Medical tomographic image loading method and system, electronic equipment and storage medium

Abstract

The invention discloses a medical tomographic image loading method and system, electronic equipment and a storage medium. The medical cross-sectional image loading method comprises the following steps: based on attribute information of a checked first medical cross-sectional image, determining a second medical cross-sectional image associated with the first medical cross-sectional image according to a preset rule, and pre-loading the second medical cross-sectional image; and in response to the operation of a user on the first medical cross-sectional image and / or the second medical cross-sectional image, selectively loading partial hierarchical images or image areas of the first medical cross-sectional image and / or the second medical cross-sectional image under the given hierarchical loading structure. According to the method, through predictive preloading and layered loading technologies, the loading efficiency of the medical cross-sectional image can be remarkably improved, and the display flexibility is enhanced.

Description

Technical Field

[0001] This application relates to the field of medical image processing, specifically to a method and system for loading medical tomographic images, an electronic device, and a storage medium. Background Technology

[0002] In the field of medical diagnostics, medical computed tomography (CT) imaging is widely used in various medical imaging examinations. With the continuous growth of medical image data, existing image loading and processing methods have room for improvement in terms of loading speed, memory usage, display flexibility, and storage efficiency. During image loading, various factors can influence the process, including file size, network transmission conditions, and system resource status. In certain application scenarios, fluctuations in these factors may have a certain impact on the efficiency of medical diagnosis.

[0003] Therefore, there is a need to provide more efficient and flexible medical image loading and display solutions to meet the growing demand for medical diagnosis.

[0004] The background art description is provided solely for the purpose of understanding the relevant technologies in this field and is not intended as an admission of prior art. Summary of the Invention

[0005] In this regard, the embodiments of this application aim to provide a method and system for loading medical tomographic images, an electronic device and a storage medium, which can improve the loading efficiency of medical tomographic images and enhance display flexibility.

[0006] In a first aspect, embodiments of this application provide a method for loading medical tomographic images, comprising: Based on the attribute information of the first medical tomographic image being viewed, a second medical tomographic image associated with the first medical tomographic image is determined according to a preset rule, and the second medical tomographic image is preloaded. In response to user operations on the first and / or second medical tomographic images, selectively load a portion of the first and / or second medical tomographic images or image regions under a given layered loading structure.

[0007] In some embodiments, the hierarchical loading structure includes one or more of the following: spatial hierarchical loading structure, sequence interval hierarchical loading structure, resolution hierarchical loading structure, region of interest (ROI) hierarchical loading structure, and reconstruction plane hierarchical loading structure.

[0008] In some embodiments, the selective loading of a portion of the layered image or image region of the first and / or second medical tomographic images under a given layered loading structure in response to a user's operation on the first and / or second medical tomographic images includes: Determine the current layer position of the tomographic image in the first and / or second medical tomographic images currently being viewed by the user; The range of adjacent layers is determined based on the current layer position and the preset number of adjacent layers, thus obtaining a target layer list; Load the tomographic images corresponding to the target layer list from the first medical tomographic image and / or the second medical tomographic image.

[0009] In some embodiments, the selective loading of a portion of the layered image or image region of the first and / or second medical tomographic images under a given layered loading structure in response to a user's operation on the first and / or second medical tomographic images includes: Obtain a complete list of slice sequences of the first medical tomographic image and / or the second medical tomographic image; Based on the layer interval parameters set by the user, interval layers are selected from all layer sequences of the first medical tomographic image and / or the second medical tomographic image to obtain a list of interval layers. Load the tomographic images corresponding to the list of interval layers from the first medical tomographic image and / or the second medical tomographic image; In response to a user's action of viewing other layers that are not interstitial layers, tomographic images of the corresponding other layers in the first medical tomographic image and / or the second medical tomographic image are loaded.

[0010] In some embodiments, the selective loading of a portion of the layered image or image region of the first and / or second medical tomographic images under a given layered loading structure in response to a user's operation on the first and / or second medical tomographic images includes: Load a first-resolution image of the first medical tomographic image and / or the second medical tomographic image for user preview and / or navigation operations; In response to a user's zoom-in operation, determine the coordinate range of the layer sequence or zoom-in region corresponding to the zoom-in operation; Load a second resolution image or image region corresponding to the magnified region in the first medical tomographic image and / or the second medical tomographic image, wherein the second resolution is greater than the first resolution.

[0011] In some embodiments, the selective loading of a portion of the layered image or image region of the first and / or second medical tomographic images under a given layered loading structure in response to a user's operation on the first and / or second medical tomographic images includes: In response to the user's selection operation on the first medical tomographic image and / or the second medical tomographic image, determine the coordinate range of the region of interest (ROI) corresponding to the selection operation; The region outside the region of interest in the first and / or second medical tomographic images is retained as a third-resolution image or image region. Load a fourth resolution image region corresponding to the region of interest from the first medical tomographic image and / or the second medical tomographic image, wherein the fourth resolution is greater than the third resolution.

[0012] In some embodiments, the selective loading of a portion of the layered image or image region of the first and / or second medical tomographic images under a given layered loading structure in response to a user's operation on the first and / or second medical tomographic images includes: In response to a user's planar selection operation on the first medical tomographic image and / or the second medical tomographic image, the planar direction corresponding to the planar selection operation is determined; Based on the plane orientation, a reconstructed planar image corresponding to the plane orientation is dynamically reconstructed from the original tomographic data of the first medical tomographic image and / or the second medical tomographic image; Load the reconstructed planar image.

[0013] In some embodiments, the preset rules include one or more of the following: examination type association rules, diagnostic process association rules, time association rules, and lesion area association rules.

[0014] In some embodiments, determining the second medical tomographic image associated with the first medical tomographic image based on the attribute information of the viewed first medical tomographic image according to a preset rule includes: Obtain the examination type and patient identifier of the first medical computed tomography image; Based on the association rules of the inspection type, query other inspection types associated with the inspection type to obtain a list of associated inspection types; The medical tomographic images belonging to the list of associated examination types are selected from the medical tomographic images corresponding to the patient identifier and used as the second medical tomographic images.

[0015] In some embodiments, determining the second medical tomographic image associated with the first medical tomographic image based on the attribute information of the viewed first medical tomographic image according to a preset rule includes: Obtain the sequence type and examination type of the first medical computed tomography image; According to the diagnostic process association rules, query other sequence types in the diagnostic process corresponding to the sequence type to obtain a list of associated sequence types; Medical tomographic images that relate to the list of associated sequence types are selected from the medical tomographic images corresponding to the examination type and used as the second medical tomographic images.

[0016] In some embodiments, determining the second medical tomographic image associated with the first medical tomographic image based on the attribute information of the viewed first medical tomographic image according to a preset rule includes: Obtain the patient identification, examination site, and examination time of the first medical tomographic image; Based on the time association rules, the historical time range of the association is determined according to the inspection time; The medical tomographic images corresponding to the patient identifier that involve the examination site and whose examination time is within the historical time range are selected as the second medical tomographic images.

[0017] In some embodiments, determining the second medical tomographic image associated with the first medical tomographic image based on the attribute information of the viewed first medical tomographic image according to a preset rule includes: Obtain the lesion area marked by the user in the first medical tomographic image; The medical tomographic image containing the lesion region is determined according to the lesion region association rule and used as the second medical tomographic image.

[0018] In some embodiments, determining a second medical tomographic image associated with the first medical tomographic image based on attribute information of the viewed first medical tomographic image according to a preset rule, and preloading the second medical tomographic image, includes: Based on the attribute information of the first medical tomographic image, the second medical tomographic image is obtained from the server according to the preset rules; The acquired second medical tomographic image is preloaded into the client's memory.

[0019] In some embodiments, the method further includes: Monitor the memory usage of the client's memory; When the memory usage reaches a preset threshold, at least a portion of the memory space occupied by the medical tomographic images stored in the client's memory is released based on the access status of the medical tomographic images.

[0020] In a second aspect, embodiments of this application provide a medical tomographic image loading system, comprising: The preloading module is configured to determine and preload a second medical tomographic image associated with the first medical tomographic image based on the attribute information of the first medical tomographic image being viewed, according to preset rules. The layered loading module is configured to selectively load a portion of the layered image or image region of the first medical tomographic image and / or the second medical tomographic image under a given layered loading structure in response to user operations on the first medical tomographic image and / or the second medical tomographic image.

[0021] In some embodiments, the medical computed tomography (CT) image loading system includes a client and a server, wherein: The server includes a storage module for storing medical tomographic images; The client includes the preloading module and the hierarchical loading module; The preloading module is configured to obtain the second medical tomographic image from the medical tomographic images stored on the server according to the preset rules based on the attribute information of the first medical tomographic image, and preload the obtained second medical tomographic image into the client memory.

[0022] In some embodiments, the client further includes a memory manager configured to monitor the memory usage of the client's memory, and when the memory usage reaches a preset threshold, to release at least a portion of the memory space occupied by the medical tomographic images stored in the client's memory based on the access status of the medical tomographic images stored in the client's memory.

[0023] In some embodiments, the hierarchical loading structure includes one or more of the following: spatial hierarchical loading structure, sequence interval hierarchical loading structure, resolution hierarchical loading structure, region of interest (ROI) hierarchical loading structure, and reconstruction plane hierarchical loading structure.

[0024] In some embodiments, the layered loading module is further configured to: determine the current layer position of the tomographic image in the first medical tomographic image and / or the second medical tomographic image currently viewed by the user; determine the range of adjacent layers according to the current layer position and a preset adjacent layer number parameter to obtain a target layer list; and load the tomographic image in the first medical tomographic image and / or the second medical tomographic image corresponding to the target layer list.

[0025] In some embodiments, the layer loading module is further configured to: obtain a complete list of layer sequences of the first medical tomographic image and / or the second medical tomographic image; select interval layers in the complete layer sequences of the first medical tomographic image and / or the second medical tomographic image according to the layer interval parameters set by the user, so as to obtain an interval layer list; load the tomographic images of the first medical tomographic image and / or the second medical tomographic image corresponding to the interval layer list; and, in response to the user's operation of viewing other layers that are not interval layers, load the tomographic images of the first medical tomographic image and / or the second medical tomographic image corresponding to the other layers.

