Sacroiliac joint synthetic CT examination technology and system thereof

Abstract

The invention discloses a sacroiliac joint synthetic CT examination technology and system, and belongs to the technical field of medical image processing, and the technology comprises the steps: data input: employing an MRI image of an axial 3DT1 MGE sequence as input data, and guaranteeing that the image quality meets the subsequent processing requirements; in the deep learning model, a deep learning neural network model is designed and trained, the model can automatically learn the mapping relation between the MRI image and the CT image, and the MRI image is converted into a CT-like image with similar CT characteristics; image processing and optimization: through image enhancement, denoising and edge detection algorithms, the quality of the generated CT-like image is further optimized, and it is ensured that the CT-like image has high resolution and accuracy when displaying erosion, hardening and ankylosing lesions. The sacroiliac joint synthetic CT examination technology and the system thereof are a promising imaging evaluation method, the advantages of MRI and CT are combined, the diagnosis accuracy of sacroiliac joint lesions is improved, and meanwhile the risk that a patient receives radiation is reduced.

Description

Technical Field

[0001] The invention belongs to the technical field of medical image processing, in particular to a sacroiliac joint synthetic CT examination technology and a system thereof. Background Art

[0002] Currently, the diagnosis of sacroiliitis mainly relies on two imaging techniques: MRI and CT.

[0003] Although MRI can show bone marrow edema and inflammation with high sensitivity, it is not as good as CT in showing bone structural lesions. CT is good at showing bone details, but there is a risk of radiation. Summary of the invention

[0004] The purpose of the present invention is to provide a sacroiliac joint synthetic CT examination technology, which converts MRI data into CT-like images with high structural details through a deep learning algorithm, so as to accurately diagnose sacroiliitis and its related lesions, while following the ALARA principle to reduce patient radiation exposure, so as to solve the problems raised in the background technology.

[0005] To achieve the above object, the present invention provides the following technical solution: sacroiliac joint synthetic CT examination technology, including:

[0006] Data input: Axial 3DT1MGE sequence MRI images were used as input data to ensure that the image quality met the requirements of subsequent processing;

[0007] Deep learning model: Design and train a deep learning neural network model that can automatically learn the mapping relationship between MRI and CT images and convert MRI images into CT-like images with CT-like characteristics;

[0008] Image processing and optimization: Through image enhancement, denoising, and edge detection algorithms, the quality of the generated CT-like images is further optimized to ensure high resolution and accuracy in displaying erosion, sclerosis, and ankylosis lesions;

[0009] Clinical application evaluation: Compare and analyze the synthetic CT images with traditional MRI and CT images to verify their superiority and accuracy in the diagnosis of sacroiliitis.

[0010] Sacroiliac joint synthetic CT examination system, including:

[0011] Data acquisition module: used to obtain high-quality MRI image data;

[0012] Deep learning processing module: Integrate the trained deep learning model to realize the conversion from MRI to CT-like images;

[0013] Image processing and display module: post-processes the converted images and provides a user interface for doctors to view and analyze;

[0014] Radiation dose control module: Follows the ALARA principle to ensure that the radiation dose is minimized during the examination.

[0015] Compared with the prior art, the technical effects and advantages of the present invention are as follows:

[0016] The sacroiliac joint synthetic CT examination technology and system proposes an innovative synthetic CT technology that combines the high sensitivity of MRI and the structural display advantages of CT to generate high-quality CT-like images through a deep learning algorithm, which not only improves diagnostic accuracy but also reduces radiation risks.

[0017] The sacroiliac joint synthetic CT examination technology and system can improve diagnostic accuracy. Compared with traditional MRI and CT, synthetic CT shows higher specificity and sensitivity in detecting structural lesions of the sacroiliac joint.

