Model body testing method and device for oral cavity CBCT (cone beam computed tomography) device performance

Abstract

The invention provides an oral cavity CBCT equipment performance motif test method and equipment, and the method comprises the steps: scanning an oral cavity motif main body to obtain scanning data of a target region after determining to start an automatic scanning function, converting the scanning data into a digital image, and inputting the processed image into a preset deep learning model, obtaining an image quality evaluation result, comparing the evaluated index values with standard index values of corresponding dimensions, determining index items to be improved, and adjusting corresponding equipment parameters to be adjusted according to the difference between the index items to be improved and the standard index values from large to small. And after all the to-be-adjusted parameters of the equipment are adjusted to the maximum allowable frequency or all the evaluated index values reach the standard, obtaining a final image quality evaluation result again, and determining a performance result of the oral cavity CBCT equipment. By means of the method, intelligent and efficient testing of the performance of the oral cavity CBCT equipment can be achieved, and standardized and objective performance testing can also be achieved.

Description

Technical Field

[0001] The present application relates to the medical field, and in particular to a phantom testing method and device for oral CBCT equipment performance. Background Art

[0002] Oral CBCT (Cone Beam Computed Tomography) technology is widely used in the field of oral medicine, such as oral implants, orthodontics, oral and maxillofacial surgery, etc. As a medical device, the performance of oral CBCT equipment is directly related to the accuracy of the examination results and the effect of clinical diagnosis. With the improvement of people's awareness of oral health, the requirements and attention for the performance testing of oral CBCT equipment are getting higher and higher.

[0003] The traditional oral CBCT equipment performance test process is as follows: the relevant personnel select the appropriate oral CBCT equipment performance phantom according to the test purpose and equipment characteristics, and then select the appropriate scanning parameters to enable the oral CBCT equipment to scan the performance phantom according to the characteristics of the phantom and the test requirements after starting the oral CBCT equipment. After the scan is completed, the relevant personnel convert the scan results into an observable image form through the set channel. By observing the image, the performance test results of the oral CBCT equipment, such as artifacts, resolution, etc., can be clearly seen. For the accuracy of the test, the relevant personnel can re-test some unsatisfactory performance based on the previous test. For example, if the resolution is very unsatisfactory in the previous image, the calibration-related components of the equipment can be adjusted to reduce the test error. After the adjustment, the performance phantom is scanned again to obtain another test image. By analogy, if you want to obtain the true and optimal performance test results of the device, you need to repeatedly adjust the corresponding components many times, and only through multiple tests can you get the optimal test results of the oral CBCT equipment.

[0004] However, the performance testing method of traditional oral CBCT equipment usually relies on manual adjustment of relevant components of the equipment to conduct multiple tests. The final judgment of what is the optimal test result also relies on experience. There are problems such as inconsistent standards. It is inefficient and relies on experience, making it difficult to conduct performance testing efficiently and intelligently. Summary of the invention

[0005] The present application provides a phantom testing method and device for oral CBCT equipment performance, which is used to realize intelligent and efficient testing of oral CBCT equipment performance, which not only improves the testing efficiency, but also can realize standardized and objective performance testing.

[0006] In a first aspect, the present application provides a phantom testing method for the performance of an oral CBCT device, which is applied to an oral CBCT device. The method comprises: after determining to turn on the automatic scanning function, scanning the main body of the oral phantom to obtain scanning data of the target area, the main body of the oral phantom having a plurality of mounting holes for replaceable test components, for fixing a plurality of performance test phantoms; after converting the scanning data into a digital image, preprocessing the digital image to obtain a processed image, wherein the preprocessing includes reducing metal artifacts; inputting the processed image into a preset deep learning model, automatically evaluating the image quality, and obtaining an image quality evaluation result, wherein the deep learning model is composed of an evaluated The image quality assessment result includes the assessed index values ​​of multiple index dimensions; the assessed index values ​​are compared with the standard index values ​​of the corresponding dimensions to determine the index items to be improved that do not meet the standards; the corresponding equipment parameters to be adjusted are automatically adjusted in order from large to small according to the gap between the index items to be improved and the standard index values, and the scanning and image quality assessment are performed again; after all the parameters to be adjusted of the equipment are adjusted to the maximum allowed number of times or all the assessed index values ​​meet the standards, the automatic scanning function is started again to obtain the final image quality assessment result; the performance result of the oral CBCT equipment is determined according to the final image quality assessment result.

[0007] In the above technical scheme, the deep learning-based image quality assessment and intelligent closed-loop optimization adjustment of equipment parameters in the embodiment of the present application are adopted. By automatically evaluating image quality and adjusting equipment parameters, intelligent and efficient testing of the performance of oral CBCT equipment is achieved, which not only improves the test efficiency, but also realizes standardized and objective evaluation.

[0008] In combination with some technical solutions of the first aspect, in some technical solutions, the oral phantom body includes a low-contrast test module, which includes a plurality of lesion phantoms of different sizes and shapes, and the lesion phantoms are used to simulate different lesion types. After determining to turn on the automatic scanning function, the oral phantom body is scanned to obtain the scanning data of the target area, specifically including: obtaining a scanned image of the low-contrast test module; identifying the lesion phantom area and the background tissue area in the scanned image; after obtaining the lesion average CT value of the lesion phantom area and the background average CT value of the background tissue area, calculating the CT value difference between the lesion phantom area and the background tissue area; and determining the contrast of the area according to the CT value difference.

[0009] In the above technical solution, a digital scan image containing a lesion model can be obtained, and the lesion and background areas can be accurately extracted using image processing technology. The difference in CT values ​​between the lesion and the background is calculated, and the lesion contrast is determined based on the difference, so that the contrast reproduction performance of the device can be quantitatively evaluated. Compared with traditional empirical judgment, this technology realizes the standardization of contrast detection capabilities and improves judgment accuracy. The entire process is automatically completed by the algorithm, eliminating manual intervention and greatly improving test efficiency.

[0010] In combination with some technical solutions of the first aspect, in some technical solutions, the oral phantom body also includes a high-contrast resolution test module, which includes at least multiple line pairs of transverse sections, coronal planes and sagittal planes, and the line pairs include multiple dynamic angles, multiple materials and multiple dynamically increasing spacing line pairs. The high-contrast resolution test module is used to judge the spatial resolution of the oral CBCT device for high-contrast objects through multiple line pairs. After determining to turn on the automatic scanning function, the oral phantom body is scanned to obtain scanning data of the target area. The step specifically includes: obtaining scanned images of the transverse sections, coronal planes and sagittal planes; identifying line pairs in the scanned images by image processing technology; classifying the line pairs according to the dynamic angles, materials and spacings of the line pairs, and marking the types to obtain marked line pairs; measuring the width of the marked line pairs and the spacing between adjacent marked line pairs; and obtaining high-contrast resolution by calculation according to the width and the spacing.

