Method, apparatus, device, storage medium and program product for determining medical image

Abstract

The application relates to a medical image determination method, device, equipment, storage medium and program product. The method comprises the following steps: acquiring a first medical image collected at a historical time of a detection object and an initial medical image collected at a current time; performing quality quantization processing on the first medical image and the initial medical image to determine a first quantization result corresponding to the first medical image and an initial quantization result corresponding to the initial medical image; if the first quantization result and the initial quantization result are inconsistent, continuing to perform scanning on the detection object to obtain a second medical image, and a second quantization result corresponding to the second medical image is greater than or equal to the first quantization result. The method can ensure the accuracy of an image analysis result obtained through multiple medical images.

Description

Technical Field

[0001] This application relates to the field of computer technology, and in particular to a method, apparatus, device, storage medium, and program product for determining medical images. Background Technology

[0002] Due to clinical needs such as preventive healthcare, chronic disease management, or radiotherapy evaluation, patients often need to undergo multiple imaging re-examinations regularly or as needed in order to accurately assess changes in the patient's body and the progression of the disease.

[0003] Currently, when conducting follow-up examinations on patients, images are typically taken of the areas requiring follow-up when the patient comes to the hospital for examination. This provides images of the areas being examined, while the doctor can also obtain images of the areas taken during the previous follow-up examination. The two sets of images can then be compared and analyzed to obtain the image analysis results.

[0004] However, the aforementioned techniques cannot guarantee the accuracy of the final image analysis results. Summary of the Invention

[0005] Therefore, it is necessary to provide a method, apparatus, device, storage medium, and program product for determining medical images that can ensure the accuracy of image analysis results obtained from multiple different medical images, in order to address the aforementioned technical problems.

[0006] In a first aspect, this application provides a method for determining a medical image, the method comprising:

[0007] Acquire the first medical image of the detected object acquired at a historical moment and the initial medical image acquired at the current moment;

[0008] The first medical image and the initial medical image are subjected to quality quantization processing to determine the first quantization result corresponding to the first medical image and the initial quantization result corresponding to the initial medical image.

[0009] If the first quantization result is inconsistent with the initial quantization result, the object to be detected will continue to be scanned to obtain a second medical image; the second quantization result corresponding to the second medical image is consistent with the first quantization result.

[0010] In one embodiment, the above-described quality quantization processing of the first medical image to determine the first quantization result corresponding to the first medical image includes:

[0011] Acquire a preset quality quantification method on the target device; the target device is a device for acquiring a second medical image, and the preset quality quantification method includes at least one quantification method.

[0012] The first medical image is processed using the aforementioned preset quality quantization method to determine the first quantization result corresponding to the first medical image.

[0013] In one embodiment, the aforementioned preset quality quantification method includes at least one of the following quantification methods:

[0014] Quantization methods for image contrast;

[0015] Quantification methods for image artifacts and artifact types;

[0016] Quantization methods for image signal-to-noise ratio;

[0017] Quantization methods for image uniformity.

[0018] In one embodiment, the above-described scanning of the object to obtain a second medical image includes:

[0019] Based on the comparison results of the first quantization result and the initial quantization result, and the preset strategy relationship table, the target processing strategy corresponding to the comparison result is determined; the preset strategy relationship table includes multiple comparison results and the processing strategy corresponding to each comparison result.

[0020] The target object is further scanned according to the above-mentioned target processing strategy to obtain a second medical image.

[0021] In one embodiment, the method further includes:

[0022] The second medical image is subjected to quality quantization processing to determine the second quantization result;

[0023] The second quantification result is inserted into the image document corresponding to the second medical image according to the set method, and then saved.

[0024] In one embodiment, the above-mentioned setting method includes a tag method or a medical digital imaging and communication DICOM file method.

[0025] In one embodiment, the initial medical image is obtained by reusing the scanning protocol corresponding to the first medical image.

[0026] Secondly, this application also provides a medical image determining device, the device comprising:

[0027] The acquisition module is used to acquire the first medical image of the detected object at a historical time and the initial medical image at the current time.

[0028] The quantization module is used to perform quality quantization processing on the first medical image and the initial medical image to determine the first quantization result corresponding to the first medical image and the initial quantization result corresponding to the initial medical image.

[0029] The determination module is used to continue scanning the detection object to obtain a second medical image if the first quantization result is inconsistent with the initial quantization result; the second quantization result corresponding to the second medical image is consistent with the first quantization result.

[0030] Thirdly, this application also provides a computer device, which includes a memory and a processor. The memory stores a computer program, and the processor executes the computer program to perform the following steps:

[0031] Acquire the first medical image of the detected object acquired at a historical moment and the initial medical image acquired at the current moment;

[0032] The first medical image and the initial medical image are subjected to quality quantization processing to determine the first quantization result corresponding to the first medical image and the initial quantization result corresponding to the initial medical image.

[0033] If the first quantization result is inconsistent with the initial quantization result, the object to be detected will continue to be scanned to obtain a second medical image; the second quantization result corresponding to the second medical image is consistent with the first quantization result.

[0034] Fourthly, this application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, performs the following steps:

[0035] Acquire the first medical image of the detected object acquired at a historical moment and the initial medical image acquired at the current moment;

[0036] The first medical image and the initial medical image are subjected to quality quantization processing to determine the first quantization result corresponding to the first medical image and the initial quantization result corresponding to the initial medical image.

[0037] If the first quantization result is inconsistent with the initial quantization result, the object to be detected will continue to be scanned to obtain a second medical image; the second quantization result corresponding to the second medical image is consistent with the first quantization result.

