Medical image quality monitoring method and device, electronic equipment and storage medium

Abstract

The application discloses a medical image quality monitoring method and device, electronic equipment and storage medium, which are used to solve the problem of low quality control efficiency and reliability of manual reading in the prior art. The medical image quality monitoring method comprises the following steps: acquiring a visit image sequence, wherein the visit image sequence comprises a plurality of medical image slices; identifying a target CT quality parameter of the visit image sequence; projecting the visit image sequence into a two-dimensional image; and in response to a quality control instruction, screening target data from preprocessed data to generate a quality monitoring report, wherein the preprocessed data comprises one or a combination of the target CT quality parameter, a medical image slice corresponding to the target CT quality parameter, and the two-dimensional image.

Description

Technical Field

[0001] This application belongs to the field of computer data processing technology, and specifically relates to a method, device, electronic device and storage medium for monitoring the quality of medical images. Background Technology

[0002] The Medical Imaging Reading System (MIRS) provides a comprehensive multi-scenario solution for medical image reading, realizing the informatization and intelligentization of the entire business process from image management to reading management. In this process, the intelligent reading platform, as the image reading tool, can intelligently manage the uploading, review, and reading of images, and track image status and reading progress in real time; it is a core component of MIRS.

[0003] Traditional medical image quality monitoring requires the viewer to manually open the image sequence and scan the images in the sequence (up to 800 images). The viewer needs to browse these images and then judge and classify the relevant quality parameters based on experience, some digital information, and the label information generated by the image protocol. This process is time-consuming and has low reliability.

[0004] The information disclosed in this background section is intended only to enhance the understanding of the overall background of this application and should not be construed as an admission or in any way implying that the information constitutes prior art known to those skilled in the art. Summary of the Invention

[0005] The purpose of this application is to provide a method for monitoring the quality of medical images, which is used to solve the problem of intelligent image review.

[0006] To achieve the above objectives, this application provides a method for monitoring the quality of medical images, the method comprising:

[0007] Obtain a sequence of medical images, which includes multiple slices of medical images;

[0008] Identify the target CT quality parameters of the visited image sequence;

[0009] Project the access image sequence into a two-dimensional image;

[0010] In response to a quality control instruction, target data is selected from the preprocessed data to generate a quality monitoring report. The preprocessed data includes one or a combination of the target CT quality parameters, medical image slices corresponding to the target CT quality parameters, and two-dimensional images.

[0011] In one embodiment, in response to a quality control instruction, target data is selected from preprocessed data to generate a quality monitoring report, specifically including:

[0012] In response to quality control instructions, target data is filtered from the target CT quality parameters and two-dimensional images and assembled into a data table;

[0013] The output includes a quality control display interface for the data table, wherein the quality control display interface includes a two-dimensional image call-up control;

[0014] In response to the display operation of the two-dimensional image call-up control, the corresponding two-dimensional image is output to the quality control display interface.

[0015] In one embodiment, the quality control display interface further includes a quality parameter input control;

[0016] The method further includes:

[0017] In response to an input operation to the quality parameter input control, the data table in the quality control display interface is updated.

[0018] In one embodiment, the target CT quality parameters include preset type image identifiers, and the quality control display interface further includes an identifier image call-up control corresponding to the preset type image identifiers;

[0019] The method further includes:

[0020] In response to the display operation of the control that brings up the identification image, the corresponding identification image is output to the quality control display interface.

[0021] In one embodiment, in response to a quality control instruction, target data is selected from preprocessed data to generate a quality monitoring report, specifically including:

[0022] In response to quality control instructions, the selected two-dimensional images are labeled using at least one of the target CT quality parameters;

[0023] The output includes a quality control display interface for the annotated two-dimensional image.

[0024] In one embodiment, the quality control instruction includes scan type quality control information, and the target CT quality parameter includes scan type;

[0025] The method further includes:

[0026] In response to quality control instructions, two-dimensional images of the scan type corresponding to the scan type quality control information are selected;

[0027] Based on the selected two-dimensional images, determine whether the visited image sequence meets the quality control requirements.

[0028] In one embodiment, the quality control instruction includes quality control information for the scanned area, the target CT quality parameters include the scanned area, and the two-dimensional image includes a coronal projection image and a sagittal projection image;

[0029] The method further includes:

[0030] In response to the quality control command, the coronal projection image and / or sagittal projection image of the scanned part corresponding to the quality control information of the scanned part are selected.

[0031] Based on the selected coronal and / or sagittal projection images, determine whether the visited image sequence meets the quality control requirements.

[0032] In one embodiment, projecting image slices from the visited image sequence into a two-dimensional image further includes:

[0033] Two-dimensional images of different scanned areas belonging to the same scan period and scan window are stitched together.

