Real-time monitoring puncture robot tumor ablation method and system

Abstract

The invention discloses a real-time monitoring puncture robot tumor ablation method and system, and the method comprises the steps: obtaining a tumor molecular level image, combining the tumor molecular level image with medical image data, carrying out the multi-level reconstruction, and obtaining a three-dimensional model of an organ and a tumor; extracting feature points of a tumor and a surrounding anatomical structure, and performing precision registration on a tumor position in the three-dimensional model and an ablation needle; adopting a self-adaptive path planning algorithm to formulate an optimal insertion path of the puncture needle; a sensor network is integrated on the ultrasonic probe and the puncture needle, information of a needle tip and surrounding tissue is monitored, thermal field distribution and the real-time position of the needle are updated in combination with the three-dimensional model, and the power and time of the ablation needle are adjusted; after ablation is finished, ultrasonic and CT image combined examination is carried out, and the tumor coverage condition of an ablation area is detected. According to the system, more accurate real-time guidance can be provided in the puncture process, the system cost is remarkably reduced, and the operation convenience is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of image processing, and in particular to a real-time monitoring puncture robot tumor ablation method and system. Background Art

[0002] In recent years, the advancement of medical imaging technology has promoted the rapid development of image-guided percutaneous puncture technology, making it a research hotspot in minimally invasive surgery and widely used in the detection and treatment of tumor or cancer patients. Traditional tumor puncture surgery and interventional surgery usually rely on preoperative images, such as CT, MRI, ultrasound, etc., to understand the patient's lesions and plan the puncture path. During the operation, the doctor avoids important organs and vascular structures according to the preoperatively planned path, accurately delivers the puncture needle to the target location, and samples or treats the lesion.

[0003] The 3D reconstruction of preoperative images plays an important role in this process. Through 3D reconstruction, doctors can more intuitively understand the internal anatomical structure of the human body, which helps to plan a more accurate surgical path. However, some problems in traditional puncture surgery, such as hand-eye coordination during surgery, loss of direction, and difficulty in directly observing the internal structure of complex organs, pose great challenges to doctors' operations, especially for young doctors with insufficient experience. They face a long learning cycle when learning how to build 3D spatial perception based on 2D images, which affects the efficiency and accuracy of the surgery.

[0004] Traditional 3D CT images can provide clear 3D anatomical images before surgery, but cannot be updated and guided in real time during surgery. Although 2D ultrasound images have real-time imaging capabilities, they are obviously insufficient in accurately constructing 3D models, especially in terms of image clarity and noise, which makes surgical guidance difficult.

[0005] During this process, surgical navigation systems have gradually become an important tool to solve this problem. They combine preoperative images with the operation process during surgery, and help doctors understand the spatial relationship between surgical tools and target positions in real time through image registration and real-time positioning technology. Foreign surgical navigation technology started early and has developed to a relatively mature level, but most systems face problems such as high cost, complex operation and language barriers, which have affected their popularity.

[0006] At present, many advanced surgical navigation systems rely on expensive optical positioning devices, which are not only expensive, but also easily affected by occlusion during use and have high requirements for the operating environment. In addition, the use and maintenance of imported navigation systems also face problems such as language, technical adaptability and maintenance response speed, which is not conducive to their widespread promotion in China. Moreover, although there has been some research in surgical navigation systems in China, most of the results have not yet formed mature clinical applications and the penetration rate is low, especially the lack of low-cost and easy-to-operate navigation systems that adapt to the characteristics of the domestic surgical environment. Summary of the invention

[0007] In view of this, the purpose of the embodiments of the present invention is to provide a real-time monitoring puncture robot tumor ablation method and system, which can provide more accurate real-time guidance during the puncture process, significantly reduce the system cost, improve the convenience of operation, and help solve the problems of traditional surgical guidance being not real-time, relying on experience, and high cost.

[0008] In a first aspect, an embodiment of the present invention provides a real-time monitoring puncture robot tumor ablation method, which includes:

[0009] Quantum coherence imaging technology is used to obtain tumor molecular level images, which are combined with medical imaging data to perform multi-level reconstruction to obtain three-dimensional models of organs and tumors.

[0010] Feature points of the tumor and surrounding anatomical structures are extracted, and a registration algorithm is used to accurately register the tumor position in the three-dimensional model with the ablation needle.

[0011] An adaptive path planning algorithm is used to determine the optimal insertion path for the puncture needle.

[0012] A sensor network is integrated on the ultrasound probe and the puncture needle to monitor the information of the needle tip and surrounding tissues, and the thermal field distribution and the real-time position of the needle are updated in combination with the three-dimensional model to adjust the power and time of the ablation needle.

[0013] After ablation, a combined ultrasound and CT imaging examination was performed to detect the tumor coverage of the ablation area.

[0014] In combination with the first aspect, an embodiment of the present invention provides a first possible implementation of the first aspect, wherein the step of acquiring a tumor molecular level image by using quantum coherence imaging technology, combining the tumor molecular level image with medical imaging data, and performing multi-level reconstruction to obtain a three-dimensional model of the organ and the tumor includes:

[0015] The quantum dot contrast agent is injected into the tumor area using a syringe.

[0016] Quantum coherence imaging technology is used to scan the lesions with quantum sensors to obtain signal data reflecting the molecular characteristics of the tumor and generate molecular-level images of the tumor.

[0017] The lesion is scanned using computer tomography and magnetic resonance imaging techniques to obtain medical imaging data of the anatomical structure.

[0018] A multimodal registration algorithm based on mutual information is used to register the tumor molecular level image with the medical image data in the same coordinate system, so that the molecular level information and the anatomical structure information are spatially aligned to obtain fused multimodal image data.

[0019] A visualization toolkit is used to perform three-dimensional reconstruction on the fused multimodal image data.

[0020] The voxel-based marching cubes algorithm was used to mesh the surface of the tumor and surrounding tissue to generate a three-dimensional model of the organ and tumor.