[0018] The sacroiliac joint synthetic CT examination technology and system can reduce radiation risks, avoid additional CT scans, and reduce radiation exposure of patients;

[0019] The sacroiliac joint synthetic CT examination technology and system can optimize the medical process, simplify the examination process, and reduce the burden on patients and medical costs;

[0020] The sacroiliac joint synthetic CT examination technology and system can enhance clinical decision support, provide doctors with more comprehensive and accurate imaging information, and help formulate personalized treatment plans;

[0021] The sacroiliac joint synthetic CT examination technology and system is a promising imaging evaluation method that combines the advantages of MRI and CT, improves the diagnostic accuracy of sacroiliac joint lesions, and reduces the risk of radiation exposure to patients. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] Figure 1 is a flow chart of the present invention;

[0023] Figure 2 It is a framework diagram of the present invention. DETAILED DESCRIPTION

[0024] In the following description, a large number of specific details are provided to provide a more thorough understanding of the present invention. However, it is apparent to those skilled in the art that the present invention can be implemented without one or more of these details. In other examples, in order to avoid confusion with the present invention, some technical features well known in the art are not described.

[0025] See also Figure 1 to Figure 2 .

[0026] Sacroiliac joint synthetic CT examination technology and system, including:

[0027] Data input: Axial 3DT1MGE sequence MRI images were used as input data to ensure that the image quality met the requirements of subsequent processing;

[0028] Deep learning model: Design and train a deep learning neural network model that can automatically learn the mapping relationship between MRI and CT images and convert MRI images into CT-like images with CT-like characteristics;

[0029] Image processing and optimization: Through image enhancement, denoising, and edge detection algorithms, the quality of the generated CT-like images is further optimized to ensure high resolution and accuracy in displaying erosion, sclerosis, and ankylosis lesions;

[0030] Clinical application evaluation: Compare and analyze the synthetic CT images with traditional MRI and CT images to verify their superiority and accuracy in the diagnosis of sacroiliitis.

[0031] Sacroiliac joint synthetic CT examination system, including:

[0032] Data acquisition module: used to obtain high-quality MRI image data;

[0033] Deep learning processing module: Integrate the trained deep learning model to realize the conversion from MRI to CT-like images;

[0034] Image processing and display module: post-processes the converted images and provides a user interface for doctors to view and analyze;

[0035] Radiation dose control module: Follows the ALARA principle to ensure that the radiation dose is minimized during the examination.

[0036] The specific steps are as follows:

[0037] S1, initialize the sacroiliac joint CT examination system: First, start the sacroiliac joint CT examination system located in the professional imaging room and load a specific scanning protocol for the sacroiliac joint; this protocol contains key data such as the patient's basic information (such as name, age, gender), body position (supine or side-lying), and scanning area (the junction of the sacrum and ilium); this information is then sent to the CT console integrated with the intelligent analysis module, which is connected to the CT examination system through a high-speed interface to ensure real-time data transmission and processing;

[0038] S2, high-precision image acquisition: The X-ray source and detector built into the high-resolution CT scanner are enabled, and the auxiliary 3D body surface scanner is enabled at the same time to perform synchronous X-ray scanning of the patient's sacroiliac region and 3D reconstruction of the body surface contour; the body surface scanner is located above the scanning bed to obtain unobstructed 3D data of the sacroiliac region;

[0039] S3, intelligent image preprocessing and analysis: The CT console receives the original X-ray data from the CT scanner and the three-dimensional surface data from the surface scanner; using the built-in deep learning algorithm, the intelligent analysis module performs preliminary processing on the data, including denoising, contrast enhancement, and identification of the precise position of the sacroiliac joint; in this step, the system also uses the human anatomical model library to compare the actual scan data with the standard model to preliminarily evaluate the morphology and position of the sacroiliac joint;

[0040] S4, personalized scanning parameter optimization: Based on the analysis results of step S3, the intelligent analysis module further calculates scanning parameters suitable for the individual characteristics of the patient, such as X-ray dose, scanning layer thickness, scanning angle, etc., aiming to minimize radiation exposure while maximizing the clarity and diagnostic value of the sacroiliac joint image; these optimized parameters are then sent to the CT scanner to guide the subsequent scanning process;

