WO2022110132A1

WO2022110132A1 - Unmanned smart radiographing system and radiographing method

Info

Publication number: WO2022110132A1
Application number: PCT/CN2020/132728
Authority: WO
Inventors: 赵杰; 奥雪
Original assignee: 江苏康众数字医疗科技股份有限公司
Priority date: 2020-11-30
Filing date: 2020-11-30
Publication date: 2022-06-02

Abstract

An unmanned smart radiographing system and radiographing method. The radiographing system comprises a ray source, a camera assembly (1), a beam limiter (2) and a control platform (3); the camera assembly (1) is used for acquiring image information of a target to be radiographed and the surrounding environment thereof, the beam limiter (2) is used for adjusting the radiation field of a ray and switching the filtering of the ray, and the control platform (3) is electrically connected to both the camera assembly (1) and the beam limiter (2); the control platform (3) is provided with a processing computation module and an auxiliary module; the processing computation module can obtain, according to the image information acquired by the camera assembly (1), operation parameters of the camera assembly (1) and the beam limiter (2), and the positional relationship between the current position of the target and a preset detection position; the auxiliary module can guide the target to move to the preset detection position according to the positional relationship and guide the target to make a posture complying with radiographing requirements; and the control platform (3) can control the operation parameters of the ray source, the camera assembly (1) and the beam limiter (2) according to the operation parameters. The radiographing system and radiographing method can automatically recognize a current posture of a patient and guide same to be in a correct posture.

Description

A kind of unmanned intelligent filming system and filming method

technical field

The invention relates to the field of medical imaging equipment, in particular to an unmanned intelligent filming system and a filming method.

Background technique

After decades of continuous development, digital X-ray imaging systems have become the preferred equipment for imaging examinations. As people's concerns and expectations about medical conditions and X-ray radiation doses increase, so do the demands on the medical equipment itself and the filming process. For DR, the entire filming process, including instructing the patient to position correctly, adjusting the beamer to align the exposure area, and setting exposure parameters such as tube current and tube voltage, still relies entirely on the experience and judgment of the shooting technician. However, due to the variety of human body positions and sizes, it is impossible to achieve precise, stable and repeatable results.

Currently in DR photography applications, a typical filming process includes:

1) The doctor issues a checklist according to the diagnostic needs, and the shooting technician adjusts the distance between the tube and the flat panel detector according to the requirements of the shooting site;

2) The shooting technician instructs the patient to put on the correct shooting posture;

3) The shooting technician adjusts the opening of the beamer so that the X-ray irradiation area just covers the part to be shot;

4) The shooting technician sets the exposure parameters such as kV, mAs, etc. according to the shooting site, patient size and other factors;

5) The shooting technician presses the handbrake for exposure;

6) The shooting technician judges the image quality. If the effect is not good (overexposure or underexposure), it needs to be retaken;

7) The doctor makes a diagnosis based on the X-ray film.

It can be seen from the above process that the technician plays a very important role in the entire filming process, and the level of experience directly determines the accuracy of parameter selection, which in turn affects the radiation dose and imaging quality received by the patient. Among them, the two most important steps are patient setup and exposure dose control.

SUMMARY OF THE INVENTION

In order to solve the problem of the prior art, the present invention provides a kind of unmanned intelligent filming system and filming method, and the technical scheme is as follows:

In one aspect, the present invention provides an unmanned intelligent filming system, comprising:

a ray source for emitting rays;

a camera assembly, which is used to obtain image information of a target to be filmed and its surrounding environment;

a beamer, the beamer is used to adjust the radiation field and switch the filtering of the radiation;

a control platform, the control platform is electrically connected to the camera assembly and the beamer, the control platform is provided with a processing operation module and an auxiliary module, and the processing operation module can be based on the images obtained by the camera assembly The information obtains the operating parameters of the camera assembly and the beamer, as well as the positional relationship between the current position of the target and the preset test position, and the auxiliary module can guide the target to move to the preset test position according to the positional relationship, The control platform can control the operating parameters of the ray source, the camera assembly and the light beamer according to the operating parameters.

Further, the auxiliary module includes a speaker for guiding the movement of the target to be filmed by voice and/or a display screen for guiding the movement of the target to be filmed by graphics and text.

Further, the camera assembly includes a first RGB camera, and the first RGB camera is a zoom RGB camera.

Further, the camera assembly includes a first RGB camera and a second RGB camera, and the second RGB camera is a wide-angle RGB camera.

Further, the camera assembly includes a first RGB camera and a third RGB camera, and the third RGB camera is a telephoto RGB camera.

Further, the camera assembly further includes a depth camera, and the depth camera is used to obtain the depth information of the target to be filmed and its surrounding environment.

