Digital gastrointestinal machine imaging control method and system for radiology department

Abstract

The invention discloses a radiology department digital gastrointestinal machine imaging control method and system, and relates to the technical field of radiology department digital gastrointestinal machine imaging control, and the method comprises the steps: carrying out the data collection based on image collection and processing; carrying out image optimization and personalized dose control; and generating a report according to the acquired image and the control result. According to the method, X-ray dose parameters are predicted and adjusted in real time based on a deep learning algorithm and data collected in real time, the radiation dose is controlled at the lowest level on the premise of ensuring that diagnosis requirements are met, noise and artifacts in images are effectively removed through the technologies of noise filtering, high-pass filtering, non-local mean denoising and the like, and the diagnosis accuracy is improved. According to the method, the definition and readability of the image are improved, the diagnosis report is automatically generated according to the collected image and the control result, the time of a doctor is saved, the diagnosis efficiency is improved, the report generation process is automated, the possibility of human errors is reduced, and the report reliability is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of radiology digital gastrointestinal imaging control, and in particular to a radiology digital gastrointestinal imaging control method and system. Background Art

[0002] Digital gastrointestinal imaging technology has developed rapidly in the late 20th century and early 21st century, mainly due to the progress of computer technology, digital image processing technology and medical electronic equipment. Early gastrointestinal angiography mainly relied on fluoroscopic observation and film recording of static images, which had disadvantages such as high radiation dose and image quality affected by various factors. With the development of computed tomography (CT) and direct digital X-ray detector (DR) technology, digital gastrointestinal machines came into being, realizing real-time dynamic imaging and high-resolution static image acquisition. The imaging control system of digital gastrointestinal machines has been further developed and has an intelligent dynamic dose control function. It can automatically adjust exposure parameters according to individual differences, body shape, tissue density and clinical needs of patients to achieve the best image quality and the lowest effective dose. In addition, combined with the application of artificial intelligence and deep learning algorithms, such systems can also achieve accurate image analysis and optimization, effectively improving diagnostic accuracy and efficiency.

[0003] Although digital gastrointestinal imaging technology is constantly improving, the existing technology still has some shortcomings. The personalized dose control is insufficient. The existing technology is difficult to accurately control the dose according to the individual differences, body shape, physiological conditions and clinical diagnosis needs of the patient, which may lead to excessive radiation exposure to sensitive groups such as children and pregnant women and patients who undergo multiple follow-up examinations, increasing health risks. The image optimization effect is limited. The existing technology has limited ability to optimize the collected images and it is difficult to effectively remove noise and artifacts and highlight the edge information of anatomical structures, thereby affecting the doctor's diagnostic accuracy and efficiency. The report generation method is backward. The report generation method of the existing technology is relatively backward, and it is difficult to meet the doctor's needs for personalized report templates, content editing and intelligent auxiliary diagnosis, affecting the efficiency and accuracy of the diagnostic work. Summary of the invention

[0004] In view of the above-mentioned problems, the present invention is proposed.

[0005] Therefore, the technical problem solved by the present invention is: the existing digital gastrointestinal machine imaging control method has insufficient personalized dose control, limited image optimization effect, backward report generation method, and how to achieve precise dose control, efficient image optimization and intelligent report generation.

[0006] To solve the above technical problems, the present invention provides the following technical solutions: a radiology digital gastrointestinal machine imaging control method, including data acquisition based on image acquisition and processing; image optimization and personalized dose control; and report generation based on the acquired images and control results.

[0007] As a preferred solution of the imaging control method of the digital gastrointestinal machine of the radiology department described in the present invention, the image acquisition and processing includes receiving the original signal of the detector, converting the original signal into a digital image and processing it; the patient takes a barium meal contrast agent, performs fluoroscopic observation, the gastrointestinal machine starts the X-ray source exposure, and captures the X-ray information after passing through the gastrointestinal tissue through the flat-panel detector FPD and the IP board imaging board. The detector converts the received X-ray energy into an electrical signal, the flat-panel detector directly outputs a digital signal, and the digital signal is converted into original grayscale image data through analog-to-digital conversion.