[0026] In some embodiments, the layer loading module is further configured to: load a first resolution image of the first medical tomographic image and / or the second medical tomographic image for user preview and / or navigation operations; in response to the user's zoom-in operation, determine the coordinate range of the layer sequence or zoomed-in area corresponding to the zoom-in operation; and load a second resolution image or image area in the first medical tomographic image and / or the second medical tomographic image corresponding to the zoomed-in area, wherein the second resolution is greater than the first resolution.

[0027] In some embodiments, the layered loading module is further configured to: in response to a user's selection operation on the first medical tomographic image and / or the second medical tomographic image, determine the coordinate range of the region of interest (ROI) corresponding to the selection operation; maintain the region outside the ROI in the first medical tomographic image and / or the second medical tomographic image as a third resolution image or image region; and load a fourth resolution image region in the first medical tomographic image and / or the second medical tomographic image corresponding to the ROI, wherein the fourth resolution is greater than the third resolution.

[0028] In some embodiments, the layered loading module is further configured to: in response to a user's planar selection operation on the first medical tomographic image and / or the second medical tomographic image, determine the planar direction corresponding to the planar selection operation; dynamically reconstruct a reconstructed planar image corresponding to the planar direction from the original tomographic data of the first medical tomographic image and / or the second medical tomographic image according to the planar direction; and load the reconstructed planar image.

[0029] In some embodiments, the preset rules include one or more of the following: examination type association rules, diagnostic process association rules, time association rules, and lesion area association rules.

[0030] In some embodiments, the preloading module is further configured to: obtain the examination type and patient identifier of the first medical tomographic image; query other examination types associated with the examination type according to the examination type association rules to obtain an associated examination type list; and filter out medical tomographic images belonging to the associated examination type list from the medical tomographic images corresponding to the patient identifier as the second medical tomographic image.

[0031] In some embodiments, the preloading module is further configured to: obtain the sequence type and examination type of the first medical tomographic image; query other sequence types in the diagnostic process corresponding to the sequence type according to the diagnostic process association rules to obtain an associated sequence type list; and filter out medical tomographic images involving the associated sequence type list from the medical tomographic images corresponding to the examination type as the second medical tomographic image.

[0032] In some embodiments, the preloading module is further configured to: acquire the patient identifier, examination site, and examination time of the first medical tomographic image; determine the associated historical time range based on the examination time according to the time association rule; and select medical tomographic images involving the examination site and whose examination time is within the historical time range from the medical tomographic images corresponding to the patient identifier as the second medical tomographic image.

[0033] In some embodiments, the preloading module is further configured to: acquire the lesion region marked by the user in the first medical tomographic image; and determine the medical tomographic image containing the lesion region according to the lesion region association rule, as the second medical tomographic image.

[0034] In a third aspect, embodiments of this application provide an electronic device, including a processor and a memory, wherein the memory stores computer program instructions, and the processor, when executing the computer program instructions, implements the medical tomographic image loading method as described in the first aspect.

[0035] In a fourth aspect, embodiments of this application provide a computer storage medium storing computer program instructions, wherein when the computer program instructions are executed by a processor, the medical tomographic image loading method as described in the first aspect is implemented.

[0036] The medical tomographic image loading method provided in this application intelligently determines and preloads a second medical tomographic image associated with the first medical tomographic image based on its attribute information and according to preset rules. It also selectively loads partial layers or image regions using a layered loading structure responsive to user operations. This solves the technical problems of traditional image loading methods in terms of loading speed and memory usage. In particular, by employing a predictive preloading strategy and fine-grained layered loading technology, this solution significantly reduces user waiting time and lowers peak memory usage, thereby improving the efficiency and flexibility of medical tomographic image loading.

[0037] In a further embodiment of this application, the hierarchical loading structure may include various hierarchical loading structures such as spatial hierarchical loading structure, sequence interval hierarchical loading structure, resolution hierarchical loading structure, region of interest (ROI) hierarchical loading structure, and reconstruction plane hierarchical loading structure. These hierarchical loading structures can be flexibly combined and used according to different user operation types. This further solution solves the technical problem of differentiated loading requirements under different application scenarios. By selectively choosing a suitable hierarchical loading structure, this further solution can achieve optimized loading performance under different operation scenarios. For example, spatial hierarchical loading is used during scrolling browsing, and resolution hierarchical loading is used during zooming in, enabling the system to flexibly adapt to various diagnostic operation requirements.

[0038] In a further embodiment of this application, the preset rules may include examination type association rules, diagnostic process association rules, time association rules, lesion area association rules, etc., and these preset rules can be flexibly combined and used according to different situations. By predicting associated images based on the actual workflow of medical diagnosis, this further approach makes preloading result in a smoother user experience, more efficient resource utilization, and significantly improves the diagnostic efficiency of medical tomographic images.

[0039] In a further embodiment of this application, in the case of a client-server architecture, client memory usage is monitored in real time. This solution, by monitoring client memory usage in real time, intelligently releases unused image data when a preset threshold is reached. This maintains system stability in scenarios with concurrent loading of multiple images and effectively avoids the risk of system crashes due to memory overflow.

[0040] Optional features and other effects of the embodiments of this application are described in part below, and in part will be apparent from reading this document. Attached Figure Description

[0041] The embodiments of this application will be described in detail with reference to the accompanying drawings. The elements shown are not limited to the scale shown in the drawings, and the same or similar reference numerals in the drawings denote the same or similar elements, wherein: Figure 1 A flowchart of a medical tomographic image loading method according to an embodiment of this application is shown; Figure 2 A flowchart of a medical tomographic image loading method according to an embodiment of this application is shown; Figure 3 A flowchart of a medical tomographic image loading method according to an embodiment of this application is shown; Figure 4 A flowchart of a medical tomographic image loading method according to an embodiment of this application is shown; Figure 5 A flowchart of a medical tomographic image loading method according to an embodiment of this application is shown; Figure 6 A flowchart of a medical tomographic image loading method according to an embodiment of this application is shown; Figure 7 A flowchart of a medical tomographic image loading method according to an embodiment of this application is shown; Figure 8 A flowchart of a medical tomographic image loading method according to an embodiment of this application is shown; Figure 9 A flowchart of a medical tomographic image loading method according to an embodiment of this application is shown; Figure 10A flowchart of a medical tomographic image loading method according to an embodiment of this application is shown; Figure 11 A flowchart of a medical tomographic image loading method according to an embodiment of this application is shown; Figure 12 A flowchart of a medical tomographic image loading method according to an embodiment of this application is shown; Figure 13 An exemplary block diagram of a medical tomographic image loading system according to an embodiment of this application is shown; Figure 14 An exemplary block diagram of a medical tomographic image loading system based on a client-server architecture according to an embodiment of this application is shown; and Figure 15 An exemplary structural diagram of an electronic device that can implement the methods according to embodiments of this application is shown. Detailed Implementation

[0042] To make the objectives, technical solutions, and advantages of this application clearer, the application will be further described in detail below with reference to specific embodiments and accompanying drawings. Here, the illustrative embodiments and descriptions of this application are used to explain this application, but are not intended to limit this application.

[0043] The term "comprising" and its variations as used herein signify open inclusion, i.e., "including but not limited to". Unless otherwise stated, the term "or" means "and / or". The term "based on" means "at least partially based on". The terms "one example embodiment" and "one embodiment" mean "at least one example embodiment". The term "another embodiment" means "at least one additional embodiment". The terms "first", "second", etc., may refer to different or the same objects.

[0044] The acquisition, processing, storage, transmission, and use of user data that may be involved in the embodiments of this application, such as patient health information, biometric information, and other sensitive personal information (hereinafter collectively referred to as "user data"), strictly comply with the laws and regulations of relevant countries and regions (such as, but not limited to, the Personal Information Protection Law, the Data Security Law, and the Regulations on the Supervision and Administration of Medical Devices) and industry standards. The collection, acquisition, and use of user data involved in the embodiments of this application are all conducted with the full knowledge, understanding, and separate authorization of the user / patient. In implementing the embodiments of this application, the user / patient will be informed of the types of user data or information that may be involved, the scope of use, and the usage scenarios through appropriate means, and authorization will be obtained. Any user data processing activity will be conducted on a legal basis (such as obtaining the separate consent of the personal information subject or being necessary for the performance of a contract), and will only be processed within the scope stipulated by laws and regulations or explicitly agreed upon by the user / patient. The user / patient's refusal to process personal information beyond the information necessary to achieve the basic functions will not affect the normal use of the core functions of this application.

[0045] Any artificial intelligence algorithms, decision-making models, or recommendation models (if applicable) involved in the embodiments of this application have been designed to be free from any discriminatory or biased factors. The input features and decision-making logic of the algorithms and models are strictly based on objective medical and technical indicators to ensure that they do not violate social morality, do not harm public interests, and comply with the principles of scientific and technological ethics.

[0046] As mentioned earlier, in the field of medical diagnostics, there is room for improvement in the loading and processing of medical computed tomography images in terms of loading speed, memory usage, and display flexibility. These issues become more pronounced when the image data volume is large, system resources are limited, or frequent switching between different images is required, potentially disrupting the physician's diagnostic workflow.

[0047] For example, some known medical image loading schemes typically use a full-load approach, loading the entire image file into memory at once. However, this method has the following problems: First, the loading time is long, requiring doctors to wait for the complete image to load before viewing it, affecting diagnostic efficiency; second, it consumes a lot of memory, especially when multiple images need to be viewed simultaneously, potentially leading to system resource strain or even crashes; third, the display is not flexible enough, unable to dynamically adjust the loaded content according to the doctor's actual viewing needs, resulting in unnecessary resource consumption; fourth, it lacks an intelligent prediction mechanism, unable to preload related images that the doctor might view, requiring a reloading process every time images are switched.

