Device based on virtual dissection intelligent image processing platform

Abstract

The application relates to the technical field of medicine and medical image processing equipment, and particularly discloses an equipment based on a virtual dissection intelligent image processing platform; the equipment comprises a hardware unit and a software unit, the hardware unit is a packaged virtual dissection image processing black box, and the hardware unit is essentially an industrial control computing host; the mainboard of the industrial control computing host is provided with a high-performance central processing unit; and the mainboard further comprises a standard desktop full-height full-length PCIe x16 slot and a high-performance desktop independent display card which is inserted into the standard desktop full-height full-length PCIe x16 slot. The software unit is integrated in the hardware unit, and the software unit comprises multiple function modules; the software unit can process corpse CT related data to generate various images, and can generate color and dynamic three-dimensional images through an AI learning function and adapt to a VR equipment format and the like. The application is specially designed for virtual dissection, can solve the limitations of traditional equipment, can improve image processing efficiency, stability and environmental adaptability, can provide intuitive, comprehensive and efficient image reference data for forensic doctors to judge death causes, and realizes non-invasive and intelligent virtual dissection analysis.

Description

Technical Field

[0001] This invention relates to the field of medical and medical image processing equipment technology, specifically to equipment based on a virtual anatomy intelligent image processing platform. Background Technology

[0002] In virtual dissection practice, it is necessary to perform a full-body CT scan on the cadaver and process massive amounts of raw tomographic image data to generate three-dimensional models, dynamic images, and virtual reality content. This entire process places high demands on the graphics processing capabilities, data throughput, long-term operational stability, and adaptability to the working environment of the computing hardware.

[0003] Currently, most forensic institutions use general-purpose graphics workstations or servers for processing. These devices are not optimized for continuous high-load image processing tasks 24 / 7, and are prone to overheating, frequency reduction, lag, or even crashes during long-term operation. Their cooling systems are noisy under high loads, which can interfere with the quiet autopsy analysis environment. Furthermore, conventional metal chassis may interfere with the internal precision electronic components in high electromagnetic radiation environments such as CT rooms, affecting stability and lifespan. At the same time, the storage capacity is not expandable enough, making it difficult to locally store large amounts of large cadaver CT datasets.

[0004] Therefore, there is an urgent need for an integrated hardware platform designed specifically for high-intensity image processing tasks in virtual anatomy, which features powerful computing capabilities, quiet and stable operation, large-capacity storage, and adaptability to the complex environment of a CT room. Summary of the Invention

[0005] The purpose of this invention is to provide a virtual anatomical intelligent image processing platform that integrates high-performance computing, silent heat dissipation, massive storage, and radiation environment adaptability.

[0006] To achieve the above objectives, the present invention provides the following technical solution:

[0007] The device based on the virtual anatomical intelligent image processing platform includes a hardware unit and a software unit. The hardware unit is a virtual anatomical image processing black box packaged as a dedicated device. The black box is an industrial control computing host. The motherboard of the industrial control computing host is equipped with a high-performance central processing unit. The motherboard integrates a standard desktop full-height and full-length PCIe x16 slot, and a high-performance desktop discrete graphics card is inserted into the slot.

[0008] The software unit is integrated into the hardware unit. The software unit includes a module for generating whole-body black-and-white grayscale images from raw cadaver CT data, a module for generating whole-body angiography images from cadaver CT data after contrast agent injection, a module for generating whole-body energy spectrum analysis images from CT energy spectrum scan data, a module for generating color 3D images of cadavers from black-and-white grayscale images based on AI learning function, a module for generating dynamic 3D images using color 3D images and other images based on AI learning function, and a module for processing the generated image data into a format suitable for VR devices.

[0009] Preferably, the hardware unit further includes a silent and efficient heat dissipation system, which includes a large-area heat pipe heatsink for the central processing unit, an enhanced heat dissipation module for the discrete graphics card, and an intelligent airflow channel composed of multiple large-size, low-speed, silent fans.

