0047] To make the objectives, technical solutions and advantages of the embodiments of the present application clearer, the following will be combined with the accompanying drawings for the embodiments of the present application to make a clear and complete description of the technical solutions in the embodiments of the present application. It should be understood that the accompanying drawings in the present application are only for the purpose of illustration and description, and are not used to limit the protection scope of the present application. In addition, it should be understood that the schematic drawings are not drawn according to the actual proportions. The flowcharts used in the present application show the operations implemented according to some embodiments of the present application. It should be understood that the operations of the flowcharts can not be implemented in sequence, and the steps without logical context relationship can be reversed in sequence or implemented simultaneously. In addition, one or more other operations can be added to the flowcharts or one or more operations can be removed from the flowcharts under the guidance of the content of the present application.

[0048] In addition, the described embodiments are only some of the embodiments of the present application, not all the embodiments. The components of the embodiments of the present application described and shown in the accompanying drawings can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present application provided in the accompanying drawings is not intended to limit the scope of the claimed present application, but only represents selected embodiments of the present application. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without creative labor fall within the scope of the present application.

[0049] In order to enable those skilled in the art to use the content of the present application, the following implementation is given in combination with a specific application scenario "medical device field". Those skilled in the art can apply the general principles defined herein to other embodiments and application scenarios without departing from the spirit and scope of the present application. Although the present application is mainly described in connection with the "medical device field", it should be understood that this is only an exemplary embodiment.

[0050] It should be noted that the term "comprising" will be used in the embodiments of the present application to indicate the presence of the features declared thereafter, but does not exclude the addition of other features.

[0051] Reference Figure 1 As shown in the figure, a structure schematic diagram of a medical puncture robot provided by the embodiments of the present application is shown, which includes a positioning device 101 and an eyeball puncture device 102 connected in communication, the positioning device 101 includes:

[0052] The acquisition module 101 is configured to acquire an initial needle insertion position of a target eyeball.

[0053] In the implementation of the present application, the initial needle insertion position is determined according to an eyeball image of the target eyeball. The target eyeball is an eyeball that needs to be punctured. The eyeball can be an eyeball of any organism, such as a mouse, etc.

[0054] As Figure 2 shown, a structure schematic diagram of the acquisition module 101 provided by the embodiment of the application is provided:

[0055] The acquisition unit 201 is configured to acquire a first eyeball image of a target eyeball and a second eyeball image obtained by performing edge extraction on the first eyeball image.

[0056] In the embodiment of the application, a high-resolution camera is used to capture an image of a mouse eyeball surface to obtain an original eyeball image; the original eyeball image is subjected to bilateral filtering through the following formula to obtain the first eyeball image:

[0057]

[0058] wherein I(x, y) is the first eyeball image, x is the horizontal direction size of the first eyeball image, y is the vertical direction size of the first eyeball image, p is the center pixel point of the original eyeball image, S is the set of pixel points in the original eyeball image, q is any pixel point in the original eyeball image, I(p) is the pixel value of the center pixel point of the original eyeball image, I(q) is the pixel value of the pixel point q in the original eyeball image, i is the horizontal coordinate of the center pixel point of the original eyeball image, j is the vertical coordinate of the center pixel point of the original eyeball image, m is the horizontal coordinate of the pixel point q in the original eyeball image, n is the vertical coordinate of the pixel point q in the original eyeball image, σ s and σ r are both preset filtering coefficients (used to represent the filtering degree).

[0059] Here, the bilateral filtering of the original eyeball image highlights the edges, and the bilateral filter can smooth the image while retaining the edge information of the image.

[0060] Further, as shown in Figure 3 , a flowchart for acquiring the second eyeball image is provided, which is applied to the acquisition unit 201 and includes the following steps:

[0061] S301, acquiring an initial second eyeball image under a plurality of preset scales corresponding to the first eyeball image.

[0062] In the embodiment of the application, a plurality of preset scales are preset in advance, and the initial second eyeball image under the plurality of preset scales corresponding to the first eyeball image is acquired.

[0063] Specifically, when the acquisition unit 201 performs the step of acquiring the initial second eyeball image under the plurality of scales corresponding to the first eyeball image, it is specifically configured to:

[0064] Step one, performing convolution on the first eyeball image through the Gaussian kernel of each preset scale to obtain the convolution image under each preset scale.

[0065] In the embodiments of the present application, the scale of the Gaussian kernel is represented by the standard deviation, i.e. the preset scale can also be referred to as a preset standard deviation. The first eye image is convolved by the Gaussian kernel of each preset scale to obtain a convolution image under each preset scale according to the following formula:

[0066] I smooth (x,y,σ i )=G(x,y,σ i )*I(x,y);

[0067] wherein I smooyh (x,y,σ i ) is the convolution image under the i-th preset scale, G(x,y,σ i ) is the Gaussian kernel of the i-th preset scale, and * is the convolution operation.

