Electrode direction identification method, device, equipment, medical system, medium and product

Abstract

The embodiment of the present invention discloses an electrode direction identification method, device, equipment, medical system, medium and product, wherein the method comprises: obtaining an original CT image and an X-ray plane image containing a target object; identifying the electrode position information of the target electrode in the original CT image, and replacing the area in the original CT image at least including the target electrode with the corresponding electrode template according to the electrode position information, to obtain a reference electrode template CT image; the target electrode is a directional electrode implanted in the target object; adjusting the electrode direction of the electrode template in the reference electrode template CT image, and obtaining a CT image coronal projection image corresponding to the reference electrode template CT image under multiple electrode directions; determining the electrode direction of the directional electrode implanted in the target object according to the similarity between the CT image coronal projection image and the X-ray plane image under each electrode direction. The embodiment of the present invention can automatically identify the orientation of the implanted electrode.

Description

Technical Field

[0001] Embodiments of the present invention relate to the field of medical image processing technology, and in particular, to an electrode direction recognition method, device, equipment, medical system, medium and product. Background Art

[0002] Deep brain stimulation (DBS) is an invasive neuromodulation technology used to change the electrical activity and function of brain neural circuits and networks. Currently, directional electrodes are often used to replace traditional electrodes in this technology. Before electrical stimulation, the electrode orientation (direction) of the directional electrode needs to be determined to achieve stimulation of brain tissue in a specific direction.

[0003] However, in the existing technology for determining directional electrodes, doctors usually manually compare the patient's cranial X-ray images with standard images, which cannot be automatically identified and has low accuracy. Alternatively, the electrode direction is determined by analyzing and quantitatively calculating the imaging artifacts of the directional electrodes in the postoperative CT (Computed Tomography) images. In this method, the metal artifact characteristics cannot accurately indicate the electrode direction. Summary of the invention

[0004] Embodiments of the present invention provide an electrode direction identification method, device, equipment, medical system, medium and product, which can automatically, comprehensively and accurately identify the directional electrode orientation after electrode implantation.

[0005] In a first aspect, an embodiment of the present invention provides a method for identifying an electrode direction, the method comprising:

[0006] Acquire an original CT image and an X-ray plane image containing a target object; wherein the target object is an object implanted with directional electrodes;

[0007] Identify electrode position information of a target electrode in an original CT image, and replace a region in the original CT image at least including the target electrode with a corresponding electrode template according to the electrode position information, to obtain a reference electrode template CT image; wherein the target electrode is at least one directional electrode implanted in the target object;

[0008] Adjusting the electrode direction of the electrode template in the reference electrode template CT image, and obtaining a coronal projection image of the CT image corresponding to the reference electrode template CT image under multiple electrode directions; wherein the electrode direction is the electrode orientation of the directional electrode;

[0009] The electrode direction of the directional electrode implanted in the target object is determined according to the similarity between the coronal projection image of the CT image and the X-ray plane image under each electrode direction.

[0010] In a second aspect, an embodiment of the present invention provides an electrode direction identification device, the device comprising:

[0011] An original image acquisition module, used to acquire an original CT image and an X-ray plane image containing a target object; wherein the target object is an object implanted with directional electrodes;

[0012] A reference image acquisition module, used to identify the electrode position information of the target electrode in the original CT image, and replace the area in the original CT image at least including the target electrode with the corresponding electrode template according to the electrode position information, to obtain a reference electrode template CT image; wherein the target electrode is at least one directional electrode implanted in the target object;

[0013] A multi-angle reference image acquisition module is used to adjust the electrode direction of the electrode template in the reference electrode template CT image, and obtain a coronal projection image of the CT image corresponding to the reference electrode template CT image under multiple electrode directions; wherein the electrode direction is the electrode orientation of the directional electrode;

[0014] The electrode direction determination module is used to determine the electrode direction of the directional electrode implanted in the target object according to the similarity between the coronal projection image of the CT image and the X-ray plane image under each electrode direction.

[0015] In a third aspect, an embodiment of the present invention further provides a computer device, the computer device comprising:

[0016] one or more processors;

[0017] A memory for storing one or more programs;

[0018] When one or more programs are executed by one or more processors, the one or more processors implement the electrode direction identification method provided by any embodiment of the present invention.

[0019] In a fourth aspect, an embodiment of the present invention further provides a medical system, characterized in that the medical system comprises:

[0020] An implantable medical device, the implantable medical device at least comprises a pulse generator implanted in the body of a target object and an electrode lead implanted in the target object, the pulse generator is connected to the electrode lead, and the implanted end of the electrode lead is provided with at least one set of directional electrodes;

[0021] monitor;

[0022] The processor is configured to obtain postoperative images of the target object after the electrode wire is implanted, execute the electrode direction recognition method provided by any embodiment of the present invention, determine the direction of the directional electrode in the electrode wire of the target object, and display the direction of the directional electrode in the electrode wire using a display.

[0023] In a fifth aspect, an embodiment of the present invention further provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the electrode direction identification method provided in any embodiment of the present invention.

[0024] In a sixth aspect, the embodiments of the present disclosure further provide a computer program product, including a computer program, which, when executed by a processor, implements the electrode direction identification method provided in any embodiment of the present invention.

[0025] The embodiments of the above invention have the following advantages or beneficial effects:

[0026] The embodiment of the present invention obtains an original CT image and an X-ray plane image containing a target object; wherein the target object is an object implanted with a directional electrode; identifies the electrode position information of the target electrode in the original CT image, and replaces at least the area including the target electrode in the original CT image with a corresponding electrode template according to the electrode position information, thereby obtaining a reference electrode template CT image; wherein the target electrode is at least one directional electrode implanted in the target object; adjusts the electrode direction of the electrode template in the reference electrode template CT image, and obtains a CT image coronal projection image corresponding to the reference electrode template CT image under multiple electrode directions; wherein the electrode direction is the electrode orientation of the directional electrode; and determines the electrode orientation of the directional electrode implanted in the target object according to the similarity between the CT image coronal projection image and the X-ray plane image under each electrode direction. The technical solution of the embodiment of the present invention solves the problem in the prior art that the orientation of the directional electrode after electrode implantation cannot be automatically and accurately identified, and can automatically identify the electrode orientation of the implanted electrode based on the X-ray film and CT image of the implanted electrode site. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] Figure 1 is a flow chart of an electrode direction identification method provided by an embodiment of the present invention;

[0028] Figure 2 It is a schematic diagram of a CT scanning computer simulation result of a directional electrode provided by an embodiment of the present invention;

[0029] Figure 3 It is a schematic diagram of a directional electrode image captured by a medical CT under conventional cranial brain scanning parameters provided by an embodiment of the present invention;

[0030] Figure 4 is a flow chart of an electrode direction identification method provided by an embodiment of the present invention;

[0031] Figure 5 is a flow chart of an electrode direction identification method provided by an embodiment of the present invention;

[0032] Figure 6 is a flow chart of an electrode direction identification method provided by an embodiment of the present invention;

[0033] Figure 7 It is a schematic diagram of an electrode and its surrounding space area mask (Lead_mask.nii.gz) provided by an embodiment of the present invention;

[0034] Figure 8 is a schematic diagram of a resampled postoperative CT scan with the electrode and the surrounding spatial area content removed, provided by an embodiment of the present invention;

[0035] Fig. 9 is a schematic diagram of a postoperative CT with an electrode model implanted (CT_with_lead_model.nii.gz) provided in an embodiment of the present invention;

[0036] Fig.10 is a schematic diagram of reconstructing a coronal orthographic projection image from a postoperative CT scan provided by an embodiment of the present invention;

[0037] Fig.11 1 is a schematic diagram of the values ​​of a difference loss function v(θ) and θ' provided in an embodiment of the present invention;

[0038] Fig.12 is a structural schematic diagram of an electrode direction identification device provided by an embodiment of the present invention;

[0039] Fig.13 is a structural schematic diagram of a computer device provided by an embodiment of the present invention;

[0040] Fig.14 It is a schematic diagram of the structure of a medical system provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0041] The present invention will be further described in detail below in conjunction with the accompanying drawings and embodiments. It is to be understood that the specific embodiments described herein are only used to explain the present invention, rather than to limit the present invention. It should also be noted that, for ease of description, only parts related to the present invention, rather than all structures, are shown in the accompanying drawings.

[0042] Figure 1 A flowchart of an electrode direction recognition method provided in an embodiment of the present invention, this embodiment can be applied to the scene of recognizing medical images of parts where electrodes have been implanted, especially the situation of recognizing the electrode direction (orientation) of implanted electrodes. The method can be executed by an electrode direction recognition device, which can be implemented by software and / or hardware and integrated into a computer device with application development function.