[0021] Its technical effects are: by using quantum coherence imaging technology to obtain tumor molecular level images, quantum coherence imaging can be optimized for tumor-specific molecular signals, thereby improving the accuracy of tumor detection; by multimodally fusing and three-dimensionally reconstructing quantum coherence imaging data with anatomical imaging data such as CT and MRI, the surface of the tumor and its surrounding tissue is finely gridded, effectively processing the differences between different imaging data sources, generating a three-dimensional model with a clear and accurate structure, improving the quality and detail expression of three-dimensional reconstruction, and being able to display the distribution of its internal molecular characteristics, helping doctors to have more comprehensive information support in surgical planning and decision-making.

[0022] In combination with the first aspect, an embodiment of the present invention provides a second possible implementation of the first aspect, wherein the extracting feature points of the tumor and surrounding anatomical structures and using a registration algorithm to accurately register the tumor position in the three-dimensional model with the ablation needle includes:

[0023] A feature-based detection algorithm is used to extract feature points of the tumor and surrounding anatomical structures in the three-dimensional model.

[0024] The random sampling consensus algorithm is used to eliminate outliers and screen out a set of valid feature points.

[0025] A group is selected from the effective feature point set as an initial feature point pair, and the feature points in the effective feature point set are quickly aligned with the initial position feature points of the ablation needle using a nearest neighbor algorithm to obtain a roughly aligned three-dimensional model.

[0026] The result of fast registration using the iterative closest point algorithm based on mutual information is used for fine registration to obtain a finely registered 3D model.

[0027] Its technical effect is: combining feature-based detection algorithms, random sampling consistency, nearest neighbor algorithms and mutual information-based ICP algorithms to achieve high-precision alignment of tumor positions and ablation needles, reducing the complexity of doctors manually adjusting the ablation needle position during surgery. Due to the precise alignment of the ablation needle and tumor position, the system can adjust the ablation power and time based on real-time feedback to ensure that the ablation range covers the entire tumor tissue while avoiding damage to surrounding healthy tissues due to excessive ablation.

[0028] In combination with the first aspect, the embodiment of the present invention provides a third possible implementation of the first aspect, wherein the adopting an adaptive path planning algorithm to formulate an optimal insertion path for the puncture needle includes:

[0029] In the three-dimensional model, the initial position of the puncture needle P0 and the tumor ablation area A are marked. T and non-puncture area A B .

[0030] The initial position P0 of the puncture needle is used as the root node V0 of the path tree, and a fast expanding random tree algorithm is used to initialize the path tree T in the three-dimensional model, and the generated path tree T is an empty tree.

[0031] The maximum number of iterations and the random sampling range are set, and random nodes are cyclically generated in the three-dimensional model.

[0032] For each of the generated random nodes, all nodes in the path tree T are traversed to find the path tree node closest to the random node.

[0033] A fixed step length is extended from the nearest path tree node toward the random node, a new random node is generated, the path tree T is traversed repeatedly, and a corresponding path tree node is generated.

[0034] Before adding the new random node to the path tree T, calculate the path interpolation point q t =q near +t·(q new -q near )(0≤t≤1),q new is a new random node, q near For the corresponding path tree node, check each path interpolation point q t Is it located in the non-puncture area A? B , if , the corresponding path is considered to be a collision.

[0035] If there is no collision on the corresponding path, the new random node q new Add to the path tree T.

[0036] Repeat the generation of the path tree nodes until the maximum number of iterations is reached, or the nodes in the path tree T are consistent with the tumor ablation area A. T The distance is less than the preset threshold.

[0037] When the path tree T is extended to the tumor ablation area A T , trace back from the expanded new node to the root node V0 to obtain the optimal insertion path of the puncture needle.

[0038] Its technical effect is: using a fast-expanding random tree algorithm to build a path tree starting from the initial position of the puncture needle, gradually generating and expanding the path, and efficiently finding a feasible puncture path in a complex three-dimensional anatomical structure. At each expansion, the path generation is more targeted by selecting the closest node in the path tree for expansion, thereby shortening the time to reach the target. By calculating the path interpolation points and checking whether they fall into the non-puncturable area, the collision of the puncture path with the surrounding important anatomical structures (such as blood vessels, nerves, etc.) is effectively detected and avoided. By obtaining the optimal insertion path of the puncture needle, the puncture process can accurately reach the optimal position of the tumor area, thereby ensuring that the ablation needle can reach the predetermined ablation position within the shortest path and maximize the coverage of the tumor tissue.

[0039] In combination with the first aspect, an embodiment of the present invention provides a fourth possible implementation of the first aspect, wherein the sensor network is integrated on the ultrasound probe and the puncture needle to monitor the information of the needle tip and surrounding tissues, and the thermal field distribution and the real-time position of the needle are updated in combination with the three-dimensional model, and the power and time of the ablation needle are adjusted, including:

[0040] A sensor network is integrated on the ultrasound probe and the puncture needle, including a temperature sensor, a pressure sensor, a position sensor and an ultrasound sensor.

[0041] The real-time image data acquired by the ultrasonic sensor is registered with the three-dimensional model to update the precise position of the puncture needle in the three-dimensional space, the puncture angle and the state of the surrounding tissue.

[0042] Using the data obtained by the temperature sensor, a heat conduction model is established Wherein, ρ is tissue density, Q is the heat source power of the ablation needle, k is the thermal conductivity of the tissue, and c is the specific heat capacity of the tissue. The real-time temperature distribution T(x, y, z, t) in the tumor ablation area is obtained by solving.

[0043] Based on the real-time temperature distribution T(x, y, z, t), a temperature threshold is set. If the temperature of the current ablation area is lower than the temperature threshold, the output power of the ablation needle is increased; if it is higher than the temperature threshold, the output power of the ablation needle is reduced.

[0044] Its technical effects are: the real-time image data obtained by the ultrasonic sensor is aligned with the three-dimensional model, which can update the position and angle of the puncture needle in the three-dimensional space in real time, and realize real-time precise positioning and feedback; the data obtained by the temperature sensor can be combined with parameters such as tissue density, heat source power, thermal conductivity and specific heat capacity of the ablation needle to optimize the thermal field distribution and realize precise ablation. Based on the real-time temperature distribution, dynamic power adjustment can be performed to avoid excessive tissue damage. Through automated power adjustment and real-time monitoring of thermal field distribution, precise heating of the tumor area can be achieved, effectively improving the ablation efficiency and shortening the ablation time.

