Medical image processing method and medical image processing device

Abstract

The invention provides a medical image processing method and a medical image processing device, which can pre-construct a three-dimensional target path image in an occluded blood vessel and solve the technical blind area that the dissection path of a far-end blood vessel cannot be developed due to the fact that a contrast agent cannot pass through the occluded blood vessel in traditional DSA radiography. Moreover, the three-dimensional target path image and a three-dimensional angiography image obtained in the operation can be registered and fused based on a preset mark point to obtain a fused image, and the fused image and the two-dimensional perspective image of the focus area of the patient are registered and fused to obtain a fused image. Accurate space alignment and dynamic superposition of the preoperative three-dimensional target path image, the intraoperative three-dimensional angiography image and the intraoperative two-dimensional perspective image are achieved, a whole-process visible accurate space positioning reference is provided for instrument pushing and vascular access selection of an operator, and the accuracy of surgical operation is improved.

Description

Technical Field

[0001] This application relates to the field of medical imaging technology, and in particular to a medical image processing method and a medical image processing device. Background Technology

[0002] Currently, for patients with chronic vascular occlusion (such as chronic intracranial artery occlusion (CIAO), chronic coronary artery occlusion, chronic limb artery occlusion, etc.), digital subtraction angiography (DSA) technology can be used during intraoperative navigation for endovascular recanalization treatment. By visualizing vascular structures during the procedure, DSA provides the surgeon with operational reference and surgical guidance to achieve recanalization of the occluded vessel.

[0003] However, when using the above method for intraoperative navigation, the contrast agent often has difficulty passing through the occluded vessel segment, thus failing to effectively visualize the occluded segment and distal vessels. Consequently, it cannot present the true anatomical path of the occluded segment and distal vessels, nor can it provide accurate spatial positioning references for the surgeon's instrument delivery and vascular access selection, resulting in a significant reduction in surgical accuracy. Summary of the Invention

[0004] This application provides a medical image processing method that can improve the accuracy of surgical procedures.

[0005] According to a first aspect of the embodiments of this application, a medical image processing method is provided, comprising: Three-dimensional angiographic images of the lesion area are obtained. The three-dimensional angiographic images are used to display the three-dimensional spatial structure information of the occluded vessels and adjacent vessels in the lesion area. Based on preset marker points, the pre-constructed three-dimensional target path image is registered and fused with the three-dimensional angiography image to obtain a fused image. The three-dimensional target path image is marked with passable paths within the occluded blood vessel. Two-dimensional perspective images of the lesion area are obtained. These images are used to display the two-dimensional spatial structure information of the occluded blood vessels and adjacent blood vessels in the lesion area, as well as the position information of the surgical instruments. Based on the landmark points, the fused image is registered and fused with the 2D perspective image to obtain the target navigation image.

[0006] In some embodiments of this application, obtaining three-dimensional angiographic images of the lesion area includes: Two-dimensional X-ray projection images of the lesion area from multiple angles were acquired using digital subtraction angiography equipment. Three-dimensional volume reconstruction is performed based on two-dimensional X-ray projection images from multiple angles to obtain three-dimensional angiographic images of the lesion area.

[0007] In some embodiments of this application, before registering and fusing a pre-constructed three-dimensional target path image with a three-dimensional angiography image based on preset marker points to obtain a fused image, the method further includes: Three-dimensional images of blood vessel walls in the lesion area are obtained using magnetic resonance imaging equipment. These images are used to display the three-dimensional spatial structure information of the occluded blood vessels in the lesion area, as well as the blood vessel walls, plaques, and vascular lumens of adjacent blood vessels. Based on the three-dimensional blood vessel wall image, determine the passable target trajectory within the occluded blood vessel; Based on the target trajectory, a 3D target path image is constructed.

[0008] In some embodiments of this application, determining a passable target trajectory within an occluded blood vessel based on a three-dimensional blood vessel wall image includes: Statistical analysis of pixel values ​​in a three-dimensional blood vessel wall image; Determine the target threshold based on the pixel value of each pixel; Based on the target threshold, a passable target trajectory within the occluded blood vessel is determined from a three-dimensional blood vessel wall image.

[0009] In some embodiments of this application, determining the target threshold based on the pixel value of each pixel includes: Based on the pixel values ​​of each pixel, determine the pixel value range corresponding to the blood vessel wall, the pixel value range corresponding to the plaque, and the pixel value range corresponding to the blood vessel lumen; Based on the pixel value range corresponding to the blood vessel wall, the pixel value range corresponding to the plaque, and the pixel value range corresponding to the blood vessel lumen, the pixel boundary value between the passable blood vessel lumen and non-blood vessel lumen tissue is determined, and the pixel boundary value is determined as the target threshold. Non-blood vessel lumen tissue includes plaque and / or blood vessel wall.

[0010] In some embodiments of this application, determining a passable target trajectory within an occluded blood vessel from a three-dimensional blood vessel wall image based on a target threshold includes: Based on the target threshold, the passable lumen of the occluded vessel is determined from the three-dimensional vessel wall image; Based on the accessible vessel lumen corresponding to the occluded vessel, determine the path extending along the accessible vessel lumen corresponding to the occluded vessel, and define the path as the accessible target trajectory within the occluded vessel.

[0011] In some embodiments of this application, constructing a three-dimensional target path image based on the target trajectory includes: The three-dimensional anatomical structure of the occluded vessel, the three-dimensional anatomical structure of the proximal vessel of the occluded vessel, and the three-dimensional anatomical structure of the distal vessel of the occluded vessel are extracted from the three-dimensional vessel wall image. Based on the target trajectory, a three-dimensional target path image is obtained by fusing the three-dimensional anatomical structure of the occluded vessel, the three-dimensional anatomical structure of the proximal vessel of the occluded vessel, and the three-dimensional anatomical structure of the distal vessel of the occluded vessel.

[0012] In some embodiments of this application, the landmarks include any one or more of bony anatomical landmarks, vascular anatomical landmarks, and landmarks with influencing characteristics.

[0013] According to a second aspect of the embodiments of this application, a medical image processing apparatus is provided, comprising: The acquisition module is used to acquire three-dimensional angiography images of the lesion area. The three-dimensional angiography images are used to display the three-dimensional spatial structure information of the occluded blood vessels and adjacent blood vessels in the lesion area. The fusion module is used to register and fuse a pre-constructed three-dimensional target path image with a three-dimensional angiography image based on preset marker points to obtain a fused image. The three-dimensional target path image is marked with passable paths within the occluded blood vessel. The acquisition module is also used to acquire two-dimensional perspective images of the lesion area. The two-dimensional perspective images are used to display the two-dimensional spatial structure information of the occluded blood vessels and adjacent blood vessels in the lesion area, as well as the position information of the surgical instruments. The fusion module is also used to register and fuse the fused image with the two-dimensional perspective image based on the marker points to obtain the target navigation image.

[0014] According to a third aspect of the embodiments of this application, a computer device is provided, the computer device including a processor and a memory, the memory being used to store at least one program, the at least one program being loaded by the processor and executed by any of the above-described medical image processing methods.