[0008] As a preferred solution of the imaging control method of the digital gastrointestinal machine of the radiology department of the present invention, the image acquisition and processing also includes noise filtering, gain correction, dark current compensation, and bad pixel repair based on the generated image; the contrast-to-noise ratio CNR of the image processing algorithm is used to analyze the image quality acquired in real time, and the contrast-to-noise ratio CNR is expressed as:

[0009]

[0010] Among them, μ1 and μ2 are the average grayscale values ​​of the region of interest, and are the standard deviations respectively. Based on the AEC system combined with the feedback signal of the detector, the X-ray tube voltage, current mA and exposure time s are adjusted. The ideal exposure E is expressed as:

[0011] E=k(mA·s)

[0012] Here, k is a coefficient related to the X-ray source characteristics and the detector sensitivity.

[0013] As a preferred solution of the imaging control method of the digital gastrointestinal machine of the radiology department of the present invention, the image optimization includes entering the detailed information of the patient based on the patient information system, and calculating using the entered data according to the pre-set clinical decision support system or dose calculation software. For X-ray fluoroscopy and contrast agent use, the radiation dose and contrast agent dosage are calculated according to the body weight and body surface area. According to the patient's age, weight, body shape, medical history information, combined with historical data in the database, the optimal exposure parameter setting is predicted. For patients of different body shapes, the body surface area BSA is used to adjust the dose, which is expressed as:

[0014] BSA=0.007184×W 0.425 ×H 0.725

[0015] Where E is weight in kg, and H is height in cm. The gastrointestinal tract region and organ contour are segmented from the image using the threshold segmentation edge detection algorithm, and feature extraction is performed. The geometric features are extracted to obtain the contour shape parameters of the gastrointestinal tract, such as area, perimeter, principal axis length, and angle change geometric features. The texture characteristics inside the tissue are analyzed using the gray-level co-occurrence matrix (GLCM) method. Based on pixel intensity information, the CT value or X-ray absorption rate of different tissue regions is quantified to reflect the difference in tissue density. The high-pass filter is used to highlight the edge information of the anatomical structure, identify the organ contour and lesion details, and remove artifacts at the same time. The non-local mean denoising technology and motion blur algorithm are used to eliminate noise and artifacts in the image. Image reconstruction is performed in CT and MRI scans, and filtered back projection is applied to generate tomographic images in spiral CT scans to adjust image quality.

[0016] As a preferred solution of the imaging control method of the digital gastrointestinal machine in the radiology department described in the present invention, the personalized dose control includes designing a deep neural network model through an X-ray dose control module based on a deep learning algorithm, selecting a recurrent neural network RNN ​​to adapt to real-time dynamic optimization according to actual conditions in combination with a reinforcement learning framework DQN, and the model structure includes different convolutional layers, pooling layers, and fully connected layers for feature extraction and decision generation. By defining a loss function based on supervised learning, the MSE mean square error is used as the objective function to represent the gap between the predicted dose and the actual optimal dose, and a prediction model Loss is established, which is expressed as:

[0017]

[0018] in, Represents the dose value predicted by the model, optimal dose is the corresponding optimal dose reference value, N represents the number of samples, and by inputting the patient's personal information age, weight, height, gender, characteristics of the current image frame and continuous multi-frame images, and historical dose information, the X-ray dose parameters required for the next moment and the next exposure, tube voltage, current, and exposure time are output.

[0019] As a preferred solution of the imaging control method of the digital gastrointestinal machine of the radiology department of the present invention, the generating report includes calculating the cumulative dose according to the exposure time t and the tube current I, using the dose calculation formula:

[0020] D=k′·I·t

[0021] Where D represents the cumulative dose, k' is a coefficient related to the radiation energy and the inverse square law of distance. Real-time dose rate monitoring relies on real-time collected data, which is quickly processed by sensors and built-in dosimeters of the equipment, and prompted according to safety threshold judgment. By comparing the threshold, when the actual dose D actual Greater than or equal to the preset safety threshold D threshold , the system triggers an alarm, and uses HTML / CSS / PDF technology to customize the report style based on the prompt situation, and perform printing, PDF export and electronic report sending.