[0038] Fifthly, this application also provides a computer program product, which includes a computer program that, when executed by a processor, performs the following steps:

[0039] Acquire the first medical image of the detected object acquired at a historical moment and the initial medical image acquired at the current moment;

[0040] The first medical image and the initial medical image are subjected to quality quantization processing to determine the first quantization result corresponding to the first medical image and the initial quantization result corresponding to the initial medical image.

[0041] If the first quantization result is inconsistent with the initial quantization result, the object to be detected will continue to be scanned to obtain a second medical image; the second quantization result corresponding to the second medical image is consistent with the first quantization result.

[0042] The aforementioned method, apparatus, device, storage medium, and program product for determining medical images acquire a first medical image of the object being tested at a historical time and an initial medical image at the current time. They then perform quality quantization processing on both the first and initial medical images to determine a first quantization result corresponding to the first medical image and an initial quantization result corresponding to the initial medical image. These two quantization results are compared; if they are inconsistent, the object being tested is scanned again to obtain a second medical image. The second quantization result corresponding to this second medical image is consistent with the first quantization result. In this method, since the quality of the medical images acquired at the current time is inconsistent, scanning of the object can continue to obtain a medical image at the current time with a quality comparable to that of the medical images at historical times. This ensures the consistency of quality between the medical images at the current time and those at historical times. Therefore, when using the medical images at the current time and those at historical times for image analysis, since multiple medical images of roughly the same quality are used, the obtained image analysis results are relatively accurate, guaranteeing the accuracy of the image analysis results obtained after analyzing and processing medical images from multiple different times. Attached Figure Description

[0043] Figure 1 This is a schematic diagram of the imaging system in one embodiment;

[0044] Figure 2 This is a flowchart illustrating a method for determining a medical image in one embodiment;

[0045] Figure 3 This is a flowchart illustrating a method for determining a medical image in another embodiment;

[0046] Figure 4 This is a flowchart illustrating a method for determining a medical image in another embodiment;

[0047] Figure 5 This is a flowchart illustrating a method for determining a medical image in another embodiment;

[0048] Figure 6 This is an example diagram of the registration interface when registering a detection object in another embodiment;

[0049] Figure 7 This is an example diagram of the inspection interface when inspecting a detection object in another embodiment;

[0050] Figure 8 This is a structural block diagram of a medical image determination device in one embodiment;

[0051] Figure 9 This is an internal structural diagram of a computer device in one embodiment. Detailed Implementation

[0052] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0053] The method for determining medical images provided in this application embodiment can be applied to, for example, Figure 1 The imaging system shown includes a scanning device 102 and a computer device 104. The scanning device 102 can scan the whole body or a specific body part of the subject, obtain scan data, and send the scan data to the computer device 104. The computer device 104 can perform image reconstruction processing on the scan data to obtain the corresponding medical image of the subject, and can also perform post-processing on the medical image, such as quantization processing, edge detection, etc. The scanning device 102 can be a single-modal imaging device such as a magnetic resonance (MR) scanner, a computed tomography (CT) scanner, or a positron emission tomography (PET) scanner, or a multimodal imaging device such as PET-CT or PET-MR; no specific limitation is made here. The computer device 104 can be a terminal or a server. If it is a terminal, it can be, but is not limited to, various personal computers, laptops, smartphones, and tablets; if it is a server, it can be implemented using a standalone server or a server cluster composed of multiple servers.

[0054] In one embodiment, such as Figure 2 As shown, a method for determining a medical image is provided, which can be applied to... Figure 1 Taking a computer device as an example, the method may include the following steps:

[0055] S202, acquire the first medical image of the detected object acquired at a historical time and the initial medical image acquired at the current time.

[0056] In this step, the first medical image and the initial medical image are of the same type, such as both being magnetic resonance imaging (MRI) images or both being CT images, etc., and generally, the first medical image and the initial medical image also have the same dimensions, such as both being three-dimensional images or both being two-dimensional images, etc. In addition, the first medical image and the initial medical image are images of the same body part of the object being detected, and the only difference between them is the time of signal acquisition.

[0057] Alternatively, as an optional embodiment, the scanning protocol of the first medical image can be obtained from its saved image DICOM file. The initial medical image can be obtained by reusing the scanning protocol corresponding to the first medical image. That is, the initial medical image can be obtained by scanning the object to be detected using the scanning protocol obtained from the DICOM file of the first medical image. Since multiple images of roughly equivalent quality usually use similar scanning protocols, reusing the scanning protocol of the first medical image to obtain the initial medical image can improve the speed of subsequently determining images of roughly equivalent quality to the first medical image from the initial medical image, thereby improving the efficiency of the scanning process.

[0058] Specifically, the first medical image of the subject acquired at a historical moment can be pre-stored on a server, in the cloud, or in a local database, and can be directly retrieved when needed. For the initial medical image of the subject acquired at the current moment, it can be obtained by scanning the subject with a scanning device at the current moment and reconstructing the image from the scan data.

[0059] S204, perform quality quantization processing on the first medical image and the initial medical image to determine the first quantization result corresponding to the first medical image and the initial quantization result corresponding to the initial medical image.

[0060] In this step, the first medical image and the initial medical image undergo quality quantification, which quantifies their image quality. This facilitates rapid comparison of the two images' quality later. Specifically, the same quality control standard can be used to perform the same quality quantification on the same regions of both images, obtaining quantification results based on the same quality control standard. This ensures the two images are comparable in subsequent analysis.