[0048] In a illustrative, and not restrictive, sense, in medical diagnostic settings, physicians' image viewing behavior typically follows certain patterns and rules. For example, when reviewing a patient's plain CT scan, physicians often need to compare it with the patient's contrast-enhanced CT images; when reviewing a particular MRI sequence, it is usually necessary to combine it with other sequences for a comprehensive diagnosis; and during follow-up diagnoses, it is necessary to compare the patient's historical images. Furthermore, the physician's actions when viewing specific images are also predictable; for example, when scrolling, they primarily focus on adjacent layers, and when zooming in, they primarily focus on specific areas.

[0049] To address this issue, this application provides a medical tomographic image loading method and a corresponding medical tomographic image loading system. Through a predictive preloading mechanism and fine-grained layered loading technology, the aforementioned problems can be effectively alleviated or overcome. Regarding preloading, based on the attribute information of the image to be viewed and preset rules, related images that may be viewed are intelligently predicted and loaded in advance. Regarding layered loading, according to the user's specific operation type, an appropriate layered loading structure is selected, loading only the currently required layers or image regions, thereby achieving dual optimization of loading efficiency and resource utilization.

[0050] The embodiments of this application will now be described in detail with reference to the accompanying drawings.

[0051] like Figure 1 As shown in the figure, this application provides a method for loading medical tomographic images.

[0052] In some embodiments, the method can be applied to a medical information system. In a preferred embodiment, the method can be applied to a medical information system based on a client-server architecture, wherein the client includes, but is not limited to, a doctor's workstation, an image diagnostic terminal, etc.

[0053] In this application, "medical tomographic images" refer to medical image sequences obtained through tomographic scanning. In some embodiments, medical tomographic images may be images in DICOM (Digital Imaging and Communications in Medicine) format, including but not limited to CT (Computed Tomography) images, MRI (Magnetic Resonance Imaging) images, PET (Positron Emission Tomography) images, etc. By way of explanation and not limitation, DICOM is a widely used standard format in the field of medical imaging, containing image data and rich metadata information. In other embodiments, medical tomographic images may also have other formats, such as, but not limited to, NIfTI (Neuroimaging Informatics Technology Initiative) format, ANALYZE format, or other suitable medical image formats. The embodiments of this application will be described below using DICOM format medical tomographic images as an example, but the scope of this application is not limited thereto.

[0054] refer to Figure 1 The medical computed tomography (CT) image loading method may include steps S110 and S120: S110: Based on the attribute information of the viewed first medical tomographic image, determine the second medical tomographic image associated with the first medical tomographic image according to preset rules, and preload the second medical tomographic image.

[0055] In this embodiment of the application, the first medical tomographic image being viewed encompasses medical tomographic images that the user (e.g., a doctor) is currently viewing or that have been viewed in the past (e.g., recently). Preferably, the first medical tomographic image is the medical tomographic image that the user is currently viewing.

[0056] In this embodiment, the attribute information of the first medical tomographic image may include, but is not limited to: patient identification (e.g., patient ID, patient name, etc.), examination type (e.g., plain CT scan, enhanced CT scan, plain MRI scan, enhanced MRI scan, PET-CT, etc.), examination site (e.g., head, chest, abdomen, pelvis, etc.), examination time (e.g., examination date and time), sequence type (e.g., for MRI images, this may include T1-weighted images, T2-weighted images, FLAIR images, DWI images, etc.), and image dimension information (e.g., number of slices, slice spacing, pixel size, etc.). This attribute information is typically stored in the metadata of the medical tomographic image, such as the DICOM tag of a DICOM format image, and can be obtained through a standard interface.

[0057] In this embodiment, the second medical tomographic image refers to a medical tomographic image that is associated with the first medical tomographic image being viewed based on preset rules.

[0058] In this embodiment, the preset rules involve a set of rules for predicting and determining associated images that may be viewed by a user. These rules enable the automatic inference of associated second medical tomographic images based on the attributes of the currently viewed first medical tomographic image, thus allowing for preloading. As an explanation, and not a limitation, the preset rules are designed based on the actual workflow of medical diagnosis and doctors' viewing habits, thereby maximizing the accuracy and effectiveness of preloading.

[0059] In this application embodiment, the preset rules may include, but are not limited to, one or more of the following: examination type association rules, diagnostic process association rules, time association rules, lesion area association rules, etc., as further described below.

[0060] As described above, the method provided in this application can be applied to a medical information system based on a client-server architecture. Therefore, one or more second medical tomographic images associated with a first medical tomographic image can be filtered from medical tomographic images stored on the server according to preset rules, and the second medical tomographic images are preloaded into the client's memory, enabling a rapid response when the user actually views these images.

[0061] Specifically, such as Figure 2 As shown, step S110 may include the following sub-steps S210 and S220: S210: Based on the attribute information of the first medical tomographic image, obtain the second medical tomographic image from the server according to preset rules.

[0062] In this embodiment of the application, in step S210, the client can generate a query request based on the attribute information of the first medical tomographic image, apply preset rules, and send the query request to the server. After receiving the query request, the server can filter out the second medical tomographic image that meets the conditions from its stored medical tomographic images according to the query request.

[0063] In some embodiments, the server can be a medical tomographic image database or a Picture Archiving and Communication System (PACS), which stores a large number of medical tomographic images and their metadata. The server searches the database or PACS system based on the filtering criteria specified in the query request (e.g., patient identifier, examination type, examination time range, examination site, etc.) to select second medical tomographic images that meet the criteria.

[0064] S220: Preload the acquired second medical tomographic image into the client memory.

[0065] In this embodiment, in step S220, the client receives the second medical tomographic image data obtained from the server and loads it into the client's memory for caching. Therefore, when the user switches to view the second medical tomographic image, the system can directly read the data from memory for display, thus significantly reducing waiting time.

[0066] In some embodiments, the server may employ a tiered return strategy when returning second medical tomographic images to the client. For example, during the preloading process, the server may first return basic-level data of the second medical tomographic images, including low-resolution images and / or key-layer images, so that the client can quickly preload and preview them; when the user actually views the second medical tomographic images, the client can then obtain detailed-level data from the server for further loading (as described in the tiered loading strategy below).

[0067] In another alternative embodiment, a continuous dynamic preloading strategy can be implemented. During the user's viewing of the first medical tomographic image, the system continuously monitors the user's viewing behavior, such as the time the user spends on a particular image, and the areas the user marks or manipulates. Based on changes in viewing behavior, the determination results of the second medical tomographic image can be dynamically updated, and the preloaded content can be adjusted in real time.

[0068] exist Figure 2 The illustrated implementation describes a specific method for preloading the second medical tomographic image in step S110 using a client-server architecture. However, it is conceivable that the method of this embodiment can also employ other architectures to implement the preloading described in step S110. For example, it can be implemented in a single-machine system, where the image data is stored in a local storage medium, thereby directly reading the second medical tomographic image from the local storage medium for preloading; or a distributed storage architecture can be used, where the image data is distributed across multiple server nodes, and the client obtains the second medical tomographic image from different nodes according to a load balancing strategy. All of the above-described different architectures fall within the scope of this application.

[0069] In some embodiments, the preset rules may include inspection type association rules. Specifically, inspection type association rules predict images of related inspection types that a user may view based on the correlation between different inspection types.

[0070] like Figure 3 As shown, when using an inspection type association rule, step S110 may include the following sub-steps: S310: Obtain the examination type and patient identification for the first medical tomographic image.

[0071] In this embodiment of the application, in step S310, the examination type and patient identifier can be extracted from the metadata of the first medical computed tomographic image. In some embodiments, the examination type identifies the type of examination to which the image belongs, such as plain CT scan, enhanced CT scan, plain MRI scan, enhanced MRI scan, PET-CT, etc. In some embodiments, the patient identifier can be used to uniquely identify the patient and can be a patient ID, patient name, or other unique identifier.

[0072] S320: Query other inspection types associated with the inspection type according to the inspection type association rules to obtain a list of associated inspection types.

[0073] In this embodiment of the application, in step S320, other inspection types associated with the current inspection type can be queried according to pre-configured inspection type association rules. In some embodiments, the inspection type association rules can be configured through an inspection type association query table, which can record the correspondence between each inspection type and its associated other inspection types.

[0074] As an explanation, and not a limitation, the examination type association lookup table can be configured based on common comparative needs in medical diagnostic practice. For example, in clinical diagnosis, when reviewing plain CT images, doctors can compare them with enhanced CT images to observe the enhancement characteristics of lesions; when reviewing CT images, they can combine them with PET-CT images for metabolic assessment. Therefore, the examination type association lookup table can include the following correspondences: plain CT associated with enhanced CT; CT associated with PET-CT, etc.

[0075] In some embodiments, the examination type association lookup table can be configured by the system administrator according to the medical institution's diagnostic process, or it can be customized by the user according to their personal habits.

[0076] S330: Select medical tomographic images that belong to the list of associated examination types from the medical tomographic images corresponding to the patient identifier, and use them as the second medical tomographic images.

[0077] In this embodiment of the application, in step S330, all medical tomographic images of the patient can be retrieved from the medical tomographic image database stored on the server according to the patient identifier, and images whose examination type belongs to the list of associated examination types can be filtered out and preloaded as second medical tomographic images.

[0078] For example, if the first medical tomographic image is a plain CT chest image of a patient, the associated examination type list can be determined in step S320 as ["CT enhanced", "PET-CT"]. Then, based on the patient's patient identifier, images with the examination type of "CT enhanced" or "PET-CT" can be queried and filtered from all of the patient's images as the second medical tomographic image. Optionally, if the patient has multiple enhanced CT examinations, the system can further filter based on conditions such as examination time and examination location, for example, prioritizing images with an examination time close to that of the first medical tomographic image, or selecting images with the same examination location.

[0079] By using examination type association rules, the system can predict which other examination types a doctor might compare when viewing images of a certain examination type. This allows for preloading of images in advance, reducing waiting time for doctors when switching images and improving diagnostic efficiency.