[0022] As a preferred solution of the imaging control method of the digital gastrointestinal machine in the radiology department described in the present invention, the report generation also includes a report generation module that obtains the original image data of the radiological examination and related patient information and examination parameters, reads the preliminary conclusions and observation records generated by the radiologist or technician when analyzing the image, selects and fills in the template, and the doctor selects a preset diagnostic report template according to the examination type. The template contains the standard structure and terminology of the specific examination. The doctor's oral or handwritten opinions are entered into the system using voice recognition technology or a handwriting input device, and are automatically filled in the corresponding template area. Content editing and modification are supported. The doctor further refines and modifies the report content in the system interface, including describing the characteristics, location, size, boundary conditions, and contrast enhancement characteristics of the lesions seen. Intelligent auxiliary diagnosis functions are supported, and preliminary interpretation suggestions are provided in combination with AI algorithms. The doctor reviews and confirms or adjusts, and dose information is added. The report contains radiation dose information. The system automatically obtains exposure dose and cumulative dose related data from the radiation equipment and integrates them into the report.

[0023] Another object of the present invention is to provide a radiology digital gastrointestinal imaging control system, which can solve the problem of low efficiency of current digital gastrointestinal imaging control methods by performing image optimization and personalized dose control.

[0024] As a preferred solution of the radiology digital gastrointestinal machine imaging control system described in the present invention, it includes: a data processing module, a dose control module, and a report generation module; the data processing module is used to perform data acquisition based on image acquisition and processing; the dose control module is used to perform image optimization and personalized dose control; the report generation module is used to generate a report based on the acquired images and control results.

[0025] A computer device comprises a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement a step of a method for controlling imaging of a digital gastrointestinal machine in a radiology department.

[0026] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of a method for controlling imaging of a digital gastrointestinal machine in a radiology department.

[0027] Beneficial effects of the present invention: The imaging control method of the digital gastrointestinal machine in the radiology department provided by the present invention performs fluoroscopic observation on the patient and uses the flat-panel detector FPD and IP board to capture X-ray information, converts the received X-ray energy into digital signals, forms original grayscale image data, and directly digitalizes the signal output and analog-to-digital conversion technology to achieve fast and efficient image acquisition, and provides a data basis for subsequent image processing and diagnosis. The flat-panel detector FPD directly outputs the digital signal, avoids the signal loss that may occur during the IP board conversion process, and improves the image resolution and signal-to-noise ratio. Compared with traditional film imaging, digital imaging technology can achieve lower radiation doses and reduce radiation exposure to patients and medical staff. By analyzing patient information and combining deep learning algorithms, image optimization and personalized dose control are performed to improve image quality and reduce radiation dose. The body surface area BSA formula is used to calculate the body surface area of ​​the patient according to the patient's condition. The body surface area is calculated based on the patient's weight and height, and the optimal exposure parameter setting is predicted in combination with factors such as the patient's age, to achieve personalized dose control and reduce the radiation risk to sensitive groups such as children and pregnant women. Based on the deep learning algorithm and real-time collected data, the X-ray dose parameters are predicted and adjusted in real time to ensure that the radiation dose is controlled at the lowest level while meeting the diagnostic needs. Noise filtering, high-pass filtering, non-local mean denoising and other technologies are used to effectively remove noise and artifacts in the image, improve the image clarity and readability, and automatically generate a diagnostic report based on the collected images and control results. It also supports personalized report templates, content editing and intelligent auxiliary diagnosis functions, and automatically generates a diagnostic report, which saves the doctor's time and improves the diagnostic efficiency. The automated report generation process reduces the possibility of human errors and improves the reliability of the report. The present invention achieves better results in terms of efficiency, stability and reliability. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0029] Figure 1 This is an overall flow chart of a radiology digital gastrointestinal imaging control method provided by the first embodiment of the present invention.

[0030] Figure 2This is an overall flow chart of a radiology digital gastrointestinal imaging control system provided in the third embodiment of the present invention. DETAILED DESCRIPTION

[0031] In order to make the above-mentioned purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in the art without creative work should fall within the scope of protection of the present invention.