[0011] In the above technical solution, the spatial resolution of oral CBCT equipment can be evaluated from all directions and angles to obtain more accurate and reliable high-contrast object imaging quality parameters, providing strong guarantees for the precise positioning of oral diseases and the observation of fine structures.

[0012] In combination with some technical solutions of the first aspect, in some technical solutions, the oral phantom body also includes a uniformity test module, and a plurality of rotatable sensors with equal distances are arranged at the bottom of the uniformity test module to detect whether the imaging of the oral CBCT is uniform. After determining to turn on the automatic scanning function, the oral phantom body is scanned to obtain the scanning data of the target area, specifically including: scanning the uniformity test module to obtain a preliminary scan image; determining the position of each sensor by scanning the preliminary image; determining the region of interest of each sensor according to the sensor position; after counting the pixel CT values ​​in each region of interest, calculating the discrete degree of the pixel CT value; and determining the uniformity of the preliminary scan image according to the discrete degree.

[0013] In the above technical scheme, the uniformity and consistency of oral CBCT equipment imaging can be quantitatively evaluated to determine whether the image is evenly distributed, such as whether there are obvious artifacts, and quantitative indicators of oral CBCT equipment imaging stability can be obtained to provide a reliable basis for subsequent performance optimization.

[0014] In combination with some technical solutions of the first aspect, in some technical solutions, after automatically adjusting the corresponding device parameters to be adjusted in sequence from large to small according to the gap between the index item to be improved and the standard index value, and performing the steps of scanning and image quality assessment again, it also includes: establishing a mapping relationship database between the device parameters to be adjusted and the image quality assessment results; optimizing the deep learning model according to the mapping relationship database to obtain an optimized model; when it is detected that the index item to be improved has reached the maximum number of adjustments and still does not meet the standard, triggering a manual intervention mode; after adjusting the device parameters to be adjusted corresponding to the index that does not meet the standard through the manual intervention mode, adding the adjustment record to the mapping relationship database to update the optimized model.

[0015] In the above technical solution, the deep learning model can be continuously updated and optimized to form a self-learning closed loop, so that the deep learning model can continuously learn and accumulate experience, and evolve autonomously, thereby continuously improving the evaluation effect, perfecting the adjustment strategy, and gradually realizing the intelligent and automatic optimization of the performance of oral CBCT equipment.

[0016] In combination with some technical solutions of the first aspect, in some technical solutions, after automatically adjusting the corresponding equipment parameters to be adjusted in sequence from large to small according to the gap between the indicator item to be improved and the standard indicator value, and performing the scanning and image quality evaluation steps again, it also includes: establishing a performance database based on historical adjustment records; judging whether there is a downward trend in performance by performing statistical analysis and trend prediction on the data in the performance database; if there is a downward trend, judging whether the decline in the performance indicator exceeds a set threshold; if it exceeds the set threshold, generating a corresponding performance warning prompt; and sending the performance warning prompt to a set receiving end for display.

[0017] In the above technical solution, it can help relevant personnel to discover abnormal fluctuations and downward trends in equipment performance in advance, and take targeted preventive maintenance measures in time, so as to maximize the stability of equipment performance and extend the service life of the equipment.

[0018] In combination with some technical solutions of the first aspect, in some technical solutions, after comparing the evaluated indicator value with the standard indicator value of the corresponding dimension respectively to determine the indicator item to be improved that does not meet the standard, it also includes: determining the improvement order of the indicator item to be improved according to the weight coefficient of the indicator item to be improved; adjusting the device parameters corresponding to each indicator item to be improved in turn according to the improvement order; after each adjustment of the device parameters corresponding to each indicator item to be improved, re-evaluating the image quality until the indicator item to be improved meets the standard or reaches the maximum allowed number of times; if all indicator items meet the standard, the adjustment process is terminated; if there are indicators to be improved that do not meet the standard, they are marked and recorded as key indicator items; the cause of the key indicator item that still does not meet the standard after multiple adjustments is analyzed to obtain the key factors affecting the image quality evaluation; after determining targeted improvement measures based on the key factors, they are sent to the set receiving end.

[0019] In the above technical solution, we can focus on the performance shortcomings of the equipment and break through key bottlenecks, so that limited optimization resources can be used effectively. For the indicators with the most significant overall performance improvement effect, relevant personnel can also directly view the key factors on the receiving end, thereby improving the pertinence and effectiveness of oral CBCT equipment performance testing and optimization.

[0020] In a second aspect, an embodiment of the present application provides an oral CBCT device, comprising: one or more processors and a memory; the memory is coupled to the one or more processors, the memory is used to store computer program code, the computer program code includes computer instructions, and the one or more processors call the computer instructions to enable the oral CBCT device to perform the method described in the first aspect and any possible implementation manner of the first aspect.

[0021] In a third aspect, an embodiment of the present application provides a computer-readable storage medium, comprising instructions, which, when executed on an oral CBCT device, causes the oral CBCT device to perform the method described in the first aspect and any possible implementation of the first aspect.

[0022] In a fourth aspect, an embodiment of the present application provides a computer program product. When the computer program product is run on an oral CBCT device, the oral CBCT device performs the method described in the first aspect and any possible implementation manner of the first aspect.

[0023] It can be understood that the oral CBCT device provided in the second aspect, the computer-readable storage medium provided in the third aspect, and the computer program product provided in the fourth aspect are all used to execute the method provided in the embodiment of the present application. Therefore, the beneficial effects that can be achieved can refer to the beneficial effects in the corresponding method, and will not be repeated here.

[0024] One or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages: 1. Due to the adoption of deep learning-based image quality assessment and intelligent closed-loop optimization adjustment of equipment parameters, automated and intelligent testing of oral CBCT equipment performance is achieved, effectively solving the inefficiency problem of existing technologies that rely on manual experience to adjust parameters multiple times, thereby achieving standardized and objective oral CBCT equipment performance evaluation.

[0025] 2. Due to the technical solution of establishing a performance database based on historical adjustment records and conducting statistical analysis to determine performance trends, the downward trend of equipment performance can be discovered in a timely manner, effectively solving the problem that the existing technology is difficult to predict performance changes and cannot take timely measures, thereby ensuring the performance stability of oral CBCT equipment and extending the service life of the equipment.