[0061] Optionally, the quality quantification process for the first medical image and the initial medical image includes: inputting the first medical image and the initial medical image into the quality control evaluation model respectively, and obtaining the quality control grade of the first medical image and the quality control grade of the initial medical image. The quality control grade of the first medical image and the quality control grade of the initial medical image can be excellent, good, fair, or poor.

[0062] The quality quantization processing here can be performed on the overall quality or local quality of a medical image. Taking the overall contrast of a medical image as an example, multiple contrast ranges can be preset, and each contrast range can be assigned a corresponding quality quantization value, which serves as the quantization result. After obtaining the first medical image and the initial medical image, the overall contrast of each image can be calculated. The calculated contrast is then matched with the multiple contrast ranges to obtain the matched contrast ranges and their corresponding quality quantization values, thus obtaining the quantization results for each of the two images.

[0063] Specifically, the same quality quantization process can be performed on the same regions of the first medical image and the initial medical image to obtain the corresponding quantization results, that is, to obtain the first quantization result corresponding to the first medical image and the initial quantization result corresponding to the initial medical image.

[0064] S206, if the first quantization result is inconsistent with the initial quantization result, the detection object is scanned again to obtain a second medical image; the second quantization result corresponding to the second medical image is consistent with the first quantization result.

[0065] In this step, after obtaining the first quantization result corresponding to the first medical image and the initial quantization result of the initial medical image, the two quantization results can be compared. If the first quantization result is inconsistent with the initial quantization result, it generally means that the initial quantization result has not reached the first quantization result. This indicates that the quality of the initial medical image acquired at the current moment is lower than the quality of the first medical image at a historical moment. At this time, it is necessary to continue scanning the detection object and continuously perform quality quantization processing on the medical images obtained during the scanning process until the quality of the obtained medical images is not lower than the quality of the first medical image.

[0066] In other words, if the initial medical image is of low quality, the subject can be scanned further to obtain a second medical image. After performing the same quality quantization processing on the same region of the second medical image as on the first medical image, the resulting second quantization result is either roughly the same as or greater than the first quantization result, meaning the quality of the second medical image is higher than that of the first medical image. This ensures that during subsequent follow-up of the subject, the image quality at the current moment is not lower than the image quality at historical moments, meaning the image quality at different times is roughly equivalent. This provides comparability for image analysis, resulting in more reliable and accurate image analysis results.

[0067] As mentioned above, the overall quality or local quality of medical images can be quantified. The following will explain how to continue the scanning process in these two cases.

[0068] I. Focusing on the overall quality of medical images, i.e., paying attention to the overall quality of medical images.

[0069] A typical complete scan sequence of a detection object consists of multiple sampling stages, each corresponding to a portion of the scan sequence. Different portions correspond to different phase encoding positions in the K-space. By filling the K-space with data collected from different stages, a combined K-space dataset can be obtained. During detection, the image reconstructed using the combined K-space dataset undergoes real-time quality quantization. If the initial quantization result does not meet the first quantization requirement, the scanning process is not interrupted, and subsequent sampling stages continue. For example, sampling of edge regions can be increased to achieve a higher fill density in the K-space. Once the obtained quantization result meets the requirements, the scanning process is interrupted, and a second medical image is obtained.

[0070] Alternatively, a complete scan sequence of the target object may consist of multiple sampling stages, each corresponding to a portion of the scan sequence. Data collected in each sampling stage is filled into different K-spaces, and multiple K-spaces form a combined K-space dataset. During detection, the image reconstructed using the combined K-space dataset undergoes real-time quality quantization. If the initial quantization result does not meet the first quantization result, the scanning process is not interrupted, and subsequent sampling stages continue to increase the sampling frequency, for example, by increasing the sampling frequency at the center of the K-space. Once the obtained quantization result meets the requirements, the scanning process is interrupted, and weighted reconstruction processing is performed on the K-space datasets collected at different frequencies to obtain a second medical image.

[0071] II. Focusing on the local quality of medical images, i.e., paying attention to the local quality of medical images.

[0072] In this case, the first quantization result corresponding to the first medical image can be determined first. The first quantization result includes a first global quantization result and a first local quantization result. The first global quantization result includes the result of quality quantization of the entire region of the first medical image, and the first local quantization result includes the result of quality quantization of the local region of interest of the first medical image.

[0073] Similarly, the initial quantization result corresponding to the initial medical image can also be determined. The initial quantization result includes the second global quantization result and the second local quantization result. The second global quantization result includes the quality quantization result of the entire region of the initial medical image, and the second local quantization result includes the quality quantization result of the local region of interest of the initial medical image.

[0074] Then, it can be determined whether the first global quantization result in the first quantization result is consistent with the second global quantization result of the initial quantization result. If they are inconsistent, the detection object is re-scanned.

[0075] If the first global quantization result is consistent with the second global quantization result, then it is further determined whether the first local quantization result in the first quantization result is consistent with the second local quantization result of the initial quantization result. If the first local quantization result is consistent with the second local quantization result, then the scanning is terminated.

[0076] If the first local quantization result is inconsistent with the second local quantization result, the size of the scanning FOV field of view is adjusted so that the adjusted FOV area is adapted to the region of interest, and the region of interest is locally scanned according to the adjusted FOV area.

