Aadrenal vein blood sampling auxiliary system based on three-dimensional reconstruction

Abstract

The invention discloses an adrenal vein blood sampling auxiliary system based on three-dimensional reconstruction. The system comprises an image acquisition module used for acquiring medical image data of an adrenal gland and a surrounding human organ tissue structure; the image preprocessing module carries out preprocessing operation on the acquired image data; the contour recognition module recognizes contours of adrenal gland, blood vessels and peripheral human organ tissue structures from the preprocessed image; the three-dimensional reconstruction module constructs a three-dimensional model of the adrenal vein and the peripheral human organ tissue structure according to the contour information; the model correction module is used for correcting and perfecting the three-dimensional model; the rendering module carries out rendering processing on the corrected three-dimensional model so as to enhance the visualization effect; and the positioning auxiliary module provides positioning auxiliary information for adrenal vein blood sampling operation. The system can effectively cope with the complex condition of a blood vessel loop, improves the three-dimensional reconstruction precision, provides accurate guidance for adrenal vein blood sampling, and assists in clinical decision making.

Description

Technical Field

[0001] The present invention belongs to the technical field of medical clinical application, and specifically refers to an adrenal vein blood sampling auxiliary system based on three-dimensional reconstruction. Background Art

[0002] Adrenal venous sampling (AVS) is a minimally invasive interventional examination method, mainly used for precise positioning and typing diagnosis of primary aldosteronism (PA). Unilateral PA with a clear typing diagnosis can be cured by surgery.

[0003] Because the adrenal veins are thin and highly variable, and there are many interfering blood vessels around them, the failure rate of adrenal venous blood sampling is high (the success rate reported at home and abroad is about 60%). Therefore, clinical experts have long believed that the difficulty and risk of AVS are far greater than adrenal surgery.

[0004] The 3D visualization model of the inferior vena cava generated by 3D reconstruction technology facilitates accurate positioning of the adrenal vein and provides precision and accuracy for adrenal vein blood sampling. However, it is currently impossible to achieve 3D reconstruction of adrenal vein CT images through conventional hospital PACS systems.

[0005] 3D reconstruction technology has important applications in the field of medical imaging, especially in the 3D reconstruction of the inferior vena cava. Through medical imaging data, including computed tomography (CT), magnetic resonance imaging (MRI) and angiography, 3D reconstruction technology can generate a mathematical model of the geometric shape and spatial structure of the inferior vena cava, providing comprehensive visual information to help doctors more accurately evaluate and analyze the morphology, size, distribution and lesions of the adrenal veins and kidneys and adrenal glands. This has important guiding significance for the classification diagnosis, treatment planning and surgical procedure selection of primary aldosteronism.

[0006] The spatially intuitive display of the inferior vena cava condition can provide richer information and play an important role in doctors' judgment of the disease. Therefore, it is necessary to design an adrenal venous blood collection auxiliary system based on three-dimensional reconstruction to effectively assist adrenal venous blood collection. Summary of the invention

[0007] In order to solve the above-mentioned problems in the prior art, the present invention proposes an adrenal venous blood sampling auxiliary system based on three-dimensional reconstruction, which can integrate multi-source image data, improve the image quality of such image data through various technical means, reconstruct a three-dimensional model, realize precise anatomical visualization, and provide strong support for users' blood collection path planning.

[0008] In order to solve the above technical problems, the technical solution adopted by the present invention is as follows: an adrenal vein blood sampling auxiliary system based on three-dimensional reconstruction, including an image acquisition module, an image preprocessing module, a contour recognition module, a three-dimensional reconstruction module, a model correction module, a rendering module, and a positioning auxiliary module, wherein: The image acquisition module is used to collect medical image data of the adrenal gland and its surrounding human organ tissue structure; The image preprocessing module performs preprocessing operations on the collected image data; The contour recognition module recognizes the contours of the adrenal glands, blood vessels and surrounding human organ tissue structures from the preprocessed image; The three-dimensional reconstruction module constructs a three-dimensional model of the adrenal vein and surrounding human organ tissue structure based on the contour information; The model correction module corrects and improves the three-dimensional model; The rendering module performs rendering processing on the corrected three-dimensional model to enhance the visualization effect; The positioning auxiliary module provides positioning auxiliary information for adrenal venous blood sampling operations.