[0015] According to a fourth aspect of the embodiments of this application, a computer-readable storage medium is provided, which stores at least one program, which is loaded and executed by a processor to implement any of the above-described medical image processing methods.

[0016] Therefore, the aforementioned medical image processing method can pre-construct a three-dimensional target path image within the occluded blood vessel, overcoming the technical blind spot of traditional DSA angiography where the contrast agent cannot pass through the occluded vessel, resulting in the inability to visualize the distal vascular anatomy path. Furthermore, based on preset marker points, the three-dimensional target path image can be registered and fused with the intraoperative three-dimensional angiography image to obtain a fused image. This fused image is then registered and fused with a two-dimensional fluoroscopic image of the patient's lesion area, achieving precise spatial alignment and dynamic overlay of the preoperative three-dimensional target path image with the intraoperative three-dimensional angiography image and two-dimensional fluoroscopic image. This provides the surgeon with a fully visualized and precise spatial positioning reference for instrument delivery and vascular access selection, improving the accuracy of the surgical procedure. Attached Figure Description

[0017] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0018] Figure 1 A flowchart illustrating a medical image processing method provided in an embodiment of this application; Figure 2 A schematic diagram of a preoperative assessment image and a preoperative high-resolution MR image for a complication case provided in an embodiment of this application; Figure 3 This application provides an embodiment of a case involving intraoperative fusion navigation and timely symptomatic treatment for complications. Figure 4 A schematic diagram of a successful preoperative assessment image and a preoperative high-resolution MR image of a patient, provided as an embodiment of this application; Figure 5 This is a schematic diagram illustrating the successful activation and display of intraoperative fusion navigation for a case, as well as the resulting images, provided in an embodiment of this application. Figure 6 An overall flowchart of MRI-DSA fusion navigation is provided for an embodiment of this application; Figure 7 A schematic diagram illustrating 3D MR-3D DSA registration and fusion provided for an embodiment of this application; Figure 8 A schematic diagram illustrating a 3D MR-DSA image fusion example provided in an embodiment of this application; Figure 9 This is a schematic diagram of the structure of a medical image processing device provided in an embodiment of this application; Figure 10This is a schematic diagram of the structure of a terminal provided in an embodiment of this application; Figure 11 This is a schematic diagram of the structure of a server provided in an embodiment of this application. Detailed Implementation

[0019] To make the objectives, technical solutions, and advantages of this application clearer, the embodiments of this application will be described in further detail below with reference to the accompanying drawings.

[0020] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application.

[0021] In this application, the terms "first," "second," etc., are used to distinguish identical or similar items that have essentially the same function. It should be understood that there is no logical or temporal dependency between "first," "second," and "nth," nor does it limit the quantity or execution order. It should also be understood that although the following description uses the terms "first," "second," etc., to describe various objects, these objects should not be limited by the terms.

[0022] These terms are simply used to distinguish one object from another. For example, without departing from the various examples, a first action can be called a second action, and similarly, a second action can be called a first action. Both the first and second actions can be actions, and in some cases, they can be separate and distinct actions.

[0023] "At least one" refers to one or more actions. For example, at least one action can be one action, two actions, three actions, or any integer number of actions greater than or equal to one. "Multiple" refers to two or more actions. For example, multiple actions can be two actions, three actions, or any integer number of actions greater than or equal to two.

[0024] Currently, for patients with chronic vascular occlusion (e.g., chronic intracranial artery occlusion (CIAO), chronic coronary artery occlusion, chronic limb artery occlusion, etc.), digital subtraction angiography (DSA) can be used for intraoperative navigation during endovascular recanalization. This technique uses intraoperative angiography to visualize vascular structures, providing the surgeon with operational references and surgical guidance to achieve recanalization of the occluded vessel. However, when using this method for intraoperative navigation, the contrast agent often has difficulty passing through the occluded vessel segment. Therefore, it is impossible to effectively visualize the occluded segment and distal vessels, thus failing to reveal the true anatomical path of the occluded segment and distal vessels. Furthermore, it cannot provide precise spatial positioning references for instrument delivery and vascular access selection, resulting in a significant reduction in surgical accuracy.

[0025] To address the aforementioned technical issues, this application provides a medical image processing method that enables precise spatial alignment and dynamic overlay of preoperative three-dimensional target path images with intraoperative three-dimensional angiography images and two-dimensional fluoroscopic images. This provides surgeons with a fully visualized and precise spatial positioning reference for instrument delivery and vascular access selection, thereby improving the accuracy of surgical procedures.

[0026] Figure 1 This is a flowchart illustrating a medical image processing method provided in an embodiment of this application. The following is a summary of the process. Figure 1 The medical image processing method is described in detail below. The executing entity of the medical image processing can be a terminal device such as a desktop computer or a laptop computer, a client installed on the terminal device, or a server. The following description only uses the server as the executing entity to describe the medical image processing method. The medical image processing method can include: S101 to S104, as follows.

[0027] S101, acquire a three-dimensional angiographic image of the lesion area. The three-dimensional angiographic image is used to display the three-dimensional spatial structure information of the occluded blood vessels in the lesion area and the blood vessels adjacent to the occluded blood vessels.

[0028] The server can communicate with digital subtraction angiography (DSA) equipment (e.g., Siemens AIXIOM Artis dBC, Siemens AIXIOM Artis zee floor, etc.). During endovascular recanalization surgery, a contrast agent (e.g., iohexol, iodixanol, etc.) can be injected at a constant rate into the blood vessels within the lesion area. The contrast agent flows with the blood flow, filling the occluded vessel and adjacent vessels within the lesion area. The lesion area refers to the anatomical region formed by the occluded vessel and its adjacent vessels. For example, in interventional treatment of lower extremity arterial occlusion, the lesion area may include the occluded segment of the superficial femoral artery, the normal vessel segments proximal and distal to the occluded segment, and the soft tissue surrounding these vessels. Similarly, in the treatment of chronic total coronary artery occlusion (CTO), the lesion area may include the occluded coronary artery segment, its proximal and distal vessel segments, and plaque tissue on the vessel wall.

[0029] Subsequently, the digital subtraction angiography (DSA) equipment can acquire three-dimensional angiographic images of the lesion area and send the acquired three-dimensional angiographic images to the server. These three-dimensional angiographic images can be used to display the three-dimensional spatial structure information of the occluded vessel and its adjacent vessels within the lesion area, including but not limited to the overall course of the occluded vessel, the location of the occluded segment, the vessel wall contour, the distribution, diameter, and spatial relationship of adjacent vessels, and the relative spatial arrangement between the occluded vessel and its adjacent vessels.

[0030] S102, based on preset marker points, the pre-constructed three-dimensional target path image and the three-dimensional angiography image are registered and fused to obtain a fused image, in which the passable path within the occluded blood vessel is marked.

[0031] Before performing endovascular recanalization surgery on a patient, the server can pre-construct a three-dimensional target path image. This three-dimensional target path image can mark the passable path within the occluded blood vessel. The passable path is a true lumen channel through which surgical instruments can pass, which can avoid occluded tissue, calcified plaques, etc.