[0080] In some embodiments, the preset rules may include diagnostic process association rules. These rules can predict which sequences of images a user might view, based on the sequence order within a typical diagnostic process.

[0081] like Figure 4 As shown, when using diagnostic process association rules, step S110 may include the following sub-steps: S410: Obtain the sequence type and examination type of the first medical tomographic image.

[0082] In this embodiment of the application, in step S410, the sequence type and examination type can be extracted from the metadata of the first medical computed tomographic image. In a specific example, the sequence types applicable to MRI images include, but are not limited to, T1-weighted images, T2-weighted images, FLAIR images, DWI images, etc., where different sequences provide different tissue contrast information. In this example, the examination type can indicate the type of examination to which the image belongs, such as brain MRI, abdominal MRI, etc.

[0083] S420: Query other sequence types in the diagnostic process corresponding to the sequence type according to the diagnostic process association rules to obtain a list of associated sequence types.

[0084] In this embodiment of the application, in step S420, other sequence types in the diagnostic process corresponding to the current sequence type can be queried according to the pre-configured diagnostic process association rules.

[0085] In a illustrative and not restrictive sense, different examination sites typically have their own typical diagnostic procedures and sequence combinations. For example, in MRI diagnosis, in the brain MRI diagnostic procedure, doctors usually review multiple sequences such as T1-weighted images, T2-weighted images, FLAIR images, and DWI images. These sequences provide complementary diagnostic information, and combined analysis can improve diagnostic accuracy. In the abdominal MRI diagnostic procedure, common sequences include T1-weighted images, T2-weighted images, and diffusion-weighted images. Accordingly, a diagnostic flow procedure list can contain the correspondence between typical diagnostic procedures and sequence combinations.

[0086] In some embodiments, the list of diagnostic flow procedures can be configured based on the diagnostic guidelines of a medical institution or according to standard diagnostic procedures in medical literature.

[0087] In a specific example, diagnostic workflow association rules can be configured through a diagnostic workflow procedure list. Accordingly, the diagnostic workflow procedure list can be queried based on the sequence type of the first medical computed tomographic image to obtain other sequence types in the diagnostic workflow as an associated sequence type list. For example, if the first medical computed tomographic image is a T1-weighted image of a brain MRI, the system can obtain an associated sequence type list of ["T2-weighted image", "FLAIR image", "DWI image"] after querying the diagnostic workflow procedure list.

[0088] S430: Select medical tomographic images that relate to the list of associated sequence types from the medical tomographic images of the examination corresponding to the examination type, and use them as the second medical tomographic images.

[0089] In this embodiment of the application, in step S430, all images involved in the examination can be retrieved from the medical tomographic image database stored on the server according to the examination type of the first medical tomographic image, and images whose sequence type belongs to the associated sequence type list can be selected and preloaded as the second medical tomographic image.

[0090] As an explanation rather than a limitation, by using diagnostic workflow association rules, it is possible to predict other sequences of images that a doctor may need to view when viewing a certain sequence of images, based on the diagnostic workflow. This allows for preloading in advance, ensuring that doctors can switch smoothly when viewing multiple sequences according to the diagnostic workflow, thereby improving diagnostic efficiency.

[0091] In some embodiments, the preset rules may include time-related rules. Time-related rules can predict historical images that a user may view based on the time correlation of historical inspections.

[0092] like Figure 5 As shown, when using time association rules, step S110 may include the following sub-steps: S510: Obtain patient identification, examination site, and examination time for first-degree medical tomography images.

[0093] In this embodiment of the application, in step S510, the patient identifier, examination site, and examination time can be extracted from the metadata of the first medical tomographic image.

[0094] S520: Determine the historical time range of association based on the inspection time according to the time association rules.

[0095] In this embodiment of the application, in step S520, the time range of historical images that need to be preloaded can be determined based on the examination time of the first medical tomographic image according to the pre-configured time association rules.

[0096] In a context of follow-up diagnosis, and not limitation, physicians typically compare a patient's historical medical records to assess disease progression, stabilization, or improvement. Time-related rules can determine the historical timeframe based on factors such as disease type and follow-up duration.

[0097] In some embodiments, the time association rule can dynamically adjust the historical time range based on the disease type. For example, for rapidly progressing diseases (such as acute inflammation or rapidly growing tumors), the historical time range can be set to a shorter period; for slowly progressing diseases (such as chronic inflammation or benign tumors), the historical time range can be set to a longer period.

[0098] In some embodiments, users can customize time range parameters, and the system can determine the historical time range based on the parameters set by the user.

[0099] S530: Select medical tomographic images that involve the examination site and whose examination time is within the historical time range from the medical tomographic images corresponding to the patient identifier, and use them as the second medical tomographic images.

[0100] In this embodiment of the application, in step S530, all medical tomographic images of the patient can be retrieved from the medical tomographic image database stored on the server according to the patient identifier, and for example, images that meet the following conditions can be further selected as second medical tomographic images: the examination site is the same as or similar to the first medical tomographic image; the examination time is within the historical time range determined in step S520.

[0101] As an explanation rather than a limitation, time-related rules can be used to predict historical images that doctors may need to compare during follow-up diagnoses, thus enabling pre-loading and allowing doctors to quickly obtain historical images for comparative analysis, thereby improving the efficiency and accuracy of follow-up diagnoses.

[0102] In some embodiments, the preset rules may include lesion region association rules. Based on the lesion regions marked by the user, the lesion region association rules predict other images that the user may view that involve the same lesion region or the corresponding location.

[0103] like Figure 6 As shown, when using lesion region association rules, step S110 may include the following sub-steps: S610: Obtain the lesion area marked by the user in the first medical tomographic image.

[0104] In this embodiment, step S610 can detect the user's marking operations on the first medical tomographic image. By way of explanation and not limitation, during medical image diagnosis, users (such as doctors) typically mark areas of interest on the image, for example, by drawing circles, boxes, or clicking to mark areas such as tumors, nodules, and lesions. Accordingly, the system can capture these marking operations through the user interface to obtain the location information of the lesion area, such as its three-dimensional coordinate range, slice position, and pixel coordinates.

[0105] S620: Based on the lesion region association rules, determine the medical tomographic image containing the lesion region as the second medical tomographic image.

[0106] In this embodiment of the application, in step S620, images containing the lesion area or the corresponding location can be found in other medical tomographic images based on the location information of the lesion area marked by the user.

[0107] In some embodiments, cross-image matching of lesion regions can be achieved based on image registration information. Specifically, if the system maintains registration information between different images, the registration information can be used to map the lesion region in the first medical tomographic image to the coordinate system of other images, thereby accurately finding the image layer in other images that contains the lesion region.

[0108] By using lesion region association rules, the system can predict that after a doctor marks a lesion, he may need to view the corresponding location of the lesion in other images, thereby preloading relevant images in advance to assist doctors in conducting multi-dimensional lesion analysis.

[0109] In some embodiments, the above-mentioned preset rules can be applied individually.

[0110] In other embodiments, two or more preset rules can be applied simultaneously to more comprehensively predict the second medical tomographic images that a user might view. When multiple rules are applied simultaneously, the second medical tomographic images can be the union or intersection of medical tomographic images that satisfy each rule. For example, examination type association rules and time association rules can be applied simultaneously to determine one set of second medical tomographic images (e.g., all enhanced CT images of the patient) based on the examination type association rule, and another set of second medical tomographic images (e.g., images of the patient within a historical time range) based on the time association rule. If a union strategy is used, the union of the two sets of images can be preloaded as the second medical tomographic images; if an intersection strategy is used, only images that simultaneously satisfy both rules (e.g., enhanced CT images within a historical time range) can be preloaded.

[0111] In some embodiments, priorities can be set for each preset rule. When the number of second medical tomographic images determined by multiple rules exceeds a preset threshold, a subset of medical tomographic images can be selected as second medical tomographic images based on priority. In some embodiments, priorities can be set or adjusted as needed, for example, by a system administrator or user.

[0112] In this embodiment of the application, an intelligent preloading mechanism is realized by setting various preset rules through step S110 and its sub-steps. It can accurately predict and preload related images that the user may view based on the actual workflow of medical diagnosis and the viewing habits of users (such as doctors), which significantly reduces the waiting time when switching images and improves diagnostic efficiency.

[0113] S120: In response to the user's operation on the first medical tomographic image and / or the second medical tomographic image, selectively load a portion of the first medical tomographic image and / or the second medical tomographic image under a given layer loading structure, either a partial layer image or an image region.

[0114] In this application embodiment, the term "layered loading" refers to decomposing medical tomographic images according to specific layers or dimensions, and dynamically loading the required layers or dimensions of images and / or image regions according to the user's actual operational needs, rather than loading all the data of the complete image at once. For illustrative purposes, and not as a limitation, medical tomographic images typically contain a large amount of data; for example, CT or MRI images can contain numerous tomographic images, each containing millions of pixels of data. Loading all the data at once would consume significant time and memory resources. Layered loading technology allows loading only the necessary data based on the user's current operation, thereby significantly improving loading speed and resource utilization efficiency. For illustrative purposes, the term "layered loading" in this application embodiment refers to decomposing medical tomographic images according to specific layers or dimensions, and is not limited to the specific layers of a "tomographic" image.

[0115] In this application embodiment, the "layer" of layered loading can be defined from multiple dimensions. In this application embodiment, the layered loading structure can include, but is not limited to, one or more of the following: spatial layered loading structure, sequential interval layered loading structure, resolution layered loading structure, region of interest (ROI) layered loading structure, and reconstruction plane layered loading structure. In some embodiments, layering can be spatial layering, for example, organizing different layers of tomographic images as different layers. In other embodiments, layering can be resolution layering, for example, treating low-resolution and high-resolution versions of the same image as different layers. In still other embodiments, layering can be region layering, for example, treating regions of interest and non-regions of interest of an image as different layers. In yet other embodiments, layering can be planar layering, for example, treating reconstructed images in different planar orientations as different layers. This will be further described below.