[0026] 3. Since the technical solution of determining the improvement order according to the weight coefficient of the indicator to be improved is adopted, the most critical performance indicators affecting the quality of oral CBCT images can be optimized first, which effectively solves the problem of lack of focus in the adjustment of various indicators in the existing technology, and thus realizes the efficient concentration of limited resources on the indicators with the most significant effect on improving equipment performance. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] Figure 1 It is a flow chart of a method for testing the performance of an oral CBCT device in a phantom according to an embodiment of the present application; Figure 2 It is a schematic diagram of a scenario of a phantom testing method for oral CBCT equipment performance in an embodiment of the present application; Figure 3 It is another flow chart of a method for testing the performance of an oral CBCT device in a phantom according to an embodiment of the present application; Figure 4 This is a schematic diagram of the functional module structure of the oral CBCT device in the embodiment of the present application; Figure 5 It is a schematic diagram of the physical device structure of the oral CBCT equipment in the embodiment of the present application. DETAILED DESCRIPTION

[0028] The terms used in the following embodiments of the present application are only for the purpose of describing specific embodiments, and are not intended to be used as limitations to the present application. As used in the specification and appended claims of the present application, the singular expressions "one", "a kind of", "the", "above", "the" and "this" are intended to also include plural expressions, unless there is a clear indication to the contrary in the context. It should also be understood that the term "and / or" used in the present application refers to any or all possible combinations comprising one or more listed items.

[0029] In the following, the terms "first" and "second" are used for descriptive purposes only and are not to be understood as suggesting or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features, and in the description of the embodiments of the present application, unless otherwise specified, "plurality" means two or more.

[0030] For ease of understanding, a related application scenario is introduced below.

[0031] When the dental hospital purchased a new oral CBCT device, dentist Xiao Wang needed to perform a performance test on the device to ensure image quality. Xiao Wang selected an oral CBCT performance phantom with different test items based on the test purpose. This phantom included a line pair module for testing high contrast resolution and a low contrast module for testing low contrast detection rate. After starting the new device, Xiao Wang selected the standard scanning parameter settings based on the characteristics of the phantom and completed the scanning of the performance phantom. The acquired scanned image was output to the workstation. Xiao Wang observed the quality of the scanned image and found that the image had obvious burr artifacts and too low contrast resolution. In order to improve the test accuracy, Xiao Wang modified the scanning parameters and re-scanned the phantom. The quality of the new image improved but was still unsatisfactory. Xiao Wang adjusted the parameters and scanned it many times, relying on visual inspection to judge the quality of the image each time. After adjusting many times, he judged the performance of the device based on the optimal image quality. The entire testing process was repetitive and time-consuming. The results depended on Xiao Wang's personal experience, and it was difficult to determine the optimal parameters.

[0032] This scenario shows that the performance test of traditional oral CBCT equipment relies on multiple manual parameter adjustments and scans. The judgment criteria vary based on personal experience and cannot be completed efficiently and intelligently, making it difficult to maximize the performance test of the equipment.

[0033] By adopting the deep learning-based image quality assessment and intelligent optimization and adjustment of equipment parameters in the embodiments of the present application, intelligent and efficient testing of the performance of oral CBCT equipment is achieved through automatic evaluation of image quality and adjustment of equipment parameters, which not only improves the test efficiency but also realizes standardized and objective evaluation.

[0034] The following is a description of the process of the method provided in the embodiment of the present application. Figure 1 , Figure 1 It is a flow chart of a phantom testing method for oral CBCT equipment performance in an embodiment of the present application.

[0035] S101, after determining to start the automatic scanning function, scanning the main body of the oral phantom to obtain scanning data of the target area, the main body of the oral phantom having a plurality of installation positions of replaceable test components for fixing a plurality of performance test phantoms; The main body of the oral phantom is specially designed for the performance test of oral CBCT equipment. It has multiple installation holes for replaceable test components reserved inside and outside. Different performance test phantoms can be selected and fixed in corresponding positions according to the test requirements. For example, uniformity test phantom, noise test phantom, low contrast test phantom, etc. Each test component is used to test different performance indicators.

[0036] After the automatic scanning function is determined to be turned on, that is, after the operator selects the automatic scanning program through the console of the oral CBCT device and clicks to start, the oral CBCT device will automatically control the ray generator and the detector to perform a full-scale scan of the oral phantom body to obtain scanning data of the scanning target area, wherein the target area may be an area including the performance test phantom installed on the oral phantom body. The scanning parameters such as scanning range, scanning time, voltage, current, etc. can be determined according to a preset automatic scanning scheme.

[0037] S102, after converting the scan data into a digital image, preprocessing the digital image to obtain a processed image, wherein the preprocessing includes reducing metal artifacts; After obtaining the scan data, the oral CBCT device converts the scan data into a two-dimensional digital image, that is, processes the three-dimensional scan data into a specific two-dimensional slice image. Considering that there is a certain amount of noise and image artifacts in the original digital image, directly using the original digital image for subsequent processing is not conducive to obtaining accurate image quality analysis results. Therefore, the oral CBCT device can perform image enhancement and quality improvement, such as denoising, contrast enhancement, sharpening and other pre-processing operations.

[0038] In addition, in real life, there are metal materials such as implants in the oral and maxillofacial area. If a model containing high-density metal materials such as dental dentures and implants is used for performance testing, it will cause serious beam hardening effects and scattering. This will cause dark bands (negative artifacts) and bright bands (positive artifacts) to appear in the area around the metal, which will have a negative impact on subsequent image analysis. Therefore, a special metal artifact reduction algorithm is also required in image preprocessing to process the original digital image. For example, a metal object area mask can be generated based on an image segmentation method, and then the mask is applied inversely to the original image to filter and suppress the metal artifact area. After data conversion and preprocessing, the oral CBCT device can obtain clear and reliable digital images for subsequent automated quality assessment.

[0039] S103, inputting the processed image into a preset deep learning model to automatically evaluate the image quality and obtain an image quality evaluation result, wherein the deep learning model is trained by the evaluated digital image, and the image quality evaluation result includes evaluated indicator values ​​of multiple indicator dimensions; The oral CBCT device can be pre-integrated with a deep learning model trained by a large number of evaluated digital images. The deep learning model can input the processed digital image, automatically extract the key features of the image, and output the image quality evaluation results for multiple dimensions, such as spatial resolution, image noise, contrast, artifacts, edge clarity, etc. Each quality evaluation indicator can get a quantitative score. If an image quality evaluation is performed, the oral CBCT device will mark the evaluated indicators with the evaluated indicator value, which can more intuitively display the evaluation of each indicator and facilitate subsequent analysis and processing. For those indicators for which the deep learning model does not output the evaluation value, the corresponding indicator category item can be marked as "not evaluated". The subsequent image quality optimization can consider these indicators that have not been evaluated, or it can ignore these indicators and treat them as indicators that have little influence in image quality evaluation.

[0040] Through learning, deep learning models can map and predict high-dimensional image features, avoiding the limitations of traditional rule-based algorithms and providing a more accurate and comprehensive evaluation of factors that affect image quality. Compared with traditional algorithms, deep learning-based evaluation methods are more intelligent and automated, and can process a large number of images quickly and efficiently. In addition, as the number of evaluation samples accumulates, deep learning models can continue to generalize and optimize, improving the accuracy of evaluation.