[0032] To eliminate spatial discrepancies between the pre-constructed 3D target path image and the intraoperative 3D angiography image caused by changes in patient position and differences in equipment coordinate systems, and to achieve a complete match between the pre-constructed 3D target path image and the patient's actual vascular anatomy during the operation, thus providing accurate path guidance for subsequent intraoperative navigation, the server can register and fuse the pre-constructed 3D target path image and the 3D angiography image based on preset marker points, thereby obtaining a fused image.

[0033] Preset landmarks are reference points that are selected in advance on the vascular anatomy and have clear and stable anatomical features. They can provide a unified spatial reference benchmark for the three-dimensional target path image pre-constructed before the operation and the three-dimensional angiography image acquired during the operation, so as to achieve the unification of the coordinate system and the calibration of the spatial position.

[0034] S103, acquire a two-dimensional perspective image of the lesion area. The two-dimensional perspective image is used to display the two-dimensional spatial structure information of the occluded blood vessel and the blood vessels adjacent to the occluded blood vessel in the lesion area, as well as the position information of the surgical instruments.

[0035] The server can communicate with 2D fluoroscopic acquisition equipment (e.g., X-ray fluoroscopy equipment). During endovascular recanalization surgery, the server can acquire real-time 2D fluoroscopic images of the lesion area from the 2D fluoroscopic acquisition equipment. These images can display the real-time spatial structure of the occluded vessel and adjacent vessels within the lesion area, including the vessel's real-time course, outline, and relative position. Simultaneously, it can clearly capture the real-time position information of surgical instruments (e.g., guidewires, catheters), providing the surgeon with a real-time relative position reference between the instruments and the vessel, as well as the accessible path. This allows the surgeon to adjust the direction of instrument operation promptly, preventing instruments from deviating from the accessible path, damaging the vessel wall, or plaque.

[0036] S104, based on the marker points, register and fuse the fused image with the two-dimensional perspective image to obtain the target navigation image.

[0037] The server can register and fuse a fused image with a 2D perspective image based on marker points to obtain a target navigation image. Specifically, it can adjust the spatial projection angles and positions of the fused image and the 2D perspective image to ensure that the 2D projection of the vascular structure in the fused image precisely matches the vascular structure in the 2D perspective image. This allows the fused image to be superimposed on the 2D perspective image, ensuring that the marked traversable paths in the fused image accurately correspond to the real-time vascular structures in the 2D perspective image, thus obtaining the target navigation image. During endovascular recanalization surgery, the surgeon can visually observe the correspondence between the vascular anatomy under real-time fluoroscopy and the pre-planned traversable paths through the target navigation image. Using this as a navigation basis, the surgeon can manipulate surgical instruments such as guidewires and catheters to safely and accurately pass through the occluded vascular segment along the planned path, improving the accuracy and safety of the surgical procedure.

[0038] Therefore, the aforementioned medical image processing method can pre-construct a three-dimensional target path image within the occluded blood vessel, overcoming the technical blind spot of traditional DSA angiography where the contrast agent cannot pass through the occluded vessel, resulting in the inability to visualize the distal vascular anatomy path. Furthermore, based on preset marker points, the three-dimensional target path image can be registered and fused with the intraoperative three-dimensional angiography image to obtain a fused image. This fused image is then registered and fused with a two-dimensional fluoroscopic image of the patient's lesion area, achieving precise spatial alignment and dynamic overlay of the preoperative three-dimensional target path image with the intraoperative three-dimensional angiography image and two-dimensional fluoroscopic image. This provides the surgeon with a fully visualized and precise spatial positioning reference for instrument delivery and vascular access selection, improving the accuracy of the surgical procedure.

[0039] In some embodiments of this application, S101 is involved in acquiring a three-dimensional angiographic image of the lesion area. S101 may include S1011 and S1012, as follows.

[0040] S1011 uses digital subtraction angiography equipment to acquire two-dimensional X-ray projection images of the lesion area from multiple angles.

[0041] The server can communicate with a digital subtraction angiography (DSA) device. The DSA device performs continuous rotational scanning around the lesion area according to preset scanning parameters and angle ranges, simultaneously acquiring two-dimensional X-ray projection images from multiple angles. The scanning parameters and angle ranges can be adaptively set according to the course of blood vessels in the lesion area and the extent of the lesion, ensuring that the acquired projection angles comprehensively cover all directions of the blood vessels in the lesion area.

[0042] In some embodiments of this application, non-vascular tissue images such as bones, muscles, and skin in two-dimensional X-ray projection images can also be removed by digital subtraction angiography equipment, leaving only the images of blood vessels and the contrast agent filling them. This can effectively improve the contrast between the vascular structure and the surrounding tissues, making it easier to accurately identify the vascular contour in the subsequent three-dimensional reconstruction process.

[0043] S1012, based on two-dimensional X-ray projection images from multiple angles, performs three-dimensional volume reconstruction to obtain three-dimensional angiographic images of the lesion area.

[0044] The server can employ a pre-defined 3D volumetric reconstruction algorithm to perform 3D volumetric reconstruction based on 2D X-ray projection images from multiple angles, obtaining a 3D angiographic image of the lesion area. 3D volumetric reconstruction can restore the 3D spatial coordinates, course, diameter, vessel wall contour, and relative positional relationships of the blood vessels in the lesion area. The 3D volumetric reconstruction algorithm can include maximum intensity projection (MIP), volume rendering (VR), multiplanar reconstruction (MPR), and extended reconstruction algorithms, among others. The specific algorithm chosen in practice can be adaptively selected based on the display requirements of the vascular structure.

[0045] In some embodiments of this application, the server may first perform preprocessing operations on the two-dimensional X-ray projection images from multiple angles, including but not limited to noise reduction, artifact removal, image alignment, and contrast optimization. Then, three-dimensional volume reconstruction can be performed based on the preprocessed images.

[0046] In some embodiments of this application, S102 is involved, in which the server can register and fuse a pre-constructed three-dimensional target path image with a three-dimensional angiography image based on preset marker points to obtain a fused image. Before S102, the above method also includes S105 to S107, as follows.

[0047] S105 uses magnetic resonance imaging equipment to acquire three-dimensional images of the blood vessel walls in the lesion area. The three-dimensional images of the blood vessel walls are used to display the three-dimensional spatial structure information of the occluded blood vessels in the lesion area, as well as the blood vessel walls, plaques, and blood vessel lumens of the adjacent blood vessels.

[0048] Before performing endovascular recanalization surgery on a patient, the server can pre-construct a three-dimensional target path image. Specifically, the server can establish a communication connection with a magnetic resonance imaging (MRI) device (e.g., Siemens MAGNETOM Skyra) to perform a high-resolution scan of the patient's lesion area before surgery. High-resolution scanning preferentially uses the 3D HR-VWI SPACE sequence, which has the advantages of high spatial resolution and high soft tissue contrast, enabling precise capture of the fine structure of the vessel wall and clear differentiation between the vessel wall, plaque, and lumen. During the scanning process, the surgeon can adjust the patient's position to a comfortable and stable scanning posture, and use a fixation device to stabilize the patient's torso and the limbs corresponding to the lesion site, avoiding image artifacts caused by the patient's breathing movements and slight changes in position during the scan. This ensures the accuracy and reliability of the acquired raw image data and reduces the interference of artifacts on subsequent structural identification.

