Method for transforming X-ray chest radiography system

Abstract

A method for transforming an X-ray chest radiography system comprises the following steps that 1, a detector auxiliary lifting device and a voice prompt loudspeaker are arranged in an original X-ray machine room; 2, arranging a high-definition camera in an original X-ray machine room; 3, setting a main control computer, and constructing an artificial intelligence visual identification model in the main control computer; 4, corresponding computer wireless control modules are arranged at the main control computer and the remote control equipment; the computer wireless control module comprises a signal transmitting end and a signal receiving end, and the computer wireless control module is used for transmitting an instruction sent by the main control computer from the signal transmitting end to the signal receiving end in a wireless signal mode and controlling remote control equipment corresponding to the signal receiving end to act; the remote control equipment comprises a detector auxiliary lifting device, a voice prompt loudspeaker and a radiation shielding door; and step 5, configuring an exposure control module for exposure for the original X-ray machine.

Description

Technical Field

[0001] The present invention belongs to the technical field of X-ray chest radiography, and particularly relates to a method for transforming an X-ray chest radiography system. Background Art

[0002] With the increasing awareness of people's health, the number of people undergoing regular physical examinations is also increasing. X-ray chest radiography is a relatively important item in regular physical examinations, which leads to a large amount of shooting work for radiographers responsible for shooting during physical examinations. Moreover, the shooting process is single, the work is boring, and the workload is very large. To reduce the workload of radiographers in chest radiography, a better way is to purchase a full set of self-service X-ray chest radiography systems. However, the cost of purchasing a new full set of self-service X-ray chest radiography systems is relatively high. On the premise that the old X-ray equipment can still meet the usage requirements, hospitals or physical examination institutions generally do not want to spend a large amount of money to purchase new equipment. And purchasing new equipment also means that the old X-ray equipment will be idle, resulting in a waste of resources.

[0003] Currently, there is a main control computer outside the X-ray examination room, and an X-ray machine is installed inside the X-ray examination room. The radiographer outside the X-ray examination room controls the shooting of the X-ray machine through the main control computer.

[0004] Therefore, in order to reduce the workload of radiographers in chest radiography, a method for transforming an X-ray chest radiography system needs to be designed. Summary of the Invention

[0005] The purpose of the present invention is to provide a method for transforming an X-ray chest radiography system to solve the problems in the background art that during physical examinations, radiographers responsible for shooting face a large amount of shooting work, the shooting process is single, the work is boring, and the workload is very large. However, the cost of purchasing a full set of self-service X-ray chest radiography systems is relatively high, and it will cause the old X-ray equipment to be idle.

[0006] To achieve the above purpose, the present invention provides a method for transforming an X-ray chest radiography system, including the following steps:

[0007] Step 1: In the original X-ray examination room, a detector auxiliary lifting device and a voice prompt speaker are set. The detector auxiliary lifting device is used to control the lifting of the X-ray machine detector; the voice prompt speaker is used to play voice prompts;

[0008] Step 2: A high-definition camera is set at a position opposite to the X-ray machine detector in the original X-ray examination room;

[0009] Step 3: A main control computer is set, and an artificial intelligence visual recognition model is built in the main control computer. The artificial intelligence visual recognition model is used to judge the relative position of the X-ray machine detector relative to the patient captured by the high-definition camera and issue instructions;

[0010] Step 4: Set corresponding computer wireless control modules at the main control computer and the remote control device; the computer wireless control module includes a signal transmitter and a signal receiver, and is used to transmit the instructions sent by the main control computer from the signal transmitter to the signal receiver in the form of wireless signals, and control the corresponding remote control device at the signal receiver to act; the remote control device includes a detector auxiliary lifting device, a voice prompt speaker, and a radiation shielding door;

[0011] Step 5: Configure an exposure control module for the original X-ray machine, and the exposure control module is used to control the X-ray machine to perform exposure operations.