[0041] S104, comparing the evaluated indicator value with the standard indicator value of the corresponding dimension, and determining the indicator items to be improved that have not met the standard; The oral CBCT device is equipped with theoretical standard thresholds for multiple dimensional indicators of image quality assessment. These standard thresholds can be determined in advance based on clinical diagnostic needs and equipment performance benchmarks. The oral CBCT device can automatically extract the evaluated indicator values ​​of each dimension output by the deep learning model, and compare them with the corresponding standard thresholds one by one to determine whether the evaluated indicators of each dimension meet the standard requirements. If they do not meet the standard requirements, the evaluated indicators that do not meet the requirements will be determined as indicators to be improved. These indicators to be improved may be due to improper adjustment of the device's own parameters, resulting in substandard evaluation results. Therefore, these indicators to be improved can be adjusted by adjusting the parameters of the device in the future. For example, the evaluated value of spatial resolution is 2.5lp / mm, and the standard threshold is 5lp / mm. Then the oral CBCT device can determine that the spatial resolution indicator does not meet the standard and determine it as an indicator to be improved.

[0042] S105, automatically adjusting the corresponding parameters of the device to be adjusted in order from large to small according to the difference between the indicator item to be improved and the standard indicator value, and performing scanning and image quality evaluation again; For the indicators to be improved determined in step S104, the oral CBCT device can sort them in descending order according to the gap between the current value of the indicator and the standard threshold. The larger the gap, the farther the indicator is from the standard requirement. Prioritizing adjustment can make limited adjustment resources more concentrated on the items that have a greater impact on image quality improvement, thereby completing the optimization adjustment of the overall performance in the most efficient way.

[0043] Then, the oral CBCT device can determine which device parameter adjustments correspond to improving the indicator item based on the empirical rule database and the sample data obtained by deep learning model training, and can calculate the adjustment step. For example, if the spatial resolution does not meet the standard, the X-ray tube voltage and detector acquisition parameters can be adjusted. The oral CBCT device will automatically adjust the corresponding device parameters in sequence, conduct a new round of scanning and image quality evaluation, and see whether the adjusted indicator value has improved.

[0044] As the iterative adjustment proceeds, the difference between each indicator item to be improved and the standard indicator value will gradually narrow, and the adjustment priority will change dynamically, so that the overall adjustment process focuses on the items that have the greatest impact on improving image quality.

[0045] S106: After all parameters to be adjusted of the device have been adjusted to the maximum allowed times or all evaluated index values ​​have reached the standard, the automatic scanning function is started again to obtain the final image quality evaluation result.

[0046] When all indicators to be improved have either met the standard requirements through adjustment or have reached the maximum allowable number of adjustments, the oral CBCT equipment will start the automatic scanning program again with the current last adjusted parameter settings, scan the main body of the oral model, and input the deep learning model for image quality assessment to obtain the final image quality assessment results for each indicator.

[0047] S107: Determine the oral CBCT equipment performance result according to the final image quality evaluation result.

[0048] After obtaining the final image quality assessment result, the image quality assessment result is analyzed to obtain assessment results of multiple dimensions of image quality, such as contrast resolution, artifacts, grayscale value stability, and contrast detectability. The performance of the oral CBCT device is determined based on the evaluation results of multiple dimensions, such as the contrast resolution performance and contrast detectability performance of the oral CBCT device.

[0049] A final performance evaluation report can also be generated based on the image quality evaluation results and the historical records of previous adjustments to device parameters. The report can list in detail the original value, number of adjustments, final value, judgment results, etc. of each indicator as a basis for device performance tracking and quality control.

[0050] In some embodiments, the oral CBCT device will store a complete record of each device performance test, establish a performance database based on historical adjustment records, set a reasonable time interval, such as monthly, use statistical tools to analyze the performance data in the database, and calculate the number of equipment adjustments and degree of variation corresponding to each indicator. By performing statistical analysis and trend prediction on the data in the performance database, it is determined whether there is a downward trend in performance. If there is a downward trend, it is determined whether the decline in the performance indicator exceeds the set threshold. The set threshold is the lower limit of the decline set by the relevant personnel. If it is determined that the decline in the indicator is greater than the set threshold, the oral CBCT device will actively generate performance warning information and point out the problem indicator. The generated warning information is then sent to a designated receiving terminal, such as a doctor management platform, so that technicians can view and take maintenance measures. By establishing a performance database and intelligently analyzing and judging performance trends, problems can be exposed early, and warnings can be issued at critical moments to ensure the stability of the performance of the oral CBCT device.

[0051] The above-mentioned deep learning-based image quality assessment and intelligent closed-loop optimization adjustment of equipment parameters in the embodiments of the present application realize intelligent and efficient testing of oral CBCT equipment performance by automatically evaluating image quality and adjusting equipment parameters, which not only improves the testing efficiency but also realizes standardized and objective performance testing.

[0052] In some embodiments, the oral phantom body can be loaded with multiple test phantoms to test various performances of the oral CBCT device. The following is a supplement to the scenario of this embodiment. Figure 2 , Figure 2 It is a scene schematic diagram of a phantom testing method for the performance of an oral CBCT device in an embodiment of the present application.

[0053] Figure 2 (a) shows an oral phantom main structure. The main material of the oral phantom can be a material similar to the human body, such as polymethyl methacrylate, which has the advantages of biocompatibility and X-ray absorption characteristics similar to human tissue, which is conducive to simulating real scanning scenes. The size can be similar to the size of an adult human head, which is used to simulate the scene of an oral CBCT device actually scanning the head. A plurality of standardized mounting holes are set inside the phantom body for fixing different modules, such as low-contrast modules, high-contrast modules, uniformity modules, etc., for testing different performance indicators of oral CBCT equipment. The mounting holes can be installed with the following modules: Figure 2 (b) and Figure 2 Performance test phantom shown in (c).

[0054] Figure 2 (b) shows the structure of the low contrast test module. The height of the low contrast test module can be Figure 2 The height of the oral phantom body shown in (a) is similar, and can also be designed to be slightly lower than the height of the oral phantom body for easy assembly. In the low-contrast test module, multiple circular holes of different diameters are provided, and these circular holes can be inserted into the lesion phantom. The low-contrast test module includes multiple lesion phantoms of different sizes and shapes, and the lesion phantoms are used to simulate different lesion types to comprehensively evaluate the low-contrast display performance of the device. If the operator puts the lesion phantom into the circular hole of the low-contrast test module, and then puts the low-contrast test module into the mounting hole of the oral phantom body, and then turns on the automatic scanning function, the oral CBCT device will perform a full-scale scan of the oral phantom body containing the low-contrast test module to obtain a digital scan image containing each lesion phantom. The scanned image is analyzed by image processing methods such as image segmentation, and the area corresponding to each lesion phantom in the image and the background tissue area adjacent to it are identified, wherein the background tissue area refers to the remaining background material area in the low-contrast test module except the area containing the lesion phantom. Then, the average CT value of each lesion area and the average CT value of the background tissue area are statistically calculated to evaluate the difference in X-ray absorption between the two. For each lesion area, the difference between its average CT value and the CT value of the adjacent background tissue area is calculated. The CT value difference = background average CT value - lesion average CT value. This difference reflects the contrast between the two.