[0043] The application scenarios of the electrode direction identification method include deep brain stimulation (DBS), an invasive neuromodulation technology, or the application scenarios of electrode stimulation technology in other parts. In the above scenarios, stimulating electrodes are implanted in specific neural structures or other designated parts of the human brain through stereotactic surgery, and a neurostimulator is implanted in the human body to connect the electrodes, and weak electric pulses that can be adjusted and controlled are emitted, thereby changing the electrical activity and function of the brain neural circuit or other parts, so as to achieve the purpose of controlling and improving the patient's symptoms. An implantable neurostimulation system (an implantable medical system) mainly includes a stimulator implanted in the patient's body and a programmable device set outside the patient's body. Existing neuromodulation technology mainly implants electrodes in specific structures (i.e., targets) in the body through stereotactic surgery, and the stimulator implanted in the patient's body emits discharge pulse width to the target through the electrodes, regulates the electrical activity and function of the corresponding neural structure and network, thereby improving symptoms and relieving pain. The stimulator may be any one of an implantable neural stimulation device, an implantable cardiac stimulation system (also known as a pacemaker), an implantable drug delivery system (IDDS) and a lead switching device. Examples of implantable neural stimulation devices include a deep brain stimulation system (DBS), an implantable cortical nerve stimulation system (CNS), an implantable spinal cord stimulation system (SCS), an implantable sacral nerve stimulation system (SNS), an implantable vagus nerve stimulation system (VNS), etc.

[0044] In some embodiments, the stimulator may include an implantable pulse generator (IPG), an electrode wire, and an extension wire arranged between the implantable pulse generator and the electrode wire, and the data interaction between the implantable pulse generator and the electrode wire is realized through the extension wire, and the implantable pulse generator is arranged in the patient's body. In response to the program-controlled instructions sent by the program-controlled device, the sealed battery and the circuit are used to provide controllable electrical stimulation energy to the body tissue, and one or two controllable specific electrical stimulations are delivered to specific areas of the body tissue through the implanted extension wire and the electrode wire. The extension wire is used in conjunction with the implantable pulse generator as a transmission medium for the electrical stimulation signal, and the electrical stimulation signal generated by the implantable pulse generator is transmitted to the electrode wire. The electrode wire delivers electrical stimulation to specific areas of the body tissue through the electrode contacts thereon. The stimulator is provided with one or more electrode wires on one side or both sides, and a plurality of electrode contacts are provided on the electrode wire.

[0045] In other embodiments, the stimulator may only include an implantable pulse generator and an electrode wire, wherein the implantable pulse generator may be embedded in the patient's skull, and the electrode wire may be implanted in the patient's skull, in which case the implantable pulse generator is directly connected to the electrode wire without the need for extending the wire.

[0046] The electrode wire can be a nerve stimulation electrode, and the electrode wire delivers electrical stimulation to a specific area of ​​tissue in the body through a plurality of electrode contacts. The stimulator is provided with one or more electrode wires on one side or both sides, and a plurality of electrode contacts are provided on the electrode wire, and the electrode contacts can be arranged uniformly or non-uniformly in the circumferential direction of the electrode wire. As an example, the electrode contacts can be arranged in an array of 4 rows and 3 columns (a total of 12 electrode contacts) in the circumferential direction of the electrode wire. The electrode contacts can include stimulation contacts and / or collection contacts. The electrode contacts can be, for example: in the shape of sheets, rings, dots, etc.

[0047] In some possible ways, the stimulated in vivo tissue may be the patient's brain tissue, and the stimulated site may be a specific site of the brain tissue. When the patient's disease type is different, the stimulated site is generally different, and the number of stimulation contacts (single source or multiple sources), the use of one or more (single channel or multiple channels) of specific electrical stimulation signals, and the stimulation parameter data are also different. It can be considered that when the stimulation contacts used are multi-source, multi-channel (multi-channel), a larger amount of data will be generated compared to a single source, single channel.

[0048] The embodiments of the present invention do not limit the types of diseases that can be used, and they can be diseases that can be used for deep brain stimulation (DBS), spinal cord stimulation (SCS), pelvic stimulation, gastric stimulation, peripheral nerve stimulation, and functional electrical stimulation. Among them, the types of diseases that DBS can be used to treat or manage include, but are not limited to: spastic diseases (e.g., epilepsy), pain, migraine, mental illness (e.g., major depressive disorder (MDD)), bipolar disorder, anxiety, post-traumatic stress disorder, mild depression, obsessive-compulsive disorder (OCD), behavioral disorders, mood disorders, memory disorders, mental state disorders, movement disorders (e.g., essential tremor or Parkinson's disease), Huntington's disease, Alzheimer's disease, drug addiction, autism, or other neurological or psychiatric diseases and injuries.

[0049] Stimulation parameters may include: stimulation frequency (for example, the number of electrical stimulation pulse width signals within a unit time of 1s, in Hz), pulse width (the duration of each pulse width, in μs), current amplitude (generally expressed in voltage, that is, the intensity of each pulse width, in V), timing (for example, it can be continuous or triggered), stimulation mode (including one or more of current mode, voltage mode, timed stimulation mode and cyclic stimulation mode), one or more of the upper and lower limits controlled by the doctor (the range adjustable by the doctor) and the upper and lower limits controlled by the patient (the range adjustable by the patient).

[0050] The current new electrode design splits the original circular stimulation output metal contact into multiple pieces, usually divided into three equal pieces, and there are even some special-shaped contact designs. These electrodes support independent regulation of the stimulation output parameters of one or more pieces, thereby achieving stimulation of target tissue in a specific direction, and are therefore called "directional electrodes."

[0051] Currently, there are multiple ways to obtain electrode orientation information after directional electrodes are implanted, including:

[0052] The electrode orientation information is obtained by comparing the brain X-ray film with the pre-taken or drawn standard images. This method has the following defects: (1) It relies on the doctor to manually compare the patient's brain X-ray film image with the standard image, and cannot be automatically identified; (2) The angle difference between the two adjacent standard images determines the minimum accuracy of the electrode angle that can be determined by this method. The current mainstream solution is to divide 360° into 8 images, and the minimum resolution angle is 45°; (3) The X-ray film is a plane image, and it is impossible to accurately know the trajectory of the electrode in three-dimensional space; (4) X-rays can only clearly develop bony structures such as the skull, and cannot show soft tissues such as brain tissue and ventricles, or fluid decomposition, so it is impossible to identify the specific position of the electrode relative to the nuclei in the brain.

[0053] There are also certain defects in the method of determining the electrode orientation by analyzing and quantitatively calculating the imaging artifacts of directional electrodes in postoperative CT images. Due to the current mainstream three-equal-division segmented directional electrodes, although the contact design and marker design have broken the symmetry of the mechanical structure, the metal artifact characteristics presented by these asymmetric structures in CT scans cannot accurately indicate the electrode orientation. The metal artifacts of the three-equal-division metal contact development are six rays of alternating light and dark at equal angles, where each bright line corresponds to the center of the metal contact or the gap between two metal contacts. This is because each gap will produce two dark lines, which are emitted from the edges of two adjacent metal contacts, such as Figure 2 shown. Figure 2 This is the computer simulation result of CT scanning of directional electrodes. The connection between the two ends of the same metal sheet produces a dark line, so each gap corresponds to two dark lines.

[0054] However, the current mainstream medical CT cannot distinguish the locations where the two dark lines are emitted, so it is impossible to know whether the bright area between the two dark lines corresponds to a metal contact or a gap. In other words, one of the two adjacent bright areas corresponds to a contact and the other corresponds to a gap, but which one corresponds to the contact cannot be known from the CT image, as shown in Figure 3. Figure 3 is a directional electrode image taken by medical CT under conventional cranial scanning parameters in the application of DBS technology. It is impossible to distinguish whether the bright line corresponds to an electrode sheet or a gap between electrode sheets.

[0055] In summary, currently, it is difficult to realize automatic, comprehensive, and accurate postoperative directional electrode orientation identification, whether it is cranial X-ray plain film or postoperative CT. Figure 1 The electrode direction identification method shown is used to solve the above problems.

[0056] like Figure 1 As shown, the electrode direction identification method of this embodiment includes the following steps:

[0057] S110 , acquiring an original CT image and an X-ray plane image containing a target object.

[0058] The target object is a subject implanted with directional electrodes. The target object can be a site in a human or animal where a directional electrode is implanted, or any site that requires electrode stimulation.

[0059] The original CT image and X-ray plane image are images collected after the directional electrodes are implanted in the target object. The original CT image contains multiple CT image layers, which can be used to reconstruct a three-dimensional image of the target object. The X-ray plane image is a two-dimensional plane image. To obtain the result, it is necessary to perform rigid registration with the standard head atlas and then perform image analysis.

[0060] S120, identifying electrode position information of a target electrode in an original CT image, and replacing a region in the original CT image at least including the target electrode with a corresponding electrode template according to the electrode position information, to obtain a reference electrode template CT image.