[0010] Preferably, the hardware unit further includes a large-capacity local storage array, which has multiple built-in hard drive bays, is configured with a RAID array consisting of multiple large-capacity mechanical hard drives, and is equipped with high-speed solid-state drives as system disks and cache disks for frequently used data. The total storage capacity can be expanded to tens of TB levels.

[0011] Preferably, the storage array supports RAID 5 or RAID 6 configuration.

[0012] Preferably, the chassis of the hardware unit adopts a multi-layer composite structure shell, the inner layer is a high-strength metal frame; the middle layer is an electromagnetic shielding layer, which adopts a high magnetic permeability metal mesh or plating; the outer layer is a corrosion-resistant and easy-to-clean engineering plastic shell, and the chassis is equipped with handles or casters for easy handling and adopts a sealed design to prevent dust.

[0013] Preferably, the high-performance desktop dedicated graphics card is a current mainstream high-performance gaming graphics card or a professional graphics card.

[0014] Preferably, the intelligent air duct is designed as a vertical air duct that flows forward and backward or downward and upward.

[0015] Preferably, the AI ​​learning function is implemented based on a deep learning model.

[0016] Preferably, the dynamic three-dimensional image includes the display of the separation, transparency, rotation, or pathological process simulation of organ blood vessels.

[0017] Preferably, each module of the software unit supports the DICOM protocol, and the interface panel of the chassis provides a high-speed network interface for connecting CT equipment, multiple video output interfaces for outputting to display devices and VR devices, and necessary USB management interfaces.

[0018] The beneficial effects of this invention are as follows:

[0019] This invention firstly integrates a high-performance desktop discrete graphics card into an industrial control computer architecture, which can overcome the bottleneck of traditional equipment graphics processing and meet the computing power requirements related to virtual anatomy. Secondly, the quiet and efficient heat dissipation system of this invention can ensure stable and low-noise operation of the equipment for a long time. On the other hand, the large-capacity scalable storage array enables local secure and efficient management of massive amounts of data, and the radiation-shielded chassis of this invention is adaptable to complex environments. Therefore, this invention can provide a dedicated high-reliability solution for virtual anatomy, which can improve image processing efficiency and adaptability.

[0020] The above description is merely an overview of the technical solution of the present invention. In order to better understand the technical means of the present invention and to implement it in accordance with the contents of the specification, the preferred embodiments of the present invention are described in detail below with reference to the accompanying drawings. Attached Figure Description

[0021] Figure 1 This is a schematic diagram of the main structure of the present invention;

[0022] Figure 2 This is a schematic diagram of the base plate structure of the present invention;

[0023] Figure 3 This is a schematic diagram of the front baffle structure of the present invention;

[0024] Figure 4 This is a schematic diagram of the rear baffle structure of the present invention;

[0025] Figure 5 This is a schematic diagram of the graphics card bracket structure of the present invention. Detailed Implementation

[0026] The technical solution of the present invention will now be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0027] In the description of this invention, it should be noted that the terms "center," "upper," "lower," "left," "right," "vertical," "horizontal," "inner," and "outer," etc., indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. They are used only for the convenience of describing the invention and for simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limitations on the invention. Furthermore, the terms "first," "second," and "third" are used for descriptive purposes only and should not be construed as indicating or implying relative importance.

[0028] In the description of this invention, it should be noted that, unless otherwise explicitly specified and limited, the terms "installation," "connection," and "linking" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; and they can refer to the internal connection of two components. Those skilled in the art can understand the specific meaning of the above terms in this invention based on the specific circumstances.

[0029] Furthermore, the technical features involved in the different embodiments of the present invention described below can be combined with each other as long as they do not conflict with each other.

[0030] like Figures 1-5 As shown, the device based on the virtual anatomy intelligent image processing platform includes a hardware unit and a software unit. The hardware unit is a virtual anatomy image processing black box packaged as a dedicated device. The black box is an industrial control computing host (industrial computer). The motherboard of the industrial control computing host (industrial computer) is equipped with a high-performance central processing unit (CPU). The motherboard integrates a standard desktop full-height and full-length PCIe x16 slot, and a high-performance desktop discrete graphics card (GPU) is plugged into the slot.