[0049] The server can adjust the window width and window level of the image to optimize the contrast of the vessel wall, plaque, and lumen. It then employs multiplanar reconstruction (MPR) and volumetric rendering (VRT) techniques to reconstruct the original image data. Simultaneously, with the linked cursor function, it accurately locates the initiation and termination points of the occluded vessel and determines the extent of the lesion, obtaining a three-dimensional image of the vessel wall in the lesion area. This three-dimensional vessel wall image can be used to display the three-dimensional spatial structure information of the occluded vessel and adjacent vessels' walls, plaques, and lumens within the lesion area. Compared to traditional three-dimensional angiography images, this three-dimensional vessel wall image not only clearly displays the morphology and course of the vessel lumen but also directly presents detailed information about the vessel wall, such as wall thickness, plaque location, size, and composition.

[0050] S106. Based on the three-dimensional blood vessel wall image, determine the passable target trajectory within the occluded blood vessel.

[0051] S107, Construct a 3D target path image based on the target trajectory.

[0052] Specifically, the server can segment the three-dimensional blood vessel wall image to extract the blood vessel wall region, plaque region, and blood vessel lumen region of the occluded blood vessel. Then, it can analyze the blood vessel lumen region of the occluded blood vessel and identify the passable true lumen part, that is, the tiny channel that is not completely blocked by plaque or occluded tissue, has a certain passage space, and can allow surgical instruments to pass smoothly.

[0053] Then, the server can determine the passable target trajectory within the occluded blood vessel, i.e. the passable path within the occluded blood vessel, based on the identified passable true lumen portion, and construct a three-dimensional target path image based on the three-dimensional spatial coordinates, extension direction, and key node information of the target trajectory.

[0054] In some embodiments of this application, S106 is involved, in which the server can determine the passable target trajectory within the occluded blood vessel based on the three-dimensional blood vessel wall image. S106 may include S1061 to S1063, as follows.

[0055] S1061, Statistically analyze the pixel values ​​of each pixel in the three-dimensional blood vessel wall image.

[0056] S1062, Determine the target threshold based on the pixel value of each pixel.

[0057] S1063, based on the target threshold, determines the passable target trajectory within the occluded blood vessel from the three-dimensional blood vessel wall image.

[0058] Specifically, the server can traverse and count all pixels in the three-dimensional blood vessel wall image to obtain the pixel value corresponding to each pixel. This pixel value can reflect the signal intensity difference of the corresponding tissue in the image, so as to distinguish different tissue regions such as blood vessel wall, plaque and blood vessel lumen based on the pixel value.

[0059] The server can analyze the distribution characteristics of blood vessel walls, plaques, and blood vessel lumens based on the statistically obtained pixel value distribution, and determine the target threshold. This target threshold can be used as a basis for judgment to effectively distinguish the blood vessel lumen area from impassable areas such as blood vessel walls and plaques.

[0060] Then, based on the occlusion start and end points determined in the aforementioned steps, the server can locate the region where the occluded blood vessel is located in the three-dimensional blood vessel wall image. Then, based on the target threshold, the pixels in the region are segmented, and the regions whose pixel values ​​meet the target threshold requirements are identified as passable blood vessel lumen regions. Based on the spatial distribution, direction of travel, and start and end positions of the passable blood vessel lumen regions, a target trajectory that can be passed through the occluded blood vessel is generated to guide the safe movement of the surgical instruments.

[0061] In some embodiments of this application, the target trajectory can also be determined by a combination of automatic server planning and manual operator correction. Specifically, the server can generate an initial target trajectory based on a trajectory planning algorithm. Then, the operator can manually fine-tune the deviation of the initial target trajectory by combining their own clinical experience and the detailed features of the three-dimensional blood vessel wall image, correcting the offset between the trajectory and the true lumen channel, and generating the final target trajectory, thereby improving the accuracy and safety of the target trajectory.

[0062] In some embodiments of this application, S1062 is involved, in which the server can determine the target threshold based on the pixel value of each pixel. S1062 may include S10621 and S10622, as follows.

[0063] S10621, Based on the pixel values ​​of each pixel, determine the pixel value range corresponding to the blood vessel wall, the pixel value range corresponding to the plaque, and the pixel value range corresponding to the blood vessel lumen.

[0064] S10622, Based on the pixel value range corresponding to the blood vessel wall, the pixel value range corresponding to the plaque, and the pixel value range corresponding to the blood vessel lumen, determine the pixel boundary value between the passable blood vessel lumen and non-blood vessel lumen tissue, and determine the pixel boundary value as the target threshold. Non-blood vessel lumen tissue includes plaque and / or blood vessel wall.

[0065] The server can divide all statistically obtained pixel values ​​in a 3D blood vessel wall image into intervals to determine the pixel value intervals corresponding to the regions where the blood vessel wall, plaque, and blood vessel lumen are located. For example, in a 3D blood vessel wall image, the blood vessel lumen region typically has lower signal intensity, corresponding to a lower pixel value interval; blood vessel wall tissue has medium signal intensity, corresponding to a medium pixel value interval; and plaque tissue has high signal intensity, corresponding to a higher pixel value interval.

[0066] The server can select a pixel boundary value that clearly distinguishes between passable blood vessel lumens and non-vascular tissue based on the pixel value ranges corresponding to the blood vessel wall, plaque, and blood vessel lumen. This boundary value is then used as the target threshold. For example, the server can compare the minimum value of the pixel value range corresponding to the blood vessel wall with the minimum value of the pixel value range corresponding to the plaque, taking the smaller value as the minimum pixel value for non-vascular tissue. Then, the server uses the midpoint between the maximum pixel value of the pixel value range corresponding to the blood vessel lumen and the aforementioned minimum pixel value as the target threshold.

[0067] In some embodiments of this application, S1063 is involved, in which the server can determine the passable target trajectory in the occluded blood vessel from the three-dimensional blood vessel wall image based on the target threshold. S1063 may include S10631 and S10632, as follows.

[0068] S10631, Based on the target threshold, determine the passable lumen of the occluded vessel from the three-dimensional vessel wall image.

[0069] S10631, Based on the accessible vessel lumen corresponding to the occluded vessel, determine the path extending along the direction of the accessible vessel lumen corresponding to the occluded vessel, and define the path as the accessible target trajectory within the occluded vessel.

[0070] The server can compare the pixel values ​​of each pixel in the region of the occluded blood vessel in a 3D blood vessel wall image with a target threshold, and filter out pixels with values ​​less than the target threshold to form a continuous region. This region is the passable lumen of the occluded blood vessel that is not blocked by plaque or blood vessel wall and can be used by surgical instruments.