[0045] In combination with the first aspect, the embodiment of the present invention provides a fifth possible implementation of the first aspect, which further includes:

[0046] During the ablation process, the position of the current ablation area acquired in real time is compared with the boundary of the tumor ablation area through the sensor network.

[0047] If the deviation distance between the current ablation area and the boundary of the tumor ablation area exceeds the set threshold, it is determined that the current ablation area deviates from the tumor ablation area, and the puncture path is recalculated with the current position of the puncture needle as the root node of the path tree.

[0048] Its technical effect is that when the deviation distance exceeds the set threshold, the system will automatically determine that the ablation area has deviated from the target area and take corresponding adjustment measures to compensate for the deviation more quickly and accurately, avoiding unnecessary damage to healthy tissue due to deviation of the ablation needle.

[0049] In combination with the first aspect, an embodiment of the present invention provides a sixth possible implementation of the first aspect, wherein after performing the precision registration, the method further includes:

[0050] For the puncture needle and the ablation needle, a multi-needle coordinated ablation technology is adopted.

[0051] A three-dimensional finite element simulation model is established based on the three-dimensional model and the data collected by the sensor network.

[0052] Finite element analysis is used to simulate heat conduction during the ablation process in the three-dimensional finite element simulation model to predict the thermal field distribution of the ablation needle at different insertion positions and angles.

[0053] By setting the objective function to maximize tumor coverage and minimize healthy tissue damage, the optimization algorithm is used to calculate the optimal insertion position and optimal insertion angle of multiple needles.

[0054] Based on the optimal insertion position and the optimal insertion angle, an adaptive path planning algorithm is used to formulate the optimal insertion path of each puncture needle and avoid non-puncturable areas.

[0055] The real-time position of each needle and the state of the surrounding tissue are monitored by the integrated sensor network. If it is detected that the ablation area deviates from the expected target, the path of the corresponding needle is recalculated so that the ablation area covers the tumor.

[0056] Its technical effect is: the use of multi-needle collaborative ablation technology can perform thermal ablation treatment at multiple locations at the same time, effectively improving the efficiency of ablation. At the same time, the insertion position and angle of each needle can be flexibly adjusted during the operation to better adapt to the shape and size of the tumor and improve adaptability to irregular tumors.

[0057] In combination with the first aspect, an embodiment of the present invention provides a seventh possible implementation of the first aspect, wherein after the ablation is completed, a combined examination of ultrasound and CT images is performed to detect the tumor coverage of the ablation area, including:

[0058] A real-time ultrasound image and a CT image of the area after the ablation are obtained, and the ultrasound image and the CT image are registered to obtain a fused image.

[0059] The ablated area and the unablated tumor tissue are extracted from the fused image by using a segmentation method.

[0060] The three-dimensional model reconstructed before ablation is spatially superimposed with the extracted ablation area, and the coverage rate of the ablation area on the tumor is calculated.

[0061] If the coverage rate reaches the set threshold, the ablation surgery is judged to be effective; otherwise, the location of the residual tumor is marked and the treatment results are fed back.

[0062] Its technical effect is: through the joint examination of ultrasound and CT images, using image registration, segmentation, spatial superposition and coverage calculation, it can achieve accurate evaluation of the ablation area and non-ablated tumor tissue, and provide an automated postoperative effect judgment and feedback mechanism, thereby improving the detection accuracy of the ablation area and achieving accurate identification of tumor residues, providing accurate targeting information for subsequent supplementary ablation or other treatment methods, and helping doctors to develop more targeted treatment plans.

[0063] In combination with the first aspect, the embodiment of the present invention provides an eighth possible implementation of the first aspect, wherein after the ablation is completed, the method further includes:

[0064] The heat conduction data of the area after the ablation is completed is obtained, and the heat conduction data is fused with the three-dimensional model to establish a tumor thermal field distribution model.

[0065] Combined with the patient's tumor biological parameters, a personalized postoperative care and follow-up plan is generated.

[0066] Its technical effect is: by obtaining the heat conduction data after ablation and fusing it with the three-dimensional model, personalized postoperative care and review plans are generated in combination with the patient's biological parameters, thereby achieving accurate evaluation of the ablation effect and personalized postoperative management, improving the quality of postoperative rehabilitation, optimizing the review plan, reducing the risk of complications, promoting data-driven optimization of treatment effects, and providing patients with more scientific and effective postoperative management services.

[0067] In a second aspect, an embodiment of the present invention further provides a real-time monitoring puncture robot tumor ablation system, which includes:

[0068] The lesion modeling module is used to obtain tumor molecular level images using quantum coherence imaging technology, combine the tumor molecular level images with medical imaging data, perform multi-level reconstruction, and obtain a three-dimensional model of the organ and tumor.

[0069] The feature point matching module is used to extract the feature points of the tumor and the surrounding anatomical structure, and use a registration algorithm to accurately register the tumor position in the three-dimensional model with the ablation needle.

[0070] The path design module is used to formulate the optimal insertion path of the puncture needle using an adaptive path planning algorithm.

[0071] The sensor module is used to integrate a sensor network on the ultrasound probe and the puncture needle, monitor the information of the needle tip and surrounding tissues, update the thermal field distribution and the real-time position of the needle in combination with the three-dimensional model, and adjust the power and time of the ablation needle.

[0072] The combined inspection module is used to conduct combined inspection of ultrasound and CT images after ablation to detect the tumor coverage of the ablation area.

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

[0074] The present invention uses quantum coherence imaging technology to obtain molecular-level images of tumors, combines them with traditional medical images such as CT and MRI, performs multimodal registration and three-dimensional reconstruction, and accurately displays the morphology of the tumor and the surrounding anatomical structure.

[0075] The present invention can automatically generate the optimal puncture path by rapidly expanding adaptive path planning algorithms such as random trees, avoiding the risk of collision in non-puncturable areas and improving the safety of the operation.

[0076] The present invention monitors the status of the puncture needle and tissue in real time through a sensor network, integrates temperature, pressure, and position sensors on the puncture needle and ultrasound probe, and can monitor the needle tip position and thermal field distribution in real time, and dynamically adjust the power and time of the ablation needle based on this information, thereby more accurately controlling the ablation range and effect.