[0055] Here, the contrast of the background area can be set to 1 as a benchmark. The contrast is calculated based on the CT value difference. The contrast is proportional to the CT value difference. The relationship can be expressed as: Contrast = k * CT value difference + 1, where k is an empirical constant, indicating the change in contrast per unit CT value difference. Substituting the CT value difference into the above formula, the contrast structure of the lesion area relative to the background can be solved. Based on the contrast results obtained, the contrast reproduction ability of the image can be evaluated.

[0056] Figure 2 (c) shows a structure of a high-contrast resolution test module, which is used to determine the spatial resolution of the oral CBCT device for high-contrast objects through multiple line pairs.

[0057] The high-contrast resolution test module includes at least multiple line pairs in the transverse, coronal and sagittal planes. Figure 2 The right side of (c) shows three groups of line pairs, which are line pairs composed of multiple lines of the same size and the same interval, line pairs composed of multiple lines of different sizes and different intervals, and line pairs composed of multiple lines of different sizes and the same distance. In practical applications, many other forms of line pairs can also be used to test device performance. The cross-section represents the line pairs on the slice surface, which can be designed as multiple groups of black and white line pairs with different intervals to test the device's ability to resolve details laterally. These line pairs are arranged at different angles on the slice plane, covering multi-angle resolution tests. The coronal line pairs can be designed as concentric circles, radial lines, and grid-shaped line pairs to test the vertical resolution of the device. The sagittal line pairs represent the line pairs on the sagittal plane of the anterior and posterior head, which can be designed as multiple groups of black and white line pairs with different intervals to test the resolution of the device in the anterior and posterior directions.

[0058] These line pairs can be made of materials with different contrasts to test various situations. They can also be arranged at different angles on each surface to cover all azimuths. The line pair spacing can also be gradually reduced from coarse to fine to evaluate the presentation effect at different resolutions. By setting multiple sets of line pair targets in three-dimensional space, the device's ability to resolve and present high-contrast details can be fully tested.

[0059] These line pairs can be set on a small cylinder. The operator can place the small cylinder inside the high-contrast resolution test module, and then place the high-contrast resolution test module on the mounting hole of the oral model body for testing. After turning on the automatic scanning of the device, a scanned image containing line pairs is obtained. Use image processing technology to identify each line pair in the scanned image and determine its outline. According to the angle, material and spacing parameters of each identified line pair, it is automatically classified and marked with a type to obtain a marked line pair. Measure the width of each marked line pair area, the spacing between adjacent line pairs and other geometric features, and calculate the high-contrast resolution based on the error between the line pair spacing and the corresponding measured spacing. The more accurate the spacing presentation, the higher the resolution. Combine the resolution results of all-directional line pairs to evaluate the overall resolution performance of the equipment.

[0060] In some embodiments, the oral phantom body may also include a uniformity test module, and a plurality of rotatable sensors with equal distances are arranged at the bottom of the uniformity test module to detect whether the imaging of the oral CBCT is uniform, because the fixed sensor can only measure the intensity / quality of the rays in a single direction, while the rotatable sensor can measure the ray information in different directions by changing its own angle, so as to more comprehensively evaluate the uniformity of the image quality. Similarly, the operator puts the uniformity test module into the mounting hole of the oral phantom body, and after confirming to turn on the automatic scanning function of the device, the oral phantom containing the uniformity test module is scanned in all directions, and after scanning, a two-dimensional digital preliminary scan image can be obtained.

[0061] For the obtained preliminary scanned image, the two-dimensional plane position of each sensor in the scanned image can be determined by image processing techniques such as sensor template matching to determine their precise distribution on the image. According to the precise position of each sensor determined in the previous step, the coordinates of each sensor can be used as the center point on the image to set a reasonable radius to draw the region of interest, that is, a circular local area around each sensor as the region of interest, and the size of the area can be set according to the size of the sensor. Traverse all the pixels in the region of interest corresponding to each sensor in the image, statistically calculate the CT value of each pixel, and obtain the CT value set of all pixels in each region of interest. For the CT value set of pixels in each region of interest, use statistical methods such as calculating the standard deviation and variance to quantitatively evaluate the discrete degree of the CT value in each region. The smaller the discrete degree, the more uniform the CT value of the region. The overall uniformity performance of the test equipment can be quantitatively determined by combining the discrete degree results of the CT values ​​of all sensor regions. The smaller the comprehensive value of the discrete degree, the higher the uniformity of the image can be judged. According to the uniformity results, the scanning parameters can be adjusted in a targeted manner, the scan evaluation can be re-performed, and the parameter combination with the best uniformity can be selected to test the imaging uniformity performance of the equipment.

[0062] In some embodiments, the performance of the oral CBCT device may be reduced only by some of the more important components or factors of the oral CBCT device. It is difficult to intuitively know which specific factors have a greater impact on the performance test using traditional methods. In this case, the method of the embodiments of the present application can be used to determine which are the key factors affecting the device performance test.

[0063] After combining the above scenarios, the following is a more detailed description of the process of the method provided by this implementation. Figure 3 , Figure 3 It is another flow chart of a method for testing the performance of an oral CBCT device in an embodiment of the present application.

[0064] S301, determining the improvement order of the indicator item to be improved according to the weight coefficient of the indicator item to be improved; After determining all the image quality indicators to be improved, the oral CBCT device needs to determine the order of improvement of these indicators so that limited optimization resources can be focused on the indicators that have the most significant effect on improving the overall image quality. To this end, the oral CBCT device can have a built-in indicator weight database, which gives the weight coefficients of various common image quality indicators. These coefficients are determined in advance based on the degree of influence of each indicator on the image diagnosis effect.

[0065] For example, spatial resolution is one of the most critical indicators affecting image clarity and detail, and its weight coefficient may be 0.5; while image uniformity has a smaller impact on diagnostic results, and its weight coefficient may be 0.1.

[0066] After obtaining the current values ​​of all indicators to be improved, the oral CBCT device will consult the built-in indicator weight database and sort them according to the weight coefficient of each indicator. The indicator with a larger weight coefficient will be determined as the indicator with a higher priority for improvement. In this way, optimization resources can be more concentrated on the items that have a greater impact on image quality.