[0061] The target electrode is at least one directional electrode implanted in the target object. The number of target electrodes can be determined according to the requirements of electrical stimulation and structural characteristics.

[0062] The electrode position information of the target electrode in the original CT image can be obtained by identifying the original CT image through a pre-trained electrode recognition model to obtain the coordinate position of the electrode pixel point in each image slice in the original CT image. The coordinates of the electrode pixel points in all image slices in the original CT image are connected to obtain the coordinate track of the target electrode. Each coordinate track corresponds to a target electrode.

[0063] The electrode template corresponding to the target electrode may be an electrode template file describing the three-dimensional structure of the electrode. The target electrode and the electrode template correspond to the same type of electrode. The electrode direction of the target electrode is uncertain, while in the electrode template, the electrode direction is adjustable.

[0064] The electrode template can be placed at the electrode position indicated by the electrode position information identified in the above step to replace the original target electrode, that is, the target electrode is simulated by the electrode template, thereby obtaining a reference electrode template CT image. In this process, it is necessary to ensure that the original target electrode is completely replaced. It can be that at least one image area containing the target electrode template is replaced as a whole.

[0065] S130, adjusting the electrode direction of the electrode template in the reference electrode template CT image, and obtaining a coronal projection image of the CT image corresponding to the reference electrode template CT image under multiple electrode directions.

[0066] The electrode direction is the electrode orientation of the directional electrode.

[0067] The electrode direction of the electrode template in the reference electrode template CT image is adjusted, that is, the electrode direction of the electrode template in the reference electrode template CT image is known, and each adjustment can obtain a reference electrode template CT image with a known electrode direction.

[0068] Furthermore, each reference electrode template CT image is projected in the coronal plane to obtain coronal projection images of the CT image at multiple electrode direction angles.

[0069] S140, determining the electrode direction of the directional electrode implanted in the target object according to the similarity between the coronal projection image of the CT image and the X-ray plane image under each electrode direction.

[0070] The X-ray plane image also contains the target electrode, and the electrode orientation of the target electrode is unknown. The similarity between the CT image coronal projection image and the X-ray plane image under each electrode orientation can be calculated respectively. The electrode orientation corresponding to the CT image coronal projection image with the highest similarity to the X-ray plane image is determined as the electrode orientation of the target electrode implanted in the target object.

[0071] The technical solution of this embodiment is to obtain an original CT image and an X-ray plane image containing a target object; wherein the target object is an object implanted with a directional electrode; identify the electrode position information of the target electrode in the original CT image, and replace the area in the original CT image at least including the target electrode with the corresponding electrode template according to the electrode position information, to obtain a reference electrode template CT image; wherein the target electrode is at least one directional electrode implanted in the target object; adjust the electrode direction of the electrode template in the reference electrode template CT image, and obtain a CT image coronal projection image corresponding to the reference electrode template CT image under multiple electrode directions; wherein the electrode direction is the electrode orientation of the directional electrode; determine the electrode direction of the directional electrode implanted in the target object according to the similarity between the CT image coronal projection image and the X-ray plane image under each electrode direction. The technical solution of the embodiment of the present invention solves the problem that the prior art cannot automatically and accurately identify the orientation of the directional electrode after electrode implantation, and can automatically identify the electrode orientation of the implanted target electrode based on the X-ray film and CT image of the implanted electrode site.

[0072] Figure 4 A flowchart of an electrode direction recognition method provided in an embodiment of the present invention, which belongs to the same inventive concept as the electrode direction recognition method in the above embodiment, further describes the process of obtaining a reference electrode template CT image. The method can be performed by an electrode direction recognition device, which can be implemented by software and / or hardware and integrated into a computer device with application development function.

[0073] like Figure 4 As shown, the electrode direction identification method of this embodiment includes the following steps:

[0074] S210: Acquire an original CT image and an X-ray plane image containing a target object.

[0075] The target object is a subject implanted with directional electrodes.

[0076] The original CT images and X-ray plane images are images acquired after the directional electrodes are implanted in the target object. After the electrode implantation surgery, the surgical site (target object) where the directional electrodes are implanted will mostly not remain in the standard position, so correction is required to ensure that the target object in the image remains in the standard position for image analysis. For example, in DBS, the original CT image may be taken when the head with the directional electrodes implanted is tilted to one side, and rigid registration with the standard head atlas is required before image analysis.

[0077] The original CT image is rigidly calibrated to obtain the original CT image with standard image orientation. This process only allows the image to be translated and rotated, but does not allow it to be scaled, sheared, or locally deformed. Using rigid registration can avoid deformation of the image that is not in line with clinical reality, and only serves to constrain the image orientation.

[0078] S220 , identifying electrode position information of the target electrode in the original CT image.

[0079] The target electrode is at least one directional electrode implanted in the target object.

[0080] S230: Determine a target region including a target electrode in the original CT image according to the electrode position information.

[0081] In an optional implementation, in order to completely replace the original target electrodes with the electrode template, a target region including the target electrodes may be determined first, and then the electrode template may be replaced with the target region as a whole.

[0082] In the process of determining the target area, the electrode position information in the original CT images of different acquisition layers may be obtained first, and then the electrode trajectory coordinates indicated by the electrode position information corresponding to the original CT images of different acquisition layers may be linearly fitted to obtain the fitted electrode trajectory line. The linear fitting may be an algorithm such as linear regression or least squares method. Furthermore, any spatial region including the fitted electrode trajectory line may be used as the target area.

[0083] In an optional embodiment, the process of determining the spatial area including the fitting electrode trajectory line may be: determining a cylindrical area with a preset length as a radius along a direction perpendicular to the fitting electrode trajectory line; and determining a spherical area with a preset length as a radius with the end point of the fitting electrode trajectory line as the center of the sphere; and taking the union of the cylindrical area and the spherical area as the target area.

[0084] S240 , applying a region mask corresponding to the target region to the original CT image to remove the target electrode in the original CT image.

[0085] That is, the area covered by the regional mask is replaced with pure black, and the content of the area outside the area covered by the regional mask remains unchanged, thereby removing the target electrode in the corrected original CT image.

[0086] S250 , according to the electrode trajectory coordinates indicated by the electrode position information, placing the electrode model file that matches the model of the target electrode into the original CT image that has been processed with a regional mask, to obtain a reference electrode template CT image.

[0087] Use the electrode model file to replace the electrode trajectory coordinates of the original target electrode, obtain the CT file with the electrode model inserted, and refer to the electrode template CT image. According to the principle of CT imaging, different density materials have different Hounsfield units (HU) in the CT scanning imaging results. HU is a unit of measurement for measuring the density of a local tissue or organ in the human body. The HU of brain tissue is usually 25~45, the HU of cerebrospinal fluid is usually 0~12, the HU of compact bone is usually 900~1500, the HU of air is usually less than or equal to -900, and the HU of DBS electrodes and other metal parts is usually greater than or equal to 1600. According to the directional electrode model implanted in the patient, import the high-precision model file of the corresponding electrode model. In the area covered by the regional mask, the HU value corresponding to the pixel point at the electrode trajectory coordinate position is set to be greater than or equal to 1600. The HU value corresponding to the pixel point other than the electrode trajectory coordinate can be determined according to the target object tissue characteristics of the implanted target electrode.

[0088] S260, adjusting the electrode direction of the electrode template in the reference electrode template CT image, and obtaining a coronal projection image of the CT image corresponding to the reference electrode template CT image under multiple electrode directions.

[0089] The electrode direction is the electrode orientation of the directional electrode.

[0090] S270: Determine the electrode direction of the directional electrode implanted in the target object according to the similarity between the coronal projection image of the CT image and the X-ray plane image under each electrode direction.

[0091] The technical solution of this embodiment is to obtain an original CT image and an X-ray plane image containing a target object; identify the electrode position information of the target electrode in the original CT image; determine a target area containing the target electrode in the original CT image according to the electrode position information; apply a regional mask corresponding to the target area to the original CT image to remove the target electrode in the original CT image; place an electrode model file matching the model of the target electrode in the original CT image processed by the regional mask according to the electrode trajectory coordinates indicated by the electrode position information to obtain a reference electrode template CT image; adjust the electrode direction of the electrode template in the reference electrode template CT image, and obtain a CT image coronal projection image corresponding to the reference electrode template CT image under multiple electrode directions; determine the electrode direction of the directional electrode implanted in the target object according to the similarity between the CT image coronal projection image and the X-ray plane image under each electrode direction. The technical solution of the embodiment of the present invention solves the problem that the prior art cannot automatically and accurately identify the orientation of the directional electrode after electrode implantation, and can automatically identify the electrode orientation of the implanted target electrode based on the X-ray film and CT image of the implanted electrode site.