[0116] In this embodiment, step S120 describes the operation of layered loading for a first medical tomographic image and / or a second medical tomographic image. In some embodiments, layered loading can be applied to, for example, the currently viewed first medical tomographic image, or to a pre-loaded (but not yet viewed) second medical tomographic image, or a combination of both. In this embodiment, when layered loading is performed on the second medical tomographic image, the layered loading level or dimension may differ from the pre-loaded level or dimension; however, in another embodiment, when layered loading is performed on the second medical tomographic image, layered loading and pre-loading can be combined, i.e., steps S110 and S120 described above can be combined. Accordingly, the above configuration can be applied to all specific embodiments described below, and will not be repeated here.

[0117] In an alternative embodiment, layered loading can also be applied to other medical tomographic images that have not been viewed and / or preloaded. In a further alternative embodiment, for any medical tomographic image that the user directly selects to view, a layered loading structure can be applied for selective loading, regardless of whether the image has been preloaded.

[0118] In some embodiments, the layered loading structure may include a spatial layered loading structure. The spatial layered loading structure is based on the layered organization of tomographic images in a spatial dimension, and dynamically loads images of neighboring layers (such as adjacent layers) according to the layer position currently viewed by the user.

[0119] like Figure 7 As shown, when a spatial layered loading structure is used, step S120 may include the following sub-steps: S710: Determine the current layer position of the tomographic image in the first and / or second medical tomographic images currently being viewed by the user.

[0120] In this embodiment of the application, in step S710, the position of the image layer that the user is currently viewing can be detected, such as the position of the layer in the first tomographic image. For explanation, medical tomographic images typically contain multiple slices of tomographic images, each corresponding to a specific spatial location.

[0121] S720: Determine the range of adjacent layers based on the current layer position and the preset number of adjacent layers to obtain a list of target layers.

[0122] In this embodiment of the application, in step S720, the range of adjacent layers to be loaded can be calculated based on the current layer position and the preset number of adjacent layers.

[0123] The adjacent layer number parameter defines how many image layers are loaded before and after the current layer. For illustrative purposes, and not as a limitation, when a doctor scrolls through CT images, they typically move from one layer to the adjacent layers; therefore, preloading several adjacent layers ensures a smooth browsing experience for the user. The adjacent layer number parameter can be configured based on factors such as system performance, network bandwidth, and memory capacity. In some embodiments, the adjacent layer number parameter can be set to a fixed value, such as loading 2 layers before and after the current layer, i.e., loading a total of 4 image layers (2 before and 2 after) or 5 image layers (including the current layer). In some embodiments, the adjacent layer number parameter can be selected as needed, for example, but not limited to 1 to 10 layers, preferably 4 to 6.

[0124] In another alternative embodiment, the adjacent layer number parameter can be dynamically adjusted based on the system resource status. For example, the system can detect the current network bandwidth and client memory usage. When the network bandwidth is higher than the bandwidth threshold and the memory usage is lower than the memory threshold, the adjacent layer number parameter is increased to preload more adjacent layers; when the network bandwidth is lower than the bandwidth threshold or the memory usage is higher than the memory threshold, the adjacent layer number parameter is decreased.

[0125] S730: Load the tomographic images of the corresponding target layer list from the first medical tomographic image and / or the second medical tomographic image.

[0126] In this embodiment of the application, in step S730, tomographic image data with corresponding layer numbers can be loaded from the first medical tomographic image and / or the second medical tomographic image according to the target layer list.

[0127] In this embodiment, the spatial layered loading structure dynamically loads images of adjacent layers based on the user's scrolling operation, avoiding loading all layers at once. This significantly reduces loading time and memory usage while ensuring a smooth browsing experience. The spatial layered loading structure is particularly suitable for browsing tomographic images containing a large number of layers, such as CT and MRI scans.

[0128] In some embodiments, the hierarchical loading structure may include a sequentially spaced hierarchical loading structure. The sequentially spaced hierarchical loading structure selectively loads images of spaced layers based on a layer spacing parameter.

[0129] like Figure 8 As shown, when a sequential interval hierarchical loading structure is used, step S120 may include the following sub-steps: S810: Obtain a complete list of slice sequences for the first medical tomographic image and / or the second medical tomographic image.

[0130] In this embodiment of the application, in step S810, the sequence information of all layers contained in the medical tomographic image can be obtained from the metadata of the medical tomographic image. The sequence list records the layer number or layer identifier of each layer in the image, for example [1, 2, 3, ..., 300], indicating that the image contains 300 tomographic images from layer 1 to layer 300.

[0131] S820: Based on the layer interval parameters set by the user, select the interval layers from all layer sequences of the first medical tomographic image and / or the second medical tomographic image to obtain a list of interval layers.

[0132] In this embodiment of the application, in step S820, a partial layer can be selected from the entire layer sequence at a certain interval according to the layer interval parameter set by the user, and an interval layer list can be generated.

[0133] The layer interval parameter defines how many layers to select for loading.

[0134] In some embodiments, the layer spacing parameter can be set as needed, for example, but not limited to loading one layer every 2 layers, every 5 layers, or an integer number of layers (such as every 10 layers).

[0135] In some embodiments, the layer interval parameter can be set by the user according to actual needs. For example, the user can select "Quick Browse Mode" or "Detailed Browse Mode" in the user interface, and the system will set different layer interval parameters accordingly. Quick Browse Mode can set a larger layer interval (e.g., every 10 layers), while Detailed Browse Mode can set a smaller layer interval (e.g., every 2 layers) or not use any interval (i.e., load all layers).

[0136] S830: Load the tomographic images of the corresponding septal layer list in the first medical tomographic image and / or the second medical tomographic image.

[0137] In this embodiment of the application, in step S830, tomographic image data with the corresponding layer number can be loaded from the medical tomographic image according to the interval layer list.

[0138] S840: In response to a user's operation of viewing other layers that are not interstitial layers, load the tomographic images of the corresponding other layers in the first medical tomographic image and / or the second medical tomographic image.

[0139] In this embodiment of the application, in step S840, when the user needs to view other layers between the gap layers after a quick browse, the image of the non-gap layer specified by the user (e.g., currently clicked to view) can be loaded in response to the user's operation.

[0140] In this embodiment, by using a sequential interval layered loading structure, the system can load only the images in the interval layer when the user is browsing quickly, which greatly reduces the amount of data and time of the initial loading, allowing the user to quickly obtain an overall impression of the image.

[0141] In some embodiments, the hierarchical loading structure may include a resolution-hierarchical loading structure. The resolution-hierarchical loading structure loads a low-resolution image first for quick preview, based on different levels of image resolution, and then loads a high-resolution image or image region according to the user's zoom-in operation.

[0142] like Figure 9 As shown, when a resolution-layered loading structure is used, step S120 may include the following sub-steps: S910: Load a first resolution image of the first medical tomographic image and / or the second medical tomographic image for user preview and / or navigation operations.

[0143] In this embodiment of the application, in step S910, a first resolution version of the medical tomographic image may be loaded first. The first resolution is, for example, a lower resolution, used to provide a quick preview.

[0144] In some embodiments, the first-resolution image can be pre-generated and stored on the server, and the pre-generated low-resolution image can be directly returned when requested by the client.

[0145] In some embodiments, step S910 may be combined with step S110, for example, when preloading a first resolution image of a second medical tomographic image.

[0146] S920: In response to the user's zoom-in operation, determine the coordinate range of the layer sequence or zoom-in region corresponding to the zoom-in operation.

[0147] In some embodiments, in step S920, the user's zoom-in operation can be detected, and the target area that the user wishes to zoom in on can be determined. In this embodiment, the user can perform the zoom-in operation in various ways, such as, but not limited to, selecting a certain area with the mouse, clicking the zoom-in button, double-clicking to zoom in, using the scroll wheel to zoom in, and using zoom gestures.

[0148] In these embodiments, the coordinate range of the magnified area can be determined based on the user's zoom-in operation. In some embodiments, the coordinate range can be represented as a circular or rectangular area in a two-dimensional coordinate system, such as the upper left corner coordinates (x1, y1) and the lower right corner coordinates (x2, y2), but this application is not limited thereto.

[0149] In an alternative embodiment, in step S920, when a user's zoom-in operation is detected, it can be assumed that the user wants to zoom in on the current layer, thereby determining the layer sequence of the current layer.

[0150] S930: Load a second resolution image or image region of the corresponding magnified area in the first medical tomographic image and / or the second medical tomographic image, wherein the second resolution is greater than the first resolution.

[0151] In some embodiments, in step S930, a second resolution version of the image region can be loaded from the medical tomographic image according to the coordinate range of the magnified region, while the remaining regions can still retain the first resolution. Here, the second resolution is a higher resolution, for example, it can be the original resolution or a high resolution close to the original resolution.

[0152] In an alternative embodiment, when the layer sequence of the current layer is determined, a second resolution image of the corresponding layer sequence can be loaded according to the layer sequence of the current layer.

[0153] In this embodiment of the application, by using a resolution-layered loading structure, only a low-resolution image can be provided for quick preview during the initial loading. When the user needs to view detailed content, a high-resolution image or image area is then loaded, thereby significantly reducing the initial loading time and data transmission volume while ensuring diagnostic needs are met.

[0154] In some embodiments, the hierarchical loading structure may include a Region of Interest (ROI) hierarchical loading structure. The ROI hierarchical loading structure can load high-resolution data only for regions of interest identified by the user (e.g., selected by a bounding box), while keeping other regions at low resolution, thereby concentrating resources on loading content of interest to the user.

[0155] like Figure 10 As shown, when using a hierarchical ROI loading structure, step S120 may include the following sub-steps: S1010: In response to the user's ROI marking operation on the first medical tomographic image and / or the second medical tomographic image, determine the coordinate range of the region of interest (ROI) corresponding to the ROI marking operation.