[0009] Furthermore, the image acquisition module includes an imaging device connection unit, an image acquisition parameter setting unit and an image transmission unit, wherein: The imaging device connection unit is used to connect medical imaging devices, and the medical imaging devices include computer tomography (CT) devices; The image acquisition parameter setting unit sets the acquisition parameters of the imaging device; The image transmission unit transmits the collected image data to the image preprocessing module.

[0010] Furthermore, the image preprocessing module includes an image denoising unit, an image enhancement unit and an image segmentation unit, wherein: The image denoising unit uses a filtering algorithm to remove noise in the image; The image enhancement unit enhances the image contrast and brightness by using image enhancement technology; The image segmentation unit utilizes the numerical differences of different organ tissues in the image data of different medical imaging devices to preliminarily segment the adrenal glands, blood vessels and surrounding human organ tissue structures from the image through a threshold segmentation method.

[0011] Furthermore, the contour recognition module includes a multi-structure edge detection unit and a contour refinement unit, wherein: The multi-structure edge detection unit uses an edge detection algorithm to determine the edges of the adrenal glands, blood vessels, and surrounding human organ tissue structures; The outline refinement unit refines the identified edge outline, specifically by using a topological refinement algorithm to continuously delete pixel points of the edge outline of the adrenal vein to achieve a skeleton structure of unit width, so that the branching direction and connection relationship of the blood vessel are more clearly displayed, and by using a regional growing algorithm, taking a seed point as a starting point, the pixel points adjacent to it and having similar attributes are merged into a region to further refine the edge outline of the adrenal gland and surrounding human organ tissue structure, and by using a texture-based segmentation method, the edge outline between neural tissue and other tissues with low contrast is distinguished by calculating texture feature parameters.

[0012] Furthermore, the three-dimensional reconstruction module includes a point arrangement unit and a surface construction unit, wherein: The point placement unit arranges coordinate points along the identified blood vessel contour according to the identified blood vessel contour, and converts the spatial coordinates; The surface construction unit compares feature points of adjacent images, finds corresponding feature points, connects lines between the feature points, and constructs a surface using a triangulation method.

[0013] Furthermore, the model correction module includes a topology detection unit and a multi-source model correction unit, wherein: The topology detection unit is used to detect whether there is any abnormality in the topology structure of the three-dimensional model, and detect whether there is any abnormal intersection and interruption of the blood vessels; The multi-source model correction unit is capable of receiving and integrating image data from a variety of different medical imaging devices. The image data of medical imaging devices include not only image data from computed tomography (CT) devices, but also image data from magnetic resonance imaging (MRI) devices and angiography devices. Independent three-dimensional models of adrenal veins and surrounding human organ tissue structures are constructed for the image data from each device source. These models are compared and analyzed, and the differences in the morphology, direction, branch position of the blood vessels, and the relative position relationship of the surrounding human organ tissue structures between the models are checked through algorithms and model matching technology. For the parts with differences, comprehensive evaluation and correction are performed based on the characteristics and credibility weights of the image data from different devices, so as to obtain a more accurate, complete and real anatomical three-dimensional model.

[0014] Furthermore, the rendering module includes a material lighting setting unit and a visualization rendering unit, wherein: The material and lighting setting unit adds material and lighting effects to the three-dimensional model through texture mapping and ray tracing technology; The visualization rendering unit can switch the visibility of different blood vessels and human tissues in the model to facilitate separate observation.

[0015] Furthermore, the positioning auxiliary module includes a marker positioning unit and a path marking unit, wherein: The marking positioning unit is used for doctors to mark different selected blood vessel sections with different colors, so as to facilitate rapid differentiation and positioning of blood vessels; The path marking unit is used to mark the blood sampling path, so that the doctor can confirm the blood sampling path at any time.