[0092] The technical solution of this embodiment is to obtain a CT image and an X-ray plane image containing a target part of a target object, and to perform rigid calibration on the CT image to obtain a CT image to be identified with a standard image orientation; wherein the target object is an object implanted with a directional electrode, and the target part is a part of the target object implanted with a directional electrode; identify electrode position information of the target electrode in the CT image to be identified, and perform image resampling on the CT image to be identified to obtain a target CT image to be identified corresponding to the target voxel accuracy; wherein the target electrode is at least one directional electrode implanted in the target part of the target object; determine a target area containing the target electrode in the CT image to be identified according to the electrode position information; apply a regional mask corresponding to the target area to the target CT image to remove the target electrode in the target CT image to be identified; and perform image resampling on the CT image to be identified according to the electrode position information. The electrode model file matching the target electrode model is placed in the target CT image to be identified after the regional mask processing to obtain the electrode template CT image to be identified; the electrode direction of the electrode template in the electrode template CT image to be identified is adjusted, and the electrode template CT image to be identified after the electrode direction adjustment is projected in the coronal plane to obtain the coronal projection image of the CT image under multiple electrode direction angles; the electrode area image containing the target electrode in each CT image coronal projection image and the X-ray plane image is extracted respectively to obtain the target electrode area CT image and the target electrode area X-ray plane image under multiple electrode direction angles; the similarity between each target electrode area CT image and the target electrode area X-ray plane image is calculated respectively to obtain the similarity result, and the electrode direction of the target electrode implanted in the target part of the target object is determined according to the similarity result.

[0093] Figure 5 This is a flow chart of an electrode direction recognition method provided in an embodiment of the present invention. This embodiment and the electrode direction recognition method in the above embodiment belong to the same inventive concept, and further illustrates the process of adjusting the electrode orientation in the electrode template. The method can be performed by an electrode direction recognition device, which can be implemented by software and / or hardware and integrated into a computer device with application development function.

[0094] like Figure 5 As shown, the electrode direction identification method of this embodiment includes the following steps:

[0095] S310, acquiring an original CT image and an X-ray plane image containing a target object, and performing rigid calibration on the original CT image to obtain a CT image with a standard image orientation.

[0096] The target object is a subject implanted with directional electrodes.

[0097] S320, identifying the electrode position information of the target electrode in the CT image of the standard image orientation, and replacing at least the area including the target electrode in the CT image of the standard image orientation with the corresponding electrode template according to the electrode position information, to obtain a reference electrode template CT image.

[0098] The target electrode is at least one directional electrode implanted in the target object.

[0099] In some scenarios, such as when the resolution of the original CT image is relatively low, the CT image with the standard image orientation can also be resampled to improve the voxel accuracy in the CT image and avoid losing the detail information of the target electrode. This is because the resolution of the CT image is usually not high, and the dimension of the electrode is relatively small, so image resampling is required to improve the image resolution. Image resampling of the corrected original CT image can obtain a CT image corresponding to the target voxel accuracy.

[0100] S330, taking the electrode direction of the electrode template when it is placed in the reference electrode template CT image as the initial electrode direction, adjusting the electrode direction of the electrode template according to a preset angle step, and obtaining the reference electrode template CT image under multiple electrode directions.

[0101] The initial electrode direction can be expressed as θ, and adjusting the electrode direction of the electrode template according to the preset angle step can be to increase 1° or other angle values ​​corresponding to the preset angle step on the basis of θ each time the electrode direction is adjusted. The smaller the value of the preset angle step, the more fine-grained the angle adjustment result is, and the reference electrode template CT images under more electrode direction angles can be obtained. Accordingly, in the subsequent similarity comparison process between the target electrode area CT image and the target electrode area X-ray plane image, a more accurate angle value can be obtained. Furthermore, a preset angle range can be selected as the end condition, for example, the angle range can be a circumference (i.e., 360°), and the reference electrode template CT image is obtained for each adjustment within a circumference.

[0102] S340 , respectively perform coronal plane projection on each reference electrode template CT image to obtain coronal projection images of the CT image in multiple electrode directions.

[0103] S350, determining the electrode direction of the directional electrode implanted in the target object according to the similarity between the coronal projection image of the CT image and the X-ray plane image under each electrode direction.

[0104] The technical solution of this embodiment is to obtain an original CT image and an X-ray plane image containing a target object, and perform rigid calibration on the original CT image to obtain a CT image with a standard image orientation; identify the electrode position information of the target electrode in the CT image with the standard image orientation, and replace at least the area including the target electrode in the CT image with the corresponding electrode template according to the electrode position information to obtain a reference electrode template CT image; take the electrode direction of the electrode template in the reference electrode template CT image when it is inserted as the initial electrode direction, adjust the electrode direction of the electrode template according to a preset angle step until the end condition of the adjustment is met, and obtain the reference electrode template CT image under multiple electrode directions; perform coronal plane projection on each reference electrode template CT image respectively to obtain coronal projection images of the CT image under multiple electrode directions; and determine the electrode direction of the directional electrode implanted in the target object according to the similarity between the coronal projection image of the CT image and the X-ray plane image under each electrode direction. The technical solution of the embodiment of the present invention solves the problem in the prior art that the directional electrode orientation after electrode implantation cannot be automatically and accurately identified, and at the same time solves the problem of how to adjust the electrode angle in the electrode template. The electrode orientation of the implanted target electrode can be automatically identified based on the X-ray film and CT image of the electrode implantation site.

[0105] Figure 6 This is a flowchart of an electrode direction identification method provided in an embodiment of the present invention. This embodiment and the electrode direction identification method in the above embodiment belong to the same inventive concept, and further illustrates the process of extracting the electrode region image containing the target electrode in the coronal projection image of the CT image and the X-ray plane image. The method can be executed by an electrode direction identification device, which can be implemented by software and / or hardware and integrated in a computer device with application development function.

[0106] like Figure 6 As shown, the electrode direction identification method of this embodiment includes the following steps:

[0107] S410, acquiring an original CT image and an X-ray plane image containing a target object, and performing rigid calibration on the original CT image to obtain a CT image with a standard image orientation.

[0108] The target object is a subject implanted with directional electrodes.

[0109] S420 , identifying electrode position information of a target electrode in a CT image with a standard image orientation, and performing image resampling on the CT image with a standard image orientation to obtain a target CT image corresponding to a target voxel accuracy.

[0110] The target electrode is at least one directional electrode implanted in a target part of the target object.

[0111] S430. According to the electrode position information, replace at least the region including the target electrode in the target CT image with the corresponding electrode template to obtain a reference electrode template CT image.

[0112] S440, adjusting the electrode direction of the electrode template in the reference electrode template CT image, and obtaining a coronal projection image of the CT image corresponding to the reference electrode template CT image under multiple electrode directions.

[0113] The electrode direction is the electrode orientation of the directional electrode.

[0114] S450, extracting the electrode region image including the target electrode from each CT image coronal projection image and X-ray plane image respectively, and obtaining the target electrode region CT image and the target electrode region X-ray plane image at multiple electrode direction angles.

[0115] The X-ray plane image also contains the target electrode, and the electrode orientation of the target electrode is unknown. Extracting the electrode region image containing the target electrode in each CT image coronal projection image and X-ray plane image can be achieved through image recognition and image segmentation methods, and obtaining the target electrode region CT image and the target electrode region X-ray plane image under multiple electrode orientation angles.

[0116] In an optional embodiment, when extracting the electrode region image containing the target electrode, pixels can be screened in each CT image coronal projection image and X-ray plane image according to the pixel value of the metal material corresponding to the target electrode in the image to obtain an initial metal mask; then, the initial metal mask is expanded to obtain the target electrode region mask. The initial metal mask is expanded several times to obtain the target electrode region mask composed of the directional electrode and its surrounding area, which can ensure that all directional electrode regions are covered inside the target electrode region mask.

[0117] Furthermore, the target electrode region CT images and target electrode region X-ray plane images at multiple electrode direction angles are obtained based on the target electrode region mask. Image segmentation and extraction are performed in the corresponding CT image coronal projection image and X-ray plane image through the target electrode region mask, so that the target electrode region CT images and target electrode region X-ray plane images at multiple electrode direction angles can be obtained.

[0118] Among them, the process of obtaining the target electrode area mask can also be to perform straight line detection in the target electrode area CT image and the target electrode area X-ray plane image to obtain the straight line equation corresponding to the target electrode; and obtain the target electrode area mask including the target electrode according to the straight line equation.

[0119] S460, respectively calculating the similarity between each target electrode region CT image and the target electrode region X-ray plane image to obtain a similarity result, and determining the electrode direction of the directional electrode implanted in the target object according to the similarity result.