[0077] In the aforementioned method for determining medical images, a first medical image of the target object acquired at a historical time and an initial medical image acquired at the current time are obtained. The first and initial medical images are then subjected to quality quantization processing to determine a first quantization result corresponding to the first medical image and an initial quantization result corresponding to the initial medical image. These two quantization results are compared. If they are inconsistent, the target object is scanned again to obtain a second medical image. The second quantization result corresponding to this second medical image is consistent with the first quantization result. In this method, since the quality of the medical images obtained at the current time is inconsistent, the target object can continue to be scanned to obtain a medical image at the current time with a quality comparable to that of the historical images. This ensures the consistency of quality between the current and historical medical images. Therefore, when using the current and historical medical images for image analysis, since multiple medical images of roughly the same quality are used, the obtained image analysis results are relatively accurate, guaranteeing the accuracy of the image analysis results obtained after analyzing multiple medical images from different times.

[0078] In another embodiment, such as Figure 3 As shown, another method for determining a medical image is provided. Based on the above embodiment, the process of quantizing the first medical image in S204 may include the following steps:

[0079] S302, Obtain a preset quality quantification method on the target device; the target device is a device for acquiring a second medical image, and the preset quality quantification method includes at least one quantification method.

[0080] In this step, the first medical image acquired at a historical moment and the second medical image acquired at the current moment may be obtained by different devices. Images acquired by different devices generally have differences, and the quality control standards on different devices are also different, resulting in varying image quality. This makes it difficult to conduct image comparison and analysis during subsequent follow-up. In addition, using equipment from different manufacturers or using different software versions for image acquisition may lead to problems with the quality of multiple images obtained. Therefore, to facilitate accurate comparison of images from two different periods, quality quantification processing can be performed on the medical images from historical moments on the device that acquired the current medical image, ensuring that images from two different periods obtain the same quality quantification results.

[0081] Specifically, when comparing and analyzing images from multiple different periods, the quality control standards set on the device that acquired the medical image at the current moment can be obtained first. These quality control standards can be preset quality quantification methods.

[0082] For medical images, the quality of medical images can generally be quantified from multiple dimensions. In other words, as optional, the above-mentioned preset quality quantification methods include at least one of the following: quantification methods for image contrast; quantification methods for image artifacts and artifact types; quantification methods for image signal-to-noise ratio; and quantification methods for image uniformity.

[0083] The preset quality quantization method here can be either a method for quantizing the overall quality of the image or a method for quantizing the quality of a local area of ​​the image. The following explains the specific settings for each quality quantization method:

[0084] The quantization method for image contrast can be to pre-set multiple contrast ranges, and each contrast range can be set with a corresponding quality quantization result, that is, to set the quantization method for image contrast.

[0085] For quantization of image artifacts, multiple pre-defined artifact severity ranges can be used, with each artifact severity range having a corresponding quality quantization result. In other words, the quantization method for image artifacts can be pre-defined. Alternatively, multiple pre-defined artifact types can be used, with each artifact type treated as a quality quantization result. This also allows for the setting of a quantization method specific to each image artifact type.

[0086] The quantization method for image signal-to-noise ratio can be to pre-set multiple signal-to-noise ratio ranges, and each signal-to-noise ratio range can be set with a corresponding quality quantization result, that is, to set the quantization method for image signal-to-noise ratio.

[0087] The quantization method for image uniformity can be to pre-set multiple uniformity ranges, and each uniformity range can be set with a corresponding quality quantization result, that is, to set the quantization method for image uniformity.

[0088] In addition, the quality quantification results mentioned above may include quality quantification values ​​and / or artifact types, and of course, other content may also be included.

[0089] S304, the first medical image is subjected to quality quantization processing using the aforementioned preset quality quantization method to determine the first quantization result corresponding to the first medical image.

[0090] In this step, after obtaining the first medical image and the quality quantification method set on the target device, the parameters corresponding to the quality quantification method can be calculated on the first medical image, and the obtained parameters can be matched with multiple ranges or types corresponding to the quality quantification method to obtain the successfully matched ranges or types and their corresponding quality quantification results.

[0091] If there is only one quality quantization method, then the obtained quality quantization result can be directly used as the first quantization result corresponding to the first medical image; if there are multiple quality quantization methods, then the obtained multiple quality quantization results can be summed, or the summed and averaged, and the final result can be used as the first quantization result corresponding to the first medical image.

[0092] For example, taking the overall contrast of an image as an example, the overall image contrast of the first medical image can be calculated, and the calculated contrast can be matched with multiple contrast ranges in the quantization method for image contrast to obtain the successfully matched contrast range and its corresponding quality quantization result, that is, to obtain the first quantization result corresponding to the first medical image.

[0093] In this embodiment, by acquiring the quality quantification method set on the device acquiring the second medical image, and using this quality quantification method to perform quality quantification processing on the first medical image, a first quantification result is obtained. This allows multiple medical images at different times to use the same quality quantification method, thus ensuring the comparability of the obtained quality quantification results and guaranteeing the consistency of quality among multiple medical images at different times. This method is particularly suitable for applying the quality control experience of highly skilled operators in a digital and automated form to subsequent review / follow-up or to guide the operation of other operators, which helps to reduce the experience level requirements of operators and ensure high-quality scanning results. Furthermore, the device acquiring the second medical image is equipped with multiple quality quantification methods, which allows for comprehensive quantification of multiple medical images at different times, improving the comprehensiveness and accuracy of quantification, and meeting the different quality quantification needs of different users.

[0094] In another embodiment, such as Figure 4 As shown, another method for determining medical images is provided. Based on the above embodiments, the process of continuing to scan the detection object in S206 may include the following steps:

[0095] S402, based on the comparison results of the first quantization result and the initial quantization result and the preset strategy relationship table, determine the target processing strategy corresponding to the comparison result; the preset strategy relationship table includes multiple comparison results and the processing strategy corresponding to each comparison result.