[0034] In one embodiment, the target CT quality parameters include at least one of scan type, scan period, scan window, slice spacing, slice thickness, cross-sectional orientation, slice missing, scan location, motion artifacts, metal artifacts, external markers, and externally added text.

[0035] In one embodiment, identifying the target CT quality parameters of the visit image sequence specifically includes:

[0036] Identify the scan type of the visited image sequence and calculate the cross-sectional orientation of each image slice in the CT scan sequence to filter out cross-sectional image slices.

[0037] The image identifiers in the cross-sectional image slices are identified to filter out the corresponding image slices, and the image channels of the cross-sectional image slices are identified to filter out VR image slices, resulting in pre-stitched image slices. The image identifiers include at least one of external markers, externally added text, metal artifacts, and motion artifacts.

[0038] Identify the scanning information of the pre-stitched image slice, wherein the scanning information includes at least one of layer thickness, interlayer spacing, scanning window, scanning period, and scanning location.

[0039] This application also provides a medical image quality monitoring device, comprising:

[0040] The acquisition module is used to acquire a sequence of medical images, which includes multiple medical image slices.

[0041] The identification module is used to identify the target CT quality parameters of the visited image sequence;

[0042] The projection module is used to project the access image sequence into a two-dimensional image;

[0043] The generation module is used to filter target data from preprocessed data in response to quality control instructions to generate a quality monitoring report. The preprocessed data includes one or a combination of the target CT quality parameters, medical image slices corresponding to the target CT quality parameters, and two-dimensional images.

[0044] This application also provides an electronic device, including:

[0045] At least one processor; and

[0046] The memory stores instructions that, when executed by the at least one processor, cause the at least one processor to perform the medical image quality monitoring method as described above.

[0047] This application also provides a machine-readable storage medium storing executable instructions that, when executed, cause the machine to perform the medical image quality monitoring method as described above.

[0048] Compared with the prior art, the medical image quality monitoring method according to this application identifies target CT quality parameters in the visit image sequence and projects the visit image sequence into a two-dimensional image. During quality control, target data can be screened from the preprocessed data according to the quality control requirements, and a quality monitoring report can be generated, which improves the efficiency of quality control while ensuring the reliability of quality control.

[0049] On the other hand, quality monitoring reports can be output to the quality control display interface as an intermediate process output, and quality control personnel can assist in quality control by interacting with the UI of the quality control display interface.

[0050] On the other hand, quality monitoring reports can also serve as the basis for medical image quality monitoring devices to automatically perform quality control and directly output quality control results indicating whether the requirements are met. Attached Figure Description

[0051] Figure 1 This is a schematic diagram illustrating the application scenario of the medical image quality monitoring method of this application;

[0052] Figure 2 This is a flowchart of a medical image quality monitoring method according to an embodiment of this application;

[0053] Figure 3 This is a tag information diagram of a DICOM file in a medical image quality monitoring method according to an embodiment of this application;

[0054] Figure 4It is an image slice image corresponding to the target CT quality parameters identified in a medical image quality monitoring method according to an embodiment of this application;

[0055] Figure 5 This is a flowchart of a medical image quality monitoring method according to an embodiment of this application;

[0056] Figures 6 to 8 This is a UI diagram illustrating the generation of a quality monitoring report in scenario 1 of a medical image quality monitoring method according to an embodiment of this application.

[0057] Figure 9 This is a flowchart of a medical image quality monitoring method according to an embodiment of this application;

[0058] Figure 10 This is a UI diagram illustrating the generation of a quality monitoring report in scenario 2 of a medical image quality monitoring method according to an embodiment of this application.

[0059] Figure 11 This is a flowchart of a medical image quality monitoring method according to an embodiment of this application;

[0060] Figure 12 This is a UI diagram illustrating the generation of quality monitoring results in scenario 3 of a medical image quality monitoring method according to an embodiment of this application.

[0061] Figure 13 This is a flowchart of a medical image quality monitoring method according to an embodiment of this application;

[0062] Figure 14 This is a UI diagram illustrating the generation of quality monitoring results in scenario 4 of a medical image quality monitoring method according to an embodiment of this application.

[0063] Figure 15 This is a schematic diagram of the principle framework of a medical image quality monitoring method according to an embodiment of this application;

[0064] Figure 16 A block diagram of a medical image quality monitoring device according to an embodiment of this application;

[0065] Figure 17 This is a hardware structure diagram of an electronic device according to an embodiment of this application. Detailed Implementation

[0066] The present application will now be described in detail with reference to the embodiments shown in the accompanying drawings. However, these embodiments do not limit the present application, and any structural, methodological, or functional modifications made by those skilled in the art based on these embodiments are included within the protection scope of the present application.