[0016] The beneficial effects of the adrenal vein blood sampling auxiliary system based on three-dimensional reconstruction of the present invention are as follows: Accurate anatomical visualization: With the help of a series of modules such as three-dimensional reconstruction, model correction and rendering, the adrenal vein and the surrounding complex human organ tissue structure are intuitively presented. Doctors can observe the relationship between various structures and vascular details more clearly in space, avoiding errors that may occur due to two-dimensional image interpretation, thereby more accurately judging the condition and making more scientific diagnostic decisions; the positioning auxiliary module allows doctors to easily mark different vascular segments, quickly distinguish and locate blood vessels, and quantify the factors affecting the blood sampling path, calculate and compare the cost function, plan the best blood sampling path and highlight it, which allows doctors to perform more accurate blood sampling operations in actual blood sampling operations. During the operation, the operation path can be determined more conveniently and efficiently, the blindness and uncertainty of the operation can be reduced, and the standardization and fluency of the operation can be improved; the success rate of blood collection can be improved. The traditional adrenal vein blood collection has a high failure rate due to the thin adrenal veins, large variability and many surrounding interfering blood vessels. The system uses three-dimensional reconstruction technology to accurately present a three-dimensional model of the adrenal veins and surrounding human organ tissue structure, clearly displaying key information such as the morphology, direction, and branch location of the blood vessels, assisting doctors to more accurately locate the adrenal veins and plan the best path for blood collection operations, which is expected to significantly improve the success rate of adrenal vein blood collection, so that more patients with primary aldosteronism can receive more appropriate follow-up treatment through accurate typing diagnosis. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 This is a system architecture diagram of an adrenal venous blood sampling auxiliary system based on three-dimensional reconstruction according to the present invention; Figure 2 This is a system architecture diagram of an image acquisition module of an adrenal venous blood sampling auxiliary system based on three-dimensional reconstruction according to the present invention; Figure 3 This is a system architecture diagram of an image preprocessing module of an adrenal venous blood sampling auxiliary system based on three-dimensional reconstruction according to the present invention; Figure 4 This is a system architecture diagram of a contour recognition module of an adrenal venous blood sampling auxiliary system based on three-dimensional reconstruction according to the present invention; Figure 5 A system architecture diagram of a three-dimensional reconstruction module of an adrenal venous blood sampling auxiliary system based on three-dimensional reconstruction according to the present invention; Figure 6 This is a system architecture diagram of a model correction module of an adrenal venous blood sampling auxiliary system based on three-dimensional reconstruction according to the present invention; Figure 7 This is a system architecture diagram of a rendering module of an adrenal venous blood sampling auxiliary system based on three-dimensional reconstruction according to the present invention; Figure 8 This is a system architecture diagram of a positioning assistance module of a low-carbon travel system based on big data analysis in the present invention.

[0018] Among them, 1-image acquisition module, 11-imaging device connection unit, 12-image acquisition parameter setting unit, 13-image transmission unit, 2-image preprocessing module, 21-image denoising unit, 22-image enhancement unit, 23-image segmentation unit, 3-contour recognition module, 31-multi-structure edge detection unit, 32-contour refinement unit, 4-3D reconstruction module, 41-point layout unit, 42-surface construction unit, 5-model correction module, 51-topology detection unit, 52-multi-source model correction unit, 6-rendering module, 61-material lighting setting unit, 62-visualization rendering unit, 7-positioning auxiliary module, 71-mark positioning unit, 72-path marking unit. DETAILED DESCRIPTION

[0019] The technical solution of the present invention will be described clearly and completely below in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0020] like Figure 1-8 As shown, the present invention is an adrenal venous blood sampling auxiliary system based on three-dimensional reconstruction, including an image acquisition module 1, an image preprocessing module 2, a contour recognition module 3, a three-dimensional reconstruction module 4, a model correction module 5, a rendering module 6 and a positioning auxiliary module 7, wherein: The image acquisition module 1 is used to collect medical image data of the adrenal gland and its surrounding human organ tissue structure; The image preprocessing module 2 performs preprocessing operations on the collected image data; The contour recognition module 3 recognizes the contours of the adrenal gland, blood vessels and surrounding human organ tissue structures from the preprocessed image, and the surrounding human organ tissue structures include the adrenal gland tissue structure, nerve tissue structure, fat tissue structure and bone structure around the adrenal vein; The three-dimensional reconstruction module 4 constructs a three-dimensional model of the adrenal vein and surrounding human organ tissue structure based on the contour information; The model correction module 5 corrects and improves the three-dimensional model; The rendering module 6 performs rendering processing on the corrected three-dimensional model to enhance the visualization effect; The positioning auxiliary module 7 provides positioning auxiliary information for adrenal venous blood sampling operation.