[0096] In this step, when setting the quality quantization method on the target device, multiple different comparison results and multiple different processing strategies can be preset for the same quality quantization method, and the multiple comparison results and multiple processing strategies can be bound together to obtain a preset strategy relationship table.

[0097] The comparison results here may include the quantization value of the current image being less than the quantization value of the historical image, or the quantization value of the current image being not less than the quantization value of the historical image, or the type of the current image being inconsistent with the type of the historical image, or the type of the current image being consistent with the type of the historical image, or may include other comparison results.

[0098] Specifically, after obtaining the first quantization result and the initial quantization result, the quantization results of the same type in the two quantization results can be compared to obtain the comparison result, and the corresponding target processing strategy can be found in the preset strategy relationship table according to the comparison result.

[0099] S404, The detection object is further scanned according to the above target processing strategy to obtain a second medical image.

[0100] In this step, after obtaining the target processing strategy, the initial medical image can be processed using the target processing strategy, or the detection object can be re-scanned / continued to be scanned, etc., so as to finally obtain a second medical image with approximately the same quality as the first medical image.

[0101] For example, if during a lumbar spine re-examination, the artifacts caused by intestinal peristalsis in the currently acquired image are found to be more pronounced than those in the previously acquired image, a corresponding processing strategy can be output. This strategy could be prompting the user to intervene, or the system could automatically optimize the acquisition strategy (such as automatically adding saturation bands). As another example, if the signal-to-noise ratio (SNR) of the currently acquired image is worse than that of images acquired at historical times, a corresponding processing strategy can be output. This strategy could be the scanning system automatically increasing the number of repeated acquisitions, prompting the user to increase the number of repeated acquisitions, or activating an AI-powered reconstruction algorithm to optimize the SNR.

[0102] In this embodiment, by comparing the first quantization result and the initial quantization result, the target processing strategy corresponding to the comparison result is obtained from a strategy table that includes multiple processing strategies. The target processing strategy is then used to continue scanning the detection object to obtain a second medical image. In this way, by continuing to scan the detection object using the strategy obtained from the strategy table, the scanning of the detection object can be obtained and accurately implemented, thereby improving the efficiency and accuracy of obtaining the second medical image.

[0103] In another embodiment, such as Figure 5 As shown, another method for determining medical images is provided. Based on the above embodiments, the method may further include the following steps:

[0104] S502, perform quality quantization processing on the second medical image to determine the second quantization result.

[0105] In this step, when performing quality quantization on the second medical image, the quality quantization method on the target device can be used, and the same quality quantization method used on the first medical image can be used. For example, the first medical image, the initial medical image, and the second medical image can all be quality quantized using a method that targets image contrast. The final result of quality quantization of the second medical image is denoted as the second quantization result.

[0106] S504, insert the second quantization result into the image document corresponding to the second medical image according to the set method, and save it.

[0107] In this step, after obtaining the second quantization result of the second medical image, the corresponding quality quantization result of the second medical image can be recorded and saved. Simultaneously, the corresponding quality control items (e.g., quality control / quality quantization processing for image contrast) can also be recorded and saved together. The recording and saving method can be to bind the image document of the second medical image (e.g., medical digital imaging and communication DICOM data) with the corresponding second quantization result and quality control items for recording and saving together; alternatively, the second quantization result and quality control items can be inserted into the image document of the second medical image in a set manner. This setting method can be optional, including tag-based methods or medical digital imaging and communication DICOM file methods.

[0108] For each medical image that has undergone quantification, the corresponding quantification results can be recorded and saved in this manner. This way, if subsequent image follow-ups are performed on the same equipment from the same manufacturer and with the same software version, the previously used quality control items and the obtained quantification results can be quickly parsed from the saved documents and applied to the current examination, thereby improving the efficiency and accuracy of the current examination.

[0109] In this embodiment, by inserting the quantization result of the second medical image into the corresponding image document and saving it in a predetermined manner, the information can be quickly and accurately obtained when using the quantization result of the second medical image quality in subsequent use, avoiding information loss and thus improving the efficiency and accuracy of subsequent examinations. Furthermore, inserting the quantization result into the image document using tags or DICOM files can improve the efficiency of subsequent parsing, thereby further improving the efficiency of subsequent examinations.

[0110] In another embodiment, if the first quantization result is inconsistent with the initial quantization result, a prompt message can be generated. The prompt message could be, for example, information about movement of the detected object during scanning or a malfunction of the receiving coil. This prompt message allows doctors or technicians to quickly understand the current scanning status, enabling timely adjustments and improving the efficiency and accuracy of the entire scanning process.

[0111] In another embodiment, a method for determining a medical image includes:

[0112] Acquire the first medical image of the detected object acquired at a historical moment and the initial medical image acquired at the current moment;

[0113] The first medical image and the initial medical image are subjected to quality quantization processing to determine the first quantization result corresponding to the first medical image and the initial quantization result corresponding to the initial medical image.

[0114] In response to the inconsistency between the first quantization result and the initial quantization result, motion artifacts are determined to exist in the first medical image. Optionally, the first medical image can be input into a set image processing model to obtain a detection result of motion artifacts in the first medical image; or, the first medical image and the initial medical image can be subjected to subtraction processing to generate a subtraction result, and the detection result of motion artifacts in the first medical image can be obtained based on the subtraction result. Optionally, the image processing model can be a model trained based on a neural network.

[0115] Generate a prompt message indicating that the detected object is moving during the scanning process, and generate feedback information prompting the detected object to remain stationary.