[0156] In this embodiment of the application, step S1010 can detect the user's operation of marking (e.g., selecting) the Region of Interest (ROI) on the medical tomographic image. The marking operation can be implemented in various ways, such as, but not limited to, selecting by bounding box or point selection. In a specific example, the user can draw a rectangular box, a circular box, or a polygonal box of any shape on the image. Therefore, the coordinate range of the ROI can be obtained based on the user's marking (e.g., selecting by bounding box) operation.

[0157] The coordinate range of the region of interest can be represented as the boundary of the region in a two-dimensional coordinate system. For example, a rectangle can be represented by the coordinates of its top-left corner (x1, y1) and bottom-right corner (x2, y2), and a circle can be represented by the coordinates of its center (x1, y1). c , y c The polygon box can be represented by a list of vertex coordinates, where r is the radius and r is the radius.

[0158] In some embodiments, a user can select a region of interest on a certain layer of an image, and the system can apply that region to multiple layers.

[0159] S1020: Keep the region outside the region of interest in the first medical tomographic image and / or the second medical tomographic image as the third resolution image or image region.

[0160] In this embodiment of the application, in step S1020, a lower third resolution can be maintained for regions outside the region of interest (i.e., regions not of interest).

[0161] In some embodiments, if a region outside the region of interest has already been loaded at a low resolution (e.g., a first resolution image has been loaded in step S910), the system can directly maintain that low resolution without reloading.

[0162] S1030: Load the fourth resolution image region corresponding to the region of interest in the first medical tomographic image and / or the second medical tomographic image, wherein the fourth resolution is greater than the third resolution.

[0163] In this embodiment, in step S1030, a fourth resolution version of the region of interest (ROI) can be loaded from the medical tomographic image based on the coordinate range of the ROI. Here, the fourth resolution is a higher resolution, typically the original resolution or a high resolution close to the original resolution. By loading high-resolution data onto the ROI, the user can clearly view the detailed features of the ROI.

[0164] In some embodiments, after loading a high-resolution image region of the ROI, it can be displayed in the user interface in an overlay manner, that is, the high-resolution region of interest can be overlaid on the low-resolution full image, so that the user can see both the context of the overall image and the clear details of the region of interest.

[0165] In the embodiments of this application, the region of interest (ROI) hierarchical loading structure is particularly suitable for diagnostic scenarios that focus on specific lesion areas, such as measuring tumor size and assessing lesion morphological characteristics.

[0166] In this embodiment, by using the Region of Interest (ROI) hierarchical loading structure, resources can be concentrated on loading high-resolution data for the region of interest that the user has clearly marked, while keeping other regions at low resolution. This significantly reduces data transmission volume and memory usage while ensuring the diagnostic quality of key regions.

[0167] In some embodiments, the layered loading structure may include a reconstructed plane layered loading structure. By way of explanation and not limitation, the reconstructed plane layered loading structure is based on multi-planar reconstruction (MPR) technology, which allows for the dynamic reconstruction and loading of reconstructed planar images in the corresponding orientation based on the planar orientation selected by the user.

[0168] like Figure 11 As shown, when using a reconstructed planar layered loading structure, step S120 may include the following sub-steps: S1110: In response to the user's planar selection operation on the first medical tomographic image and / or the second medical tomographic image, determine the planar direction corresponding to the planar selection operation.

[0169] In this embodiment of the application, in step S1110, the user's plane selection operation can be detected, and the plane direction that the user wishes to view can be determined. The plane direction includes an axial plane, a coronal plane, a sagittal plane, or an oblique plane at any angle.

[0170] In a specific example, a user can select the plane direction through the user interface, such as by clicking the "coronal plane" button, the "sagittal plane" button, or by dragging the interactive control to specify the direction of the inclined plane at any angle.

[0171] S1120: Based on the planar orientation, dynamically reconstruct a reconstructed planar image corresponding to the planar orientation from the original tomographic data of the first medical tomographic image and / or the second medical tomographic image.

[0172] In this embodiment of the application, in step S1120, the system extracts the original tomographic data of the medical tomographic image and reconstructs the image of the corresponding plane according to the determined planar direction.

[0173] In explanatory and not limiting sense, multiplanar reconstruction (MPR) is a technique for extracting two-dimensional cross-sectional images from three-dimensional volume data in arbitrary directions. The raw data of medical tomographic imaging is typically three-dimensional volume data acquired layer by layer in transverse sections. MPR technology allows slicing along any direction within this three-dimensional volume data to generate corresponding two-dimensional images. For example, for CT data acquired in transverse sections, MPR can generate coronal and sagittal images. These images provide perspectives of anatomical structures from different directions, facilitating a more comprehensive assessment of lesions.

[0174] In some embodiments, the generation of the reconstructed planar image can employ any suitable algorithm, which will not be elaborated here.

[0175] S1130: Load the reconstructed planar image.

[0176] In this embodiment, in step S1130, the reconstructed planar image can be loaded into memory for display to the user in the user interface. Thus, the user can view the reconstructed planar image to observe anatomical structures and lesions from different perspectives and obtain more comprehensive diagnostic information.

[0177] In some embodiments, users can scroll through a reconstructed planar image to view slices at different locations along that planar direction.

[0178] In some embodiments, multi-plane parallel loading can be implemented, that is, the above steps S1110 to S1130 can be applied to multiple planes in parallel.

[0179] In this embodiment of the application, by reconstructing the planar layered loading structure, the corresponding planar image can be dynamically reconstructed and loaded according to the planar direction selected by the user, without the need to pre-generate and store reconstructed images of all possible directions, thereby saving storage space and providing flexible multi-view viewing functions.

[0180] In some embodiments, only one hierarchical loading structure may be used. In other embodiments, the system may apply a combination of two or more hierarchical loading structures, which falls within the scope of this application.

[0181] Based on the above description of the various layered loading structures of step S120 and its sub-steps, the embodiments of this application provide diverse layered loading strategies, which can achieve efficient and flexible loading of medical tomographic images according to different user operations and diagnostic needs.

[0182] In some embodiments, such as Figure 12 As shown, the method in this application embodiment may further include a memory management mechanism to optimize the use of client memory.

[0183] like Figure 12 As shown, the method may further include the following steps: S1210: Monitors the memory usage of the client's memory.

[0184] In this embodiment of the application, in step S1210, the client's memory usage can be continuously monitored to obtain the current memory usage rate. For example, real-time memory usage information can be obtained through interfaces provided by the operating system or memory management libraries.

[0185] S1220: When the memory usage reaches a preset threshold, release at least a portion of the memory space occupied by the medical tomographic images stored in the client's memory based on the access status of the medical tomographic images.

[0186] In this embodiment of the application, in step S1220, when the memory usage rate is detected to reach or exceed a preset threshold, a memory release mechanism can be triggered to release part of the memory space occupied by medical tomographic images, so as to avoid system performance degradation or crash due to insufficient memory.

[0187] In this embodiment, the preset threshold can be configured according to the total memory capacity and operating requirements of the system.

[0188] In some embodiments, it is possible to determine which images should be released based on their access history. In some specific examples, memory space occupied by medical tomographic images that meet one of the following conditions can be released: they have been accessed and the last access occurred more than a first preset time threshold; or they have not been accessed after being preloaded and the loading time occurred more than a second preset time threshold. In some embodiments, medical tomographic images to be released can be determined in order of priority.

[0189] In some embodiments, when releasing the memory space occupied by medical tomographic images, the metadata and thumbnails of the released medical tomographic images may be retained.

[0190] Through the memory management mechanism, the embodiments of this application can intelligently manage loaded and preloaded medical tomographic images under limited memory resources, ensuring that the system can still maintain stable operation in scenarios with concurrent viewing of multiple images, and avoiding system performance degradation or crashes due to insufficient memory.

[0191] In other alternative embodiments, not shown, the following means related to medical tomographic image processing may also be provided.

[0192] In some embodiments, the server may implement storage optimization to improve storage efficiency. In these embodiments, the method may include: performing lossless compression on medical tomographic images stored on the server; selecting different compression strategies based on the access frequency of each medical tomographic image, wherein medical tomographic images with high access frequency use a fast compression algorithm with a lower compression ratio, and medical tomographic images with low access frequency use an efficient compression algorithm with a higher compression ratio.

[0193] In some embodiments, the server may implement cache management to improve data access speed. In these embodiments, the method may include: counting the access frequency of each medical tomographic image stored on the server; marking medical tomographic images whose access frequency exceeds a preset frequency threshold as hot images; caching hot images to a high-speed storage medium; and when the cache space is insufficient, evicting some cached medical tomographic images based on their access frequency.

[0194] In some embodiments, the server may implement security auditing to ensure the security and compliance of image data. In these embodiments, the method may include: recording user access operation logs for medical computed tomography images, the access operation logs including the accessing user identifier, access time, accessed image identifier, and operation type; and generating an audit report based on the access operation logs.

[0195] The steps and sub-steps described in the embodiments of this application can be executed independently or separately, or they can be combined or merged without contradiction. Furthermore, the order of steps in the embodiments of this application is not absolutely limited; the execution order of some steps can be adjusted or they can be executed in parallel according to actual needs, provided that the technical solution is not affected.

[0196] Accordingly, this application provides a method for loading medical tomographic images. This method, through the combination of a predictive preloading mechanism and fine-grained layered loading technology, can significantly improve the loading speed of medical tomographic images, reduce memory usage, and enhance display flexibility, thereby effectively supporting doctors' diagnostic workflow and improving diagnostic efficiency and quality.

[0197] like Figure 13 As shown in the illustration, this application also provides a medical tomographic image loading system 1300. The system includes a preloading module 1310 and a layered loading module 1320. The preloading module 1310 is configured to determine and preload a second medical tomographic image associated with the first medical tomographic image based on attribute information of the viewed first medical tomographic image, according to preset rules. The layered loading module 1320 is configured to selectively load portions or regions of the first and / or second medical tomographic images under a given layered loading structure in response to user operations on the first and / or second medical tomographic images.

[0198] In some embodiments, such as Figure 13 and Figure 14 As shown, the medical computed tomography imaging loading system 1300 can adopt a client-server architecture, including client 1301 and server 1302.