[0067] In the description and claims of this application and the above-mentioned drawings, terms such as "first", "second", "third", "fourth", etc. (if any) are used to distinguish similar objects and do not necessarily describe a specific order or sequence. It should be understood that the data used in this way can be interchanged under appropriate circumstances, so that the embodiments of this application described here can be implemented in an order other than those illustrated or described here. In addition, the terms "comprising" and "corresponding to" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product or device that includes a series of steps or units does not necessarily have to be limited to those steps or units clearly listed, but may include other steps or units not clearly listed or inherent to these processes, methods, products or devices.

[0068] Refer Figure 1 , in a typical system architecture to which this application is applied, it may include a server and a terminal. A user can use the terminal to interact with the server to receive or send messages, etc. The medical image quality monitoring method disclosed in this application can be executed by the server. Correspondingly, the medical image quality monitoring device disclosed in this application can be set in the server.

[0069] The user can send a quality control instruction to the server through the terminal. After receiving the quality control instruction, the server executes the corresponding medical image quality monitoring method and generates a quality monitoring report. The user's quality control instruction can be input based on clinical quality guidelines. The server can also, for example, output a quality monitoring report in a suitable form according to the requirements of different clinical quality guidelines received and display it through the terminal.

[0070] Of course, in some system architectures, the medical image quality monitoring method disclosed in this application can also be executed by a server cluster capable of communicating with the terminal device. Correspondingly, the medical image quality monitoring device disclosed in this application can be set in the server cluster.

[0071] In a system architecture where the terminal can provide matching computing power, the medical image quality monitoring method disclosed in this application can also be directly executed by the terminal. Correspondingly, the medical image quality monitoring device disclosed in this application can be set in the terminal.

[0072] Refer Figure 2 , an embodiment of the medical image quality monitoring method of this application is introduced. In this embodiment, the method includes:

[0073] S11. Obtain a sequence of visit images.

[0074] The medical image quality monitoring method of this application can be for an image sequence at the visit level. The "sequence of visit images" refers to all the image sequences collected for a subject during a single visit image collection.

[0075] Specifically, after a participant joins a clinical trial for a particular drug, they need to visit the trial site periodically or as required by the trial to communicate with doctors (or nurses, social workers, or other researchers) so that their health can be monitored. A "visit" can be understood as a participant visiting the trial site once during the course of taking a new drug or receiving a new treatment plan. During each visit, the participant needs to undergo some medical examinations (such as medical imaging) or laboratory tests (such as complete blood count and urinalysis), and will also be examined and questioned by a doctor to receive further guidance.

[0076] During the above visits, the image collection plan is determined in advance, and all image collection and scanning are completed based on this plan. Typically, the first image collection and scanning may correspond to the "baseline visit." At certain intervals after medication, such as four weeks or six weeks later, images can be acquired again using the same image collection plan as at the baseline visit. This repeated collection of images for a specific period of time, tailored to specific needs and for the same patient, is called a visit image sequence.

[0077] According to the image collection protocol, subjects can be examined using various techniques such as CT (Computed Tomography) and MRI (Magnetic Resonance Imaging), and corresponding medical image sequences can be generated.

[0078] In this embodiment, the visit image sequence can be saved as DICOM images (i.e., DICOM files). DICOM files are saved as follows: one medical image from a CT scan sequence is saved as one DICOM file. If an image series is acquired, such as a brain image series or a whole-body image series, it will be saved as a corresponding number of DICOM files. Here, one DICOM file refers to a single file (e.g., a file with the *.dcm extension). Each DICOM file's image data corresponds to an image slice within the medical image sequence, and multiple image sequences can correspond to one study.

[0079] From the perspective of image storage hierarchy, a visit can include multiple studies (1-M), each study can include multiple series (1-N), and each series can include multiple specific DICOM images. In this embodiment, the determination of valid scan areas, scan periods, etc., can be based on the DICOM images contained at the series level.

[0080] Correspondingly, in this embodiment, after receiving the accessed image sequence, it can be parsed into study-level and series-level images based on the DICOM standard protocol. Exemplarily, the parsing can be based on libraries in computer languages ​​such as JAVA or PYTHON used for parsing the DICOM standard.

[0081] S12. Identify the target CT quality parameters of the visit image sequence.

[0082] Table ① illustrates some target CT quality parameters and their corresponding classifications.

[0083] Table ①

[0084]

[0085]

[0086] The following is an illustrative demonstration of the process for identifying the aforementioned target CT quality parameters.

[0087] ① Scan type identification

[0088] In this embodiment, the identification of the aforementioned target CT quality parameters can be based on DICOM images decomposed to the series level. Taking the DICOM 3.0 standard as an example, the information carried in each medical image can be specifically divided into the following four categories: Patient, Study, Series, and Image.