[0032] Example 1, reference Figure 1 , as an embodiment of the present invention, provides a radiology digital gastrointestinal imaging control method, comprising:

[0033] S1: Data collection based on image acquisition and processing.

[0034] Furthermore, image acquisition and processing include receiving the original signal from the detector, converting the original signal into a digital image and processing it; the patient takes a barium meal contrast agent, performs fluoroscopic observation, and the gastrointestinal machine starts the X-ray source exposure, and the X-ray information after passing through the gastrointestinal tissue is captured by the flat-panel detector FPD and the IP board imaging board. The detector converts the received X-ray energy into an electrical signal, and the flat-panel detector directly outputs a digital signal, which is converted into original grayscale image data through analog-to-digital conversion.

[0035] It should be noted that image acquisition and processing also include noise filtering, gain correction, dark current compensation, and bad pixel repair based on the generated image; the contrast-to-noise ratio CNR of the image processing algorithm is used to analyze the image quality acquired in real time. The contrast-to-noise ratio CNR is expressed as:

[0036]

[0037] Among them, k1 and k2 are the average grayscale values ​​of the region of interest, and are the standard deviations respectively. Based on the AEC system combined with the feedback signal of the detector, the X-ray tube voltage, current mA and exposure time s are adjusted. The ideal exposure E is expressed as:

[0038] E=k(mA·s)

[0039] Here, k is a coefficient related to the X-ray source characteristics and the detector sensitivity.

[0040] It should also be noted that, through the image acquisition and processing steps, the system receives the original signal from the detector and converts it into a digital image, and generates high-quality grayscale image data after analog-to-digital conversion. The main function of this step is to capture the X-ray information in the patient's gastrointestinal tissue and ensure the effective conversion from the original signal to the digital image. The beneficial effect of this step is reflected in the use of digital signal processing technology, such as noise filtering, gain correction, dark current compensation and bad pixel repair, etc., to improve the clarity and accuracy of the image, especially in low-contrast environments, to ensure that doctors can accurately diagnose lesions through high-quality images. In this process, real-time analysis of the contrast-to-noise ratio (CNR) is also performed to achieve dynamic monitoring of image quality, ensuring that the acquired images are clear enough to meet clinical needs.

[0041] S2: Perform image optimization and personalized dose control.

[0042] Furthermore, image optimization includes entering detailed patient information into the patient information system, performing calculations based on the entered data according to a pre-set clinical decision support system or dose calculation software, and calculating radiation dose and contrast agent dosage based on body weight and body surface area for X-ray fluoroscopy and contrast agent use. The optimal exposure parameter settings are predicted based on the patient's age, weight, body shape, and medical history information, combined with historical data in the database. For patients of different body shapes, the dose is adjusted using body surface area BSA, expressed as:

[0043] BSA=0.007184×W 0.425 ×H 0.725

[0044] Where W is weight in kg, and H is height in cm. The gastrointestinal tract region and organ contour are segmented from the image using the threshold segmentation edge detection algorithm, and feature extraction is performed. The geometric features are extracted to obtain the contour shape parameters of the gastrointestinal tract, such as area, perimeter, principal axis length, and angle change geometric features. The texture characteristics inside the tissue are analyzed using the gray-level co-occurrence matrix (GLCM) method. Based on pixel intensity information, the CT value or X-ray absorption rate of different tissue regions is quantified to reflect the difference in tissue density. The edge information of the anatomical structure is highlighted based on a high-pass filter, and the organ contour and lesion details are identified. At the same time, artifacts are removed. The non-local mean denoising technology and motion blur algorithm are used to eliminate noise and artifacts in the image. Image reconstruction is performed in CT and MRI scans. Filtered back projection is applied to generate tomographic images in spiral CT scans to adjust image quality.