[0077] The present invention uses multi-needle collaborative ablation and finite element simulation analysis technology to optimize the insertion position and angle of multiple needles, improve tumor coverage, and reduce damage to healthy tissues;

[0078] After ablation, the present invention can accurately detect tumor coverage through the combined examination of ultrasound and CT images, and generate personalized postoperative care and review plans based on thermal conduction data and the patient's biological parameters. BRIEF DESCRIPTION OF THE DRAWINGS

[0079] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for use in the embodiments are briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without creative work.

[0080] Figure 1 A flow chart of the real-time monitored puncture robot tumor ablation method of the present invention;

[0081] Figure 2 Schematic diagram of the technical route of the real-time monitored puncture robot tumor ablation method of the present invention. DETAILED DESCRIPTION

[0082] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Generally, the components of the embodiments of the present invention described and shown in the drawings here can be arranged and designed in various different configurations.

[0083] Please refer to Figure 1 to Figure 2The first embodiment of the present invention provides a real-time monitoring puncture robot tumor ablation method, which includes: using quantum coherence imaging technology to obtain tumor molecular level images, combining the tumor molecular level images with medical imaging data, performing multi-level reconstruction, and obtaining three-dimensional models of organs and tumors; extracting feature points of the tumor and surrounding anatomical structures, and using a registration algorithm to accurately align the tumor position in the three-dimensional model with the ablation needle; using an adaptive path planning algorithm to formulate an optimal insertion path for the puncture needle; integrating a sensor network on an ultrasound probe and the puncture needle to monitor information on the needle tip and surrounding tissues, updating the thermal field distribution and the real-time position of the needle in combination with the three-dimensional model, and adjusting the power and time of the ablation needle; after the ablation is completed, performing a joint inspection of ultrasound and CT images to detect the tumor coverage of the ablation area.

[0084] In combination with the first aspect, an embodiment of the present invention provides a first possible implementation of the first aspect, wherein the use of quantum coherence imaging technology to obtain a tumor molecular level image, combining the tumor molecular level image with medical imaging data, and performing multi-level reconstruction to obtain a three-dimensional model of the organ and the tumor includes: using a syringe to inject a quantum dot contrast agent into the tumor area to improve the contrast between the tumor and surrounding normal tissues; using quantum coherence imaging technology, using a quantum sensor to scan the lesion, obtaining signal data reflecting the molecular characteristics of the tumor, and generating a tumor molecular level image; the quantum sensor uses quantum dots or superconducting quantum interference devices to detect tiny magnetic field changes inside the tumor; using computed tomography (CT) and (M The lesion is scanned by MRI technology to obtain medical image data of the anatomical structure; CT images are mainly used to accurately display the relative position relationship between the tumor position and the organ, while MRI images are used to provide high-contrast information of the soft tissue; a multimodal registration algorithm based on mutual information is used to register the tumor molecular level image with the medical image data in the same coordinate system, so that the molecular level information and the anatomical structure information are aligned in space to obtain fused multimodal image data; a visualization toolkit is used to perform three-dimensional reconstruction of the fused multimodal image data; a voxel-based marching cube algorithm is used to grid the surface of the tumor and surrounding tissue to generate a three-dimensional model of the organ and the tumor.

[0085] Among them, combined with the molecular information provided by quantum coherence imaging, the high metabolic areas, low metabolic areas and necrotic areas inside the tumor can be distinguished in the three-dimensional model.

[0086] Specifically, the step of using the visualization toolkit to perform three-dimensional reconstruction on the fused multimodal image data includes: importing the fused multimodal image data (including CT, MRI and quantum coherence imaging results) into the visualization toolkit VTK, storing it in DICOM format, reading and importing it using vtkDICOMImageReader, performing image enhancement, noise filtering and other preprocessing to ensure the reconstruction quality; using vtkImageData to store the preprocessed multimodal image data, setting the voxel size according to the required spatial resolution Among them, v x,y,z Represents the intensity value of voxels in three-dimensional space, which is used to reflect the different densities of tumors and surrounding tissues. Use vtkVolume and vtkVolumeMapper to map volume data into three-dimensional space, adjust density and transparency through different transfer functions, and highlight the boundary between tumors and surrounding tissues. In a specific embodiment, the transfer function presents high-density areas (such as bones) and low-density areas (such as soft tissues) in different colors, thereby improving the readability of the image.

[0087] Specifically, the steps of using the voxel-based marching cubes algorithm to grid the surface of the tumor and surrounding tissues to generate a three-dimensional model of the organ and the tumor include: setting an equal value threshold α to distinguish between the tumor and normal tissue, Among them, f(x, y, z) represents the binarization result of the voxel in the three-dimensional space. According to the setting of α, the boundary of the tumor tissue or organ structure is extracted; each cubic unit of the volume data is traversed, and the cubic unit is composed of eight adjacent voxel points. According to the binarization result of the voxel point, the corresponding triangular mesh is matched in the lookup table. Among them, v i The index represents the binarization result of the eight vertices of the unit cube, and is used to find a suitable triangle configuration in the lookup table; according to the triangle configuration in the lookup table, each unit cube is converted into multiple triangles, and a complete three-dimensional mesh of the tumor and organ surface is generated by splicing the multiple triangles together.

[0088] The method further includes optimizing and adjusting the surface smoothness and detail level of the three-dimensional model using three-dimensional slice reconstruction software to ensure the accuracy of the tumor and its surrounding tissue structure, wherein the specific steps include: smoothing the triangular mesh to eliminate sharp edges and noise on the surface, adjusting the position of each vertex to make it close to the average value of the neighboring vertices, Among them, v′ i is the vertex position after smoothing, λ is the smoothing coefficient, N(i) is the vertex v ineighborhood; based on smoothing, the Decimation algorithm is used to optimize the mesh, reduce the number of triangles to improve processing efficiency, and retain key structural details; the surface reconstruction function of 3DSlicer is used to generate a 3D model with better visualization effect, ensuring that the level of detail is retained when displaying the tumor and surrounding tissues, providing a more accurate surgical reference.