[0021] Furthermore, the image acquisition module 1 includes an imaging device connection unit 11, an image acquisition parameter setting unit 12 and an image transmission unit 13, wherein: The imaging device connection unit 11 is used to connect medical imaging devices, and the medical imaging devices include computed tomography (CT) devices; The image acquisition parameter setting unit 12 sets acquisition parameters of the imaging device, and the acquisition parameters include resolution, layer thickness, scanning direction and angle; The image transmission unit 13 transmits the collected image data to the image preprocessing module 2 .

[0022] Furthermore, the image preprocessing module 2 includes an image denoising unit 21, an image enhancement unit 22 and an image segmentation unit 23, wherein: The image denoising unit 21 uses a filtering algorithm to remove noise in the image; The image enhancement unit 22 enhances the image contrast and brightness by using image enhancement technology, and the image enhancement technology includes grayscale transformation and histogram equalization; The image segmentation unit 23 utilizes the numerical differences of different organ tissues in the image data of different medical imaging devices to preliminarily segment the adrenal glands, blood vessels and surrounding human organ tissue structures from the image through a threshold segmentation method. The numerical differences include CT values ​​(CT imaging) and signal intensity (MRI imaging) differences.

[0023] Furthermore, the contour recognition module 3 includes a multi-structure edge detection unit 31 and a contour refinement unit 32, wherein: The multi-structure edge detection unit 31 uses an edge detection algorithm to determine the edges of the adrenal glands, blood vessels, and surrounding human organ tissue structures; The outline refinement unit 32 refines the identified edge outline. Specifically, the topological refinement algorithm is used to continuously delete pixel points of the edge outline of the adrenal vein to achieve a skeleton structure of unit width, so that the branch direction and connection relationship of the blood vessel are more clearly displayed. The regional growing algorithm is used to merge the pixel points adjacent to a seed point and having similar attributes into a region, so as to further refine the edge outline of the adrenal gland and the surrounding human organ tissue structure. The texture-based segmentation method is used to distinguish the edge outline between the neural tissue and other tissues with low contrast by calculating the texture feature parameters.

[0024] Furthermore, the three-dimensional reconstruction module 4 includes a point arrangement unit 41 and a surface construction unit 42, wherein: The point arrangement unit 41 arranges coordinate points along the identified blood vessel contour according to the identified blood vessel contour, and converts the spatial coordinates; The surface construction unit 42 compares feature points of adjacent images, finds corresponding feature points, connects lines between the feature points, and constructs a surface using a triangulation method.

[0025] In addition to constructing a three-dimensional model of the adrenal vein, a three-dimensional model of other blood vessels and kidney organs around the adrenal vein is also constructed to facilitate comparative positioning and confirmation of the position of the adrenal vein.

[0026] Furthermore, the model correction module 5 includes a topology detection unit 51 and a multi-source model correction unit 52, wherein: The topology detection unit 51 is used to detect whether there is any abnormality in the topology structure of the three-dimensional model, and whether there is any abnormal intersection and interruption of blood vessels; The multi-source model correction unit 52 is capable of receiving and integrating image data from a variety of different medical imaging devices. The image data of medical imaging devices include not only image data from computed tomography (CT) devices, but also image data from magnetic resonance imaging (MRI) devices and angiography devices. Independent three-dimensional models of the adrenal vein and surrounding human organ tissue structures are constructed for the image data from each device source. These models are compared and analyzed. Through algorithms and model matching techniques, the differences between the models in the morphology, direction, branch position of the blood vessels, and the relative position relationship of the surrounding human organ tissue structures are checked. For the parts with differences, comprehensive evaluation and correction are performed based on the characteristics and credibility weights of the image data from different devices, so as to obtain a more accurate, complete and real anatomical three-dimensional model.