[0068] Step two, edge extraction is performed on the convolution image under each preset scale to obtain an initial second eye image under each preset scale.

[0069] In the embodiments of the present application, the Sobel operator is used to perform edge extraction on the convolution image under each preset scale, and the extraction formula is as follows:

[0070]

[0071] wherein M(x,y,σ i ) is the initial second eye image under the i-th preset scale, G x (x,y,σ i ) 2 is the horizontal direction gradient of the convolution image under the i-th preset scale, G y (x,y,σ i ) is the vertical direction gradient of the convolution image under the i-th preset scale, is the partial derivative.

[0072] S302, according to the preset scale corresponding to each initial second eye image, the weight corresponding to each initial second eye image is calculated.

[0073] In the embodiments of the present application, all the initial second eye images are sorted according to the corresponding preset scale in ascending order to obtain the sequence number corresponding to each initial second eye image; and the weight corresponding to each initial second eye image is calculated according to the sequence number corresponding to each initial second eye image and the number of preset scales.

[0074] For example, the preset scale corresponding to the first initial second eyeball image is a, the preset scale corresponding to the second initial second eyeball image is b, and the preset scale corresponding to the third initial second eyeball image is c; wherein b < a < c, so the serial number corresponding to the first initial second eyeball image is 2, the serial number corresponding to the second initial second eyeball image is 1, and the serial number corresponding to the third initial second eyeball image is 3.

[0075] Specifically, the serial number corresponding to each initial second eyeball image and the number of preset scales are substituted into the following formula to obtain the weight corresponding to each initial second eyeball image.

[0076]

[0077] wherein ω i is the weight corresponding to the initial second eyeball image with the serial number i, and n is the number of preset scales. i

[0078] Here, the initial second eyeball images under different preset scales are not distinguished, the smaller preset scale can capture the details of the image, and the larger preset scale can smooth the noise, so the present application adopts a bimodal distribution as the basis for calculating the weight, that is, the above formula for calculating the weight.

[0079] S303, weighted summing all initial second eyeball images according to the weight corresponding to each initial second eyeball image to obtain a target second eyeball image.

[0080] The determining unit 202 is configured to determine a position meeting a preset needle insertion condition in the region between the outer sclera contour and the inner sclera contour in the second eyeball image to obtain an initial needle insertion position of the target eyeball.

[0081] In the embodiment of the present application, the preset needle insertion condition is a needle insertion position constraint condition preset by the user according to the position of the eyeball puncture device and the position of the target eyeball. For example, if the initial needle insertion position is preset to be on the left side of the target eyeball, the initial needle insertion position will be selected in the left half of the region between the outer sclera contour and the inner sclera contour; the user can determine the specific content of the needle insertion condition according to the actual situation.

[0082] Referring to Figure 4 Fig. 2 shows a flowchart of a process for determining the outer sclera contour and the inner sclera contour in the second eyeball image, which is applied to the determining unit 202 and specifically includes:

[0083] S401, for each first circle in the second eyeball image, counting the number of pixel points meeting the equation of the first circle on all circles in the first eyeball image to obtain a score corresponding to the first circle.

[0084] ​In the embodiments of the present application, a circle in the first eyeball image is detected based on the Hough circle transform; a circle in the second eyeball image is detected based on the Hough circle transform to obtain a first circle; edge pixel points of all the circles detected in the first eyeball image are mapped into a parameter space; and for each first circle in the second eyeball image, the number of edge pixel points in the parameter space that meet the equation of the first circle is counted. Here, if the coordinates of the edge pixel points are substituted into the equation of the first circle, the equation still holds, which means that the edge pixel points meet the equation of the first circle.

[0085] For example, if the number of edge pixel points in the parameter space that meet the equation of the first circle A is 10, the score corresponding to the first circle A is 10.

[0086] S402, determining the first circle with the highest score as the outer contour of the sclera of the target eyeball.

[0087] S403, determining the concentric circle of the first circle with the highest score in the second eyeball image as a second circle.

[0088] In the embodiments of the present application, the concentric circle of the first circle with the highest score refers to a circle with the same center as the first circle with the highest score.

[0089] S404, determining the second circle with the largest radius as the inner contour of the sclera of the target eyeball.

[0090] The first control module 102 is configured to control the eyeball puncture device to insert an initial puncture needle at an initial needle insertion position of the target eyeball until the initial puncture needle reaches a first preset area of the target eyeball, and then withdraws; and record the needle insertion posture of the initial puncture needle.