[0012] In a specific embodiment, in the said Step 3, the steps of constructing the artificial intelligence vision recognition model are as follows:

[0013] First, batch convert the videos transmitted back by the high-definition camera into pictures, and according to the specific conditions of the pictures, classify the picture tags according to five detector states: too high position, too low position, correct position, no person state, and other states;

[0014] Then preprocess the picture data,

[0015] Next, divide the picture data set into a training set, a validation set, and a test set,

[0016] Construct a deep learning network, and use the training set to train the initialized deep learning network, and use the validation set to verify the trained deep learning network,

[0017] Iteratively execute the above training and verification until the accuracy rate of the trained deep learning network reaches the requirement, and then the artificial intelligence vision recognition model is obtained; and use the test set to test the recognition effect of the artificial intelligence vision recognition model, and if the test is qualified, the artificial intelligence vision recognition model that meets the requirements is obtained.

[0018] In a specific embodiment, a deep learning network is constructed through the tensorflow module, and the deep learning network includes initialization, a fully connected layer, a convolutional layer, a pooling layer, and an auxiliary layer.

[0019] In a specific embodiment, when the result judged by the artificial intelligence vision recognition model is too high position, the main control computer controls the operation of the detector auxiliary lifting device by transmitting wireless signals through the computer wireless control module, so that the X-ray machine detector moves downward;

[0020] When the result judged by the artificial intelligence vision recognition model is too low position, the main control computer controls the operation of the detector auxiliary lifting device by transmitting wireless signals through the computer wireless control module, so that the X-ray machine detector moves upward;

[0021] When the result judged by the artificial intelligence visual recognition model is the unmanned state, the main control computer controls the operation of the voice prompt speaker by transmitting a wireless signal through the computer wireless control module, and the voice prompt is that there is no shooting target;

[0022] When the result judged by the artificial intelligence visual recognition model is other states, the main control computer controls the operation of the voice prompt speaker by transmitting a wireless signal through the computer wireless control module, and the voice prompt is that the standing position is incorrect, please adjust;

[0023] When the result judged by the artificial intelligence visual recognition model is the correct position, the main control computer controls the operation of the voice prompt speaker by transmitting a wireless signal through the computer wireless control module, and the voice prompt is for the patient to control the X-ray machine to perform the exposure operation.

[0024] In a specific embodiment, the method for modifying the X-ray chest radiography system further includes: setting a hand-held positioning rod at the lower end of the X-ray machine detector. When the result judged by the artificial intelligence visual recognition model is the correct position, the main control computer controls the operation of the voice prompt speaker and the positioning rod by transmitting a wireless signal through the computer wireless control module, and the voice prompt is for the patient to grasp the positioning rod, and the positioning rod extends slightly backward and moves towards the patient to ensure that the scapulae are placed on both sides of the chest.

[0025] In a specific embodiment, the computer wireless control module is a wireless control module using radio frequency technology.

[0026] In a specific embodiment, the detector auxiliary lifting device includes a servo motor and a linear slide table module. The original X-ray machine detector is arranged on the linear slide table module, and the servo motor is used to control the lifting of the X-ray machine detector through the linear slide table module.

[0027] In a specific embodiment, the exposure control module is a mobile X-ray machine exposure controller. Before exposure, the main control computer will play a voice prompt through the voice prompt speaker for the patient to hold their breath, and after exposure is completed, it will play a voice prompt for the patient to breathe freely.

[0028] In a specific embodiment, the method for modifying the X-ray chest radiography system further includes: setting a turnstile outside the radiation shielding door, and setting a code scanning device on the turnstile. The code scanning device is used to scan the code to check the patient's information. The turnstile is controlled to open the gate by a button or by the main control computer, and the radiation shielding door is controlled to open and close by a button or by the main control computer. The remote control device further includes a radiation warning light and a guiding warning light.

[0029] In a specific embodiment, the main control computer is set beside the turnstile, and the main control computer is provided with a main screen and a secondary screen. The main screen is a touch screen for confirming patient information, and the secondary screen is used to scroll and play the usage process and precautions.

[0030] Compared with the prior art, the present invention has the following beneficial effects:

[0031] The self-service or semi-self-service chest X-ray shooting mode implemented by the present invention can not only reduce the work complexity and workload of physical examination technicians, but also save human resource costs. For example, it can change the two-person work mode into a one-person work mode. At the same time, it can also effectively control the hospital renovation cost, avoiding the situation of purchasing expensive new equipment and making the old equipment idle. It has high application value and is a very potential renovation method, which can not only obtain the intelligent effect but also effectively control the cost, and is worthy of being further promoted and used.