[0067] S302, adjusting the device parameters corresponding to the device parameters of the indicator items to be improved in sequence according to the improvement order; After determining the order of improvement for each indicator to be improved, the oral CBCT equipment will start the iterative adjustment process for image quality optimization.

[0068] Using this improvement sequence, the oral CBCT device will first focus on the indicator with the highest improvement weight coefficient, that is, the indicator with the greatest impact on image quality. Combined with the device parameter mapping database, the device parameter combination that is most likely to improve the indicator can be determined, and then the device parameters can be adjusted. S303, after adjusting the device parameters corresponding to the indicator item to be improved each time, re-evaluate the image quality until the indicator item to be improved meets the standard or reaches the maximum allowed number of times; After each round of adjusting device parameters, the oral CBCT device can re-evaluate the image quality of the newly scanned digital images to determine whether the round of adjustment has improved the performance of the corresponding indicator items.

[0069] Specifically, the newly scanned image is input into the same deep learning model, and the updated evaluation value of the image quality index in each dimension is output. Then it is compared with the standard threshold of the index adjusted in this round to determine whether the new current value of the index meets or is close to the standard.

[0070] If the standard has been met, the next round of indicator adjustment will be entered; if the standard has not been met but is close, the current parameters can be maintained for a new round of adjustment; if the gap with the standard threshold has not changed or widened, it is necessary to re-analyze the parameter adjustment strategy until the standard is met or the preset maximum number of adjustments is reached, and then re-scan and image quality assessment can be performed.

[0071] In some embodiments, the device parameters corresponding to the indicators with heavier weights to be improved may be adjusted once, and then the device parameters corresponding to the indicators with other weights to be improved may be adjusted once. When all adjustments are completed, re-scanning and image quality evaluation are performed. This is not limited here.

[0072] In some embodiments, the oral CBCT device can record the current device parameters and the corresponding image quality assessment results during each round of parameter adjustment, and these records will be organized into a mapping relationship database. The database establishes a mapping relationship between the device parameter combination and the image quality assessment index. The oral CBCT device inputs the sample images and device parameter labels recorded in the mapping relationship database into the deep learning model for retraining. The model optimizes the network parameters by learning the impact of parameter changes on image quality to obtain an optimized model with stronger performance. If the image quality index is still not up to standard after the optimized model evaluation, the oral CBCT device will trigger the manual intervention mode, such as issuing a prompt similar to "Please adjust manually" to remind the staff to make manual adjustments. The technician's adjustment operation records and results will also be stored in the mapping relationship database to further enrich the samples and reflect manual experience. The records of the previous round of manual parameter adjustment will also be used for further optimization of the model, so that it can accumulate manual tuning experience and obtain a more accurate model.

[0073] S304. If all indicators meet the standards, the adjustment process ends; if there are indicators that do not meet the standards and need to be improved, they are marked and recorded as key indicators; After each round of adjusting the device parameters corresponding to the index items, the oral CBCT device will re-evaluate the image quality of the newly acquired scanned images. If the evaluation results show that all the indicators to be improved have reached the preset standard threshold requirements, it means that through the iterative parameter adjustment and optimization process, the key performance indicators of the oral CBCT device that affect the image quality have been effectively improved and enhanced to meet the needs of clinical use.

[0074] At this point, the oral CBCT device can end the entire parameter adjustment and optimization process, use the current parameter settings as the final configuration of the device, generate a device performance report under the final configuration, and send the performance report to the display terminal for display.

[0075] On the other hand, if there are still some indicators that need to be improved and fail to meet the standard requirements, the oral CBCT equipment will mark these indicators that do not meet the standards and record them as key indicators. These indicators may correspond to core components that affect the performance of the equipment, and their performance improvement has bottlenecks and needs to be specifically targeted.

[0076] S305, analyzing the causes of the key indicator items that still fail to meet the standards after multiple adjustments, and obtaining key factors affecting image quality assessment; For the key indicator items marked in the previous step, the oral CBCT device will initiate targeted cause analysis processing to find out the reasons why these key indicators cannot be met, that is, the key factors affecting image quality assessment.

[0077] First, the oral CBCT equipment will extract the changing trends of the evaluation values ​​of these key indicators during each round of parameter adjustment, such as whether they show a characteristic of gradual improvement but difficult to continue to improve after reaching a certain point. Then, the oral CBCT equipment will analyze the physical formation process and influencing factors of these key indicators based on information such as the working principle of the equipment in the experience knowledge base. For example, it is determined that insufficient sensitivity of the detector may be the reason why low-contrast resolution cannot be improved. Furthermore, the oral CBCT equipment can also carry out detection and diagnosis of key components, such as detecting the detector to obtain the signal-to-noise ratio, and judging whether the insufficient signal-to-noise ratio has caused an image quality bottleneck. Finally, based on the above analysis results, the oral CBCT equipment can determine the key factors that are most likely to affect the image quality evaluation of key indicators, such as detector failure, insufficient X-ray dose, etc., to provide a basis for subsequent customized optimization.

[0078] S306: After determining targeted improvement measures based on the key factors, send them to a set receiving end.

[0079] After clarifying the key factors that affect the image quality assessment of key indicators, the oral CBCT equipment will take different targeted improvement measures according to different factors. If the factor is caused by component damage, the corresponding replacement plan will be determined; if the parameter setting is improper, a better plan will be reset; if it is an algorithm defect, the algorithm process will be adjusted. The oral CBCT equipment can directly determine the optimization measures for the current analysis results based on the key factor-processing plan mapping relationship summarized in the experience knowledge base.

[0080] Then, the oral CBCT device will send the finalized improvement measures to the designated receiving end and display them on the display end for relevant technicians to view. The receiving end can be a mobile terminal, etc.

[0081] The improvement measures sent may include: analysis results of the reasons for non-compliance of key indicators, suggested solutions to key factors, a list of parts and parameters that need to be replaced or adjusted, and estimated improvement effects, etc. Based on the guidance of the improvement measures, the technicians at the receiving end take targeted optimization measures for the oral CBCT equipment to solve the key factors that affect image quality assessment, thereby effectively improving the diagnostic performance of the equipment.

[0082] The following is an introduction to an oral CBCT device in an embodiment of the present application from the perspective of a module. Figure 4 , Figure 4 It is a schematic diagram of the functional module structure of the oral CBCT device in the embodiment of the present application.