[0116] After the object to be detected responds to the feedback information, the object to be detected is scanned again to obtain a second medical image; the second quantification result corresponding to the second medical image is consistent with the first quantification result.

[0117] Here, an image processing model is used to perform artifact removal on the first medical image and / or the initial medical image. This allows for rapid identification of artifacts in the first medical image, enabling the subsequent rapid acquisition of the second medical image by eliminating these artifacts. Furthermore, outputting prompts to the detection subject allows for quick awareness of the current scanning status, reminding the subject to make timely adjustments, thereby improving the efficiency and accuracy of the entire scanning process.

[0118] In another embodiment, a method for determining a medical image includes:

[0119] Acquire the first medical image of the detected object acquired at a historical moment and the initial medical image acquired at the current moment;

[0120] The first medical image and the initial medical image are subjected to quality quantization processing to determine the first quantization result corresponding to the first medical image and the initial quantization result corresponding to the initial medical image.

[0121] In response to the inconsistency between the first quantization result and the initial quantization result, a prompt message is generated indicating a receiver coil fault.

[0122] After troubleshooting the receiving coil based on the prompts, the object being scanned is scanned again to obtain a second medical image; the second quantization result corresponding to the second medical image is consistent with the first quantization result.

[0123] Optionally, the fault indication message for the receiving coil can be determined in the following way:

[0124] Acquire the data collected from each channel of the receiving coil corresponding to the first medical image;

[0125] Multiple sets of noise data are determined based on the data collected from each channel, with each set of noise data corresponding to one channel of the receiving coil.

[0126] Determine the distribution information of each group of noise data, and identify the channel where the fault occurred based on the distribution information of each group of noise data.

[0127] For example, the real and imaginary parts of the noise data can be obtained separately. The noise data may conform to a Weibull distribution. By obtaining the logarithmic curves of the Weibull distribution for the real and imaginary parts respectively, the faulty channel can be identified. The logarithmic curve of the Weibull distribution can have the horizontal axis representing the logarithm of the real or imaginary data, and the vertical axis representing the logarithmic structure of the real or imaginary data after processing with the probability density of the Weibull distribution.

[0128] In this embodiment, it is possible to distinguish between the inconsistency between the first quantization result and the initial quantization result caused by a fault in the receiving coil or a fault in a non-receiving coil (e.g., movement of the detected object during scanning) during the data acquisition process, thereby realizing automatic monitoring of the scanning process and enabling operators to make timely adaptive adjustments to the scanning process.

[0129] In another embodiment, several example diagrams are given below when scanning the object to be detected. Before scanning the object, it is generally necessary to register its information. See [link to relevant documentation]. Figure 6 The example registration interface shown is divided into two main categories on the left: patient information and examination information. Patient information includes, for example, the patient's name, the identification ID assigned by the hospital, gender, and age. Examination information includes, for example, the examination items (e.g., abdomen, head, chest, etc.), the purpose of the examination, and clinical symptoms. The right half mainly focuses on the examination plan for the examinee, which can display the examinee's most recent examination plan, including the most recent scan (e.g., the abdominal MRI plain scan + contrast scan 3 months ago in the image) and quality control results (e.g., excellent quality control in the image). Additionally, the registration interface provides the user (doctor or technician) with the option to reuse the previous examination plan. The user can choose to reuse or not reuse it. After making a selection, the pre-registration can be saved, or the examination can be started for the examinee.

[0130] After the inspection of the object to be inspected begins, see [link to relevant documentation]. Figure 7The display interface, as shown, offers multiple inspection protocol queues on the left, allowing users to select one. It also provides "Continue" buttons to continue scanning using the selected protocol and "Stop" buttons to stop scanning. During the scanning process using the selected protocol, the interface simultaneously displays the image from the current inspection and the previous inspection in the center, allowing users to visually observe the differences between them. On the right side of the interface, the image quality control results for this inspection are displayed, including multiple control items such as motion artifacts, uniformity, and radio frequency interference. Users can choose to manually or automatically select these control items and select whether to repeat them. By displaying multiple inspection protocols, images from multiple time periods, and quality control items on the interface, users can quickly and intuitively understand the differences between the current and previous inspections, improving the efficiency of obtaining images with the same quality control level within the current inspection.

[0131] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.

[0132] Based on the same inventive concept, this application also provides a medical image determination apparatus for implementing the above-described method for determining medical images. The solution provided by this apparatus is similar to the implementation described in the above-described method; therefore, the specific limitations in one or more embodiments of the medical image determination apparatus provided below can be found in the limitations of the medical image determination method described above, and will not be repeated here.

[0133] In one embodiment, such as Figure 8 As shown, a medical image determination device is provided, comprising: an acquisition module 11, a quantization module 12, and a determination module 13, wherein:

[0134] The acquisition module 11 is used to acquire the first medical image of the detection object acquired at a historical time and the initial medical image acquired at the current time;

[0135] Quantization module 12 is used to perform quality quantization processing on the first medical image and the initial medical image to determine the first quantization result corresponding to the first medical image and the initial quantization result corresponding to the initial medical image.

[0136] The determination module 13 is used to continue scanning the detection object to obtain a second medical image if the first quantization result is inconsistent with the initial quantization result; the second quantization result corresponding to the second medical image is consistent with the first quantization result.

[0137] Optionally, the initial medical image is obtained by reusing the scanning protocol corresponding to the first medical image.

[0138] In another embodiment, a different medical image determination device is provided. Based on the above embodiments, the quantization module 12 may include:

[0139] A quantization method acquisition unit is used to acquire a preset quality quantization method on a target device; the target device is a device for acquiring a second medical image, and the preset quality quantization method includes at least one quantization method.