[0031] The software unit is integrated into the hardware unit. The software unit includes a module for generating whole-body black-and-white grayscale images from raw cadaver CT data, a module for generating whole-body angiography images from cadaver CT data after contrast agent injection, a module for generating whole-body energy spectrum analysis images from CT energy spectrum scan data, a module for generating color 3D images of cadavers from black-and-white grayscale images based on AI learning function, a module for generating dynamic 3D images using color 3D images and other images based on AI learning function, and a module for processing the generated image data into a format suitable for VR devices.

[0032] Specifically, the hardware unit also includes a silent and efficient heat dissipation system, which includes a large-area heat pipe radiator for the central processing unit (CPU), an enhanced heat dissipation module for the discrete graphics card (GPU), and an intelligent airflow system consisting of multiple large-sized, low-speed, silent fans. The fan speed is dynamically adjusted based on feedback from internal temperature sensors to ensure that the core component temperature is within the efficient operating range while keeping the overall operating noise below 35 decibels, thus adapting to a quiet forensic working environment.

[0033] Specifically, the hardware unit also includes a large-capacity local storage array, which has multiple built-in hard drive bays and is equipped with a RAID array consisting of multiple large-capacity mechanical hard drives (HDDs) for secure and high-speed storage of raw CT data and various image and model files generated during processing. It is also equipped with a high-speed solid-state drive as a system disk and a cache disk for frequently used data to improve software response and data reading speed. The total storage capacity can be expanded to tens of TB.

[0034] Specifically, the storage array supports RAID 5 or RAID 6 configurations, providing large capacity while ensuring data security.

[0035] Specifically, the hardware unit's chassis adopts a multi-layer composite structure shell. The inner layer is a high-strength metal frame to ensure structural stability; the middle layer is an electromagnetic shielding layer, which uses a high-permeability metal mesh or plating to effectively attenuate electromagnetic radiation and radio frequency interference generated by the CT room and nearby equipment, protecting the internal electronic components; the outer layer is a corrosion-resistant and easy-to-clean engineering plastic shell. The chassis is equipped with handles or casters for easy handling and adopts a sealed design to prevent dust.

[0036] Specifically, a high-performance desktop discrete graphics card (GPU) is a current mainstream high-performance gaming graphics card (GPU) or professional graphics card (GPU) with no less than 8GB of video memory.

[0037] Specifically, the intelligent airflow design is a vertical airflow channel that flows forward and backward or downward and upward, ensuring that cool air flows directly through the heat dissipation fins of the central processing unit (CPU) and discrete graphics card (GPU).

[0038] Specifically, the AI ​​learning function is based on a deep learning model, which is trained using a dataset of cadaver CT images.

[0039] Specifically, dynamic 3D images include the display of the separation, transparency, rotation, or simulation of pathological processes of organ blood vessels.

[0040] Specifically, each module of the software unit supports the DICOM protocol, and the chassis interface panel provides a high-speed network interface (such as 10 Gigabit fiber optic) for connecting CT equipment, multiple video output interfaces (such as HDMI and DisplayPort) for outputting to display devices and VR devices, and necessary USB management interfaces.

[0041] When using

[0042] The virtual anatomical intelligent image processing platform is placed in the CT room and connected to the CT equipment via a high-speed network interface on the chassis panel. After the CT equipment completes a full-body scan of the cadaver, it obtains raw data, which is then transmitted to the platform's large-capacity local storage array. The data is securely stored using a RAID array, and high-speed solid-state drives simultaneously cache the data to improve the response speed of subsequent processing.

[0043] After the platform is started, all modules of the software unit begin to run. The raw cadaver CT data will generate whole-body black and white grayscale images. The CT data after the injection of contrast agent will be processed to obtain whole-body angiography images. At the same time, whole-body energy spectrum analysis images will be generated through CT energy spectrum scanning data.

[0044] Subsequently, the AI ​​learning function uses a deep learning model to generate color 3D images of the corpse from black and white grayscale images. It then combines these images with other images to generate images that simulate the separation, transparency, rotation, or pathological processes of organs and blood vessels. Finally, the relevant image data is processed into a format suitable for VR devices.