[0027] Furthermore, the rendering module 6 includes a material lighting setting unit 61 and a visualization rendering unit 62, wherein: The material and lighting setting unit 61 adds material and lighting effects to the three-dimensional model through texture mapping and ray tracing technology; The visualization rendering unit 62 can switch the visibility of different blood vessels and human tissues in the model to facilitate separate observation.

[0028] Furthermore, the positioning auxiliary module 7 includes a mark positioning unit 71 and a path marking unit 72, wherein: The marking positioning unit 71 is used for the doctor to mark different selected blood vessel sections with different colors, so as to facilitate the rapid identification and positioning of blood vessels; The path marking unit 72 is used to mark the blood sampling path, so that the doctor can confirm the blood sampling path at any time.

[0029] The beneficial effects of the adrenal vein blood sampling auxiliary system based on three-dimensional reconstruction of the present invention are as follows: Accurate anatomical visualization: With the help of a series of modules such as three-dimensional reconstruction, model correction and rendering, the adrenal vein and the surrounding complex human organ tissue structure are intuitively presented. Doctors can observe the relationship between various structures and vascular details more clearly in space, avoiding errors that may occur due to two-dimensional image interpretation, thereby more accurately judging the condition and making more scientific diagnostic decisions; the positioning auxiliary module allows doctors to easily mark different vascular segments, quickly distinguish and locate blood vessels, and quantify the factors affecting the blood sampling path, calculate and compare the cost function, plan the best blood sampling path and highlight it, which allows doctors to perform more accurate blood sampling operations in actual blood sampling operations. During the operation, the operation path can be determined more conveniently and efficiently, the blindness and uncertainty of the operation can be reduced, and the standardization and fluency of the operation can be improved; the success rate of blood collection can be improved. The traditional adrenal vein blood collection has a high failure rate due to the thin adrenal veins, large variability and many surrounding interfering blood vessels. The system uses three-dimensional reconstruction technology to accurately present a three-dimensional model of the adrenal veins and surrounding human organ tissue structure, clearly displaying key information such as the morphology, direction, and branch location of the blood vessels, assisting doctors to more accurately locate the adrenal veins and plan the best path for blood collection operations, which is expected to significantly improve the success rate of adrenal vein blood collection, so that more patients with primary aldosteronism can receive more appropriate follow-up treatment through accurate typing diagnosis.

[0030] The present invention and its embodiments are described above, which is not restrictive. What is shown in the accompanying drawings is only one of the embodiments of the present invention, and the actual content is not limited to this. In short, if ordinary technicians in this field are inspired by it and do not deviate from the purpose of the invention, they can creatively design structural methods and embodiments similar to the technical scheme, which should all fall within the scope of protection of the present invention.

Claims

1. An adrenal vein blood sampling auxiliary system based on three-dimensional reconstruction, characterized in that: It comprises an image acquisition module (1), an image preprocessing module (2), a contour recognition module (3), a three-dimensional reconstruction module (4), a model correction module (5), a rendering module (6), and a positioning auxiliary module (7), wherein: The image acquisition module (1) is used to collect medical image data of the adrenal gland and its surrounding human organ tissue structure; The image preprocessing module (2) performs a preprocessing operation on the collected image data; The contour recognition module (3) recognizes the contours of the adrenal glands, blood vessels and surrounding human organ tissue structures from the preprocessed image; The three-dimensional reconstruction module (4) constructs a three-dimensional model of the adrenal vein and surrounding human organ tissue structure based on the contour information; The model correction module (5) corrects and improves the three-dimensional model; The rendering module (6) performs rendering processing on the corrected three-dimensional model to enhance the visualization effect; The positioning auxiliary module (7) provides positioning auxiliary information for adrenal venous blood sampling operations.

2. The adrenal venous blood sampling auxiliary system based on three-dimensional reconstruction according to claim 1, characterized in that: The image acquisition module (1) comprises an imaging device connection unit (11), an image acquisition parameter setting unit (12) and an image transmission unit (13), wherein: The imaging device connection unit (11) is used to connect a medical imaging device, wherein the medical imaging device includes a computer tomography (CT) device; The image acquisition parameter setting unit (12) sets acquisition parameters of the imaging device, the acquisition parameters including resolution, layer thickness, scanning direction and angle; The image transmission unit (13) transmits the collected image data to the image pre-processing module (2).