[0045] It should be noted that personalized dose control includes designing a deep neural network model through the X-ray dose control module based on the deep learning algorithm, selecting the recurrent neural network RNN ​​to adapt to real-time dynamic optimization according to the actual situation combined with the reinforcement learning framework DQN, and the model structure includes different convolutional layers, pooling layers, and fully connected layers for feature extraction and decision generation. By defining the loss function based on supervised learning, the MSE mean square error is used as the objective function to represent the gap between the predicted dose and the actual optimal dose, and the prediction model Loss is established, which is expressed as:

[0046]

[0047] in, Represents the dose value predicted by the model, optimal dose is the corresponding optimal dose reference value, N represents the number of samples, and by inputting the patient's personal information age, weight, height, gender, characteristics of the current image frame and continuous multi-frame images, and historical dose information, the X-ray dose parameters required for the next moment and the next exposure, tube voltage, current, and exposure time are output.

[0048] It should also be noted that in the image optimization and personalized dose control steps, the system makes personalized adjustments to the X-ray exposure based on the patient's detailed information. Specifically, the system calculates the optimal radiation dose through the body surface area (BSA) model based on the patient's weight, body shape, age and other information, combined with historical data in the database, to ensure that the X-ray dose meets the patient's individual characteristics. The system also applies a threshold segmentation algorithm to segment the gastrointestinal area in the image, extract geometric features, and analyze the texture characteristics of the tissue. These features can more accurately identify the lesion area.

[0049] S3: Generate a report based on the acquired images and control results.

[0050] Furthermore, the generated report includes cumulative dose calculation based on exposure time t and tube current I, using the dose calculation formula:

[0051] D=k′·I·t

[0052] Where D represents the cumulative dose, k′ is a coefficient related to the radiation energy and the inverse square law of distance. Real-time dose rate monitoring relies on real-time collected data, which is quickly processed by sensors and built-in dosimeters of the equipment, and prompted according to safety threshold judgment. By comparing the threshold, when the actual dose D actual Greater than or equal to the preset safety threshold D threshold , the system triggers an alarm, and uses HTML / CSS / PDF technology to customize the report style based on the prompt situation, and perform printing, PDF export and electronic report sending.

[0053] It should be noted that report generation also includes a report generation module that obtains the original image data of the radiological examination and related patient information and examination parameters, reads the preliminary conclusions and observation records generated by the radiologist or technician when analyzing the image, and selects and fills in the template. The doctor selects the preset diagnostic report template according to the examination type. The template contains the standard structure and terminology of the specific examination. The doctor's oral or handwritten opinions are entered into the system using voice recognition technology or handwriting input equipment, and automatically filled in the corresponding template area. Content editing and modification are supported. The doctor further refines and modifies the report content in the system interface, including describing the characteristics, location, size, boundary conditions, and contrast enhancement characteristics of the lesions seen. It supports intelligent auxiliary diagnosis functions and provides preliminary interpretation suggestions in combination with AI algorithms. The doctor reviews and confirms or adjusts them, and dose information is added. The report contains radiation dose information. The system automatically obtains exposure dose and cumulative dose related data from the radiation equipment and integrates them into the report.

[0054] It should also be noted that in the report generation step, the system calculates the cumulative dose based on the exposure time and tube current to ensure that the patient's radiation dose record is clear and accurate. At the same time, the system automatically generates a detailed examination report based on the collected image data and the results of personalized dose control. The report includes information such as the radiologist's diagnosis, image analysis results, and the radiation dose received by the patient. In addition, the system also supports the use of HTML, PDF and other formats to generate reports, simplifying the report generation and delivery process.

[0055] Example 2 is an embodiment of the present invention, which provides a radiology digital gastrointestinal imaging control method. In order to verify the beneficial effects of the present invention, scientific demonstration is carried out through economic benefit calculation and simulation experiments.