[0032] The implementation of the present invention can achieve a fully self-service X-ray chest radiography solution by using the artificial intelligence visual recognition of the camera. It uses fewer sensors (only the camera and the barcode scanner), has a low system complexity, low cost, a simple technical route, and is stable. The accuracy of the artificial intelligence automatic judgment is high, which can reduce human error, improve the success rate of chest X-ray shooting, reduce the secondary rework shooting, and thus reduce the overall radiation dose of the chest X-ray shooting group.

[0033] In terms of equipment connection, all actuators are controlled by a wireless control module using radio frequency technology, which reduces the line complexity, avoids the trouble of punching and wiring in the radiation shielding computer room, and does not need to apply to the radiation protection management agency for computer room renovation. It has low cost and simple technical implementation.

[0034] In addition to the purposes, features and advantages described above, the present invention has other purposes, features and advantages. The following will refer to the drawings to further elaborate on the present invention in detail. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] The drawings forming a part of this application are used to provide a further understanding of the present invention. The schematic embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation to the present invention. In the drawings:

[0036] Figure 1 is the technical route diagram of the overall solution of the fully self-service X-ray chest radiography in an embodiment of the present invention;

[0037] Figure 2 is the layout and design diagram of the fully self-service X-ray chest radiography computer room in an embodiment of the present invention;

[0038] Among them, A is the main control computer; B is the main screen and the secondary screen; C is the bi-directional turnstile; D is the code scanning device; E is the radiation shielding door; F is the original X-ray machine console; G is the shielding wall of the machine room; H is the detector auxiliary lifting device; J is the X-ray machine detector; K is the hand-held positioning rod; L is the voice prompt speaker; M is the guiding prompt light; N is the high-definition camera; P is the original X-ray tube of the X-ray machine;

[0039] Figure 3 It is the flowchart of training the artificial intelligence visual recognition model in an embodiment of the present invention;

[0040] Figure 4 It is the flowchart of the precise positioning and control system of the artificial intelligence detector in an embodiment of the present invention;

[0041] Figure 5 It is the technical schematic diagram of the computer simulation radio frequency control system in an embodiment of the present invention. Specific implementation manners

[0042] The following will describe the embodiments of the present invention in detail with reference to the accompanying drawings. The specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0043] Embodiment 1

[0044] A method for transforming an X-ray chest radiography system includes the following steps:

[0045] Step 1: In the original X-ray machine room, set a detector auxiliary lifting device and a voice prompt speaker. The detector auxiliary lifting device is used to control the lifting of the X-ray machine detector; the voice prompt speaker is used to play voice prompts;

[0046] Step 2: Set a high-definition camera at a position opposite to the X-ray machine detector in the original X-ray machine room;

[0047] Step 3: Set a main control computer, and build an artificial intelligence visual recognition model in the main control computer. The artificial intelligence visual recognition model is used to judge the relative position of the X-ray machine detector captured by the high-definition camera relative to the patient and issue instructions;

[0048] Step 4: Set corresponding computer wireless control modules at the main control computer and the remote control device; the computer wireless control module includes a signal transmitting end and a signal receiving end. The computer wireless control module is used to transmit the instructions issued by the main control computer from the signal transmitting end to the signal receiving end in the form of wireless signals, and control the corresponding remote control device at the signal receiving end to perform actions; the remote control devices include a detector auxiliary lifting device, a voice prompt speaker, and a radiation shielding door;

[0049] Step 5: Configure an exposure control module for the original X-ray machine. The exposure control module is used to control the X-ray machine to perform exposure operations.

[0050] The master computer can also achieve some operations by controlling the original X-ray machine console. The exposure control module can perform exposure either by pressing a button set on the hand-held positioning rod or by the radiographer operating the master computer to control the original X-ray machine console for exposure.

[0051] In step 3, the steps for constructing the artificial intelligence visual recognition model are as follows:

[0052] First, batch convert the videos transmitted back by the high-definition camera into pictures, and classify the picture tags according to the specific conditions of the pictures into five detector states: too high position, too low position, correct position, no person state, and other states.

[0053] Then, preprocess the picture data.