[0045] Throughout the entire process of handling the body, the silent and efficient heat dissipation system dynamically adjusts the fan speed through intelligent air ducts, ensuring stable and low-noise operation of the central processing unit and discrete graphics card. After processing, various images can be output to display devices or VR devices through the video output interface, allowing forensic doctors to conduct and analyze the body to complete their work.

[0046] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0047] The embodiments described above are merely illustrative of several implementations of the present invention, and while the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the invention patent. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of the present invention, and these all fall within the protection scope of the present invention. Therefore, the protection scope of this invention patent should be determined by the appended claims.

Claims

1. A device based on a virtual anatomical intelligent image processing platform, characterized in that, It includes hardware units and software units. The hardware unit is a virtual anatomical image processing black box packaged as a dedicated device. The black box is an industrial control computing host. The motherboard of the industrial control computing host is equipped with a high-performance central processing unit. The motherboard integrates a standard desktop full-height and full-length PCIe x16 slot, and a high-performance desktop discrete graphics card is inserted into the slot. The software unit is integrated into the hardware unit. The software unit includes a module for generating whole-body black-and-white grayscale images from raw cadaver CT data, a module for generating whole-body angiography images from cadaver CT data after contrast agent injection, a module for generating whole-body energy spectrum analysis images from CT energy spectrum scan data, a module for generating color 3D images of cadavers from black-and-white grayscale images based on AI learning function, a module for generating dynamic 3D images using color 3D images and other images based on AI learning function, and a module for processing the generated image data into a format suitable for VR devices.

2. The device based on the virtual anatomy intelligent image processing platform according to claim 1, characterized in that, The hardware unit also includes a silent and efficient heat dissipation system, which includes a large-area heat pipe heatsink for the central processing unit, an enhanced heat dissipation module for the discrete graphics card, and an intelligent airflow system composed of multiple large-size, low-speed, silent fans.

3. The device based on the virtual anatomy intelligent image processing platform according to claim 1, characterized in that, The hardware unit also includes a large-capacity local storage array, which has multiple hard drive bays and is configured with a RAID array consisting of multiple large-capacity mechanical hard drives. It is also equipped with a high-speed solid-state drive as a system disk and a cache disk for frequently used data. The total storage capacity can be expanded to tens of TB.

4. The device based on the virtual anatomy intelligent image processing platform according to claim 3, characterized in that, The storage array supports RAID 5 or RAID 6 configuration.

5. The device based on the virtual anatomy intelligent image processing platform according to claim 1, characterized in that, The chassis of the hardware unit adopts a multi-layer composite structure shell. The inner layer is a high-strength metal frame; the middle layer is an electromagnetic shielding layer, which adopts a high magnetic permeability metal mesh or plating; the outer layer is a corrosion-resistant and easy-to-clean engineering plastic shell. The chassis is equipped with handles or casters for easy handling and adopts a sealed design to prevent dust.

6. The device based on the virtual anatomy intelligent image processing platform according to claim 1, characterized in that, The high-performance desktop dedicated graphics card is a current mainstream high-performance gaming graphics card or a professional graphics card.

7. The device based on the virtual anatomy intelligent image processing platform according to claim 2, characterized in that, The intelligent air duct is designed as a vertical air duct that flows forward and out backward or from bottom to top.

8. The device based on the virtual anatomy intelligent image processing platform according to claim 1, characterized in that, The AI ​​learning function is implemented based on a deep learning model.

9. The device based on the virtual anatomy intelligent image processing platform according to claim 1, characterized in that, The dynamic three-dimensional images include displays of organ blood vessels being separated, made transparent, rotated, or simulated from pathological processes.

10. The device based on the virtual anatomy intelligent image processing platform according to claim 1, characterized in that, Each module of the software unit supports the DICOM protocol, and the interface panel of the chassis provides a high-speed network interface for connecting CT equipment, multiple video output interfaces for outputting to display devices and VR devices, and necessary USB management interfaces.

Images