[0089] Its technical effects are: by using quantum coherence imaging technology to obtain tumor molecular level images, quantum coherence imaging can be optimized for tumor-specific molecular signals, thereby improving the accuracy of tumor detection; by multimodally fusing and three-dimensionally reconstructing quantum coherence imaging data with anatomical imaging data such as CT and MRI, the surface of the tumor and its surrounding tissue is finely gridded, effectively processing the differences between different imaging data sources, generating a three-dimensional model with a clear and accurate structure, improving the quality and detail expression of three-dimensional reconstruction, and being able to display the distribution of its internal molecular characteristics, helping doctors to have more comprehensive information support in surgical planning and decision-making.

[0090] In combination with the first aspect, an embodiment of the present invention provides a second possible implementation of the first aspect, wherein the extracting feature points of the tumor and surrounding anatomical structures and using a registration algorithm to accurately register the tumor position in the three-dimensional model with the ablation needle includes: using a feature-based detection algorithm to extract feature points of the tumor and surrounding anatomical structures in the three-dimensional model, specifically, using a feature detection algorithm such as SIFT (Scale Invariant Feature Transform) or SURF (Speeded Up Robust Features) to extract feature points of the tumor and its surrounding anatomical structures from the three-dimensional model, each feature point will generate a descriptor, which is a feature vector of the local image for subsequent matching and registration; using a random sampling consistency algorithm to eliminate outliers and screen out a set of valid feature points, specifically, the random sampling consistency algorithm iteratively randomly selects feature point pairs, fits the model, and evaluates the inliers and outliers of the model, sets a threshold, screens out a set of valid feature points, eliminates outliers that do not conform to the model, and outputs a set of valid feature points P. valid ={p1,p2,...,p n}; Select a group from the effective feature point set as the initial feature point pair, use the nearest neighbor algorithm to quickly align the feature points in the effective feature point set with the initial position feature points of the ablation needle to obtain a coarsely registered three-dimensional model. Specifically, select a group from the effective feature point set as the initial feature point pair P init ={p i1 ,p i2 ,...,p ik}, calculate the distance d(p i ,p j), using the nearest neighbor algorithm to match the feature points in the effective feature point set with the initial position feature points of the ablation needle, for each feature point p i In the effective feature point set P valid In the ablation needle feature point set, find the nearest neighbor point Record the matching results to form a rough registration 3D model M coarse ; The result of the rapid registration using the iterative closest point algorithm based on mutual information is finely registered to obtain a finely registered three-dimensional model. Specifically, the coarsely registered three-dimensional model M coarse As the initial input, the registration accuracy is gradually improved through iterative optimization method. In each iteration, the mutual information of the two sets of points is calculated. Update the model according to the change in mutual information, optimize the transformation matrix T until convergence, and obtain a finely registered 3D model M fine .

[0091] By comparing the finely registered three-dimensional model with the initial three-dimensional model, the degree of overlap is calculated, and the registration accuracy is quantitatively evaluated. Specifically, the voxel overlap rate index is used for evaluation.

[0092] Its technical effect is: combining feature-based detection algorithms, random sampling consistency, nearest neighbor algorithms and mutual information-based ICP algorithms to achieve high-precision alignment of tumor positions and ablation needles, reducing the complexity of doctors manually adjusting the ablation needle position during surgery. Due to the precise alignment of the ablation needle and tumor position, the system can adjust the ablation power and time based on real-time feedback to ensure that the ablation range covers the entire tumor tissue while avoiding damage to surrounding healthy tissues due to excessive ablation.

[0093] In combination with the first aspect, the embodiment of the present invention provides a third possible implementation of the first aspect, wherein the use of an adaptive path planning algorithm to formulate an optimal insertion path for the puncture needle includes: marking the initial position P0 of the puncture needle, the tumor ablation area A in the three-dimensional model; T and non-puncture area A B ; Taking the initial position P0 of the puncture needle as the root node V0 of the path tree, using the fast expansion random tree algorithm, initialize in the three-dimensional model, and generate a path tree T as an empty tree; setting the maximum number of iterations and the random sampling range, cyclically generating random nodes in the three-dimensional model; for each generated random node, traverse all nodes in the path tree T, and find the path tree node closest to the random node; extending a fixed step from the nearest path tree node toward the random node, generating a new random node, repeatedly traversing the path tree T, and generating the corresponding path tree node; before adding the new random node to the path tree T, calculating the path interpolation point q t=q near +t·(q new -q near )(0≤t≤1),q new is a new random node, q near For the corresponding path tree node, use linear interpolation to check whether the path from the nearest path tree node to the new random node is consistent with the non-puncture area A B Crossover, check each of the path interpolation points q t Is it located in the non-puncture area A? B , if , the corresponding path is considered to be a collision; if the corresponding path does not collide, the new random node q new Add to the path tree T; Repeat the generation of the path tree node until the maximum number of iterations is reached, or the node in the path tree T is consistent with the tumor ablation area A. T The distance is less than a preset threshold; when the path tree T is extended to the tumor ablation area A T , trace back from the expanded new node to the root node V0 to obtain the optimal insertion path of the puncture needle.

[0094] Its technical effect is: using a fast-expanding random tree algorithm to build a path tree starting from the initial position of the puncture needle, gradually generating and expanding the path, and efficiently finding a feasible puncture path in a complex three-dimensional anatomical structure. At each expansion, the path generation is more targeted by selecting the closest node in the path tree for expansion, thereby shortening the time to reach the target. By calculating the path interpolation points and checking whether they fall into the non-puncturable area, the collision of the puncture path with the surrounding important anatomical structures (such as blood vessels, nerves, etc.) is effectively detected and avoided. By obtaining the optimal insertion path of the puncture needle, the puncture process can accurately reach the optimal position of the tumor area, thereby ensuring that the ablation needle can reach the predetermined ablation position within the shortest path and maximize the coverage of the tumor tissue.