[0054] Next, divide the picture data set into a training set, a validation set, and a test set.

[0055] Construct a deep learning network, and use the training set to train the initialized deep learning network. Use the validation set to verify the trained deep learning network.

[0056] Iteratively execute the above training and verification until the accuracy rate of the trained deep learning network reaches the requirement, and then the artificial intelligence visual recognition model is obtained; and use the test set to test the recognition effect of the artificial intelligence visual recognition model. If the test is qualified, the artificial intelligence visual recognition model that meets the requirements is obtained.

[0057] Build a deep learning network through the tensorflow module. The deep learning network includes initialization, fully connected layer, convolutional layer, pooling layer, and auxiliary layer. Initialization is used to specify the initial point for starting iteration and determine the reference direction for model training. The fully connected layer can map the "distributed feature representation" learned by the model to the sample label space, greatly reducing the influence of feature positions on the classifier. The convolutional layer can effectively reduce the number of parameters, improve the accuracy of the model, and has the advantages of translational invariance and capturing local correlations. The pooling layer aggregates local features into a representative value through an aggregation operation, thereby reducing the dimension and complexity, and improving the training speed while retaining important features. The auxiliary layer includes a dropout layer and a relu layer, mainly used to prevent the overfitting of the model, so that the model has good generalization ability.

[0058] When the result judged by the artificial intelligence visual recognition model is that the position is too high, the master computer controls the operation of the detector auxiliary lifting device by transmitting a wireless signal through the computer wireless control module, so that the X-ray machine detector moves downward.

[0059] When the result judged by the artificial intelligence vision recognition model is that the position is too low, the main control computer controls the operation of the detector auxiliary lifting device by transmitting a wireless signal through the computer wireless control module, so that the X-ray machine detector moves upward;

[0060] When the result judged by the artificial intelligence vision recognition model is the no-person state, the main control computer controls the operation of the voice prompt speaker by transmitting a wireless signal through the computer wireless control module, and the voice prompts that there is no shooting target;

[0061] When the result judged by the artificial intelligence vision recognition model is other states, the main control computer controls the operation of the voice prompt speaker by transmitting a wireless signal through the computer wireless control module, and the voice prompts that the standing position is incorrect, please adjust;

[0062] When the result judged by the artificial intelligence vision recognition model is that the position is correct, the main control computer controls the operation of the voice prompt speaker by transmitting a wireless signal through the computer wireless control module, and the voice prompts the patient to control the X-ray machine to perform the exposure operation.

[0063] The method for transforming the X-ray chest radiography system further includes: a hand-held positioning rod is arranged at the lower end of the X-ray machine detector. When the result judged by the artificial intelligence vision recognition model is that the position is correct, the main control computer controls the operation of the voice prompt speaker and the positioning rod by transmitting a wireless signal through the computer wireless control module, and the voice prompts the patient to grasp the positioning rod, and the positioning rod extends slightly backward and moves backward to ensure that the scapulae are placed on both sides of the chest.

[0064] The computer wireless control module is a wireless control module using radio frequency technology.

[0065] The detector auxiliary lifting device includes a servo motor and a linear slide table module. The original X-ray machine detector is arranged on the linear slide table module, and the servo motor is used to control the lifting of the X-ray machine detector through the linear slide table module.

[0066] The exposure control module is a mobile X-ray machine exposure controller. Before exposure, the main control computer will play a voice prompt through the voice prompt speaker to prompt the patient to hold their breath, and after the exposure is completed, it will play a voice prompt to prompt the patient to breathe freely.

[0067] The method for transforming the X-ray chest radiography system further includes: a turnstile is arranged outside the radiation shielding door, and a code scanning device is arranged on the turnstile. The code scanning device is used to scan the code to check the patient's information. The turnstile is controlled to open the gate by a button or by the main control computer, and the radiation shielding door is controlled to open and close by a button or by the main control computer.

[0068] The main control computer is set beside the turnstile, and there is a main screen and a secondary screen on the main control computer. The main screen is a touch screen for confirming patient information, and the secondary screen is used to scroll and play the usage process and precautions.