[0091] In the embodiments of the present application, the eyeball puncture device can refer to a mechanical arm of a medical puncture robot. The first preset area is generally a certain area in the target eyeball for puncture and located in front of the second preset area. For example, if the second preset area is the retina, the first preset area can be the sclera.

[0092] The needle insertion posture can include the angle between the initial puncture needle and the center point of the first preset area, the Euclidean distance between the initial puncture needle and the center point of the first preset area, etc.

[0093] The determination module 103 is configured to determine a target needle insertion position of the target eyeball according to the bleeding area of the target eyeball after the initial puncture needle is inserted.

[0094] In the embodiment of the present application, since the target eyeball moves, the real needle insertion position of the initial puncture needle has changed, so it is necessary to re-determine the needle insertion position of the initial puncture needle, i.e. the target needle insertion position. The target needle insertion position is the current actual needle insertion position of the initial puncture needle. So that the actual needle insertion position of the target puncture needle is the same as the actual needle insertion position of the initial puncture needle.

[0095] Specifically, the determining module 103 specifically determines the bleeding mark of each pixel point in the image of the target eyeball after the initial puncture needle is inserted, to obtain the bleeding area, by the following formula:

[0096]

[0097] Wherein, R G_ratio (z1, z2) is the pixel ratio of the R channel (red) and the G channel (green) of the pixel point (z1, z2) in the image of the target eyeball after the initial puncture needle is inserted, R(z1, z2) is the pixel value corresponding to the R channel (red) of the pixel point (z1, z2), G(z1, z2) is the pixel value corresponding to the G channel (green) of the pixel point (z1, z2), ∈ is a preset color deviation value, B final (z1, z2) is the bleeding mark of the pixel point (z1, z2), T G_ratio is a preset ratio; B final (z1, z2) is 1, indicating that the pixel point (z1, z2) is a bleeding point.

[0098] Specifically, the center point of the bleeding area is determined as the target needle insertion position of the target eyeball.

[0099] The second control module 104 is configured to control the eyeball puncture device to insert the target puncture needle at the target needle insertion position of the target eyeball in the needle insertion posture until the target puncture needle reaches the second preset area of the target eyeball to complete the eyeball puncture.

[0100] In the embodiment of the present application, the target puncture needle refers to the puncture needle used for eyeball puncture. The diameter of the initial puncture needle is greater than the diameter of the target puncture needle. The target puncture needle completes the eyeball puncture when it reaches the second preset area of the target eyeball. The target puncture needle is inserted at the target needle insertion position of the target eyeball in the needle insertion posture to make the target puncture needle inserted into the target eyeball along the needle insertion path of the initial puncture needle inserted into the target eyeball, so as to avoid the bending of the target puncture needle and the problem that the puncture needle cannot be accurately inserted into the puncture point. Moreover, the present application can avoid the problem that the puncture needle cannot be accurately inserted into the puncture point due to the small area of the eyeball by automatic puncture of the medical puncture robot.

[0101] The second control module 104 is specifically configured to:

[0102] Step one, obtaining the current position of the target puncture needle.

[0103] In the embodiments of the present application, the current position of the target puncture needle is acquired in real time during the process of inserting the target puncture needle.

[0104] Step two, judging whether the current position is the target needle insertion position.

[0105] Step three, if the current position is the target needle insertion position, controlling the eyeball puncture device to insert the target puncture needle according to the needle insertion posture.

[0106] Optionally, during the insertion process, the current eyeball image is captured in real time by two cameras respectively, and the current needle insertion depth of the target puncture needle is calculated according to the current eyeball image; if the current needle insertion depth is the needle insertion depth corresponding to the second preset region of the target eyeball, it is indicated that the target puncture needle has reached the second preset region, and the eyeball puncture is completed.

[0107] Here, the formula for calculating the current needle insertion depth of the target puncture needle is as follows:

[0108]

[0109] Wherein, Z is the depth of the target puncture needle, f is the distance (i.e. the baseline distance) of the two cameras, B is the focal length of the camera, and d is the pixel difference of the target puncture needle in the current eyeball image captured by the two cameras.

[0110] Step four, if the current position is not the target needle insertion position, the moving speed of the target puncture needle corresponding to the current position is acquired; and according to the current position and the moving speed, it is judged whether the target puncture needle can reach the target needle insertion position.

[0111] In the embodiments of the present application, the light flow technology is used to track the target puncture needle position recognized by the CNN in the continuous image frames, to estimate the position information and the moving speed of the target puncture needle after a period of time. The result of the light flow tracking is processed by Kalman filtering to reduce the noise influence and optimize the position estimation of the target puncture needle.