[0140] The quantization processing unit is used to perform quality quantization processing on the first medical image using the aforementioned preset quality quantization method, and to determine the first quantization result corresponding to the first medical image.

[0141] Optionally, the above-mentioned preset quality quantization method includes at least one of the following quantization methods: quantization method for image contrast; quantization method for image artifacts and artifact types; quantization method for image signal-to-noise ratio; and quantization method for image uniformity.

[0142] In another embodiment, a different medical image determination device is provided. Based on the above embodiments, the determination module 13 may include:

[0143] The strategy determination unit is used to determine the target processing strategy corresponding to the comparison result based on the comparison result of the first quantization result and the initial quantization result and the preset strategy relationship table; the preset strategy relationship table includes multiple comparison results and the processing strategy corresponding to each comparison result.

[0144] The image determination unit is used to continue scanning the detection object according to the above-mentioned target processing strategy to obtain a second medical image.

[0145] In another embodiment, a different medical image determination device is provided, which, based on the above embodiments, may further include:

[0146] The quantization result determination module is used to perform quality quantization processing on the second medical image and determine the second quantization result.

[0147] The insertion module is used to insert the second quantification result into the image document corresponding to the second medical image according to the set method, and then save it.

[0148] Optionally, the above settings can be configured using tags or medical digital imaging and communication DICOM files.

[0149] The modules in the aforementioned medical image determination device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device, or stored in the memory of a computer device as software, so that the processor can call and execute the operations corresponding to each module.

[0150] In one embodiment, a computer device is provided, taking a terminal as an example, whose internal structure diagram can be as follows: Figure 9 As shown, the computer device includes a processor, memory, communication interface, display screen, and input devices connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, mobile cellular networks, NFC (Near Field Communication), or other technologies. When executed by the processor, the computer program implements a method for determining medical images. The display screen can be an LCD screen or an e-ink screen. The input devices can be a touch layer covering the display screen, buttons, a trackball, or a touchpad mounted on the computer device casing, or an external keyboard, touchpad, or mouse.

[0151] Those skilled in the art will understand that Figure 9 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0152] In one embodiment, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to perform the following steps:

[0153] The system acquires a first medical image of the target object acquired at a historical time and an initial medical image acquired at the current time; it performs quality quantization processing on the first medical image and the initial medical image to determine the first quantization result corresponding to the first medical image and the initial quantization result corresponding to the initial medical image; if the first quantization result and the initial quantization result are inconsistent, the system continues to scan the target object to obtain a second medical image; the second quantization result corresponding to the second medical image is consistent with the first quantization result.

[0154] In one embodiment, the processor, when executing a computer program, also performs the following steps:

[0155] A preset quality quantization method is obtained on the target device; the target device is a device for acquiring a second medical image, and the preset quality quantization method includes at least one quantization method; the first medical image is subjected to quality quantization processing using the preset quality quantization method to determine the first quantization result corresponding to the first medical image.

[0156] In one embodiment, the preset quality quantization method includes at least one of the following quantization methods: quantization method for image contrast; quantization method for image artifacts and artifact types; quantization method for image signal-to-noise ratio; and quantization method for image uniformity.

[0157] In one embodiment, the processor, when executing a computer program, also performs the following steps:

[0158] Based on the comparison between the first quantification result and the initial quantification result, and the preset strategy relationship table, the target processing strategy corresponding to the comparison result is determined; the preset strategy relationship table includes multiple comparison results and the processing strategy corresponding to each comparison result; the detection object is further scanned according to the target processing strategy to obtain a second medical image.

[0159] In one embodiment, the processor, when executing a computer program, also performs the following steps:

[0160] The quality of the second medical image is quantified to determine the second quantization result; the second quantization result is then inserted into the image document corresponding to the second medical image according to the set method and saved.

[0161] In one embodiment, the initial medical image is obtained by reusing the scanning protocol corresponding to the first medical image.

[0162] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, the computer program performing the following steps when executed by a processor:

[0163] The system acquires a first medical image of the target object acquired at a historical time and an initial medical image acquired at the current time; it performs quality quantization processing on the first medical image and the initial medical image to determine the first quantization result corresponding to the first medical image and the initial quantization result corresponding to the initial medical image; if the first quantization result and the initial quantization result are inconsistent, the system continues to scan the target object to obtain a second medical image; the second quantization result corresponding to the second medical image is consistent with the first quantization result.

[0164] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0165] A preset quality quantization method is obtained on the target device; the target device is a device for acquiring a second medical image, and the preset quality quantization method includes at least one quantization method; the first medical image is subjected to quality quantization processing using the preset quality quantization method to determine the first quantization result corresponding to the first medical image.

[0166] In one embodiment, the preset quality quantization method includes at least one of the following quantization methods: quantization method for image contrast; quantization method for image artifacts and artifact types; quantization method for image signal-to-noise ratio; and quantization method for image uniformity.

[0167] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0168] Based on the comparison between the first quantification result and the initial quantification result, and the preset strategy relationship table, the target processing strategy corresponding to the comparison result is determined; the preset strategy relationship table includes multiple comparison results and the processing strategy corresponding to each comparison result; the detection object is further scanned according to the target processing strategy to obtain a second medical image.

[0169] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0170] The quality of the second medical image is quantified to determine the second quantization result; the second quantization result is then inserted into the image document corresponding to the second medical image according to the set method and saved.

[0171] In one embodiment, the initial medical image is obtained by reusing the scanning protocol corresponding to the first medical image.