[0199] like Figure 14 As shown, client 1301 may include the aforementioned preloading module 1310 and layered loading module 1320. Here, preloading module 1310 is further configured to obtain a second medical tomographic image from the medical tomographic images stored on server 1302 according to preset rules based on the attribute information of the first medical tomographic image, and preload the obtained second medical tomographic image into the client memory.

[0200] Accordingly, server 1302 includes storage module 1350, which is configured to store medical tomographic images. In some embodiments, storage module 1350 may adopt a PACS (Picture Archiving and Communication System) architecture to provide centralized storage, management and distribution functions for medical images.

[0201] In some embodiments, the client 1301 may further include a user interface 1340 configured to provide a browsing interface for medical tomographic images. This interface allows users to zoom, pan, and switch between the first and / or second medical tomographic images, and provides real-time feedback on the loading progress. The user interface 1340 can provide an intuitive graphical user interface, such as an image display window, toolbar, scroll bars, zoom controls, etc., enabling doctors to easily browse and manipulate the images.

[0202] In some embodiments, client 1301 may further include memory manager 1330, configured to monitor the memory usage of client memory, and when the memory usage reaches a preset threshold, release at least a portion of the memory space occupied by the medical tomographic images stored in client memory based on the access status of the medical tomographic images. The specific functions and implementation of memory manager 1330 may correspond to the memory management steps described in the preceding method embodiments.

[0203] In some embodiments, the server 1302 may further include a data distribution module 1360, configured to extract corresponding medical tomographic image data from the storage module 1350 and distribute it to the client 1301 in response to a request from the client 1301, supporting concurrent access by multiple clients. The data distribution module 1360 can implement data transmission based on the DICOM network protocol, such as using DICOM services like C-GET and C-MOVE.

[0204] In some embodiments, the server 1302 may further include a cache manager 1370, configured to count the access frequency of each medical tomographic image, cache medical tomographic images whose access frequency exceeds a preset frequency threshold to a high-speed storage medium, and evict some cached medical tomographic images according to the access frequency when the cache space is insufficient. The specific functions of the cache manager 1370 correspond to the cache management method described above.

[0205] In some embodiments, the server 1302 may further include a storage optimization module 1380, configured to perform lossless compression on the medical tomographic images stored in the storage module 1350, and select different compression strategies based on the access frequency of each medical tomographic image. The specific function of the storage optimization module 1380 corresponds to the storage optimization method described above.

[0206] In some embodiments, the server 1302 may further include a security audit module 1390, configured to record user access operation logs for medical computed tomography images. The access operation logs include the accessing user identifier, access time, accessed image identifier, and operation type. The specific functions of the security audit module 1390 correspond to the security audit method described above.

[0207] It should be noted that the steps, sub-steps, and features of the medical tomographic image loading method described in the embodiments of this application can be combined with the medical tomographic image loading system of the embodiments of this application in a non-contradictory manner to obtain new embodiments. Conversely, the components, modules, units, or features of the medical tomographic image loading system described in the embodiments of this application can also be combined with the medical tomographic image loading method of the embodiments of this application in a non-contradictory manner to obtain new embodiments.

[0208] In this application embodiment, an electronic device is also provided, which may include a processor and a memory storing a computer program, the processor being configured to execute the method of any embodiment of this application when running the computer program.

[0209] Figure 15 A schematic diagram of an exemplary electronic device 1500 that can implement the methods of embodiments of this application is shown. In some embodiments, it may include more or fewer electronic devices than shown. In some embodiments, it may be implemented using a single or multiple electronic devices. In some embodiments, it may be implemented using cloud-based or distributed electronic devices.

[0210] like Figure 15 As shown, the electronic device 1500 includes a processor 1501, which can perform various appropriate operations and processes based on programs and / or data stored in read-only memory (ROM) 1502 or programs and / or data loaded from storage portion 1508 into random access memory (RAM) 1503. The processor 1501 can be a single-core or multi-core processor, or may include multiple processors. In some embodiments, the processor 1501 may include a general-purpose main processor (such as a CPU) and one or more special coprocessors, such as a graphics processing unit (GPU), a neural network processor (NPU), a digital signal processor (DSP), or other general-purpose or application-specific integrated circuits. Various programs and data required for the operation of the electronic device 1500 are also stored in RAM 1503. The processor 1501, ROM 1502, and RAM 1503 are interconnected via a bus 1504. An input / output (I / O) interface 1505 is also connected to the bus 1504.

[0211] The processor and memory described above are used together to execute a program stored in the memory. When the program is executed by a computer, it can implement the steps or functions of the methods described in the above embodiments.

[0212] The following components are connected to I / O interface 1505: input section 1506 including keyboard, mouse, etc.; output section 1507 including display, speakers, etc.; storage section 1508 including hard disk, etc.; and communication section 1509 including network interface card, modem, etc. Communication section 1509 performs communication processing via a network such as the Internet. Drive 1510 is also connected to I / O interface 1505 as needed. Removable media 1511, such as disk, optical disk, magneto-optical disk, semiconductor memory, etc., are installed on drive 1510 as needed so that computer programs read from them can be installed into storage section 1508 as needed.

[0213] Figure 15 The electronic device shown is merely illustrative, but the electronic device according to embodiments of this application may include more than [other components]. Figure 15 The electronic device shown has more or fewer components or has more or fewer components than the one shown. Figure 15 The embodiments shown have the same, partially the same, or different architectures.

[0214] In the embodiments of this application, the electronic device can also be combined with various components to obtain methods, apparatus and systems with the advantages of this application.

[0215] Although not shown, this application also provides a computer-readable storage medium storing a computer program configured to execute the methods of any of the embodiments of this application. The computer program includes various program modules / units constituting the apparatus according to the embodiments of this application. When executed, the computer program, composed of the various program modules / units, can perform the functions corresponding to the various steps in the methods described in the above embodiments. The computer program can also run on electronic devices as described in the embodiments of this application.

[0216] Although not shown, some embodiments also provide a program product comprising a computer program configured to be run to perform the methods of any of the embodiments of this application.

[0217] The storage medium in embodiments of this application includes non-volatile and / or volatile articles that can store information by any method or technology. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), RAMbus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and RAMbus dynamic RAM (RDRAM), etc.

[0218] Those skilled in the art will understand that the embodiments of this specification can be implemented in various forms, such as methods, systems, or computer program products. Therefore, those skilled in the art will realize that the functional modules / units or controllers and related method steps described in the above embodiments can be implemented in software, hardware, or a combination of software and hardware.

[0219] Unless explicitly stated otherwise, the actions or steps of the methods and procedures described in the embodiments of this application do not necessarily have to be performed in a specific order and can still achieve the desired results. In some implementations, multitasking and parallel processing are also possible or may be advantageous.

[0220] This document describes several embodiments, but for the sake of brevity, the descriptions of the embodiments are not exhaustive, and identical or similar features or parts between the embodiments may be omitted. In this document, "one embodiment," "some embodiments," "example," "specific example," or "some examples" refers to at least one embodiment or example applicable to this application, but not all embodiments. The above terms do not necessarily mean referring to the same embodiment or example. Without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of the different embodiments or examples.

[0221] The exemplary systems and methods of this application have been specifically shown and described with reference to the above embodiments, which are merely examples of the best mode for implementing the systems and methods. Those skilled in the art will understand that various changes can be made to the embodiments of the systems and methods described herein without departing from the spirit and scope of this application as defined in the appended claims when implementing the systems and / or methods.

Claims

1. A method for loading medical tomographic images, characterized in that, include: Based on the attribute information of the first medical tomographic image being viewed, a second medical tomographic image associated with the first medical tomographic image is determined according to a preset rule, and the second medical tomographic image is preloaded. In response to user operations on the first and / or second medical tomographic images, selectively load a portion of the first and / or second medical tomographic images or image regions under a given layered loading structure.

2. The medical tomographic image loading method according to claim 1, characterized in that, The hierarchical loading structure includes one or more of the following: spatial hierarchical loading structure, sequence interval hierarchical loading structure, resolution hierarchical loading structure, region of interest (ROI) hierarchical loading structure, and reconstruction plane hierarchical loading structure.

3. The medical tomographic image loading method according to claim 2, characterized in that, The selective loading of partial layer images or image regions of the first and / or second medical tomographic images under a given layer loading structure in response to user operations on the first and / or second medical tomographic images includes: Determine the current layer position of the tomographic image in the first and / or second medical tomographic images currently being viewed by the user; The range of adjacent layers is determined based on the current layer position and the preset number of adjacent layers, thus obtaining a target layer list; Load the tomographic images corresponding to the target layer list from the first medical tomographic image and / or the second medical tomographic image.

4. The medical tomographic image loading method according to claim 2, characterized in that, The selective loading of partial layer images or image regions of the first and / or second medical tomographic images under a given layer loading structure in response to user operations on the first and / or second medical tomographic images includes: Obtain a complete list of slice sequences of the first medical tomographic image and / or the second medical tomographic image; Based on the layer interval parameters set by the user, interval layers are selected from all layer sequences of the first medical tomographic image and / or the second medical tomographic image to obtain a list of interval layers. Load the tomographic images corresponding to the list of interval layers from the first medical tomographic image and / or the second medical tomographic image; In response to a user's action of viewing other layers that are not interstitial layers, tomographic images of the corresponding other layers in the first medical tomographic image and / or the second medical tomographic image are loaded.

5. The medical tomographic image loading method according to claim 2, characterized in that, The selective loading of partial layer images or image regions of the first and / or second medical tomographic images under a given layer loading structure in response to user operations on the first and / or second medical tomographic images includes: Load a first-resolution image of the first medical tomographic image and / or the second medical tomographic image for user preview and / or navigation operations; In response to a user's zoom-in operation, determine the coordinate range of the layer sequence or zoom-in region corresponding to the zoom-in operation; Load a second resolution image or image region corresponding to the magnified region in the first medical tomographic image and / or the second medical tomographic image, wherein the second resolution is greater than the first resolution.