[0120] The similarity between each target electrode region CT image and the target electrode region X-ray plane image can be calculated by identifying the similarity between the two images for similarity calculation through an image matching model, or by determining the corresponding similarity through algorithms such as image pixel analysis. Further, the target electrode region CT image corresponding to the highest similarity value in the similarity result is determined as the target electrode region CT image that best matches the target electrode region X-ray plane image; the electrode direction in the best matching target electrode region CT image is determined as the electrode direction of the target electrode implanted in the target part of the target object.

[0121] The similarity between each target electrode region CT image and the target electrode region X-ray plane image is calculated respectively, and the corresponding difference can also be calculated. A pattern matching algorithm can be used to match the X-ray plain film image containing only the electrode and its surrounding area with the CT image containing only the electrode and its surrounding area, and the difference between the two is calculated. The difference can be estimated using a defined loss function, including but not limited to: Dice coefficient, cross entropy and other functions for measuring image difference.

[0122] Furthermore, the electrode direction of the target electrode implanted in the target part of the target object can be determined based on the similarity result or the difference result, that is, the electrode direction of the direction electrode in the CT image of the target electrode area with the highest similarity or the smallest difference with the X-ray plane image of the target electrode area is the electrode direction of the target electrode implanted in the target part of the target object.

[0123] The technical solution of this embodiment is to obtain an original CT image and an X-ray plane image containing a target object, and perform rigid calibration on the original CT image to obtain a CT image with a standard image orientation; identify the electrode position information of the target electrode in the CT image with a standard image orientation, and perform image resampling on the CT image with a standard image orientation to obtain a target CT image corresponding to the target voxel accuracy; replace the area in the target CT image at least including the target electrode with the corresponding electrode template according to the electrode position information to obtain a reference electrode template CT image; adjust the electrode direction of the electrode template in the reference electrode template CT image, and obtain a CT image coronal projection image corresponding to the reference electrode template CT image under multiple electrode directions; respectively extract the electrode area image containing the target electrode in each CT image coronal projection image and the X-ray plane image to obtain the target electrode area CT image and the target electrode area X-ray plane image under multiple electrode direction angles; respectively calculate the similarity between each target electrode area CT image and the target electrode area X-ray plane image to obtain a similarity result, and determine the electrode direction of the directional electrode implanted in the target object according to the similarity result. The technical solution of the embodiment of the present invention solves the problem in the prior art that the directional electrode orientation after electrode implantation cannot be automatically and accurately identified, and also solves the problem of how to extract the electrode area image containing the target electrode in the coronal projection image of the CT image and the X-ray plane image. The electrode orientation of the implanted target electrode can be automatically identified based on the X-ray film and CT image of the implanted electrode site.

[0124] In a specific application example of the electrode direction recognition method, taking DBS, where one directional electrode is implanted in each of the left and right sides of the brain, for a total of two electrodes, as an example, how to determine the orientation of the directional electrodes is explained.

[0125] It is understandable that the electrode direction identification method is compatible with unilateral brain implantation of one electrode and other wider scenarios, including but not limited to: one electrode implanted in one side of the brain and two electrodes implanted in the other side of the brain, for a total of three electrodes; or two electrodes implanted in each side of the brain, for a total of four electrodes; or other electrode implantation situations.

[0126] The specific implementation process is as follows:

[0127] Postoperative CT scans after electrode implantation were rigidly registered to a standard neuroimaging orientation.

[0128] The postoperative CT image is rigidly registered with the standard adult neurological image orientation (including but not limited to the MNI152 template, etc.). Rigid registration only allows the image to be translated and rotated, but not scaled, sheared, or locally deformed. Using rigid registration can avoid deformation of the image that is not in line with clinical reality, and only serves to constrain the image orientation. Save the obtained affine transformation matrix (CT_align_to_template_affine.txt) and the transformed postoperative CT image (CT_align_to_template.nii.gz).

[0129] Second, the electrode trajectory is tracked and reconstructed to obtain the trajectory coordinates. The electrode trajectory coordinates are reconstructed from CT_align_to_template.nii.gz using manual annotation, PaCER, or other computer algorithms. The left and right brain electrode trajectory coordinate files are Lead_L.txt and Lead_R.txt, respectively.

[0130] Third, resample the postoperative CT images to improve voxel accuracy. Resample CT_align_to_template.nii.gz to unify the voxel size to 0.1 × 0.1 × 0.1 mm to obtain CT_align_to_template_resampled.nii.gz to improve voxel accuracy and prepare for the subsequent placement of high-precision electrode models and coronal projection.

[0131] Fourth, based on the electrode trajectory coordinate information, obtain the electrode and its surrounding space area mask. Use linear regression or least squares algorithm to fit a ray in three-dimensional space that is closest to the electrode trajectory. The end of the ray is the end of the electrode trajectory. Based on the straight line equation, draw a mask of the area around the electrode in CT_align_to_template.nii.gz, as shown in Figure 7. The available solutions here include but are not limited to:

[0132] A. The cylindrical area with a radius of 2 mm (the radius can be fine-tuned according to the electrode diameter) perpendicular to the ray direction is recorded as Ac. The spherical area with a radius of 2 mm (the radius is consistent with the radius of the cylinder) with the end of the ray as the center is recorded as As, and the mask is defined as the union of Ac and As.

[0133] B. Other given methods for defining the spatial region around an electrode.

[0134] Then, a postoperative CT image (Lead_mask.nii.gz) containing the space area around the electrode is obtained. This image is a mask image, and the voxel value corresponding to the space area around the electrode is 1, and the other areas are 0, which does not contain anatomical structure information such as the skull.

[0135] Fifth, use the above mask to remove the original electrode image in the postoperative CT. The above mask is used as a mask and applied to CT_align_to_template_resampled.nii.gz, replacing all areas inside the mask with pure black, and keeping the content outside the mask unchanged, to obtain CT_align_to_template_resampled_lead_removed.nii.gz, as shown in Figure 8. Figure 8 Resampled postoperative CT to remove the electrode and its surrounding spatial area content (CT_align_to_template_resampled_lead_removed.nii.gz)

[0136] Sixth, the electrode model file is used to replace the original electrode trajectory to obtain a CT file with the electrode model embedded.

[0137] According to the principle of CT imaging, different density materials have different Hounsfield units (HU) in CT scanning imaging results. HU is a unit of measurement for determining the density of a local tissue or organ in the human body. The HU of brain tissue is usually 25~45, the HU of cerebrospinal fluid is usually 0~12, the HU of compact bone is usually 900~1500, the HU of air is usually less than or equal to -900, and the HU of DBS electrodes and other metal parts is usually greater than or equal to 1600. According to the directional electrode model implanted in the patient, import the high-precision model file of the corresponding electrode model, place it on the spatial trajectory marked by Lead_L.txt and Lead_R.txt in CT_align_to_template_resampled_lead_removed.nii.gz, and record the electrode orientation angle θ at this time.

[0138] The HU of metal parts in the electrode model file is uniformly set to 2000. Get CT_with_lead_model.nii.gz, such as Fig. 9 Figure 9 shows the postoperative CT with the lead model implanted (CT_with_lead_model.nii.gz).

[0139] Seventh, project CT_with_lead_model.nii.gz to obtain the coronal orthographic projection. According to the principle of CT scanning, CT is a tomographic scan, so the brain CT images generated are all horizontal sections. Re-slice it in two other directions perpendicular to the horizontal section (i.e., coronal and sagittal) to obtain the patient's coronal and sagittal CT images. Overlap all coronal CT images according to specific rules, including but not limited to the following schemes:

[0140] 1. Let the total number of coronal images be N, then each image will be added and overlapped with a given opacity of 1 / N;

[0141] 2. Let the total number of coronal images be N, and use algorithms such as histogram equalization to normalize the pixel value of each image to 1 / N of its total brightness, and then add and overlap them;

[0142] 3. Other calculation methods that assign weights to each pixel in each image or the entire image according to given rules.

[0143] The above schemes can all achieve similar effects. Then, a coronal orthograph similar to a cranial X-ray can be reconstructed from CT_with_lead_model.nii.gz, as shown in Figure 10. Figure 10 is a schematic diagram of reconstructing a coronal orthograph from a postoperative CT.

[0144] Eighth, identify the electrode track in the patient's postoperative cranial X-ray film and obtain the electrode and its surrounding area mask. To obtain the electrode and its surrounding area mask in the patient's postoperative cranial X-ray film, algorithms including but not limited to the following can be used:

[0145] 1. Use fixed thresholds, pixel value percentiles and other screening methods to obtain the mask of the metal area in the image, and perform several dilation operations on the mask to obtain the mask of the metal area and its surrounding areas;

[0146] 2. Use the straight line detection algorithm to identify the DBS electrode in the image, fit the straight line equation of the electrode, and obtain the mask of the electrode and its surrounding area through this equation;

[0147] 3. Combine the above threshold screening, line detection, and other computer graphics algorithms, such as edge detection, to achieve similar effects.