[0069] The remote control device also includes a radiation warning light and a guiding warning light. After the radiation shielding door is closed, the main control computer controls the radiation warning light set outside the radiation shielding door to light up during the X-ray machine exposure period, so that the display of the radiation state is more accurate. The guiding warning light is used to cooperate with the voice prompt speaker to guide the patient to operate following the guiding warning light, such as entering the designated position in the original X-ray machine room following the guiding warning light.

[0070] Usage process of the transformed X-ray chest radiography system:

[0071] When a patient undergoes an X-ray chest radiograph, first watch the usage process and precautions scrolled and played on the secondary screen. After understanding clearly, scan the barcode on the barcode scanning device at the two-way turnstile and confirm the patient information on the main screen.

[0072] After the two-way turnstile and the radiation shielding door are opened, the patient follows the voice prompt and enters the X-ray machine room following the guiding warning light, and stands still at the predetermined position in front of the X-ray machine detector. The high-definition camera transmits the captured content to the main control computer;

[0073] The main control computer receives the real-time pictures transmitted back by the camera, first performs automatic picture data preprocessing, and then imports the processed picture data into the artificial intelligence vision recognition model;

[0074] The artificial intelligence vision recognition model in the main control computer judges the relative position of the X-ray machine detector relative to the patient captured by the high-definition camera, and issues an instruction to the computer wireless control module, and the computer wireless control module outputs a corresponding signal;

[0075] When the result judged by the artificial intelligence vision recognition model is that the position is too high, the main control computer controls the operation of the detector auxiliary lifting device by transmitting a wireless signal through the computer wireless control module, so that the X-ray machine detector moves down;

[0076] When the result judged by the artificial intelligence vision recognition model is that the position is too low, the main control computer controls the operation of the detector auxiliary lifting device by transmitting a wireless signal through the computer wireless control module, so that the X-ray machine detector moves up;

[0077] When the result judged by the artificial intelligence vision recognition model is a no-person state, the main control computer controls the operation of the voice prompt speaker by transmitting a wireless signal through the computer wireless control module, and the voice prompts that there is no shooting target;

[0078] When the result judged by the artificial intelligence vision recognition model is in other states, the main control computer controls the operation of the voice prompt speaker by transmitting a wireless signal through the computer wireless control module, and the voice prompts that the standing position is incorrect and please adjust;

[0079] When the result judged by the artificial intelligence vision recognition model is that the position is correct, the main control computer controls the operation of the voice prompt speaker by transmitting a wireless signal through the computer wireless control module, and the voice prompts the patient to control the X-ray machine to perform an exposure operation.

[0080] The patient controls the X-ray machine to perform an exposure operation through the exposure control module.

[0081] The above content is a further detailed description of the present invention in combination with specific preferred embodiments, and it cannot be determined that the specific implementation of the present invention is only limited to these descriptions. For those of ordinary skill in the technical field to which the present invention belongs, without departing from the concept of the present invention, several simple deductions and substitutions can be made, and all should be regarded as belonging to the protection scope of the present invention.

Claims

1. A method for modifying an X-ray chest radiography system, characterized in that, It includes the following steps: Step 1: In the original X-ray room, set up a detector auxiliary lifting device and a voice prompt speaker. The detector auxiliary lifting device is used to control the lifting of the X-ray machine detector; the voice prompt speaker is used to play voice prompts; Step 2: Set up a high-definition camera at a position opposite to the X-ray machine detector in the original X-ray room; Step 3: Set up a main control computer and build an artificial intelligence visual recognition model in the main control computer. The artificial intelligence visual recognition model is used to judge the relative position of the X-ray machine detector captured by the high-definition camera and issue commands; Step 4: Set up corresponding computer wireless control modules at the main control computer and the remote control device; the computer wireless control module includes a signal transmitter and a signal receiver. The computer wireless control module is used to transmit the commands issued by the main control computer from the signal transmitter to the signal receiver in the form of wireless signals to control the corresponding remote control device at the signal receiver to act; the remote control device includes a detector auxiliary lifting device, a voice prompt speaker, and a radiation shielding door; Step 5: Configure an exposure control module for the original X-ray machine. The exposure control module is used to control the X-ray machine to perform exposure operations.