[0071] Then, the server can extract the path along the overall extension direction of the accessible vessel lumen based on the spatial distribution, morphology, and orientation of the lumen corresponding to the occluded vessel, and determine it as the target trajectory that can be traversed within the occluded vessel. The target trajectory can be the central path of the accessible vessel lumen, or it can be the optimal traversal path of the accessible vessel lumen. This optimal traversal path can be a continuous path selected within the accessible vessel lumen that is farthest from the vessel wall, has the smoothest path, and passes through the beginning and end of the occluded segment.

[0072] In some embodiments of this application, S107 is involved, in which the server can construct a three-dimensional target path image based on the target trajectory. S107 may include S1071 and S1072, as follows.

[0073] S1071, extract the three-dimensional anatomical structure of the occluded vessel, the three-dimensional anatomical structure of the proximal vessel of the occluded vessel, and the three-dimensional anatomical structure of the distal vessel of the occluded vessel from the three-dimensional vessel wall image.

[0074] S1072, based on the target trajectory, the three-dimensional anatomical structure of the occluded vessel, the three-dimensional anatomical structure of the proximal vessel of the occluded vessel, and the three-dimensional anatomical structure of the distal vessel of the occluded vessel are fused to obtain a three-dimensional target path image.

[0075] The server can combine the start and end positions of the occluded vessel determined in the aforementioned steps to extract the three-dimensional anatomical structure of the occluded vessel, the three-dimensional anatomical structure of the proximal vessel (the start of occlusion), and the three-dimensional anatomical structure of the distal vessel (the end of occlusion) from the three-dimensional vessel wall image.

[0076] Subsequently, the extracted three-dimensional anatomical structures of the three types of blood vessels are spatially registered. Using a three-dimensional spatial coordinate system as a unified benchmark, the spatial positional relationship between the three types of blood vessel structures is calibrated to ensure that proximal vessels, occluded vessels, and distal vessels can be accurately aligned according to their actual clinical anatomical locations. Then, based on the passable target trajectory within the occluded vessel determined in the aforementioned steps, the server can fuse the three-dimensional anatomical structures of these three types of blood vessels according to the corresponding spatial coordinates. This ensures that the target trajectory clearly conforms to the passable lumen of the occluded vessel and is completely connected with the lumens of the proximal and distal vessels, providing clear and precise visual guidance for subsequent intraoperative navigation.

[0077] In some embodiments of this application, the landmarks may include any one or more of bony anatomical landmarks, vascular anatomical landmarks, and imaging feature landmarks. Bony anatomical landmarks may include the spinous process of the spine, the supraorbital margin of the skull, etc. Vascular anatomical landmarks may include the bifurcation of the femoral artery, the bifurcation of the coronary artery, the origin and termination points of stenotic segments of blood vessels, etc. Imaging feature landmarks may include high-contrast edge points between the vessel wall and surrounding tissues, characteristic corner points of plaque regions, etc.

[0078] In some embodiments of this application, the registration algorithm can be improved by using a hybrid registration strategy based on anatomical landmarks and vascular centerlines, combined with deep learning algorithms, to achieve more accurate image registration. The registration accuracy can be improved from the current ±0.5mm to ±0.3mm, ensuring sub-millimeter-level navigation accuracy. Simultaneously, the image processing algorithm is optimized, increasing the fused image update rate from 15Hz to 20Hz, enabling intravascular manipulation under the guidance of the fused image and achieving a smoother real-time navigation experience.

[0079] In some embodiments of this application, the patient's possible signs of complications can also be monitored in real time, and an automatic early warning mechanism can be established to promptly remind the surgeon when an abnormality is detected.

[0080] Figure 2 This application provides a schematic diagram of a preoperative assessment image and a preoperative high-resolution MR image for a case with complications, as shown in the embodiments below. Figure 2 As shown, preoperative magnetic resonance angiography (MRA) revealed occlusion of the right internal carotid artery (RICA) segment from C4 to C6. Figure 2 In the A section, diffusion-weighted imaging (DWI) showed a high signal in the right periventricular region. Figure 2 (B in the text). Perfusion-weighted imaging (PWI) suggests the presence of hemodynamic disturbances in the right cerebral hemisphere. Figure 2 C in Figure 2 D in the image). SPACE vessel wall imaging showed RICA occlusion, with residual small cavities visible in the RICAC7 segment (D). Figure 2 E1-E4 in the middle). Preoperatively, the occluded RICA and the normal left internal carotid artery (LICA) were manually delineated. Figure 2 (F in the text).

[0081] Figure 3 This application provides an embodiment of a case involving intraoperative fusion navigation and timely symptomatic treatment for complications, as illustrated in the diagram. Figure 3 As shown, the surgery was performed under general anesthesia. Two-dimensional angiography (DSA) confirmed complete occlusion of the RICA C4 to C6 segment, and three-dimensional angiographic images of the patient were obtained. Figure 3 (A) A 6F guiding catheter (Envoy, Cordis Corporation, USA) was positioned at the C1 level, and a 0.014-inch guidewire (Synchro200, Precision Vascular System, USA) was positioned proximal to the occlusion segment. A microcatheter (Excelsior SL-10, Boston Scientific Target, USA) was then inserted for coaxial manipulation. Subsequently, a 3D fused image was overlaid on the real-time fluoroscopic image for guidance. Figure 3 (B and C in the image), the guidewire successfully passed through segments C4 and C5 under image guidance ( Figure 3 (D1-D4 in the middle). However, despite using various guidewire manipulation angles, it was still not possible to successfully cross the occluded segment of C6 (D1-D4 in the middle). Figure 3 (D3-D4 in the image). During this period, the tip of the guidewire appeared to have broken through the "virtual" blood vessel wall presented by the 3D fusion imaging. Figure 3 D5), then a microcatheter injection was performed, and the contrast agent diffused into the subarachnoid space, presenting as a "cloud sign" ( Figure 3 D6 in the middle). Immediately insert two spring coils (CDF: 4mm×8cm and 3mm×6cm) into the perforation position of segment C6 for embolization. Figure 3 D4 in the middle). Postoperative angiography showed no contrast extravasation, indicating successful embolization. Figure 3 D4 in the middle). Postoperative CT showed high-density shadows in the bilateral occipital lobes and tentorium cerebelli, suggesting subarachnoid hemorrhage (D4). Figure 3 (EG in the patient), the patient eventually recovered and was discharged from the hospital.

[0082] Figure 4 This application provides a schematic diagram of a successfully activated preoperative evaluation image and a preoperative high-resolution MR image for an embodiment of the present application. Figure 4 As shown, preoperative DSA revealed occlusion of the C7 segment of the left internal carotid artery (LICA). Figure 4 (A) Cranial CT perfusion imaging (CTP) showed significantly reduced perfusion in the left cerebral hemisphere, suggesting impaired hemodynamics in the LICA-supply area. Figure 4 (B, C, and D in the image). In the SPACE sequence MRI imaging of the vessel wall, the occluded LICA and its connected middle median artery (MCA) and anterior artery (ACA) were manually delineated. Figure 4 (E and F in the text).