3. The adrenal vein blood sampling auxiliary system based on three-dimensional reconstruction according to claim 1, characterized in that: The image preprocessing module (2) comprises an image denoising unit (21), an image enhancement unit (22) and an image segmentation unit (23), wherein: The image denoising unit (21) uses a filtering algorithm to remove noise in the image; The image enhancement unit (22) enhances the image contrast and brightness through image enhancement technology; The image segmentation unit (23) utilizes the numerical differences of different organ tissues in the image data of different medical imaging devices to preliminarily segment the adrenal glands, blood vessels and surrounding human organ tissue structures from the image through a threshold segmentation method.

4. The adrenal venous blood sampling auxiliary system based on three-dimensional reconstruction according to claim 1, characterized in that: The contour recognition module (3) comprises a multi-structure edge detection unit (31) and a contour refinement unit (32), wherein: The multi-structure edge detection unit (31) uses an edge detection algorithm to determine the edges of the adrenal gland, blood vessels and surrounding human organ tissue structures; The contour refinement unit (32) refines the identified edge contour, specifically by using a topological refinement algorithm to continuously delete pixel points of the edge contour of the adrenal vein to achieve a skeleton structure of unit width, so that the branching direction and connection relationship of the blood vessel can be more clearly displayed, and by using a regional growing algorithm, taking a seed point as a starting point, the pixel points adjacent to it and having similar attributes are merged into a region to further refine the edge contour of the adrenal gland and surrounding human organ tissue structure, and by using a texture-based segmentation method, the edge contour between neural tissue and other tissues with low contrast is distinguished by calculating texture feature parameters.

5. The adrenal venous blood sampling auxiliary system based on three-dimensional reconstruction according to claim 1, characterized in that: The three-dimensional reconstruction module (4) comprises a point arrangement unit (41) and a surface construction unit (42), wherein: The point arrangement unit (41) arranges coordinate points along the identified blood vessel contour according to the identified blood vessel contour, and converts the spatial coordinates; The surface construction unit (42) compares feature points of adjacent images, finds corresponding feature points, connects lines between the feature points, and constructs a surface using a triangulation method.

6. The adrenal venous blood sampling auxiliary system based on three-dimensional reconstruction according to claim 1, characterized in that: The model correction module (5) comprises a topology detection unit (51) and a multi-source model correction unit (52), wherein: The topology detection unit (51) is used to detect whether there is an abnormality in the topology structure of the three-dimensional model, and to detect whether there is abnormal intersection and interruption of blood vessels; The multi-source model correction unit (52) is capable of receiving and integrating image data from a variety of different medical imaging devices. The image data of the medical imaging devices include not only image data from computed tomography (CT) devices, but also image data from magnetic resonance imaging (MRI) devices and angiography devices. An independent three-dimensional model of the adrenal vein and surrounding human organ tissue structure is constructed for the image data from each device source. These models are compared and analyzed. Through algorithms and model matching technology, the differences between the models in the morphology, direction, branch position of the blood vessels, and the relative position relationship of the surrounding human organ tissue structure are checked. For the parts with differences, comprehensive evaluation and correction are performed based on the characteristics and credibility weights of the image data from different devices, so as to obtain a more accurate, complete and real anatomical three-dimensional model.

7. The adrenal venous blood sampling auxiliary system based on three-dimensional reconstruction according to claim 1, characterized in that: The rendering module (6) comprises a material lighting setting unit (61) and a visual rendering unit (62), wherein: The material and lighting setting unit (61) adds material and lighting effects to the three-dimensional model through texture mapping and ray tracing technology; The visualization rendering unit (62) can switch the visibility of different blood vessels and human tissues in the model to facilitate separate observation.

8. The adrenal venous blood sampling auxiliary system based on three-dimensional reconstruction according to claim 1, characterized in that: The positioning auxiliary module (7) comprises a mark positioning unit (71) and a path marking unit (72), wherein: The marking positioning unit (71) is used for the doctor to mark different selected blood vessel sections with different colors, so as to facilitate the rapid identification and positioning of blood vessels; The path marking unit (72) is used to mark the blood sampling path.

Images