[0148] The mask is recorded as X_lead_mask. It is applied to the patient's postoperative cranial X-ray film to obtain an X-ray film image containing only the electrode and its surrounding area.

[0149] Ninth, identify the electrode trajectory in CT_orthograph and obtain the mask of the electrode and its surrounding area. Use the same algorithm as step 8 to obtain the mask of the electrode and its surrounding area in CT_orthograph, recorded as CT_lead_mask. Apply it to CT_orthograph to obtain a CT_orthograph image containing only the electrode and its surrounding area.

[0150] Tenth, match the above two electrode images and calculate the difference. Use a pattern matching algorithm to match the X-ray plain film image containing only the electrode and its surrounding area with the CT_orthograph image containing only the electrode and its surrounding area, and calculate the difference between the two. The difference can be estimated using a defined loss function, including but not limited to: Dice coefficient, cross entropy and other functions used to measure the difference of images.

[0151] Eleventh, the difference loss function v(θ) corresponding to the directional electrode orientation angle within a complete circle (ie, 360°) is calculated.

[0152] Steps 6 to 10 calculate the difference loss function value corresponding to the electrode orientation angle θ. Given the step size d of increasing θ, repeat the above steps until the calculation of the entire circumference is completed. The smaller the step size d, the greater the amount of calculation, but the more precise the result. You can choose a suitable d according to the actual task to balance the calculation efficiency and result accuracy.

[0153] Calculate θ' when v(θ) takes the minimum value, which is the orientation angle of the patient's directional electrode. The values ​​of v(θ) and θ' are as follows: Fig.11 The following algorithms may be used, including but not limited to:

[0154] Directly select the θ corresponding to the minimum value of v(θ) as θ'. If there are multiple minimum values ​​of v(θ) and the points of these minimum values ​​are close, then select the mean of these points as θ';

[0155] Use the difference algorithm to interpolate the discrete v(θ) into a continuous function, take the derivative of the function, and calculate θ when the function takes the minimum value as θ'. Fig.11 Schematic diagram of the difference loss function v(θ) and θ'. Each point ( Fig.11 The blue discrete points with fluctuations represent the difference corresponding to the orientation angle, and all points are fitted to obtain a continuous curve (red curve). By taking the derivative of this curve, we can get the electrode orientation angle with the smallest difference.

[0156] The specific steps of the algorithm for identifying the directional electrode orientation through postoperative cranial X-ray and postoperative CT are described as follows:

[0157] Step 1: rigidly register the postoperative CT to the standard neuroimaging orientation;

[0158] Step 2: Track and reconstruct the electrode trajectory to obtain the trajectory coordinates;

[0159] Step 3: Resample the postoperative CT images to improve voxel accuracy;

[0160] Step 4: Obtain the electrode and its surrounding space area mask based on the electrode trajectory coordinate information;

[0161] Step 5: Use the above mask to remove the original electrode image in the postoperative CT;

[0162] Step 6: Use the electrode model file to replace the original electrode trajectory to obtain a CT file with the electrode model inserted;

[0163] Step 7: Project CT_with_lead_model.nii.gz to obtain the coronal orthographic projection image;

[0164] Step 8: Identify the electrode track in the patient's postoperative cranial X-ray film and obtain the mask of the electrode and its surrounding area;

[0165] Step 9: Identify the electrode trajectory in CT_orthograph and obtain the mask of the electrode and its surrounding area;

[0166] Step 10: Match the above two electrode images and calculate the difference;

[0167] Step 11: Calculate the difference loss function v(θ) corresponding to the directional electrode orientation angle within a complete circle (i.e., 360°);

[0168] Step 12: Calculate θ' when v(θ) takes the minimum value, which is the orientation angle of the directional electrode of the patient.

[0169] The algorithm designed in this solution combines the imaging data of postoperative cranial CT and X-ray films to provide a fully automated solution for directional electrode orientation identification. Compared with the current mainstream solutions, this process eliminates the manual comparison link, thus avoiding human subjective bias.

[0170] The standard image comparison method currently used in the mainstream solution greatly limits the recognition accuracy of the orientation angle. For example, the most common is 8 comparison images, so the electrode orientation angle determined by the comparison method is accurate to 45° at most. The electrode direction recognition scheme provided in this embodiment can set a smaller orientation angle increase step size, so as to calculate a more refined difference loss function, and then determine a more accurate orientation angle. The electrode direction recognition provided in the embodiment uses the method of postoperative CT coronal projection to reconstruct the X-ray plain film results from CT, and then establish the comparability of postoperative CT and X-ray. On the basis of individualized analysis of patients, the information of the two is combined to obtain accurate electrode orientation results. In addition, the method of postoperative CT electrode removal and simulated placement of electrode models is used to ensure that the electrode projection characteristics of specific patients on their surgical implantation paths are fully obtained. The method of resampling CT images before electrode direction recognition to improve the accuracy of CT image voxels solves the problem of detail loss in the postoperative CT images placed by high-precision electrode models, thereby ensuring that the coronal projection retains as many electrode shape details as possible and ensures the reliability of subsequent pattern matching.

[0171] Fig.12 A structural schematic diagram of an electrode direction recognition device provided in an embodiment of the present invention. This embodiment can be applied to scenarios for recognizing medical images of parts where electrodes have been implanted, especially for identifying the electrode direction (orientation) of implanted electrodes. The electrode direction recognition device can be implemented by software and / or hardware and integrated into a computer terminal device with application development capabilities.

[0172] like Fig.12 As shown, the electrode direction identification device includes: an original image acquisition module 510, a reference image acquisition module 520, a multi-angle reference image acquisition module 530 and an electrode direction determination module 540.

[0173] Among them, the original image acquisition module 510 is used to acquire the original CT image and X-ray plane image containing the target object; wherein the target object is an object implanted with a directional electrode; the reference image acquisition module 520 is used to identify the electrode position information of the target electrode in the original CT image, and replace the area in the original CT image at least including the target electrode with the corresponding electrode template according to the electrode position information to obtain a reference electrode template CT image; wherein the target electrode is at least one directional electrode implanted in the target object; the multi-angle reference image acquisition module 530 is used to adjust the electrode direction of the electrode template in the reference electrode template CT image, and obtain the CT image coronal projection image corresponding to the reference electrode template CT image under multiple electrode directions; wherein the electrode direction is the electrode orientation of the directional electrode; the electrode direction determination module 540 is used to determine the electrode direction of the directional electrode implanted in the target object according to the similarity between the CT image coronal projection image and the X-ray plane image under each electrode direction.

[0174] The technical solution of this embodiment is to obtain an original CT image and an X-ray plane image containing a target object; wherein the target object is an object implanted with a directional electrode; identify the electrode position information of the target electrode in the original CT image, and replace the area in the original CT image at least including the target electrode with the corresponding electrode template according to the electrode position information, to obtain a reference electrode template CT image; wherein the target electrode is at least one directional electrode implanted in the target object; adjust the electrode direction of the electrode template in the reference electrode template CT image, and obtain a CT image coronal projection image corresponding to the reference electrode template CT image under multiple electrode directions; wherein the electrode direction is the electrode orientation of the directional electrode; determine the electrode direction of the directional electrode implanted in the target object according to the similarity between the CT image coronal projection image and the X-ray plane image under each electrode direction. The technical solution of the embodiment of the present invention solves the problem that the prior art cannot automatically and accurately identify the orientation of the directional electrode after electrode implantation, and can automatically identify the electrode orientation of the implanted electrode based on the X-ray film and CT image of the implanted electrode site.

[0175] In an optional implementation, the reference image acquisition module 520 is specifically used for:

[0176] According to the electrode position information, a target area including a target electrode is determined in the original CT image;

[0177] Using a regional mask corresponding to the target region to act on the original CT image, and removing the target electrode in the original CT image;

[0178] According to the electrode trajectory coordinates indicated by the electrode position information, the electrode model file matching the model of the target electrode is placed in the original CT image processed by the regional mask to obtain a reference electrode template CT image.

[0179] In an optional implementation, the reference image acquisition module 520 is specifically used for:

[0180] The electrode position information of different acquisition layers is obtained, and then a linear fitting is performed according to the electrode trajectory coordinates indicated by the electrode position information corresponding to the original CT images of different acquisition layers to obtain a fitting electrode trajectory line;

[0181] Determine a cylindrical area with a preset length as a radius along a direction perpendicular to the fitting electrode trajectory line; and determine a spherical area with a preset length as a radius with the end point of the fitting electrode trajectory line as the sphere center;

[0182] The union of the cylinder region and the sphere region is taken as the target region.