2. The method for modifying an X-ray chest radiography system according to claim 1, wherein In the above-mentioned Step 3, the steps for building the artificial intelligence visual recognition model are as follows: First, batch convert the videos transmitted back by the high-definition camera into pictures, and classify the picture tags according to the specific conditions of the pictures into five detector states: too high position, too low position, correct position, no person state, and other states; Then, preprocess the picture data, Next, divide the picture data set into a training set, a validation set, and a test set, Build a deep learning network and use the training set to train the deep learning network, and use the validation set to verify the trained deep learning network, Iteratively execute the above training and verification until the accuracy rate of the trained deep learning network reaches the requirement, and then the artificial intelligence visual recognition model is obtained; And use the test set to test the recognition effect of the artificial intelligence visual recognition model. If the test is qualified, the artificial intelligence visual recognition model that meets the requirements is obtained.

3. The method for modifying an X-ray chest radiography system according to claim 2, wherein, Build a deep learning network through the tensorflow module. The deep learning network includes an initialization layer, a fully connected layer, a convolutional layer, a pooling layer, and an auxiliary layer.

4. The method for modifying an X-ray chest radiography system according to claim 2, wherein When the result judged by the artificial intelligence visual recognition model is that the position is too high, the main control computer controls the operation of the detector auxiliary lifting device by transmitting a wireless signal through the computer wireless control module, so that the X-ray machine detector moves down; When the result judged by the artificial intelligence visual recognition model is that the position is too low, the main control computer controls the operation of the detector auxiliary lifting device by transmitting a wireless signal through the computer wireless control module, so that the X-ray machine detector moves up; When the result judged by the artificial intelligence visual recognition model is the no person state, the main control computer controls the operation of the voice prompt speaker by transmitting a wireless signal through the computer wireless control module, and the voice prompts that there is no shooting target; When the result judged by the artificial intelligence visual recognition model is other states, the main control computer controls the operation of the voice prompt speaker by transmitting a wireless signal through the computer wireless control module, and the voice prompts that the standing position is incorrect, please adjust; When the result judged by the artificial intelligence visual recognition model is that the position is correct, the main control computer controls the operation of the voice prompt speaker by transmitting a wireless signal through the computer wireless control module, and the voice prompts the patient to control the X-ray machine to perform an exposure operation.

5. The method for modifying an X-ray chest radiography system according to claim 4, wherein, The method for modifying the X-ray chest radiography system further includes: arranging a hand-held positioning rod at the lower end of the X-ray machine detector. When the result judged by the artificial intelligence visual recognition model is that the position is correct, the main control computer controls the operation of the voice prompt speaker and the positioning rod by transmitting a wireless signal through the computer wireless control module, the voice prompts the patient to grasp the positioning rod, and the positioning rod extends slightly backward and moves to ensure that the scapulae are placed on both sides of the chest.

6. The method for modifying an X-ray chest radiography system according to claim 1, wherein, The computer wireless control module is a wireless control module using radio frequency technology.

7. The method for modifying an X-ray chest radiography system according to claim 1, wherein, The detector auxiliary lifting device includes a servo motor and a linear slide table module. The original X-ray machine detector is arranged on the linear slide table module, and the servo motor is used to control the lifting of the X-ray machine detector through the linear slide table module.

8. The method for modifying an X-ray chest radiography system according to claim 1, wherein, The exposure control module is a mobile X-ray machine exposure controller. Before exposure, the exposure control module will play a voice prompt for the patient to hold their breath through the voice prompt speaker by the main control computer, and after exposure is completed, it will play a voice prompt for the patient to breathe freely.

9. The method for modifying an X-ray chest radiography system according to claim 1, characterized in that, The method for modifying the X-ray chest radiography system further includes: arranging a turnstile outside the radiation shielding door, and arranging a code scanning device on the turnstile. The code scanning device is used to scan the code to verify the patient's information. The turnstile is controlled to open the gate by a button or by the main control computer, and the radiation shielding door is controlled to open and close by a button or by the main control computer; the remote control device further includes a radiation warning light and a guiding warning light.

10. The method for modifying an X-ray chest radiography system according to claim 9, wherein, The main control computer is arranged beside the turnstile, and a main screen and a secondary screen are arranged on the main control computer. The main screen is a touch screen for confirming the patient's information, and the secondary screen is used to scroll and play the usage process and precautions.

Images