Further, the depth camera is a ToF camera or a structured light camera.

Further, both the camera assembly and the control platform are arranged on the light beamer.

Further, the control platform is also provided with an interface for communicating with external devices.

On the other hand, the present invention provides an unmanned intelligent filming method, comprising the following steps:

S1. Obtain the image information of the target to be filmed and its surrounding environment through one or more cameras;

S2, processing the image information obtained by the camera through the processing operation module, to obtain the positional relationship between the current position of the target and the preset test position, and the operating parameters required for controlling the camera;

S3, if the positional relationship exceeds the preset threshold range, the control platform adjusts the camera according to the operating parameters in step S2, the auxiliary module guides the target to move to the preset test position according to the positional relationship, and executes S1-S3, Otherwise, execute S4-S5;

S4, processing the image information currently obtained by the camera through the processing operation module to obtain the operating parameters of the beamer and the X-ray source;

S5. The control platform controls the beamer and the X-ray source to radiate the target to be filmed according to the operating parameters in the step S4.

The beneficial effects brought by the technical scheme provided by the invention are as follows:

a. According to the shooting position designated by the doctor, the current posture of the patient is automatically recognized and the correct positioning is guided;

b. Automatically adjust the opening of the beamer so that the X-ray irradiation area just covers the shooting site, and cooperate with the AEC technology to automatically control the exposure dose, thereby greatly improving the filming efficiency and effectively reducing unnecessary radiation dose;

c. Reduce unnecessary doctor-patient contact.

Description of drawings

In order to illustrate the technical solutions in the embodiments of the present invention more clearly, the following briefly introduces the accompanying drawings used in the description of the embodiments. Obviously, the accompanying drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can also be obtained from these drawings without creative effort.

1 is a schematic diagram of a framework of an unmanned intelligent filming system provided by an embodiment of the present invention;

2 is a schematic diagram of different camera shooting ranges of an unmanned intelligent filming system provided by an embodiment of the present invention;

3 is a schematic diagram of successful placement of an unmanned intelligent filming system provided by an embodiment of the present invention;

FIG. 4 is a schematic diagram of an auxiliary positioning guide of an unmanned intelligent filming system provided by an embodiment of the present invention.

Wherein, the reference numerals are as follows: 1-camera assembly, 2-beam light device, 3-control platform, 11-first RGB camera, 12-depth camera, 13-second RGB camera.

Detailed ways

In order to make those skilled in the art better understand the solutions of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only Embodiments are part of the present invention, but not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

It should be noted that the terms "first", "second" and the like in the description and claims of the present invention and the above drawings are used to distinguish similar objects, and are not necessarily used to describe a specific sequence or sequence. It is to be understood that the data so used may be interchanged under appropriate circumstances such that the embodiments of the invention described herein can be practiced in sequences other than those illustrated or described herein. Furthermore, the terms "comprising" and "having", and any variations thereof, are intended to cover non-exclusive inclusion, for example, a process, method, apparatus, product or device comprising a series of steps or units is not necessarily limited to those expressly listed Rather, those steps or units may include other steps or units not expressly listed or inherent to these processes, methods, products or devices.

In an embodiment of the present invention, an unmanned intelligent filming system is provided, as shown in FIG. 1 , including a ray source, a camera assembly 1 , a beamer 2 and a control platform 3 , and the ray source is used for shooting out rays; the camera assembly 1 is used to obtain the image information of the target to be filmed and its surrounding environment, the beamer 2 is used to adjust the field of radiation and switch the filtering of rays, and the beamer is arranged in the In front of the output end of the X-ray source, the beamer 2 is an intelligent beamer, and the beamer 2 also provides a mounting structure for installing the camera assembly 1 and the control platform 3 .

The control platform 3 is electrically connected to the camera assembly 1 and the beamer 2, and the control platform 3 is provided with a processing operation module and an auxiliary module, and the processing operation module can be obtained according to the camera assembly 1. The operating parameters of the camera assembly 1 and the beamer 2, as well as the positional relationship between the current position of the target and the preset test position, are obtained from the image information obtained by the auxiliary module, and the auxiliary module can guide the target to move to the preset position according to the positional relationship. Assuming the test position, it should be noted that moving to the preset test position also includes guiding the target to pose a posture that meets the shooting requirements, and the auxiliary module includes a speaker for voice guidance to move the target to be filmed and/or for graphic guidance. The display screen of the moving target to be filmed, the control platform 3 can control the working parameters of the ray source, the camera assembly 1 and the beamer 2 according to the operating parameters, and the control platform 3 is also provided with a control input The interface for the module to communicate with external equipment, the control input module can be used for the doctor to input the area that the patient needs to be irradiated, and the input can be performed by displaying a touch screen. The interface for external equipment communication is convenient for information output and direct control of external equipment. The control platform 3 It has the ability to control other components and perform high-intensity operations of processing and computing modules, and provide the ability to communicate with external devices on the network.