6. The medical tomographic image loading method according to claim 2, characterized in that, The selective loading of partial layer images or image regions of the first and / or second medical tomographic images under a given layer loading structure in response to user operations on the first and / or second medical tomographic images includes: In response to the user's selection operation on the first medical tomographic image and / or the second medical tomographic image, determine the coordinate range of the region of interest (ROI) corresponding to the selection operation; The region outside the region of interest in the first and / or second medical tomographic images is retained as a third-resolution image or image region. Load a fourth resolution image region corresponding to the region of interest from the first medical tomographic image and / or the second medical tomographic image, wherein the fourth resolution is greater than the third resolution.

7. The medical tomographic image loading method according to claim 2, characterized in that, The selective loading of partial layer images or image regions of the first and / or second medical tomographic images under a given layer loading structure in response to user operations on the first and / or second medical tomographic images includes: In response to a user's planar selection operation on the first medical tomographic image and / or the second medical tomographic image, the planar direction corresponding to the planar selection operation is determined; Based on the plane orientation, a reconstructed planar image corresponding to the plane orientation is dynamically reconstructed from the original tomographic data of the first medical tomographic image and / or the second medical tomographic image; Load the reconstructed planar image.

8. The medical tomographic image loading method according to claim 1, characterized in that, The preset rules include one or more of the following: examination type association rules, diagnostic process association rules, time association rules, and lesion area association rules.

9. The medical tomographic image loading method according to claim 8, characterized in that, The step of determining a second medical tomographic image associated with the first medical tomographic image based on the attribute information of the viewed first medical tomographic image and according to preset rules includes: Obtain the examination type and patient identifier of the first medical computed tomography image; Based on the association rules of the inspection type, query other inspection types associated with the inspection type to obtain a list of associated inspection types; The medical tomographic images belonging to the list of associated examination types are selected from the medical tomographic images corresponding to the patient identifier and used as the second medical tomographic images.

10. The medical tomographic image loading method according to claim 8, characterized in that, The step of determining a second medical tomographic image associated with the first medical tomographic image based on the attribute information of the viewed first medical tomographic image and according to preset rules includes: Obtain the sequence type and examination type of the first medical computed tomography image; According to the diagnostic process association rules, query other sequence types in the diagnostic process corresponding to the sequence type to obtain a list of associated sequence types; Medical tomographic images that relate to the list of associated sequence types are selected from the medical tomographic images corresponding to the examination type and used as the second medical tomographic images.

11. The medical tomographic image loading method according to claim 8, characterized in that, The step of determining a second medical tomographic image associated with the first medical tomographic image based on the attribute information of the viewed first medical tomographic image and according to preset rules includes: Obtain the patient identification, examination site, and examination time of the first medical tomographic image; Based on the time association rules, the historical time range of the association is determined according to the inspection time; The medical tomographic images corresponding to the patient identifier that involve the examination site and whose examination time is within the historical time range are selected as the second medical tomographic images.

12. The medical tomographic image loading method according to claim 8, characterized in that, The step of determining a second medical tomographic image associated with the first medical tomographic image based on the attribute information of the viewed first medical tomographic image and according to preset rules includes: Obtain the lesion area marked by the user in the first medical tomographic image; The medical tomographic image containing the lesion region is determined according to the lesion region association rule and used as the second medical tomographic image.

13. The method for loading medical tomographic images according to any one of claims 1 to 12, characterized in that, The step of determining a second medical tomographic image associated with the first medical tomographic image based on the attribute information of the viewed first medical tomographic image according to a preset rule, and preloading the second medical tomographic image, includes: Based on the attribute information of the first medical tomographic image, the second medical tomographic image is obtained from the server according to the preset rules; The acquired second medical tomographic image is preloaded into the client's memory.

14. The medical tomographic image loading method according to claim 13, characterized in that, Also includes: Monitor the memory usage of the client's memory; When the memory usage reaches a preset threshold, at least a portion of the memory space occupied by the medical tomographic images stored in the client's memory is released based on the access status of the medical tomographic images.

15. A medical tomographic image loading system, characterized in that, include: The preloading module is configured to determine and preload a second medical tomographic image associated with the first medical tomographic image based on the attribute information of the first medical tomographic image being viewed, according to preset rules. The layered loading module is configured to selectively load a portion of the layered image or image region of the first medical tomographic image and / or the second medical tomographic image under a given layered loading structure in response to user operations on the first medical tomographic image and / or the second medical tomographic image.

16. The medical tomographic imaging loading system according to claim 15, characterized in that, The medical computed tomography (CT) image loading system includes a client and a server, wherein: The server includes a storage module for storing medical tomographic images; The client includes the preloading module and the hierarchical loading module; The preloading module is configured to obtain the second medical tomographic image from the medical tomographic images stored on the server according to the preset rules based on the attribute information of the first medical tomographic image, and preload the obtained second medical tomographic image into the client memory.

17. The medical tomographic imaging loading system according to claim 16, characterized in that, The client also includes a memory manager configured to monitor the memory usage of the client's memory, and when the memory usage reaches a preset threshold, to release at least a portion of the memory space occupied by the medical tomographic images stored in the client's memory based on the access status of the medical tomographic images.

18. The medical computed tomography imaging loading system according to any one of claims 15 to 17, characterized in that, The hierarchical loading structure includes one or more of the following: spatial hierarchical loading structure, sequence interval hierarchical loading structure, resolution hierarchical loading structure, region of interest (ROI) hierarchical loading structure, and reconstruction plane hierarchical loading structure.

19. The medical tomographic imaging loading system according to claim 18, characterized in that, The hierarchical loading module is further configured as follows: Determine the current layer position of the tomographic image in the first and / or second medical tomographic images currently being viewed by the user; The range of adjacent layers is determined based on the current layer position and the preset number of adjacent layers, thus obtaining a target layer list; Load the tomographic images corresponding to the target layer list from the first medical tomographic image and / or the second medical tomographic image.

20. The medical tomographic imaging loading system according to claim 18, characterized in that, The hierarchical loading module is further configured as follows: Obtain a complete list of slice sequences of the first medical tomographic image and / or the second medical tomographic image; Based on the layer interval parameters set by the user, interval layers are selected from all layer sequences of the first medical tomographic image and / or the second medical tomographic image to obtain a list of interval layers. Load the tomographic images corresponding to the list of interval layers from the first medical tomographic image and / or the second medical tomographic image; In response to a user's action of viewing other layers that are not interstitial layers, tomographic images of the corresponding other layers in the first medical tomographic image and / or the second medical tomographic image are loaded.

21. The medical tomographic imaging loading system according to claim 18, characterized in that, The hierarchical loading module is further configured as follows: Load a first-resolution image of the first medical tomographic image and / or the second medical tomographic image for user preview and / or navigation operations; In response to a user's zoom-in operation, determine the coordinate range of the layer sequence or zoom-in region corresponding to the zoom-in operation; Load a second resolution image or image region corresponding to the magnified region in the first medical tomographic image and / or the second medical tomographic image, wherein the second resolution is greater than the first resolution.

22. The medical tomographic imaging loading system according to claim 18, characterized in that, The hierarchical loading module is further configured as follows: In response to the user's selection operation on the first medical tomographic image and / or the second medical tomographic image, determine the coordinate range of the region of interest (ROI) corresponding to the selection operation; The region outside the region of interest in the first and / or second medical tomographic images is retained as a third-resolution image or image region. Load a fourth resolution image region corresponding to the region of interest from the first medical tomographic image and / or the second medical tomographic image, wherein the fourth resolution is greater than the third resolution.

23. The medical tomographic imaging loading system according to claim 18, characterized in that, The hierarchical loading module is further configured as follows: In response to a user's planar selection operation on the first medical tomographic image and / or the second medical tomographic image, the planar direction corresponding to the planar selection operation is determined; Based on the plane orientation, a reconstructed planar image corresponding to the plane orientation is dynamically reconstructed from the original tomographic data of the first medical tomographic image and / or the second medical tomographic image; Load the reconstructed planar image.

24. The medical computed tomography imaging loading system according to any one of claims 15 to 17, characterized in that, The preset rules include one or more of the following: examination type association rules, diagnostic process association rules, time association rules, and lesion area association rules.

25. The medical tomographic imaging loading system according to claim 24, characterized in that, The preloading module is further configured as follows: Obtain the examination type and patient identifier of the first medical computed tomography image; Based on the association rules of the inspection type, query other inspection types associated with the inspection type to obtain a list of associated inspection types; The medical tomographic images belonging to the list of associated examination types are selected from the medical tomographic images corresponding to the patient identifier and used as the second medical tomographic images.

26. The medical tomographic imaging loading system according to claim 24, characterized in that, The preloading module is further configured as follows: Obtain the sequence type and examination type of the first medical computed tomography image; According to the diagnostic process association rules, query other sequence types in the diagnostic process corresponding to the sequence type to obtain a list of associated sequence types; Medical tomographic images that relate to the list of associated sequence types are selected from the medical tomographic images corresponding to the examination type and used as the second medical tomographic images.

27. The medical tomographic imaging loading system according to claim 24, characterized in that, The preloading module is further configured as follows: Obtain the patient identification, examination site, and examination time of the first medical tomographic image; Based on the time association rules, the historical time range of the association is determined according to the inspection time; The medical tomographic images corresponding to the patient identifier that involve the examination site and whose examination time is within the historical time range are selected as the second medical tomographic images.

28. The medical tomographic imaging loading system according to claim 24, characterized in that, The preloading module is further configured as follows: Obtain the lesion area marked by the user in the first medical tomographic image; The medical tomographic image containing the lesion region is determined according to the lesion region association rule and used as the second medical tomographic image.

29. An electronic device, characterized in that, The method includes a processor and a memory, wherein the memory stores computer program instructions, and the processor, when executing the computer program instructions, implements the medical tomographic image loading method as described in any one of claims 1 to 14.

30. A computer storage medium, characterized in that, The system stores computer program instructions, which, when executed by a processor, implement the medical computed tomography loading method as described in any one of claims 1 to 14.

Images