[0083] Figure 5 This application provides an embodiment of a schematic diagram illustrating the successful activation and display of intraoperative fusion navigation in a case, as well as the resulting images after activation. Figure 5 As shown, three-dimensional angiographic images of the LICA were acquired intraoperatively. Figure 5 The image (A) is then fused with the preoperative MRI image to generate a fused image that fully displays the anatomical structures of the LICA, MCA, and ACA. Figure 5 (B, C in the image), and overlay the image onto the real-time perspective view for navigation ( Figure 5 (D in the text). Subsequently, after several attempts, a 0.016-inch guidewire (Synchro 200) and a microcatheter (Excelsior SL-10) were successfully used to traverse the occluded segment. Figure 5E in the text). Post-balloon dilation and stent placement DSA showed complete recanalization of the LICA, with a perfusion score of TICI 3 (…). Figure 5 (F1 and F2 in the text), the patient recovered and was discharged from the hospital after the operation.

[0084] Figure 6 This is an overall flowchart of an MRI-DSA fusion navigation system provided in an embodiment of this application.

[0085] like Figure 6 As shown, preoperatively, 3D HR-VWI SPACE sequences can be acquired, and the window width / level can be adjusted. Multiplanar reconstruction (MPR) and volumetric rendering (VRT) techniques are employed, along with a linked cursor to locate the proximal stump and distal reconstructed segment. The vessel course is obtained through automatic segmentation on the VRT / MPR images, and the segmented vessel course of all occluded segments is optimized. If the occluded segment cannot be reliably delineated through automatic segmentation, manual delineation can be used to generate a 3D target path image. Intraoperatively, 3D angiography images are acquired, and the 3D target path image is registered and fused with the 3D angiography image to obtain a fused image. This fused image is then registered and fused with a real-time acquired 2D fluoroscopic image, and superimposed on the 2D fluoroscopic image to form a target navigation image.

[0086] Figure 7 A schematic diagram of 3D MR-3D DSA registration and fusion provided for an embodiment of this application is shown below. Figure 7 As shown, where Figure 7 AC in the text refers to the 3D fusion process. Figure 7 The AC planes in the image correspond to three observation planes displayed in multiplanar projection (MPR) images: sagittal, coronal, and transverse. The white images in the image represent MRI, while the yellow images represent three-dimensional digital subtraction angiography (DSA) images. Figure 7 In the figure, D represents the 3D fusion process displayed using volumetric rendering technology (VRT).

[0087] Figure 8 This is a schematic diagram illustrating a 3D MR-DSA image fusion example provided in an embodiment of this application. Figure 8 As shown, Figure 8 The "A" in the figure indicates that the 3D DSA showed "occlusion" of the distal right vertebral artery, and the full picture of the vertebrobasilar artery was not displayed, which brings unpredictability to the endovascular recanalization treatment. Figure 8 The B in the image indicates that the vertebrobasilar artery information was acquired using the Black Blood technique in 3D reconstruction. The 3D reconstruction showed that both vertebral arteries were patent and the proximal basilar artery was partially occluded (large arrow). This provides more comprehensive information than DSA because hemodynamic effects prevent the contrast agent from reaching the vertebrobasilar junction when the proximal basilar artery is partially occluded and the contralateral vertebral artery is patent. Figure 8The "C" in the image indicates that the 3D MR-DSA image fusion shows the entire vertebrobasilar artery, including the proximal subtotal occlusion of the basilar artery (large arrow) and the distal patent portion (small arrow), which greatly assists in endovascular recanalization surgery.

[0088] In some embodiments of this application, the above-described medical image processing method can be widely applied to minimally invasive interventional recanalization surgery for chronic vascular occlusion in various parts of the body, including but not limited to: chronic coronary artery occlusion, chronic limb artery occlusion (brachial and ulnar arteries of the upper limbs, femoral, popliteal, and anterior tibial arteries of the lower limbs, etc.), chronic trunk artery occlusion (iliac artery and branches of the abdominal aorta), and chronic organ blood supply vessel occlusion (renal artery, hepatic artery, and mesenteric artery), etc. Considering the anatomical differences of blood vessels in different locations (such as vessel diameter, degree of tortuosity, and surrounding tissue type), only during the three-dimensional vessel wall imaging acquisition stage, the magnetic resonance imaging parameters (such as scanning range, slice thickness, resolution, and gating mode) need to be adaptively adjusted according to the characteristics of the corresponding blood vessels. During the target trajectory determination stage, the morphological optimization parameters (such as aspect ratio and curvature threshold for tubular feature verification) can be finely adjusted to achieve accurate extraction of the target trajectory within the occluded blood vessel in that location and accurate construction of the three-dimensional target path image. In other words, the visual navigation technology for occluded vessels can be applied to open various chronically occluded vessels throughout the body, providing precise navigation support for minimally invasive interventional treatment of chronic occlusion in different locations, thereby improving the accuracy and success rate of the surgery.

[0089] Embodiments of this application also provide a medical image processing device, such as... Figure 9 As shown, Figure 9 This is a schematic diagram of the structure of a medical image processing device provided in an embodiment of this application. The medical image processing device 900 includes: The acquisition module 901 is used to acquire three-dimensional angiography images of the lesion area. The three-dimensional angiography images are used to display the three-dimensional spatial structure information of the occluded blood vessels and adjacent blood vessels in the lesion area. The fusion module 902 is used to register and fuse a pre-constructed three-dimensional target path image with a three-dimensional angiography image based on preset marker points to obtain a fused image. The three-dimensional target path image is marked with passable paths within the occluded blood vessel. The acquisition module 901 is also used to acquire a two-dimensional perspective image of the lesion area. The two-dimensional perspective image is used to display the two-dimensional spatial structure information of the occluded blood vessel and the blood vessels adjacent to the occluded blood vessel in the lesion area, as well as the position information of the surgical instruments. The fusion module 902 is also used to register and fuse the fused image with the two-dimensional perspective image based on the marker points to obtain the target navigation image.

[0090] In some embodiments of this application, the acquisition module 901 is further configured to acquire two-dimensional X-ray projection images of the lesion area from multiple angles using a digital subtraction angiography device; and to perform three-dimensional volume reconstruction based on the two-dimensional X-ray projection images from multiple angles to obtain a three-dimensional angiography image of the lesion area.

[0091] In some embodiments of this application, the medical image processing device 900 further includes a construction module 903; The construction module 903 is used to acquire three-dimensional blood vessel wall images of the lesion area through magnetic resonance imaging equipment. The three-dimensional blood vessel wall images are used to display the three-dimensional spatial structure information of the occluded blood vessel and the blood vessel wall, plaque and lumen of the adjacent blood vessels in the lesion area. Based on the three-dimensional blood vessel wall images, the passable target trajectory in the occluded blood vessel is determined. Based on the target trajectory, a three-dimensional target path image is constructed.

[0092] In some embodiments of this application, the construction module 903 is further configured to: count the pixel values ​​of each pixel in the three-dimensional blood vessel wall image; determine a target threshold based on the pixel values ​​of each pixel; and determine a passable target trajectory within the occluded blood vessel from the three-dimensional blood vessel wall image based on the target threshold.