Wherein, the processing operation module utilizes the acquired RGB images and depth information, and utilizes traditional image processing algorithms and neural network algorithms to achieve contour/silhouette extraction, 2D/3D key point extraction, and pose determination of the object to be photographed. , Through the auxiliary module positioning guidance, exposure area calculation and determination of the area of interest of AEC (Automatic Exposure Control Technology), it is the intelligent brain of the entire system.

In an embodiment of the present invention, the camera assembly 1 has the following composition schemes:

(1) The camera assembly 1 includes a first RGB camera 11, and the first RGB camera 11 is an ordinary RGB camera, which can be used to obtain image information of the object to be photographed and its surrounding environment from a general distance. This solution is suitable for the camera and the photographed object. For application scenarios where the distance between objects is moderate and does not change much, it can provide basic positioning assistance and automatic exposure control assistance functions;

(2) The camera assembly 1 includes a first RGB camera 11, the first RGB camera 11 is a zoom RGB camera, and the focal length can be adjusted to replace a plurality of cameras with different focal lengths. For medium and long-distance image acquisition needs, it can provide basic positioning assistance and automatic exposure control assistance functions;

(3) The camera assembly 1 includes a first RGB camera 11 and a second RGB camera 13. The first RGB camera 11 is an ordinary RGB camera, which can be used to obtain image information of the object and its surrounding environment from a general distance. The second RGB camera 13 is a wide-angle RGB camera, which can be used to obtain image information of the entire object and its surrounding environment when the camera is too close to the object to be photographed. Moderate application scenarios, which can cover most filming scenarios, and can provide basic setup assistance and automatic exposure control assistance functions;

(4) The camera assembly 1 includes a first RGB camera 11 and a third RGB camera. The first RGB camera 11 is an ordinary RGB camera, which can be used to obtain image information of the object and its surrounding environment from a general distance. The triple RGB camera is a telephoto RGB camera, which can be used to obtain high-resolution image information of the shooting part when the camera is far away from the subject or the part to be shot is small. This solution is suitable for the distance between the camera and the subject being moderate to For distant application scenarios, it can provide local high-resolution images for small shooting parts, and can provide basic positioning assistance and automatic exposure control assistance functions;

(5) The camera assembly 1 includes a first RGB camera 11, a second RGB camera 13, a third RGB camera and a depth camera 12, the first RGB camera 11 is an ordinary RGB camera, and the second RGB camera 13 is a wide-angle RGB camera camera, the third RGB camera is a telephoto RGB camera, the depth camera 12 is a ToF camera or a structured light camera, and the depth camera 12 is used to obtain the depth information of the target to be filmed and its surrounding environment, and the solution provides The most complete and accurate results for the vast majority of DR filming applications. It should be noted that the composition scheme of the camera assembly 1 includes but is not limited to the above, and the depth camera 12 can also be freely combined with the above scheme.

In an embodiment of the present invention, the camera assembly 1 includes a first RGB camera 11, a second RGB camera 13 and a depth camera 12, the first RGB camera 11 is a common RGB camera, and the second RGB camera 13 is a wide-angle camera RGB camera, the depth camera 12 is a ToF camera, which is used to obtain the depth information of the target to be filmed and its surrounding environment. The ToF camera can obtain the three-dimensional information of the object and its surrounding environment, which can help the system to perceive more accurately The position of the subject, the camera selected in this embodiment and its field of view at different distances are shown in Figure 2. The maximum shooting angles of the first RGB camera 11, the second RGB camera 13 and the depth camera 12 are respectively It is 63°, 80° and 100°. The second RGB camera 13 has the widest shooting range at 0.8m from the front of the camera assembly, and the second RGB camera 13 has the widest shooting range at 1.8m from the front of the camera assembly. The range is large and not shown in the figure, and the first RGB camera 11 has the smallest shooting range. Therefore, when shooting is required, the second RGB camera 13 can first capture the target to be filmed, and then the filming system will activate the depth camera 12 and the camera. The first RGB camera 11 is used for precise shooting and positioning in the next step. In this embodiment, the control platform is an embedded high-performance computing platform, including a CPU (central processing unit), an MCU (microcontroller unit), a general parallel computing unit and a network communication interface, which meet the requirements of small size, low power consumption, With rich hardware interfaces and powerful computing power, the Jetson Nano chip produced by NVIDIA is preferred. The processing operation module consists of multiple parts, mainly including: 1) basic unit, including image acquisition, camera calibration, data stream synchronization and mapping of different cameras, and definition of positioning requirements; 2) middle layer, using traditional image processing methods and neural The network method realizes the extraction of the silhouette and key points of the photographed object, see Figure 3, for example, human skeleton points are used as key points to locate the preset radiation area; 3) Application layer, based on filming, placement requirements and extracted information , determine the exposure area, guide the placement, and then realize the functions of controlling the beamer adjustment, calculating the AEC area of interest, etc., as shown in Figure 4; 4) Automatic evolution and upgrade modules, sorting and uploading video streams to the cloud space , the neural network is trained and upgraded online, and then the upgrade file is sent to the terminal device. The unmanned intelligent filming system also includes a flat panel detector. The flat panel detector can be connected to the above-mentioned control platform 3 in communication. Realize intelligent filming.