[0056] First, after the patient takes the barium meal contrast agent, the gastrointestinal machine is used to start the X-ray source, and the gastrointestinal tract is observed by fluoroscopy. The X-ray information after passing through the gastrointestinal tissue is captured by the flat-panel detector (FPD). The FPD directly outputs digital signals, which are converted into original grayscale image data after analog-to-digital conversion. The collected images are processed, including noise filtering, gain correction, dark current compensation and bad pixel repair, and the contrast-to-noise ratio (CNR) is used to analyze the image quality to ensure that the clarity meets the diagnostic requirements. Next, in the personalized dose control part, the system enters the patient's age, height, weight and other information, combines deep learning algorithms and historical data, and adjusts the voltage, current and exposure time of the X-ray tube in real time. The system uses a convolutional neural network (CNN) and loop-based The reinforcement learning algorithm of the RNN predicts and optimizes the radiation dose in real time to ensure that the X-ray dose received by the patient is minimized while ensuring image quality. The system further optimizes the setting of exposure parameters by calculating the BSA (body surface area) and using the MSE mean square error model to evaluate the deviation between the predicted dose and the optimal dose. Finally, the system generates a report based on the time and tube current of each exposure, records the cumulative dose, and automatically generates a diagnostic report based on the patient's examination images and the radiologist's analysis conclusions. The report contains detailed image quality analysis results, radiation dose records, and the doctor's diagnostic opinions. The report generation module supports custom template selection and intelligent auxiliary diagnosis functions to help doctors quickly complete the preparation and revision of reports.

[0057] Example 3, reference Figure 2 , as an embodiment of the present invention, provides a radiology digital gastrointestinal imaging control system, including a data processing module, a dose control module, and a report generation module.

[0058] The data processing module is used to collect data based on image acquisition and processing; the dose control module is used to perform image optimization and personalized dose control; and the report generation module is used to generate reports based on the collected images and control results.

[0059] If the function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the methods of each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc. Various media that can store program codes.

[0060] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in conjunction with such instruction execution systems, devices or apparatuses. For the purposes of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in conjunction with such instruction execution systems, devices or apparatuses.

[0061] More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk case (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be a paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering, or processing in another suitable manner as necessary, and then stored in a computer memory.

[0062] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc. It should be noted that the above embodiments are only used to illustrate the technical solution of the present invention and are not limited. Although the present invention is described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that the technical solution of the present invention can be modified or replaced by equivalents without departing from the spirit and scope of the technical solution of the present invention, which should be included in the scope of the claims of the present invention.

[0063] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A radiology digital gastrointestinal imaging control method, characterized in that: include: Data collection based on image acquisition and processing; Perform image optimization and personalized dose control; Generate reports based on acquired images and control results.

2. The imaging control method of a digital gastrointestinal machine in the radiology department as claimed in claim 1, characterized in that: The image acquisition and processing includes receiving the original signal of the detector, converting the original signal into a digital image and processing it; The patient takes a barium meal contrast agent and performs fluoroscopic observation. The gastrointestinal machine starts the X-ray source exposure, and the X-ray information after passing through the gastrointestinal tissue is captured by the flat-panel detector FPD and the IP board imaging board. The detector converts the received X-ray energy into electrical signals, and the flat-panel detector directly outputs digital signals. The digital signals are converted into original grayscale image data through analog-to-digital conversion.

3. The imaging control method of a digital gastrointestinal machine in the radiology department as claimed in claim 2, characterized in that: The image acquisition and processing also includes performing noise filtering, gain correction, dark current compensation, and bad pixel repair based on the generated image; The image quality acquired in real time is analyzed using the contrast-to-noise ratio (CNR) of the image processing algorithm. The contrast-to-noise ratio (CNR) is expressed as: Among them, μ1 and μ2 are the average grayscale values ​​of the region of interest, and are the standard deviations respectively. Based on the AEC system combined with the feedback signal of the detector, the X-ray tube voltage, current mA and exposure time s are adjusted. The ideal exposure E is expressed as: E=k(mA·s) Here, k is a coefficient related to the X-ray source characteristics and the detector sensitivity.