[0093] In some embodiments of this application, the construction module 903 is further configured to: determine the pixel value range corresponding to the blood vessel wall, the pixel value range corresponding to the plaque, and the pixel value range corresponding to the blood vessel lumen based on the pixel value of each pixel; determine the pixel boundary value between the passable blood vessel lumen and non-blood vessel lumen tissue based on the pixel value range corresponding to the blood vessel wall, the pixel value range corresponding to the plaque, and the pixel value range corresponding to the blood vessel lumen; and determine the pixel boundary value as the target threshold, wherein the non-blood vessel lumen tissue includes plaque and / or blood vessel wall.

[0094] In some embodiments of this application, the construction module 903 is further configured to: determine the passable blood vessel lumen corresponding to the occluded blood vessel from the three-dimensional blood vessel wall image based on the target threshold; determine the path along the extension direction of the passable blood vessel lumen corresponding to the occluded blood vessel based on the passable blood vessel lumen corresponding to the occluded blood vessel, and determine the path as the passable target trajectory within the occluded blood vessel.

[0095] In some embodiments of this application, the construction module 903 is further configured to extract the three-dimensional anatomical structure of the occluded blood vessel, the three-dimensional anatomical structure of the proximal blood vessel of the occluded blood vessel, and the three-dimensional anatomical structure of the distal blood vessel of the occluded blood vessel from the three-dimensional blood vessel wall image; and based on the target trajectory, fuse the three-dimensional anatomical structure of the occluded blood vessel, the three-dimensional anatomical structure of the proximal blood vessel of the occluded blood vessel, and the three-dimensional anatomical structure of the distal blood vessel of the occluded blood vessel to obtain a three-dimensional target path image.

[0096] In some embodiments of this application, the landmarks include any one or more of bony anatomical landmarks, vascular anatomical landmarks, and landmarks with influencing characteristics.

[0097] Embodiments of this application also provide a computer device, including a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein the processor executes the computer program to implement any of the above-described medical image processing methods.

[0098] Taking computer devices as terminals as an example, Figure 10 A schematic diagram of the structure of a terminal provided in an embodiment of this application is shown below. Figure 10 Terminal 1000 can be: a smartphone, tablet computer, MP3 player (Moving Picture Experts Group Audio Layer III), MP4 player (Moving Picture Experts Group Audio Layer IV), laptop computer, or desktop computer. Terminal 1000 may also be referred to as user equipment, portable terminal, laptop terminal, desktop terminal, or other names.

[0099] Typically, terminal 1000 includes a processor 1001 and a memory 1002.

[0100] In some embodiments of this application, processor 1001 may include one or more processing cores, such as a quad-core processor, a deca-core processor, etc. Processor 1001 may be implemented using at least one hardware form selected from DSP (Digital Signal Processing), FPGA (Field-Programmable Gate Array), and PLA (Programmable Logic Array). Processor 1001 may also include a main processor and a coprocessor. The main processor, also known as a CPU (Central Processing Unit), is used to process data in the wake-up state; the coprocessor is a low-power processor used to process data in the standby state. In some embodiments, processor 1001 may integrate a GPU (Graphics Processing Unit), which is responsible for rendering and drawing the content to be displayed on the screen. In some embodiments, processor 1001 may also include an AI (Artificial Intelligence) processor, which is used to handle computational operations related to machine learning.

[0101] The memory 1002 may include one or more computer-readable storage media, which may be non-transitory. The memory 1002 may also include high-speed random access memory and non-volatile memory, such as one or more disk storage devices or flash memory devices. In some embodiments, the non-transitory computer-readable storage media in the memory 1002 are used to store at least one program code, which is executed by the processor 1001 to implement the process of terminal execution in the method embodiments of this application.

[0102] In some embodiments, the terminal 1000 may also optionally include a peripheral device interface 1003 and at least one peripheral device. The processor 1001, memory 1002, and peripheral device interface 1003 can be connected via a bus or signal line. Each peripheral device can be connected to the peripheral device interface 1003 via a bus, signal line, or circuit board. Specifically, the peripheral device includes at least one of a display screen 1004, a camera assembly 1005, an audio circuit 1006, and a power supply 1007.

[0103] Peripheral device interface 1003 can be used to connect at least one I / O (Input / Output) related peripheral device to processor 1001 and memory 1002. In some embodiments, processor 1001, memory 1002 and peripheral device interface 1003 are integrated on the same chip or circuit board; in some other embodiments, any one or two of processor 1001, memory 1002 and peripheral device interface 1003 can be implemented on separate chips or circuit boards, and this application embodiment does not limit this.

[0104] Display screen 1004 is used to display a UI (User Interface). This UI may include graphics, text, icons, videos, and any combination thereof. When display screen 1004 is a touch display screen, it also has the ability to collect touch signals on or above its surface. These touch signals can be input as control signals to processor 1001 for processing. In this case, display screen 1004 can also be used to provide virtual buttons and / or a virtual keyboard, also known as soft buttons and / or a soft keyboard. In some embodiments, there may be one display screen 1004, disposed on the front panel of terminal 1000; in other embodiments, there may be at least two display screens, disposed on different surfaces of terminal 1000 or in a folded design; in still other embodiments, display screen 1004 may be a flexible display screen, disposed on a curved or folded surface of terminal 1000. Furthermore, display screen 1004 may be configured as a non-rectangular, irregular shape, i.e., a non-rectangular screen. The display screen 1004 can be made of materials such as LCD (Liquid Crystal Display) and OLED (Organic Light-Emitting Diode).

[0105] The camera assembly 1005 is used to acquire images or videos. In some embodiments, the camera assembly 1005 includes a front-facing camera and a rear-facing camera. Typically, the front-facing camera is located on the front panel of the terminal, and the rear-facing camera is located on the back of the terminal. In some embodiments, there are at least two rear-facing cameras, which are any one of a main camera, a depth-sensing camera, a wide-angle camera, and a telephoto camera, to achieve background blurring by fusion of the main camera and the depth-sensing camera, panoramic shooting by fusion of the main camera and the wide-angle camera, VR (Virtual Reality) shooting, or other fusion shooting functions. In some embodiments, the camera assembly 1005 may also include a flash. The flash can be a single-color temperature flash or a dual-color temperature flash. A dual-color temperature flash refers to a combination of a warm-light flash and a cool-light flash, which can be used for light compensation at different color temperatures.

[0106] The audio circuit 1006 may include a microphone and a speaker. The microphone is used to collect sound waves from the user and the environment, and convert the sound waves into electrical signals which are then input to the processor 1001 for processing. For stereo sound acquisition or noise reduction purposes, multiple microphones may be used, each positioned at a different location on the terminal 1000. The microphone may also be an array microphone or an omnidirectional microphone. The speaker is used to convert the electrical signals from the processor 1001 into sound waves. The speaker may be a conventional diaphragm speaker or a piezoelectric ceramic speaker. When the speaker is a piezoelectric ceramic speaker, it can convert electrical signals not only into audible sound waves but also into inaudible sound waves for purposes such as distance measurement. In some embodiments, the audio circuit 1006 may also include a headphone jack.