[0095] In combination with the first aspect, an embodiment of the present invention provides a fourth possible implementation of the first aspect, wherein a sensor network is integrated on the ultrasound probe and the puncture needle to monitor the information of the needle tip and surrounding tissues, and the thermal field distribution and the real-time position of the needle are updated in combination with the three-dimensional model, and the power and time of the ablation needle are adjusted, including: integrating a sensor network on the ultrasound probe and the puncture needle, including a temperature sensor, a pressure sensor, a position sensor and an ultrasound sensor; aligning the real-time image data acquired by the ultrasound sensor with the three-dimensional model, and updating the precise position of the puncture needle in the three-dimensional space, the puncture angle and the state of the surrounding tissues; using the data acquired by the temperature sensor to establish a heat conduction model Wherein, ρ is tissue density, Q is the heat source power of the ablation needle, k is the thermal conductivity of the tissue, and c is the specific heat capacity of the tissue. The real-time temperature distribution T(x, y, z, t) in the tumor ablation area is obtained by solving the problem. Based on the real-time temperature distribution T(x, y, z, t), a temperature threshold is set. If the temperature of the current ablation area is lower than the temperature threshold, the output power of the ablation needle is increased. If it is higher than the temperature threshold, the output power of the ablation needle is reduced. P(t+1)=P(t)+K p (T threshold -T current ), where K p is the power adjustment gain coefficient, T threshold is the temperature of the current ablation area, T current is the tissue temperature measured in real time, and P is the output power of the ablation needle.

[0096] Its technical effects are: the real-time image data obtained by the ultrasonic sensor is aligned with the three-dimensional model, which can update the position and angle of the puncture needle in the three-dimensional space in real time, and realize real-time precise positioning and feedback; the data obtained by the temperature sensor can be combined with parameters such as tissue density, heat source power, thermal conductivity and specific heat capacity of the ablation needle to optimize the thermal field distribution and realize precise ablation. Based on the real-time temperature distribution, dynamic power adjustment can be performed to avoid excessive tissue damage. Through automated power adjustment and real-time monitoring of thermal field distribution, precise heating of the tumor area can be achieved, effectively improving the ablation efficiency and shortening the ablation time.

[0097] In combination with the first aspect, an embodiment of the present invention provides a fifth possible implementation of the first aspect, which further includes: during the ablation process, the position of the current ablation area acquired in real time is compared with the boundary of the tumor ablation area through the sensor network; if the deviation distance between the current ablation area and the boundary of the tumor ablation area exceeds a set threshold, it is judged that the current ablation area deviates from the tumor ablation area, and the current position of the puncture needle is used as the root node of the path tree, and the puncture path is recalculated.

[0098] Its technical effect is that when the deviation distance exceeds the set threshold, the system will automatically determine that the ablation area has deviated from the target area and take corresponding adjustment measures to compensate for the deviation more quickly and accurately, avoiding unnecessary damage to healthy tissue due to deviation of the ablation needle.

[0099] In combination with the first aspect, an embodiment of the present invention provides a sixth possible implementation of the first aspect, wherein, after the precision alignment is performed, it also includes: for the puncture needle and the ablation needle, using multi-needle collaborative ablation technology; establishing a three-dimensional finite element simulation model based on the three-dimensional model and the data collected by the sensor network; using finite element analysis to simulate the heat conduction during the ablation process in the three-dimensional finite element simulation model, and predicting the thermal field distribution of the ablation needle at different insertion positions and angles; by setting the objective function, with the goal of maximizing tumor coverage and minimizing healthy tissue damage, using an optimization algorithm (such as a genetic algorithm or a particle swarm optimization algorithm) to calculate the optimal insertion position and optimal insertion angle of multiple needles; based on the optimal insertion position and the optimal insertion angle, using an adaptive path planning algorithm to formulate the optimal insertion path of each puncture needle, and avoiding non-puncturable areas; monitoring the real-time position and surrounding tissue status of each needle through the integrated sensor network, if it is detected that the ablation area deviates from the expected target, recalculating the path of the corresponding needle so that the ablation area covers the tumor.

[0100] Its technical effect is: the use of multi-needle collaborative ablation technology can perform thermal ablation treatment at multiple locations at the same time, effectively improving the efficiency of ablation. At the same time, the insertion position and angle of each needle can be flexibly adjusted during the operation to better adapt to the shape and size of the tumor and improve adaptability to irregular tumors.

[0101] In combination with the first aspect, an embodiment of the present invention provides a seventh possible implementation of the first aspect, wherein, after the ablation is completed, a joint examination of ultrasound and CT images is performed to detect the tumor coverage of the ablation area, including: obtaining real-time ultrasound images and CT images of the area after the ablation is completed, and performing image registration on the ultrasound image and the CT image to obtain a fused image; using a segmentation method to extract the post-ablation area and non-ablated tumor tissue from the fused image; spatially superimposing the three-dimensional model reconstructed before ablation and the extracted ablation area, and calculating the coverage rate of the ablation area on the tumor; if the coverage rate reaches the set threshold, it is determined that the ablation surgery is effective; otherwise, marking the residual tumor position and feeding back the treatment results.

[0102] Its technical effect is: through the joint examination of ultrasound and CT images, using image registration, segmentation, spatial superposition and coverage calculation, it can achieve accurate evaluation of the ablation area and non-ablated tumor tissue, and provide an automated postoperative effect judgment and feedback mechanism, thereby improving the detection accuracy of the ablation area and achieving accurate identification of tumor residues, providing accurate targeting information for subsequent supplementary ablation or other treatment methods, and helping doctors to develop more targeted treatment plans.

[0103] In combination with the first aspect, an embodiment of the present invention provides an eighth possible implementation of the first aspect, wherein, after the ablation is completed, it also includes: obtaining thermal conduction data of the area after the ablation is completed, fusing the thermal conduction data with the three-dimensional model, and establishing a tumor thermal field distribution model. Specifically, the thermal field distribution, power adjustment curve, real-time position data of the puncture needle, thermal diffusion and tissue reaction data recorded during the ablation process, and the individual tumor characteristics of the patient (such as size, shape, tissue density, etc.) are combined to establish a personalized tumor thermal field distribution model. The model reflects the conduction and attenuation of heat in the tumor and surrounding tissues during the ablation process, and is used to simulate the thermal effect and recovery of the tissue after ablation; combined with the patient's tumor biological parameters, personalized postoperative care is generated. and review plans. Specifically, the patient's biological parameters are obtained, such as the pathological type of the tumor, gene mutations, blood indicators, immune response, etc., the tissue recovery rate in the ablation area, the possible residual tumor area, and the patient's body's response to ablation are analyzed, and the tissue recovery time after ablation is predicted, including the repair rate and range of thermally damaged tissue. Combined with the thermal effect and tissue response after ablation, the need for auxiliary treatment is evaluated, such as anti-inflammatory treatment, anti-tumor drugs, etc. Specific postoperative care suggestions are provided according to the individual patient's recovery situation. Based on the residual risk and tissue recovery predicted by the thermal field model, an appropriate postoperative review time point is established. For imaging examinations of the ablation area, focus is placed on detecting changes in tissue morphology in the ablation area to observe whether there are new tumor cells or residual lesions.