4. The imaging control method of a digital gastrointestinal machine in the radiology department as claimed in claim 3, characterized in that: The image optimization includes entering detailed information of the patient into the patient information system, performing calculations using the entered data according to a pre-set clinical decision support system or dose calculation software, calculating radiation dose and contrast agent dosage according to body weight and body surface area for X-ray fluoroscopy and contrast agent use, predicting optimal exposure parameter settings according to the patient's age, weight, body shape, and medical history information in combination with historical data in a database, and adjusting the dose for patients of different body shapes using body surface area BSA, expressed as: BSA=0.007184×W 0.425 ×H 0.725 Where W is weight in kg, H is height in cm; The threshold segmentation edge detection algorithm is used to segment the gastrointestinal tract area and organ contours from the image, and feature extraction is performed. The geometric features are extracted to obtain the contour shape parameters of the gastrointestinal tract, such as area, perimeter, main axis length, and angle change geometric features. The texture characteristics inside the tissue are analyzed by the gray-level co-occurrence matrix (GLCM) method. Based on the pixel intensity information, the CT value or X-ray absorption rate of different tissue areas is quantified to reflect the difference in tissue density. Based on the high-pass filter, the edge information of the anatomical structure is highlighted, the outline of the organ and the details of the lesion are identified, and artifacts are removed at the same time. The non-local mean denoising technology and motion blur algorithm are used to eliminate noise and artifacts in the image. Image reconstruction is performed in CT and MRI scans, and filtered back projection is applied in spiral CT scans to generate tomographic images and adjust image quality.

5. The imaging control method of a digital gastrointestinal machine in the radiology department as claimed in claim 4, characterized in that: The personalized dose control includes designing a deep neural network model through an X-ray dose control module based on a deep learning algorithm, selecting a recurrent neural network RNN ​​to adapt to real-time dynamic optimization in combination with a reinforcement learning framework DQN according to actual conditions, and the model structure includes different convolutional layers, pooling layers, and fully connected layers for feature extraction and decision generation. By defining a loss function based on supervised learning, the MSE mean square error is used as the objective function to represent the gap between the predicted dose and the actual optimal dose, and a prediction model Loss is established, which is expressed as: in, Represents the dose value predicted by the model, optimal dose is the corresponding optimal dose reference value, N represents the number of samples, and by inputting the patient's personal information age, weight, height, gender, characteristics of the current image frame and continuous multi-frame images, and historical dose information, the X-ray dose parameters required for the next moment and the next exposure, tube voltage, current, and exposure time are output.

6. The imaging control method of a digital gastrointestinal machine in the radiology department as claimed in claim 5, characterized in that: The report generation includes calculating the cumulative dose based on the exposure time t and the tube current I, using the dose calculation formula: D=k'·I·t Where D represents the cumulative dose, k′ is a coefficient related to the radiation energy and the inverse square law of distance. Real-time dose rate monitoring relies on real-time collected data, which is quickly processed by sensors and built-in dosimeters of the equipment, and prompted according to safety threshold judgment. By comparing the threshold, when the actual dose D actual Greater than or equal to the preset safety threshold D threshold , the system triggers an alarm, and uses HTML / CSS / PDF technology to customize the report style based on the prompt situation, and perform printing, PDF export and electronic report sending.

7. The imaging control method of a digital gastrointestinal machine in the radiology department as claimed in claim 6, characterized in that: The report generation also includes a report generation module that obtains the original image data of the radiological examination and related patient information and examination parameters, reads the preliminary conclusions and observation records generated by the radiologist or technician when analyzing the image, and selects and fills in the template. The doctor selects a preset diagnostic report template according to the examination type. The template contains the standard structure and terminology of the specific examination. The doctor's oral or handwritten opinions are entered into the system using voice recognition technology or handwriting input equipment, and automatically filled in the corresponding template area. Content editing and modification are supported. The doctor further refines and modifies the report content in the system interface, including describing the characteristics, location, size, boundary conditions, and contrast enhancement characteristics of the lesions seen. Intelligent auxiliary diagnosis functions are supported, and preliminary interpretation suggestions are provided in combination with AI algorithms. The doctor reviews and confirms or adjusts them, and dose information is added. The report contains radiation dose information. The system automatically obtains exposure dose and cumulative dose related data from the radiation equipment and integrates them into the report.

8. A system using the imaging control method of a digital gastrointestinal machine in a radiology department as claimed in any one of claims 1 to 7, characterized in that: It includes data processing module, dosage control module and report generation module; The data processing module is used to collect data based on image acquisition and processing; The dose control module is used for image optimization and personalized dose control; The report generation module is used to generate a report based on the collected images and control results.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the imaging control method of a digital gastrointestinal machine of the radiology department according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the imaging control method of a digital gastrointestinal machine of the radiology department according to any one of claims 1 to 7 are implemented.

Images