[0041] S5, synthetic CT image generation: After the CT scanner performs the optimized scanning sequence, the collected data is sent to the advanced image processing unit; this unit uses advanced image synthesis techniques, such as iterative reconstruction algorithms, combined with body surface scan data to generate high-resolution, low-noise three-dimensional synthetic CT images of the sacroiliac joint; this process also includes automatic correction of possible motion artifacts to ensure image quality;

[0042] S6, Image display and diagnostic assistance: In the control room, doctors view synthetic CT images through the high-resolution display on the CT console; the system provides multiple viewing modes such as multi-planar reconstruction (MPR) and maximum intensity projection (MIP), which facilitates observation of the sacroiliac joint structure from different angles; in addition, the intelligent analysis module also provides preliminary diagnostic suggestions, such as automatic identification and marking of sacroiliitis, fractures, joint dislocations, etc., to assist doctors in making quick and accurate diagnoses;

[0043] S7, Report generation and data storage: Based on the doctor's diagnosis results, the system automatically generates an examination report containing detailed image analysis and diagnostic conclusions; all original data, processed images and reports are securely stored in the hospital's internal cloud server for subsequent review and scientific research analysis.

[0044] Further workflow details include:

[0045] In step S2, the body surface scanner not only provides an accurate three-dimensional model of the patient's body surface, but is also used to monitor the patient's slight movements during the scanning process in real time to ensure scanning accuracy;

[0046] The personalized parameter optimization in step S4 also includes taking into account the weight and body shape differences of the patients to adjust the coverage of the scanning area to ensure that the sacroiliac joint is completely included in the scanning field of view;

[0047] In step S5, the image synthesis technology also combines the soft tissue and bone differential enhancement algorithm to more clearly display the soft tissue structures around the sacroiliac joint, such as ligaments and muscles;

[0048] In step S6, the system also integrates a virtual reality (VR) browsing function, allowing doctors to "walk into" the image for more intuitive observation and analysis.

[0049] This embodiment demonstrates the comprehensive process of sacroiliac joint synthetic CT examination technology and its system. From initialization to final diagnosis report generation, each step incorporates advanced intelligent technology and personalized optimization, aiming to improve diagnostic efficiency and accuracy while ensuring patient safety and comfort.

[0050] It should be noted that, in this document, relational terms such as one and two are merely used to distinguish one entity or operation from another entity or operation, but do not necessarily require or imply any actual relationship or order between these entities or operations.

[0051] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. Synthetic CT examination technology of sacroiliac joint, characterized by: include: Data input: Axial 3DT1MGE sequence MRI images were used as input data to ensure that the image quality met the requirements of subsequent processing; Deep learning model: Design and train a deep learning neural network model that can automatically learn the mapping relationship between MRI and CT images and convert MRI images into CT-like images with CT-like characteristics; Image processing and optimization: Through image enhancement, denoising, and edge detection algorithms, the quality of the generated CT-like images is further optimized to ensure high resolution and accuracy in displaying erosion, sclerosis, and ankylosis lesions; Clinical application evaluation: Compare and analyze the synthetic CT images with traditional MRI and CT images to verify their superiority and accuracy in the diagnosis of sacroiliitis.

2. A sacroiliac joint synthetic CT examination system, based on the sacroiliac joint synthetic CT examination technology of claim 1, characterized in that: include: Data acquisition module: used to obtain high-quality MRI image data; Deep learning processing module: Integrate the trained deep learning model to realize the conversion from MRI to CT-like images; Image processing and display module: post-processes the converted images and provides a user interface for doctors to view and analyze; Radiation dose control module: Follows the ALARA principle to ensure that the radiation dose is minimized during the examination.

Images