[0104] Its technical effect is: by obtaining the heat conduction data after ablation and fusing it with the three-dimensional model, personalized postoperative care and review plans are generated in combination with the patient's biological parameters, thereby achieving accurate evaluation of the ablation effect and personalized postoperative management, improving the quality of postoperative rehabilitation, optimizing the review plan, reducing the risk of complications, promoting data-driven optimization of treatment effects, and providing patients with more scientific and effective postoperative management services.

[0105] The second embodiment of the present invention provides a real-time monitoring puncture robot tumor ablation system, which includes: a lesion modeling module, which is used to use quantum coherence imaging technology to obtain tumor molecular level images, combine the tumor molecular level images with medical imaging data, perform multi-level reconstruction, and obtain three-dimensional models of organs and tumors; a feature point matching module, which is used to extract feature points of tumors and surrounding anatomical structures, and use a registration algorithm to accurately align the tumor position in the three-dimensional model with the ablation needle; a path design module, which is used to use an adaptive path planning algorithm to formulate the optimal insertion path of the puncture needle; a sensor module, which is used to integrate a sensor network on the ultrasound probe and the puncture needle, monitor the information of the needle tip and surrounding tissues, update the thermal field distribution and the real-time position of the needle in combination with the three-dimensional model, and adjust the power and time of the ablation needle; a joint inspection module, which is used to perform a joint inspection of ultrasound and CT images after the ablation is completed to detect the tumor coverage of the ablation area.

[0106] The computer program product of the real-time monitored puncture robot tumor ablation method and device provided in the embodiments of the present invention includes a computer-readable storage medium storing program code. The instructions included in the program code can be used to execute the method in the previous method embodiment. The specific implementation can be found in the method embodiment, which will not be repeated here.

[0107] Specifically, the storage medium can be a general storage medium, such as a mobile disk, a hard disk, etc. When the computer program on the storage medium is run, the above-mentioned real-time monitoring puncture robot tumor ablation method can be executed, thereby providing more accurate real-time guidance during the puncture process, significantly reducing the system cost, improving the convenience of operation, and helping to solve the problems of traditional technology such as non-real-time surgical guidance, reliance on experience, and high cost.

[0108] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a non-volatile computer-readable storage medium that is executable by a processor. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0109] Finally, it should be noted that the above-described embodiments are only specific implementations of the present invention, which are used to illustrate the technical solutions of the present invention, rather than to limit them. The protection scope of the present invention is not limited thereto. Although the present invention is described in detail with reference to the above-described embodiments, ordinary technicians in the field should understand that any technician familiar with the technical field can still modify the technical solutions recorded in the above-described embodiments within the technical scope disclosed by the present invention, or can easily think of changes, or make equivalent replacements for some of the technical features therein; and these modifications, changes or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention shall be based on the protection scope of the claims.

Claims

1. A real-time monitoring puncture robot tumor ablation method, characterized in that: include: Using quantum coherence imaging technology to obtain tumor molecular level images, combining the tumor molecular level images with medical imaging data, performing multi-level reconstruction, and obtaining a three-dimensional model of the organ and tumor; Extracting characteristic points of the tumor and surrounding anatomical structures, and using a registration algorithm to accurately register the tumor position in the three-dimensional model with the ablation needle; Adopt adaptive path planning algorithm to develop the optimal insertion path of the puncture needle; Integrate a sensor network on the ultrasound probe and the puncture needle to monitor information of the needle tip and surrounding tissues, update the thermal field distribution and the real-time position of the needle in combination with the three-dimensional model, and adjust the power and time of the ablation needle; After ablation, a combined ultrasound and CT imaging examination was performed to detect the tumor coverage of the ablation area.

2. The real-time monitoring puncture robot tumor ablation method according to claim 1, characterized in that: The method of using quantum coherence imaging technology to obtain tumor molecular level images, combining the tumor molecular level images with medical imaging data, and performing multi-level reconstruction to obtain a three-dimensional model of the organ and tumor includes: The quantum dot contrast agent is injected into the tumor area using a syringe; Using quantum coherence imaging technology, quantum sensors are used to scan lesions, obtain signal data reflecting the molecular characteristics of tumors, and generate images of tumors at the molecular level; Scanning the lesion using computer tomography and magnetic resonance imaging techniques to obtain medical imaging data of the anatomical structure; Using a multimodal registration algorithm based on mutual information, the tumor molecular level image and the medical image data are registered in the same coordinate system, so that the molecular level information and the anatomical structure information are spatially aligned to obtain fused multimodal image data; Using a visualization toolkit to perform three-dimensional reconstruction on the fused multi-modal imaging data; The voxel-based marching cubes algorithm was used to mesh the surface of the tumor and surrounding tissue to generate a three-dimensional model of the organ and tumor.

3. The real-time monitoring puncture robot tumor ablation method according to claim 1, characterized in that: The extracting of characteristic points of the tumor and surrounding anatomical structures and using a registration algorithm to accurately register the tumor position in the three-dimensional model with the ablation needle includes: Using a feature-based detection algorithm to extract feature points of the tumor and surrounding anatomical structures in the three-dimensional model; Use the random sampling consensus algorithm to eliminate outliers and screen out a set of valid feature points; Selecting a group from the effective feature point set as an initial feature point pair, using a nearest neighbor algorithm to quickly align the feature points in the effective feature point set with the initial position feature points of the ablation needle to obtain a roughly registered three-dimensional model; The result of fast registration using the iterative closest point algorithm based on mutual information is used for fine registration to obtain a finely registered 3D model.