[0172] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, performs the following steps:

[0173] The system acquires a first medical image of the target object acquired at a historical time and an initial medical image acquired at the current time; it performs quality quantization processing on the first medical image and the initial medical image to determine the first quantization result corresponding to the first medical image and the initial quantization result corresponding to the initial medical image; if the first quantization result and the initial quantization result are inconsistent, the system continues to scan the target object to obtain a second medical image; the second quantization result corresponding to the second medical image is consistent with the first quantization result.

[0174] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0175] A preset quality quantization method is obtained on the target device; the target device is a device for acquiring a second medical image, and the preset quality quantization method includes at least one quantization method; the first medical image is subjected to quality quantization processing using the preset quality quantization method to determine the first quantization result corresponding to the first medical image.

[0176] In one embodiment, the preset quality quantization method includes at least one of the following quantization methods: quantization method for image contrast; quantization method for image artifacts and artifact types; quantization method for image signal-to-noise ratio; and quantization method for image uniformity.

[0177] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0178] Based on the comparison between the first quantification result and the initial quantification result, and the preset strategy relationship table, the target processing strategy corresponding to the comparison result is determined; the preset strategy relationship table includes multiple comparison results and the processing strategy corresponding to each comparison result; the detection object is further scanned according to the target processing strategy to obtain a second medical image.

[0179] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0180] The quality of the second medical image is quantified to determine the second quantization result; the second quantization result is then inserted into the image document corresponding to the second medical image according to the set method and saved.

[0181] In one embodiment, the initial medical image is obtained by reusing the scanning protocol corresponding to the first medical image.

[0182] It should be noted that the data involved in this application (including but not limited to data used for analysis, data stored, data displayed, etc.) are all information and data authorized by the user or fully authorized by all parties.

[0183] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited to these.

[0184] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0185] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A method for determining a medical image, characterized in that, The method includes: Acquire the first medical image of the object at a historical moment and the initial medical image at the current moment; The first medical image and the initial medical image are subjected to quality quantization processing to determine a first quantization result corresponding to the first medical image and an initial quantization result corresponding to the initial medical image; wherein, the first quantization result includes a first global quantization result and a first local quantization result, and the initial quantization result includes a second global quantization result and a second local quantization result, and the local quantization result is the result of quality quantization of the region of interest in the image; If the first quantization result is inconsistent with the initial quantization result, the detection object is scanned again to obtain a second medical image; the second quantization result corresponding to the second medical image is consistent with the first quantization result, including: if the first global quantization result is inconsistent with the second global quantization result, the detection object is scanned again to obtain a second medical image; if the first global quantization result is consistent with the second global quantization result, it is determined whether the first local quantization result is consistent with the second local quantization result. If the first local quantization result is consistent with the second local quantization result, then the scan is terminated; If the first local quantization result is inconsistent with the second local quantization result, the scanning field of view is adjusted to adapt to the region of interest, and the region of interest is locally scanned to obtain the second medical image.

2. The method according to claim 1, characterized in that, The step of performing quality quantization processing on the first medical image to determine the first quantization result corresponding to the first medical image includes: A preset quality quantification method is obtained on the target device; the target device is the device that acquires the second medical image, and the preset quality quantification method includes at least one quantification method. The first medical image is subjected to quality quantization processing using the preset quality quantization method to determine the first quantization result corresponding to the first medical image.

3. The method according to claim 2, characterized in that, The preset quality quantification method includes at least one of the following quantification methods: Quantization methods for image contrast; Quantification methods for image artifacts and artifact types; Quantization methods for image signal-to-noise ratio; Quantization methods for image uniformity.

4. The method according to claim 1, characterized in that, The step of continuing to scan the object to obtain a second medical image includes: Based on the comparison between the first quantization result and the initial quantization result, and a preset strategy relationship table, the target processing strategy corresponding to the comparison result is determined; the preset strategy relationship table includes multiple comparison results and the processing strategy corresponding to each comparison result. The detection object is further scanned according to the target processing strategy to obtain the second medical image.

5. The method according to claim 1, characterized in that, The method further includes: The second medical image is subjected to quality quantization processing to determine the second quantization result; The second quantization result is inserted into the image document corresponding to the second medical image according to the set method, and then saved.

6. The method according to claim 5, characterized in that, The initial medical image is obtained by reusing the scanning protocol corresponding to the first medical image.

7. A medical image determining device, characterized in that, The device includes: The acquisition module is used to acquire the first medical image of the detected object at a historical time and the initial medical image at the current time. The quantization module is used to perform quality quantization processing on the first medical image and the initial medical image to determine a first quantization result corresponding to the first medical image and an initial quantization result corresponding to the initial medical image; wherein, the first quantization result includes a first global quantization result and a first local quantization result, and the initial quantization result includes a second global quantization result and a second local quantization result, and the local quantization result is the result of quality quantization of the region of interest in the image; The determination module is configured to continue scanning the detection object to obtain a second medical image if the first quantization result and the initial quantization result are inconsistent; the second quantization result corresponding to the second medical image is consistent with the first quantization result, including: if the first global quantization result and the second global quantization result are inconsistent, continue scanning the detection object to obtain the second medical image; if the first global quantization result and the second global quantization result are consistent, determine whether the first local quantization result and the second local quantization result are consistent. If the first local quantization result is consistent with the second local quantization result, then the scan is terminated; If the first local quantization result is inconsistent with the second local quantization result, the scanning field of view is adjusted to adapt to the region of interest, and the region of interest is locally scanned to obtain the second medical image.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 6.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 6.

Images