[0083] The scanning data acquisition module 401 is used to scan the main body of the oral phantom to obtain the scanning data of the target area after determining to turn on the automatic scanning function. The main body of the oral phantom has a plurality of mounting holes for replaceable test components, which are used to fix a plurality of performance test phantoms; A processed image acquisition module 402 is used to convert the scan data into a digital image, and then pre-process the digital image to obtain a processed image, wherein the pre-processing includes metal artifact reduction; An image quality assessment module 403 is used to input the processed image into a preset deep learning model to automatically assess the image quality and obtain an image quality assessment result, wherein the deep learning model is trained by the assessed digital image, and the image quality assessment result includes assessed indicator values ​​of multiple indicator dimensions; The module 404 for determining the index items to be improved is used to compare the evaluated index values ​​with the standard index values ​​of the corresponding dimensions respectively, and determine the index items to be improved that do not meet the standards; The device parameter adjustment module 405 is used to automatically adjust the corresponding device parameter to be adjusted in descending order according to the difference between the index item to be improved and the standard index value, and perform scanning and image quality evaluation again; The image quality evaluation result re-obtaining module 406 is used to restart the automatic scanning function to obtain the final image quality evaluation result after all the parameters to be adjusted of the device have been adjusted to the maximum allowed times or all the evaluated index values ​​have reached the standard; The device performance result obtaining module 407 is used to determine the oral CBCT device performance result according to the final image quality evaluation result.

[0084] In some embodiments, the scanning data acquisition module 401 specifically includes: A first scanning image acquisition unit, used for acquiring a scanning image of the low contrast test module; A multi-region acquisition unit, used for identifying the lesion model region and the background tissue region in the scanned image; a CT value difference calculation unit, configured to calculate a CT value difference between the lesion phantom region and the background tissue region after obtaining a lesion average CT value of the lesion phantom region and a background average CT value of the background tissue region; The regional contrast obtaining unit is used to determine the regional contrast according to the CT value difference and the average CT value of the lesion.

[0085] In some embodiments, the scan data acquisition module 401 further includes: A second scanning image obtaining unit is used to obtain scanning images of the transverse plane, the coronal plane and the sagittal plane; A line pair recognition unit, used for recognizing line pairs in the scanned image by using image processing technology; A marked line pair obtaining unit is used to classify the line pair according to the dynamic angle, material and spacing of the line pair, and mark the type to obtain the marked line pair; A width and spacing measurement unit, used for measuring the width of the marked line pairs and the spacing between adjacent marked line pairs; The high contrast resolution obtaining unit is used to calculate and obtain the high contrast resolution according to the width and the spacing.

[0086] In some embodiments, the scan data acquisition module 401 further includes: A scanning preliminary image obtaining unit is used to scan the uniformity test module to obtain a scanning preliminary image; a sensor position determination unit for determining each sensor position by scanning the preliminary image; An area of ​​interest determination unit, used to determine the area of ​​interest of each sensor according to the position of the sensor; A discrete degree determination unit, used for calculating the discrete degree of the pixel CT value after counting the pixel CT value in each region of interest; The uniformity determination unit is used to determine the uniformity of the scanned preliminary image according to the discrete degree.

[0087] In some embodiments, the device parameter adjustment module 405 specifically includes: A mapping relationship database establishing unit, used to establish a mapping relationship database between the parameters to be adjusted of the device and the image quality assessment result; An optimized model obtaining unit, used to optimize the deep learning model according to the mapping relationship database to obtain an optimized model; A manual intervention mode triggering unit is used to trigger the manual intervention mode when it is detected that the indicator item to be improved has reached the maximum number of adjustments and still has not reached the standard; The optimized model updating unit is used to add the adjustment record to the mapping relationship database to update the optimized model after adjusting the equipment parameters to be adjusted corresponding to the indicators that do not meet the standards through the manual intervention mode.

[0088] In some embodiments, the device parameter adjustment module 405 further includes: A performance database establishing unit, used for establishing a performance database according to historical adjustment records; A first downward trend judgment unit, used to judge whether the performance has a downward trend by performing statistical analysis and trend prediction on the data in the performance database; A second downward trend judgment unit is used to judge whether the decreasing performance index exceeds a set threshold value if there is a downward trend; A performance warning prompt generating unit, used to generate a corresponding performance warning prompt if a set threshold is exceeded; The performance warning prompt display unit is used to send the performance warning prompt to a set receiving end for display.

[0089] In some embodiments, the module 404 for determining the indicator item to be improved specifically includes: An improvement order determination unit, used to determine the improvement order of the indicator item to be improved according to the weight coefficient of the indicator item to be improved; An index item adjustment unit to be improved, used to adjust the device parameters corresponding to each index item to be improved in sequence according to the improvement sequence; An image quality re-evaluation unit, configured to re-evaluate the image quality after adjusting the device parameters corresponding to each improvement index item each time, until the index item to be improved meets the standard or reaches the maximum allowed number of times; The key indicator item obtaining unit is used to end the adjustment process if all indicator items meet the standards; if there are indicator items to be improved that do not meet the standards, mark them and record them as key indicator items; A cause analysis unit is used to analyze the cause of the key indicator item that still fails to meet the standard after multiple adjustments, and obtain the key factors affecting the image quality assessment; The improvement measure determination unit is used to determine the targeted improvement measures according to the key factors and send them to a set receiving end.

[0090] The above describes an oral CBCT device in the embodiment of the present application from the perspective of modular functional entities. The following describes an oral CBCT device in the embodiment of the present application from the perspective of hardware processing. Figure 5 , Figure 5 It is a schematic diagram of the physical device structure of the oral CBCT equipment in the embodiment of the present application.

[0091] The oral CBCT device 500 includes: one or more processors 501 ( Figure 5 Taking a processor 501 as an example), a memory 502, an input device 503 and an output device 504. In some embodiments of the present invention, the processor 501, the memory 502, the input device 503 and the output device 504 may be connected via a bus or other means, wherein: Figure 5 The example of connecting through bus is taken in the following.

[0092] The processor 501 calls the computer instruction so that the computer program is executed by the processor to implement a phantom testing method for the performance of an oral CBCT device in an embodiment of the present application.

[0093] The memory 502 is used to store computer program codes, where the computer program codes include computer instructions.

[0094] The input device 503 is used to scan the oral phantom body.

[0095] The output device 504 is used to output the performance test results of the device.

[0096] As described above, the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present application.

[0097] As used in the above embodiments, the term "when..." may be interpreted to mean "if..." or "after..." or "in response to determining..." or "in response to detecting...", depending on the context. Similarly, the phrases "upon determining..." or "if (the stated condition or event) is detected" may be interpreted to mean "if determining..." or "in response to determining..." or "upon detecting (the stated condition or event)" or "in response to detecting (the stated condition or event)", depending on the context.

[0098] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions may be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions may be transmitted from a website site, computer, server or data center to another website site, computer, server or data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line) or wireless (e.g., infrared, wireless, microwave, etc.) mode. The computer-readable storage medium may be any available medium that a computer can access or a data storage device such as a server or data center that includes one or more available media integrated. The available medium may be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid-state hard disk), etc.