[0112] Here, the state updating process of the Kalman filter is as follows:

[0113] (1) Define the state vector X of the target puncture needle at the current time t, including the position information (x, y) of the target puncture needle and the moving speed t t t

[0114]

[0115] (2) Define the state transition equation: it is assumed that the motion of the target puncture needle between time t and t+1 can be described by a linear model: X​​​t+1 = FX t + Bu t + w t ; where X t+1 is the state vector of the target needle at the next time step t+1, F is the state transition matrix, B is the control input matrix (here, zero), u t is the control input (here, zero), w t is the process noise; F can be set as:

[0116] where Δt is the prediction step.

[0117] (3) Predict the state vector at the next time step based on (2)

[0118]

[0119] where X is the state estimate at the current time step.

[0120] (4) Predict the covariance matrix

[0121]

[0122] where P t is the covariance matrix at the current time step, Q is the process noise covariance matrix, and T is the transpose.

[0123] (5) Update the Kalman filter with the optical flow measurements:

[0124]

[0125] where Z t+1 is the optical flow measurements, H is the observation matrix, and Y t+1 is the measurement residual.

[0126] (6) Calculate the Kalman gain:

[0127]

[0128] where R is the measurement noise covariance matrix.

[0129] (7) Update the state estimate:

[0130]

[0131] (8) Update the covariance matrix:

[0132]

[0133] wherein I is an identity matrix.

[0134] Step five, if the target needle insertion position cannot be reached, the puncture path of the target puncture needle is adjusted so that the target puncture needle can reach the target needle insertion position.

[0135] The medical puncture robot provided by the embodiment of the present application comprises a positioning device and an eyeball puncture device which are communicatively connected, and the positioning device comprises: an acquisition module configured to acquire an initial needle insertion position of a target eyeball; the initial needle insertion position is determined according to an eyeball image of the target eyeball; a first control module configured to control the eyeball puncture device to insert an initial puncture needle at the initial needle insertion position of the target eyeball until the initial puncture needle reaches a first preset area of the target eyeball and then withdraws; and record a needle insertion posture of the initial puncture needle; a determination module configured to determine a target needle insertion position of the target eyeball according to a bleeding area of the target eyeball after the initial puncture needle is inserted; and a second control module configured to control the eyeball puncture device to insert a target puncture needle at the target needle insertion position of the target eyeball according to the needle insertion posture until the target puncture needle reaches a second preset area of the target eyeball and then completes eyeball puncture; the diameter of the initial puncture needle is greater than the diameter of the target puncture needle. The medical puncture robot is used to first insert a puncture needle with a larger diameter into a target eyeball, and then determine a needle insertion position of a puncture needle with a smaller diameter according to a bleeding area of the puncture needle with the larger diameter, so that the puncture needle with the smaller diameter is inserted into the target eyeball along a needle insertion path of the puncture needle with the larger diameter to perform puncture, thereby avoiding the problem that the puncture needle cannot be accurately inserted into a puncture point when the eyeball area is very small or the puncture needle has very low bending resistance, and improving the puncture effect.

[0136] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the system and device described above can refer to the corresponding process in the method embodiment, and will not be described herein again. In the several embodiments provided in the present application, it should be understood that the disclosed system, device and method can be implemented by other means. The device embodiments described above are only schematic, for example, the division of the modules is only a logical function division, and actual implementation can have another division manner, for example, a plurality of modules or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the displayed or discussed each other can be indirect coupling or communication connection through some communication interface, device or module, which can be electrical, mechanical or other forms.

[0137] The modules described as separate components may or may not be physically separate, and the components displayed as modules may or may not be physical units, i.e., may be located in one place, or may be distributed to multiple network units. Part or all of the units can be selected according to actual needs to achieve the purpose of the embodiment.

[0138] In addition, each functional unit in each embodiment of the present application can be integrated in one processing unit, or each unit can be physically present alone, or two or more units can be integrated in one unit.

[0139] If the functions are realized in the form of software functional units and sold or used as independent products, they can be stored in a non-volatile computer readable storage medium executable by a processor. Based on this understanding, the technical solutions of the present application essentially or the part of the prior art or the part of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a storage medium, including a plurality of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the information processing method described in each embodiment of the present application. The foregoing storage medium includes: U disk, mobile hard disk, ROM, RAM, magnetic disk or optical disk, and various program code storage media.