4. The real-time monitoring puncture robot tumor ablation method according to claim 1, characterized in that: The method of using an adaptive path planning algorithm to formulate an optimal insertion path for the puncture needle includes: In the three-dimensional model, the initial position of the puncture needle P0 and the tumor ablation area A are marked. T and non-puncture area A B ; Taking the initial position P0 of the puncture needle as the root node V0 of the path tree, using the fast expansion random tree algorithm, initialize in the three-dimensional model, and generate a path tree T as an empty tree; Setting a maximum number of iterations and a random sampling range, and cyclically generating random nodes in the three-dimensional model; For each of the generated random nodes, traverse all nodes in the path tree T to find the path tree node closest to the random node; Extending a fixed step from the nearest path tree node toward the random node, generating a new random node, repeatedly traversing the path tree T, and generating the corresponding path tree node; Before adding the new random node to the path tree T, calculate the path interpolation point q t =q near +t·(q new -q near )(0≤t≤1),q new is a new random node, q near For the corresponding path tree node, check each path interpolation point q t Is it located in the non-puncture area A? B , if , then the corresponding path is considered to be a collision; If there is no collision on the corresponding path, the new random node q new Add to the path tree T; Repeat the generation of the path tree nodes until the maximum number of iterations is reached, or the nodes in the path tree T are consistent with the tumor ablation area A. T The distance is less than a preset threshold; When the path tree T is extended to the tumor ablation area A T , trace back from the expanded new node to the root node V0 to obtain the optimal insertion path of the puncture needle.

5. The real-time monitoring puncture robot tumor ablation method according to claim 4, characterized in that: The sensor network is integrated on the ultrasound probe and the puncture needle to monitor the information of the needle tip and surrounding tissues, and the thermal field distribution and the real-time position of the needle are updated in combination with the three-dimensional model to adjust the power and time of the ablation needle. Integrating a sensor network on the ultrasound probe and the puncture needle, including a temperature sensor, a pressure sensor, a position sensor and an ultrasound sensor; The real-time image data acquired by the ultrasonic sensor is registered with the three-dimensional model to update the precise position of the puncture needle in the three-dimensional space, the puncture angle and the state of the surrounding tissue; Using the data obtained by the temperature sensor, a heat conduction model is established Wherein, ρ is tissue density, Q is the heat source power of the ablation needle, k is the thermal conductivity of the tissue, and c is the specific heat capacity of the tissue. The real-time temperature distribution T(x, y, z, t) in the tumor ablation area is obtained by solving; Based on the real-time temperature distribution T(x, y, z, t), a temperature threshold is set. If the temperature of the current ablation area is lower than the temperature threshold, the output power of the ablation needle is increased; if it is higher than the temperature threshold, the output power of the ablation needle is reduced.

6. The real-time monitoring puncture robot tumor ablation method according to claim 5, characterized in that: Also includes: During the ablation process, the position of the current ablation area acquired in real time is compared with the boundary of the tumor ablation area through the sensor network; If the deviation distance between the current ablation area and the boundary of the tumor ablation area exceeds the set threshold, it is determined that the current ablation area deviates from the tumor ablation area, and the puncture path is recalculated with the current position of the puncture needle as the root node of the path tree.

7. The real-time monitoring puncture robot tumor ablation method according to claim 6, characterized in that: After the precision registration is performed, the method further includes: For the puncture needle and the ablation needle, a multi-needle coordinated ablation technology is adopted; Establishing a three-dimensional finite element simulation model based on the three-dimensional model and the data collected by the sensor network; Using finite element analysis, simulating heat conduction during the ablation process in the three-dimensional finite element simulation model, and predicting the thermal field distribution of the ablation needle at different insertion positions and angles; By setting the objective function to maximize tumor coverage and minimize healthy tissue damage, the optimization algorithm is used to calculate the optimal insertion position and angle of multiple needles; Based on the optimal insertion position and the optimal insertion angle, an adaptive path planning algorithm is used to formulate an optimal insertion path for each puncture needle, and avoid non-puncturable areas; The real-time position of each needle and the state of the surrounding tissue are monitored by the integrated sensor network. If it is detected that the ablation area deviates from the expected target, the path of the corresponding needle is recalculated so that the ablation area covers the tumor.

8. The real-time monitoring puncture robot tumor ablation method according to claim 1, characterized in that: After the ablation is completed, a combined ultrasound and CT imaging examination is performed to detect the tumor coverage of the ablation area, including: Acquire a real-time ultrasound image and a CT image of the area after the ablation is completed, and perform image registration on the ultrasound image and the CT image to obtain a fused image; A segmentation method is used to extract the ablated area and the unablated tumor tissue from the fused image; spatially superimposing the three-dimensional model reconstructed before ablation with the extracted ablation area, and calculating the coverage rate of the ablation area on the tumor; If the coverage rate reaches the set threshold, the ablation surgery is judged to be effective; otherwise, the location of the residual tumor is marked and the treatment results are fed back.

9. The real-time monitoring puncture robot tumor ablation method according to claim 8, characterized in that: After the ablation is completed, the method further includes: Acquiring heat conduction data of the area after ablation, fusing the heat conduction data with the three-dimensional model, and establishing a tumor thermal field distribution model; Combined with the patient's tumor biological parameters, a personalized postoperative care and follow-up plan is generated.

10. A real-time monitoring puncture robot tumor ablation system, characterized in that: include: A lesion modeling module is used to obtain tumor molecular level images using quantum coherence imaging technology, combine the tumor molecular level images with medical imaging data, perform multi-level reconstruction, and obtain a three-dimensional model of the organ and tumor; A feature point matching module is used to extract feature points of the tumor and surrounding anatomical structures, and use a registration algorithm to accurately register the tumor position in the three-dimensional model with the ablation needle; A path design module is used to formulate the optimal insertion path of the puncture needle using an adaptive path planning algorithm; A sensor module, which is used to integrate a sensor network on the ultrasound probe and the puncture needle, monitor the information of the needle tip and surrounding tissues, update the thermal field distribution and the real-time position of the needle in combination with the three-dimensional model, and adjust the power and time of the ablation needle; The combined inspection module is used to conduct combined inspection of ultrasound and CT images after ablation to detect the tumor coverage of the ablation area.

Images