[0099] Those skilled in the art can understand that to implement all or part of the processes in the above-mentioned embodiments, the processes can be completed by computer programs to instruct related hardware, and the programs can be stored in computer-readable storage media. When the programs are executed, they can include the processes of the above-mentioned method embodiments. The aforementioned storage media include: ROM or random access memory RAM, magnetic disk or optical disk and other media that can store program codes.

Claims

1. A phantom test method for oral CBCT equipment performance, applied to oral CBCT equipment, characterized in that: The method comprises: After determining to start the automatic scanning function, scanning the main body of the oral phantom to obtain scanning data of the target area, wherein the main body of the oral phantom has a plurality of mounting holes for replaceable test components, which are used to fix a plurality of performance test phantoms; After converting the scan data into a digital image, preprocessing the digital image to obtain a processed image, wherein the preprocessing includes reducing metal artifacts; Inputting the processed image into a preset deep learning model to automatically evaluate the image quality and obtain an image quality evaluation result, wherein the deep learning model is trained by the evaluated digital image, and the image quality evaluation result includes evaluated indicator values ​​of multiple indicator dimensions; Compare the evaluated indicator values ​​with the standard indicator values ​​of the corresponding dimensions to determine the indicator items that do not meet the standards and need to be improved; According to the difference between the index item to be improved and the standard index value, the corresponding parameters to be adjusted of the equipment are automatically adjusted in order from large to small, and scanning and image quality evaluation are performed again; After all the parameters to be adjusted of the device have been adjusted to the maximum allowed number of times or all the evaluated index values ​​have reached the standard, the automatic scanning function is started again to obtain the final image quality evaluation result; The oral CBCT equipment performance result is determined based on the final image quality evaluation result.

2. The method according to claim 1, characterized in that The oral phantom body includes a low-contrast test module, which includes a plurality of lesion phantoms of different sizes and shapes, and the lesion phantoms are used to simulate different lesion types. After determining to turn on the automatic scanning function, the oral phantom body is scanned to obtain scanning data of the target area, specifically including: Acquire a scanned image of the low-contrast test module; Identifying the lesion phantom region and the background tissue region in the scanned image; After obtaining the lesion average CT value of the lesion phantom area and the background average CT value of the background tissue area, calculating the CT value difference between the lesion phantom area and the background tissue area; The regional contrast is determined according to the CT value difference and the average CT value of the lesion.

3. The method according to claim 1, characterized in that: The oral phantom body further includes a high contrast resolution test module, which includes at least a plurality of line pairs of a transverse plane, a coronal plane, and a sagittal plane, wherein the line pairs include a plurality of dynamic angles, a plurality of materials, and a plurality of line pairs of dynamically increasing spacings, and the high contrast resolution test module is used to determine the spatial resolution of the oral CBCT device for high contrast objects through the plurality of line pairs. After determining to start the automatic scanning function, the oral phantom body is scanned to obtain the scanning data of the target area, specifically including: Acquire scanning images of the transverse plane, the coronal plane and the sagittal plane; identifying line pairs in the scanned image by image processing technology; Classifying the line pairs according to their dynamic angles, materials and spacings, and marking them by type to obtain marked line pairs; measuring the width of the marked line pairs and the spacing between adjacent marked line pairs; A high contrast resolution is obtained by calculation based on the width and the spacing.

4. The method according to claim 1, characterized in that: The oral phantom body also includes a uniformity testing module. A plurality of rotatable sensors with equal distances are arranged at the bottom of the uniformity testing module to detect whether the oral CBCT imaging is uniform. After determining to turn on the automatic scanning function, the oral phantom body is scanned to obtain the scanning data of the target area, specifically including: Scanning the uniformity test module to obtain a preliminary scan image; Determine each sensor location by scanning the preliminary image; determining a region of interest for each sensor based on the sensor position; After counting the CT values ​​of the pixels in each of the regions of interest, calculating the degree of dispersion of the CT values ​​of the pixels; The uniformity of the scanned preliminary image is determined according to the discrete degree.

5. The method according to claim 1, characterized in that After the steps of automatically adjusting the corresponding parameters of the device to be adjusted in descending order according to the gap between the index item to be improved and the standard index value, and performing scanning and image quality assessment again, the method further includes: Establishing a mapping relationship database between the parameters to be adjusted of the device and the image quality assessment results; Optimize the deep learning model according to the mapping relationship database to obtain an optimized model; If it is detected that the indicator item to be improved has reached the maximum number of adjustments and still has not reached the standard, a manual intervention mode is triggered; After the equipment parameters to be adjusted corresponding to the indicators that do not meet the standards are adjusted through the manual intervention mode, the adjustment record is added to the mapping relationship database to update the optimized model.

6. The method according to claim 1, characterized in that After the steps of automatically adjusting the corresponding parameters of the device to be adjusted in descending order according to the gap between the index item to be improved and the standard index value, and performing scanning and image quality assessment again, the method further includes: Establish a performance database based on historical adjustment records; By conducting statistical analysis and trend prediction on the data in the performance database, determine whether there is a downward trend in performance; If there is a downward trend, determine whether the decline in the performance indicator exceeds the set threshold; If the set threshold is exceeded, a corresponding performance warning prompt will be generated; The performance warning prompt is sent to a set receiving end for display.

7. The method according to claim 1, characterized in that After comparing the evaluated indicator values ​​with the standard indicator values ​​of the corresponding dimensions to determine the indicator items to be improved that do not meet the standards, the method further includes: Determining the improvement order of the indicator items to be improved according to the weight coefficients of the indicator items to be improved; According to the improvement order, the equipment parameters corresponding to the indicators to be improved are adjusted in sequence; After adjusting the device parameters corresponding to each of the improvement index items each time, re-evaluating the image quality until the index item to be improved meets the standard or reaches the maximum allowed number of times; If all indicators meet the standards, the adjustment process ends; if there are indicators to be improved that do not meet the standards, they are marked and recorded as key indicators; Analyze the causes of the key indicators that still fail to meet the standards after multiple adjustments to obtain key factors affecting image quality assessment; After the targeted improvement measures are determined according to the key factors, they are sent to a set receiving end.

8. An oral CBCT device, characterized in that: The oral CBCT device comprises: one or more processors and a memory; the memory is coupled to the one or more processors, the memory is used to store computer program code, the computer program code comprises computer instructions, and the one or more processors call the computer instructions to enable the oral CBCT device to perform the method as described in any one of claims 1 to 7.

9. A computer-readable storage medium comprising instructions, characterized in that: When the instructions are executed on an oral CBCT device, the oral CBCT device is caused to perform the method according to any one of claims 1 to 7.

10. A computer program product, characterized in that When the computer program product is run on an oral CBCT device, the oral CBCT device is enabled to perform the method according to any one of claims 1 to 7.

Images