[0140] The above is only a specific embodiment of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art can easily think of changes or replacements within the technical scope disclosed in the present application, which should be covered within the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. A medical puncture robot characterized by, The medical puncture robot comprises a positioning device and an eyeball puncture device connected in communication, the positioning device comprises: An acquisition module is configured to acquire an initial needle insertion position of a target eyeball, wherein the initial needle insertion position is determined according to an eyeball image of the target eyeball; A first control module is configured to control the eyeball puncture device to insert an initial puncture needle at the initial needle insertion position of the target eyeball until the initial puncture needle reaches a first preset region of the target eyeball, and to record a needle insertion posture of the initial puncture needle; A determination module is configured to determine a target needle insertion position of the target eyeball according to a bleeding region of the target eyeball after the initial puncture needle is inserted; A second control module is configured to control the eyeball puncture device to insert a target puncture needle at the target needle insertion position of the target eyeball according to the needle insertion posture until the target puncture needle reaches a second preset region of the target eyeball to complete eyeball puncture, wherein a diameter of the initial puncture needle is greater than a diameter of the target puncture needle.

2. The medical puncture robot according to claim 1, characterized by, The acquisition module comprises: An acquisition unit is configured to acquire a first eyeball image of the target eyeball and a second eyeball image obtained by performing edge extraction on the first eyeball image; A determination unit is configured to determine a position meeting a preset needle insertion condition in a region between an outer sclera contour and an inner sclera contour in the second eyeball image to obtain the initial needle insertion position of the target eyeball.

3. The medical puncture robot according to claim 2, characterized by, The acquisition unit is specifically configured to: Acquire initial second eyeball images under a plurality of preset scales corresponding to the first eyeball image; Calculate weights corresponding to the initial second eyeball images according to the preset scales corresponding to the initial second eyeball images; Perform weighted summation on all the initial second eyeball images according to the weights corresponding to the initial second eyeball images to obtain a target second eyeball image.

4. The medical puncture robot according to claim 3, characterized by, When performing the acquiring of the initial second eyeball images under a plurality of scales corresponding to the first eyeball image, the acquisition unit is specifically configured to: Convolve the first eyeball image through a Gaussian kernel of each preset scale to obtain convolution images under the preset scales; Perform edge extraction on the convolution images under the preset scales to obtain the initial second eyeball images under the preset scales.

5. The medical puncture robot according to claim 3, characterized by, When performing the calculating of the weights corresponding to the initial second eyeball images according to the preset scales corresponding to the initial second eyeball images, the acquisition unit is specifically configured to: Sort all the initial second eyeball images according to the corresponding preset scales in ascending order to obtain sequence numbers corresponding to the initial second eyeball images; Calculate the weights corresponding to the initial second eyeball images according to the sequence numbers corresponding to the initial second eyeball images and a quantity of the preset scales.

6. The medical puncture robot according to claim 5, characterized by, When performing the calculating of the weights corresponding to the initial second eyeball images according to the sequence numbers corresponding to the initial second eyeball images and the quantity of the preset scales, the acquisition unit is specifically configured to: Substitute the sequence numbers corresponding to the initial second eyeball images and the quantity of the preset scales into the following formula to obtain the weights corresponding to the initial second eyeball images; where ω i is the weight corresponding to the initial second eye image of sequence number i, and n is the number of preset scales.

7. The medical puncture robot according to claim 2, wherein, When determining the outer sclera contour and the inner sclera contour in the second eyeball image, the determination unit is specifically configured to: For each first circle in the second eyeball image, the number of pixel points on all circles in the first eyeball image that meet the equation of the first circle is counted to obtain a score corresponding to the first circle; a first circle with the highest score is determined as the outer scleral contour of the target eyeball; a concentric circle of the first circle with the highest score in the second eyeball image is determined as a second circle; a second circle with the largest radius is determined as the inner scleral contour of the target eyeball.

8. The medical puncture robot according to claim 1, characterized by, The determining module is specifically configured to: determine a center point of the hemorrhage area as a target needle insertion position of the target eyeball.

9. The medical puncture robot according to claim 1, wherein, The second control module is specifically configured to: obtain a current position of the target puncture needle; determine whether the current position is the target needle insertion position; if the current position is the target needle insertion position, control the eyeball puncture device to insert the target puncture needle in the needle insertion posture.

10. The medical puncture robot according to claim 9, characterized by, The second control module is further configured to: if the current position is not the target needle insertion position, obtain a moving speed of the target puncture needle corresponding to the current position; and determine whether the target puncture needle can reach the target needle insertion position according to the current position and the moving speed; if the target puncture needle cannot reach the target needle insertion position, adjust a puncture path of the target puncture needle so that the target puncture needle can reach the target needle insertion position.

Images