In one embodiment of the present invention, an unmanned intelligent filming method is provided, comprising the following steps:

The unmanned intelligent filming system and filming method provided by the present invention solve the problems of low accuracy, stability and efficiency caused by the current key parameters of filming being completely determined by the shooting technician, and realize the automatic identification of patients according to the shooting position designated by the doctor The current posture and the correct positioning are guided, the opening of the beamer is automatically adjusted so that the X-ray irradiation area just covers the shooting site, and the exposure dose is automatically controlled with the AEC technology, thereby greatly improving the filming efficiency, effectively reducing unnecessary radiation dose, and can Reduce unnecessary contact between doctors and patients, and promote medical imaging equipment to go further in the direction of unmanned and intelligent.

The above are only preferred embodiments of the present invention and are not intended to limit the present invention. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection of the present invention. within the range.

Claims

An unmanned intelligent filming system, characterized in that it includes

a ray source for emitting rays;

a camera assembly (1), the camera assembly (1) is used to obtain image information of a target to be filmed and its surrounding environment;

a beamer (2), the beamer (2) is used for adjusting the radiation field and switching the filtering of the radiation;

A control platform (3), the control platform (3) is electrically connected with the camera assembly (1) and the beamer (2), and the control platform (3) is provided with a processing operation module and an auxiliary module , the processing operation module can obtain the operating parameters of the camera assembly (1) and the beamer (2) according to the image information obtained by the camera assembly (1), and the difference between the current position of the target and the preset test position a positional relationship, the auxiliary module can guide the target to move to a preset test position according to the positional relationship, and the control platform (3) can control the ray source, the camera assembly (1) and all the The working parameters of the beamer (2).
The unmanned intelligent filming system according to claim 1, wherein the auxiliary module comprises a speaker for guiding the movement of the target to be filmed by voice and/or a display screen for guiding the movement of the target to be filmed with pictures and texts .
The unmanned intelligent filming system according to claim 1, wherein the camera assembly (1) comprises a first RGB camera (11), and the first RGB camera (11) is a zoom RGB camera.
The unmanned intelligent filming system according to claim 1, wherein the camera assembly (1) comprises a first RGB camera (11) and a second RGB camera (13), and the second RGB camera (13) ) is a wide-angle RGB camera.
The unmanned intelligent filming system according to claim 1, wherein the camera assembly (1) comprises a first RGB camera (11) and a third RGB camera, and the third RGB camera is a telephoto RGB camera .
The unmanned intelligent filming system according to any one of claims 3-5, wherein the camera assembly (1) further comprises a depth camera (12), and the depth camera (12) is used to obtain the film to be filmed The depth information of the target and its surrounding environment.
The unmanned intelligent filming system according to claim 6, wherein the depth camera (12) is a ToF camera or a structured light camera.
The unmanned intelligent filming system according to claim 1, wherein the camera assembly (1) and the control platform (3) are both arranged on the beamer (2).
The unmanned intelligent filming system according to claim 1, characterized in that, the control platform (3) is further provided with an interface for communicating with external devices.
An unmanned intelligent filming method, characterized in that it comprises the following steps:

S1. Obtain the image information of the target to be filmed and its surrounding environment through one or more cameras;

S2, processing the image information obtained by the camera through the processing operation module, to obtain the positional relationship between the current position of the target and the preset test position, and the operating parameters required for controlling the camera;

S3, if the positional relationship exceeds the preset threshold range, the control platform adjusts the camera according to the operating parameters in step S2, the auxiliary module guides the target to move to the preset test position according to the positional relationship, and executes S1-S3, Otherwise, execute S4-S5;

S4, processing the image information currently obtained by the camera through the processing operation module to obtain the operating parameters of the beamer and the X-ray source;

S5. The control platform controls the beamer and the X-ray source to radiate the target to be filmed according to the operating parameters in the step S4.