[0107] The power supply 1007 is used to power the various components in the terminal 1000. The power supply 1007 can be AC ​​power, DC power, a disposable battery, or a rechargeable battery. When the power supply 1007 includes a rechargeable battery, the rechargeable battery can support wired charging or wireless charging. The rechargeable battery can also be used to support fast charging technology.

[0108] Those skilled in the art will understand that Figure 10 The structure shown does not constitute a limitation on terminal 1000 and may include more or fewer components than shown, or combine certain components, or use different component arrangements.

[0109] Taking computer equipment as a server as an example, Figure 11 This is a schematic diagram of a server structure provided in an embodiment of this application. The server 1100 can vary considerably due to different configurations or performance. It may include one or more processors 1101 (Central Processing Units, CPUs) and one or more memories 1102. The one or more memories 1102 store at least one computer program, which is loaded and executed by the one or more processors 1101 to implement the aforementioned data decompression method. Of course, the server 1100 may also have wired or wireless network interfaces, a keyboard, and input / output interfaces for input and output. The server 1100 may also include other components for implementing device functions, which will not be elaborated here.

[0110] Embodiments of this application also provide a computer-readable storage medium, which includes a stored computer program, wherein the computer program, when running, controls the device where the computer-readable storage medium is located to perform the method described above. Optionally, the computer-readable storage medium may be read-only memory (ROM), random access memory (RAM), compact-disc read-only memory (CD-ROM), magnetic tape, floppy disk, and optical data storage device, etc.

[0111] Those skilled in the art will understand that all or part of the steps of the above embodiments can be implemented by hardware or by a program instructing related hardware. The program can be stored in a computer-readable storage medium, such as a read-only memory, a disk, or an optical disk.

[0112] The above description is merely an optional embodiment of this application and is not intended to limit this application. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the protection scope of this application.

Claims

1. A medical image processing method, characterized in that, include: A three-dimensional angiographic image of the lesion area is acquired, and the three-dimensional angiographic image is used to display the three-dimensional spatial structure information of the occluded blood vessel in the lesion area and the blood vessel adjacent to the occluded blood vessel; Based on preset marker points, the pre-constructed three-dimensional target path image is registered and fused with the three-dimensional angiography image to obtain a fused image. The three-dimensional target path image is marked with the passable path in the occluded blood vessel. A two-dimensional perspective image of the lesion area is obtained, and the two-dimensional perspective image is used to display the two-dimensional spatial structure information of the occluded blood vessel and the blood vessels adjacent to the occluded blood vessel in the lesion area, as well as the position information of the surgical instruments; Based on the marker points, the fused image is registered and fused with the two-dimensional perspective image to obtain the target navigation image.

2. The method according to claim 1, characterized in that, Obtain three-dimensional angiographic images of the lesion area, including: Two-dimensional X-ray projection images of the lesion area from multiple angles were acquired using digital subtraction angiography equipment. Based on the two-dimensional X-ray projection images from the multiple angles, three-dimensional volume reconstruction is performed to obtain a three-dimensional angiographic image of the lesion area.

3. The method according to claim 1, characterized in that, Before registering and fusing the pre-constructed three-dimensional target path image with the three-dimensional angiography image based on preset marker points to obtain the fused image, the method further includes: A three-dimensional image of the blood vessel wall in the lesion area is obtained using a magnetic resonance imaging device. The three-dimensional blood vessel wall image is used to display the three-dimensional spatial structure information of the occluded blood vessel in the lesion area and the blood vessel wall, plaque and lumen of the blood vessel adjacent to the occluded blood vessel. Based on the three-dimensional blood vessel wall image, determine the passable target trajectory within the occluded blood vessel; Based on the target trajectory, the three-dimensional target path image is constructed.

4. The method according to claim 3, characterized in that, Based on the three-dimensional vessel wall image, determine the passable target trajectory within the occluded vessel, including: Statistically analyze the pixel values ​​of each pixel in the three-dimensional blood vessel wall image; The target threshold is determined based on the pixel value of each pixel; Based on the target threshold, a passable target trajectory within the occluded blood vessel is determined from the three-dimensional blood vessel wall image.

5. The method according to claim 4, characterized in that, Based on the pixel values ​​of each pixel, the target threshold is determined, including: Based on the pixel values ​​of each pixel, determine the pixel value range corresponding to the blood vessel wall, the pixel value range corresponding to the plaque, and the pixel value range corresponding to the blood vessel lumen; Based on the pixel value range corresponding to the blood vessel wall, the pixel value range corresponding to the plaque, and the pixel value range corresponding to the blood vessel lumen, a pixel boundary value between the passable blood vessel lumen and non-blood vessel lumen tissue is determined, and the pixel boundary value is determined as the target threshold. The non-blood vessel lumen tissue includes plaque and / or blood vessel wall.

6. The method according to claim 5, characterized in that, Based on the target threshold, determining a passable target trajectory within the occluded blood vessel from the three-dimensional blood vessel wall image includes: Based on the target threshold, the passable blood vessel lumen corresponding to the occluded blood vessel is determined from the three-dimensional blood vessel wall image; Based on the accessible vessel lumen corresponding to the occluded vessel, a path is determined along the extension direction of the accessible vessel lumen corresponding to the occluded vessel, and the path is determined as the accessible target trajectory within the occluded vessel.

7. The method according to claim 3, characterized in that, Based on the target trajectory, the three-dimensional target path image is constructed, including: The three-dimensional anatomical structure of the occluded vessel, the three-dimensional anatomical structure of the proximal vessel of the occluded vessel, and the three-dimensional anatomical structure of the distal vessel of the occluded vessel are extracted from the three-dimensional vessel wall image. Based on the target trajectory, the three-dimensional anatomical structure of the occluded vessel, the three-dimensional anatomical structure of the proximal vessel of the occluded vessel, and the three-dimensional anatomical structure of the distal vessel of the occluded vessel are fused to obtain the three-dimensional target path image.

8. The method according to claim 1, characterized in that, The landmarks include any one or more of the following: bony anatomical landmarks, vascular anatomical landmarks, and landmarks with influencing characteristics.

9. A medical treatment device, characterized in that, include: The acquisition module is used to acquire three-dimensional angiography images of the lesion area, wherein the three-dimensional angiography images are used to display the three-dimensional spatial structure information of the occluded blood vessels in the lesion area and the blood vessels adjacent to the occluded blood vessels; The fusion module is used to register and fuse a pre-constructed three-dimensional target path image with the three-dimensional angiography image based on preset marker points to obtain a fused image. The three-dimensional target path image is marked with a passable path within the occluded blood vessel. The acquisition module is also used to acquire a two-dimensional perspective image of the lesion area, wherein the two-dimensional perspective image is used to display the two-dimensional spatial structure information of the occluded blood vessel and the blood vessel adjacent to the occluded blood vessel in the lesion area, as well as the position information of the surgical instruments; The fusion module is also used to register and fuse the fused image with the two-dimensional perspective image based on the marker points to obtain a target navigation image.

10. A computer device, characterized in that, The computer device includes a processor and a memory, the memory being used to store at least one program, the at least one program being loaded by the processor and executed as the medical image processing method as described in any one of claims 1 to 8.

Images