[0183] In an optional implementation, the multi-angle reference image acquisition module 530 is specifically used to:

[0184] Taking the electrode direction of the electrode template when it is placed in the reference electrode template CT image as the initial electrode direction, adjusting the electrode direction of the electrode template according to a preset angle step until an end condition of the electrode direction adjustment is met, thereby obtaining the reference electrode template CT images under multiple electrode directions;

[0185] The coronal plane projection is performed on each reference electrode template CT image respectively to obtain the coronal projection images of the CT image under multiple electrode directions.

[0186] In an optional implementation, the electrode direction determination module 540 is specifically configured to:

[0187] Extracting the electrode region image containing the target electrode from each CT image coronal projection image and X-ray plane image respectively, and obtaining the target electrode region CT image and the target electrode region X-ray plane image at multiple electrode direction angles;

[0188] The similarity between the CT image of each target electrode region and the X-ray plane image of the target electrode region is calculated respectively to obtain a similarity result, and the electrode direction of the directional electrode implanted in the target object is determined according to the similarity result.

[0189] In an optional implementation, the electrode direction determination module 540 is specifically configured to:

[0190] According to the pixel value of the metal material corresponding to the target electrode in the image, pixels are screened in each CT image coronal projection image and X-ray plane image to obtain an initial metal mask;

[0191] Performing an expansion operation on the initial metal mask to obtain a target electrode region mask;

[0192] Based on the target electrode region mask, a target electrode region CT image and a target electrode region X-ray plane image are obtained at multiple electrode direction angles.

[0193] In an optional implementation, the electrode direction determination module 540 may also be used to:

[0194] In the CT image of the target electrode region and the X-ray plane image of the target electrode region, straight line detection is performed to obtain a straight line equation corresponding to the target electrode;

[0195] A target electrode region mask including the target electrode is obtained according to the straight line equation.

[0196] In an optional implementation, the electrode direction determination module 540 is specifically configured to:

[0197] The target electrode region CT image corresponding to the highest similarity value in the similarity results is determined as the target electrode region CT image that best matches the target electrode region X-ray plane image;

[0198] The electrode direction of the directional electrode implanted in the target object is determined by the electrode direction in the CT image of the target electrode area that best matches the target electrode area.

[0199] In an optional implementation, the electrode direction recognition device further includes an image correction processing module, which is used to:

[0200] After the original CT image is acquired, a rigid calibration is performed on the original CT image to obtain a CT image with a standard image orientation.

[0201] In an optional implementation, the electrode direction recognition device further includes an image resampling processing module, which is used to:

[0202] Before obtaining the reference electrode template CT image, the original CT image after rigid calibration is resampled to obtain a CT image corresponding to the target voxel accuracy;

[0203] Accordingly, the reference image acquisition module 520 may also be used for:

[0204] According to the electrode position information, a region in the CT image corresponding to the target voxel accuracy, at least including the target electrode, is replaced with a corresponding electrode template to obtain a reference electrode template CT image.

[0205] The electrode direction identification device provided in the embodiment of the present invention can execute the electrode direction identification method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0206] Fig.13 A schematic diagram of the structure of a computer device provided in an embodiment of the present invention. Fig.13 A block diagram of an exemplary computer device 12 suitable for use in implementing embodiments of the present invention is shown. Fig.13 The computer device 12 shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention. The computer device 12 can be any terminal device with computing capabilities, such as an intelligent controller and server, a mobile phone and other terminal devices.

[0207] like Fig.13 As shown, the computer device 12 is in the form of a general-purpose computing device. The components of the computer device 12 may include, but are not limited to: one or more processors or processing units 16, a system memory 28, and a bus 18 that connects various system components (including the system memory 28 and the processing unit 16).

[0208] Bus 18 represents one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, a processor or a local bus using any of a variety of bus architectures. By way of example, these architectures include, but are not limited to, an Industry Standard Architecture (ISA) bus, a Micro Channel Architecture (MAC) bus, an Enhanced ISA bus, a Video Electronics Standards Association (VESA) local bus, and a Peripheral Component Interconnect (PCI) bus.

[0209] The computer device 12 typically includes a variety of computer system readable media. These media can be any available media that can be accessed by the computer device 12, including volatile and non-volatile media, removable and non-removable media.

[0210] The system memory 28 may include computer system readable media in the form of volatile memory, such as random access memory (RAM) 30 and / or cache memory 32. The computer device 12 may further include other removable / non-removable, volatile / non-volatile computer system storage media. By way of example only, the storage system 34 may be used to read and write non-removable, non-volatile magnetic media ( Fig.13 not shown, usually called a "hard drive"). Although Fig.13Not shown in the figure, a disk drive for reading and writing to a removable non-volatile disk (e.g., a "floppy disk"), and an optical disk drive for reading and writing to a removable non-volatile optical disk (e.g., a CD-ROM, a DVD-ROM, or other optical media) may be provided. In these cases, each drive may be connected to the bus 18 via one or more data medium interfaces. The system memory 28 may include at least one program product having a set (e.g., at least one) of program modules that are configured to perform the functions of the various embodiments of the present invention.

[0211] A program / utility 40 having a set (at least one) of program modules 42 may be stored, for example, in system memory 28, such program modules 42 including, but not limited to, an operating system, one or more application programs, other program modules, and program data, each of which or some combination may include an implementation of a network environment. Program modules 42 generally perform the functions and / or methods of the embodiments described herein.

[0212] The computer device 12 may also communicate with one or more external devices 14 (e.g., keyboards, pointing devices, displays 24, etc.), one or more devices that enable a user to interact with the computer device 12, and / or any device that enables the computer device 12 to communicate with one or more other computing devices (e.g., a network card, a modem, etc.). Such communication may be performed via an input / output (I / O) interface 22. In addition, the computer device 12 may also communicate with one or more networks (e.g., a local area network (LAN), a wide area network (WAN), and / or a public network, such as the Internet) via a network adapter 20. As shown, the network adapter 20 communicates with the other modules of the computer device 12 via a bus 18. It should be understood that although Fig.13 Not shown, other hardware and / or software modules may be used in conjunction with computer device 12, including but not limited to microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0213] The processing unit 16 executes various functional applications and data processing by running the program stored in the system memory 28, for example, implementing the electrode direction identification method provided in the embodiment of the present invention, the method comprising:

[0214] Acquire an original CT image and an X-ray plane image containing a target object; wherein the target object is an object implanted with directional electrodes;

[0215] Identifying electrode position information of a target electrode in the original CT image, and replacing at least a region of the original CT image including the target electrode with a corresponding electrode template according to the electrode position information, to obtain a reference electrode template CT image; wherein the target electrode is at least one directional electrode implanted in the target object;

[0216] Adjusting the electrode direction of the electrode template in the reference electrode template CT image, and obtaining a coronal projection image of a CT image corresponding to the reference electrode template CT image under multiple electrode directions; wherein the electrode direction is the electrode orientation of a directional electrode;

[0217] The electrode direction of the directional electrode implanted in the target object is determined according to the similarity between the coronal projection image of the CT image and the X-ray plane image in each electrode direction.

[0218] Fig.14 A medical system is provided in an embodiment of the present invention. The medical system can be applied in clinical medicine.

[0219] The medical system includes: an implantable medical device, a display, and a processor.

[0220] The implantable medical device comprises at least a pulse generator implanted in the body of the target object and an electrode wire implanted in the target object. The pulse generator is connected to the electrode wire, and the implanted end of the electrode wire is provided with at least one set of directional electrodes.

[0221] A display is used to display a target image.

[0222] The processor is configured to obtain postoperative images of the target object after the electrode wire is implanted, execute the electrode direction recognition method provided by any embodiment, determine the direction of the directional electrode in the electrode wire of the target object, and display the direction of the directional electrode in the electrode wire using a display.

[0223] An embodiment of the present invention further provides a computer-readable storage medium having a computer program stored thereon. When the program is executed by a processor, the electrode direction identification method provided in any embodiment of the present invention is implemented. The method includes:

[0224] Acquire an original CT image and an X-ray plane image containing a target object; wherein the target object is an object implanted with directional electrodes;

[0225] Identifying electrode position information of a target electrode in the original CT image, and replacing at least a region of the original CT image including the target electrode with a corresponding electrode template according to the electrode position information, to obtain a reference electrode template CT image; wherein the target electrode is at least one directional electrode implanted in the target object;

[0226] Adjusting the electrode direction of the electrode template in the reference electrode template CT image, and obtaining a coronal projection image of a CT image corresponding to the reference electrode template CT image under multiple electrode directions; wherein the electrode direction is the electrode orientation of a directional electrode;

[0227] The electrode direction of the directional electrode implanted in the target object is determined according to the similarity between the coronal projection image of the CT image and the X-ray plane image in each electrode direction.

[0228] The computer storage medium of the embodiment of the present invention can adopt any combination of one or more computer-readable media. The computer-readable medium can be a computer-readable signal medium or a computer-readable storage medium. The computer-readable storage medium can be, for example, but not limited to: an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples (non-exhaustive list) of computer-readable storage media include: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this document, a computer-readable storage medium can be any tangible medium containing or storing a program, which can be used by an instruction execution system, device or device or used in combination with it.

[0229] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, which carry computer-readable program code. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer-readable signal media may also be any computer-readable medium other than a computer-readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0230] The program code embodied on the computer readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

[0231] Computer program code for performing the operation of the present invention may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as an independent software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., using an Internet service provider to connect through the Internet).

[0232] It should be understood by those skilled in the art that the modules or steps of the present invention described above can be implemented by a general-purpose computing device, they can be concentrated on a single computing device, or distributed on a network composed of multiple computing devices, optionally, they can be implemented by a program code executable by a computer device, so that they can be stored in a storage device and executed by the computing device, or they can be made into individual integrated circuit modules, or multiple modules or steps therein can be made into a single integrated circuit module for implementation. Thus, the present invention is not limited to any specific combination of hardware and software.

[0233] The embodiments of the present disclosure also provide a computer program product, including a computer program, which, when executed by a processor, implements the electrode direction identification method provided in any embodiment of the present disclosure.

[0234] In the process of implementation, the computer program product can be written in one or more programming languages ​​or a combination thereof to perform the computer program code for the disclosed operation, including object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as an independent software package, partially on the user's computer and partially on a remote computer, or completely on a remote computer or server. In the case of a remote computer, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computer (e.g., using an Internet service provider to connect through the Internet).

[0235] Note that the above are only preferred embodiments of the present invention and the technical principles used. Those skilled in the art will understand that the present invention is not limited to the specific embodiments described herein, and that various obvious changes, readjustments and substitutions can be made by those skilled in the art without departing from the scope of protection of the present invention. Therefore, although the present invention has been described in more detail through the above embodiments, the present invention is not limited to the above embodiments, and may include more other equivalent embodiments without departing from the concept of the present invention, and the scope of the present invention is determined by the scope of the appended claims.

Claims

1. A method for identifying electrode direction, characterized in that: include: Acquire an original CT image and an X-ray plane image containing a target object; wherein the target object is a part where a directional electrode is implanted and where electrode stimulation is required; Identify the electrode position information of the target electrode in the original CT image, and determine a target area containing the target electrode in the original CT image according to the electrode position information; apply a regional mask corresponding to the target area to the original CT image to remove the target electrode in the original CT image; place an electrode model file matching the model of the target electrode in the original CT image processed by the regional mask according to the electrode trajectory coordinates indicated by the electrode position information to obtain a reference electrode template CT image; wherein the target electrode is at least one directional electrode implanted in the target object; Adjusting the electrode direction of the electrode template in the reference electrode template CT image, and obtaining a coronal projection image of a CT image corresponding to the reference electrode template CT image under multiple electrode directions; wherein the electrode direction is the electrode orientation of a directional electrode; The electrode direction of the directional electrode implanted in the target object is determined according to the similarity between the coronal projection image of the CT image and the X-ray plane image in each electrode direction.

2. The method according to claim 1, characterized in that Determining a target area including the target electrode in the original CT image according to the electrode position information includes: Obtaining electrode position information in original CT images of different acquisition layers; Linear fitting is performed on the electrode trajectory coordinates indicated by the electrode position information corresponding to the original CT images of different acquisition layers to obtain a fitted electrode trajectory line; Determine a cylindrical area with a preset length as a radius along a direction perpendicular to the fitting electrode trajectory line; and determine a spherical area with a preset length as a radius with the end point of the fitting electrode trajectory line as the center of the sphere; The union of the cylindrical region and the spherical region is taken as the target region.

3. The method according to claim 1, characterized in that The step of adjusting the electrode direction of the electrode template in the reference electrode template CT image and obtaining a coronal projection image of a CT image corresponding to the reference electrode template CT image under multiple electrode directions includes: Taking the electrode direction of the electrode template when it is placed in the reference electrode template CT image as the initial electrode direction, adjusting the electrode direction of the electrode template according to a preset angle step, and obtaining the reference electrode template CT images under multiple electrode directions; Each reference electrode template CT image is projected in the coronal plane to obtain coronal projection images of the CT image in multiple electrode directions.

4. The method according to claim 1, characterized in that: The step of determining the electrode direction of the directional electrode implanted in the target object according to the similarity between the coronal projection image of the CT image and the X-ray plane image at each electrode direction angle includes: Extracting the electrode region image containing the target electrode from each of the coronal projection images of the CT image and the X-ray plane image respectively, to obtain the target electrode region CT images and the target electrode region X-ray plane images at multiple electrode direction angles; The similarity between each of the target electrode region CT images and the target electrode region X-ray plane images is calculated respectively to obtain a similarity result, and the electrode direction of the directional electrode implanted in the target object is determined according to the similarity result.

5. The method according to claim 4, characterized in that The step of respectively extracting the electrode region image containing the target electrode from each of the coronal projection images of the CT image and the X-ray plane image to obtain the target electrode region CT image and the target electrode region X-ray plane image at multiple electrode direction angles includes: According to the pixel value of the metal material corresponding to the target electrode in the image, pixel screening is performed in each of the coronal projection images of the CT image and the X-ray plane image to obtain an initial metal mask; Performing an expansion operation on the initial metal mask to obtain a target electrode region mask; Based on the target electrode region mask, a target electrode region CT image and a target electrode region X-ray plane image at multiple electrode direction angles are obtained.

6. The method according to claim 5, characterized in that The method for obtaining the target electrode region mask also includes: In the target electrode region CT image and the target electrode region X-ray plane image, straight line detection is performed to obtain a straight line equation corresponding to the target electrode; A target electrode region mask including the target electrode is obtained according to the straight line equation.

7. The method according to claim 4, characterized in that Determining the electrode direction of the directional electrode implanted in the target object according to the similarity result includes: Determine the target electrode region CT image corresponding to the highest similarity value in the similarity results as the target electrode region CT image that best matches the target electrode region X-ray plane image; The electrode direction of the directional electrode implanted in the target object is determined by using the electrode direction in the CT image of the most matching target electrode region.

8. The method according to any one of claims 1 to 7, characterized in that: After acquiring the original CT image, the method further includes: The original CT image is rigidly calibrated to obtain a CT image with a standard image orientation.

9. The method according to claim 8, characterized in that Before obtaining the reference electrode template CT image, the method further includes: Resampling the original CT image after rigid calibration to obtain a CT image corresponding to the target voxel accuracy; Correspondingly, according to the electrode position information, the region in the original CT image at least including the target electrode is replaced with the corresponding electrode template to obtain a reference electrode template CT image, including: According to the electrode position information, a region in the CT image corresponding to the target voxel accuracy, at least including the target electrode, is replaced with a corresponding electrode template to obtain a reference electrode template CT image.

10. An electrode direction identification device, characterized in that: include: An original image acquisition module, used to acquire an original CT image and an X-ray plane image containing a target object; wherein the target object is a part where a directional electrode is implanted and where electrode stimulation is required; A reference image acquisition module, used to identify the electrode position information of the target electrode in the original CT image, and determine a target area containing the target electrode in the original CT image according to the electrode position information; apply a regional mask corresponding to the target area to the original CT image to remove the target electrode in the original CT image; according to the electrode trajectory coordinates indicated by the electrode position information, place an electrode model file matching the model of the target electrode in the original CT image processed by the regional mask to obtain a reference electrode template CT image; wherein the target electrode is at least one directional electrode implanted in the target object; A multi-angle reference image acquisition module, used to adjust the electrode direction of the electrode template in the reference electrode template CT image, and obtain a CT image coronal projection image corresponding to the reference electrode template CT image under multiple electrode directions; wherein the electrode direction is the electrode orientation of the directional electrode; The electrode direction determination module is used to determine the electrode direction of the directional electrode implanted in the target object according to the similarity between the coronal projection image of the CT image and the X-ray plane image under each electrode direction.

11. A computer device, characterized in that: The computer device comprises: one or more processors; A memory for storing one or more programs; When the one or more programs are executed by the one or more processors, the one or more processors implement the electrode direction identification method as described in any one of claims 1-9.

12. A medical system, characterized in that: The medical system includes: An implantable medical device, the implantable medical device comprising at least a pulse generator implanted in a target object and an electrode wire implanted in the target object, the pulse generator being connected to the electrode wire, and the implanted end of the electrode wire being provided with at least one set of directional electrodes; monitor, The processor is configured to obtain postoperative images of the target object after the electrode wire is implanted, execute the electrode direction recognition method described in any one of claims 1 to 9, determine the direction of the directional electrode in the electrode wire of the target object, and use the display to display the direction of the directional electrode in the electrode wire.

13. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the electrode direction identification method as described in any one of claims 1 to 9 is implemented.

14. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, the computer program implements the electrode direction identification method according to any one of claims 1 to 9.

Images