[0089] The Patient information includes the patient's basic information (such as name, gender, age, etc.) and the examination study specified by the doctor; the Study information includes the examination type (such as computed tomography (CT), magnetic resonance imaging (MR), ultrasound examination, etc.) and the series of specified examinations; the Series information includes the technical conditions of the examination (such as mA, field of view (FOV), slice thickness, etc.) and the image.

[0090] A typical sequence in a CT image examination includes Group (label group), Element (element value), Title (label description), and Value (specific value). (See reference...) Figure 3 In this embodiment, for example, the value of element 0060 in the 0008 tag group (i.e., the information corresponding to the [0x0008, 0x0060] position in the standard) can be read from the Series being examined to determine the scan type (modality) information of the CT scan sequence. Exemplarily, the value of each element in the DICOM file can be read using the PYDICOM library in the Python program.

[0091] ②Identification of CT cross-sectional orientation

[0092] After identifying the scan type of each image slice in the CT scan sequence, the cross-sectional orientation of each image slice in the CT scan sequence can be further calculated to filter out the cross-sectional image slices.

[0093] Similarly, the image orientation information (ImageOrientation(Patient)) of each image slice in a medical image sequence can be read. This image orientation information includes a first spatial vector and a second spatial vector. The image orientation information typically corresponds to six numbers, where the first three correspond to the first spatial vector and the last three correspond to the second spatial vector.

[0094] Image orientation values ​​can be viewed as a six-element array, representing the endpoint coordinates per unit length along the i and j axes (patient coordinate system) of the current image plane in the world coordinate system; that is, the cosines of the angles between the i and j axes of the current image plane and the x, y, and z axes of the world coordinate system. Typically, the image plane here has its origin (0,0) at the top left corner on the i and j axes, with the positive direction of the i axis to the right and the positive direction of the j axis downwards.

[0095] Coordination Figure 3 The image orientation values ​​of an image slice are 0.995038 / -0.06089 / 0.078694 / 0.05828 / 0.997685 / 0.035051. Therefore, the first spatial vector is (0.995038, -0.06089, 0.078694), and the second spatial vector is (0.05828, 0.997685, 0.035051).

[0096] The first and second spatial vectors are then cross-producted to obtain the third spatial vector. Based on the magnitudes of the vector components in the third spatial vector, the planar information of each image slice is determined.

[0097] Specifically, the plane information of the image slice can be determined according to the absolute value of the vector components in the third spatial vector. For example, if the third spatial vector is (k1, k2, k3), among its three vector components, the largest absolute value of k1 represents the sagittal plane of the image slice, the largest absolute value of k2 represents the coronal plane of the image slice, and the largest absolute value of k3 represents the transverse plane of the image slice.

[0098] Taking the first spatial vector as (0.995038, -0.06089, 0.078694) and the second spatial vector as (0.05828, 0.997685, 0.035051) as an example, the third spatial vector after cross multiplication is (-0.080646, -0.03029, 0.996283). It can be seen that this image slice is in the transverse plane, and the transverse plane information can be marked for this image slice.

[0099] ③ Identification of image identification (external marking, externally added text, metal artifacts) and VR image slices

[0100] Ref. Figure 4 , for cross-sectional image slices, the gray value range of normal tissues is around -1000 to 900. The gray values of metals and external identifications are higher than this gray value range of normal tissues. By setting a reasonable gray value threshold, external markings and metal artifacts in cross-sectional images can be identified. At the same time, by performing projection on the image and analyzing through similarity algorithms, it can be determined whether the image is a report-type image (dose report image).

[0101] VR image slices are color three-dimensional images obtained by color rendering from the original sliced images in CT scan image slices. From the perspective of computer storage, a color three-dimensional image requires three channels of R, G, and B, while a conventional image slice only requires a gray value channel. Therefore, it can be determined whether it is a VR image slice by detecting the number of image channels of the cross-sectional image slice.

[0102] In terms of the type of image slice, image slices including external markings, externally added text, metal artifacts, and motion artifacts can be classified as the type of image slices with image identification. Through the above identification steps, image slices with image identification and VR image slices in cross-sectional image slices can be filtered out, and pre-sutured image slices can be obtained.

[0103] ④ Identification of slice thickness

[0104] The slice thickness can be determined by the slice thickness in the label.

[0105] ⑤ Identification of slice interval

[0106] The interlayer spacing of an image slice can be determined by the image position (Patient) in the label. The image position is a ternary array [x, y, z] used to represent the coordinates of the origin (top left corner) of the current image coordinates in the reference coordinate system.

[0107] Continue to cooperate with the participants Figure 3 The image shows the image position of one slice as [-136.451, -131.756, 15.1147]. Based on this image position between two adjacent image slices, the spatial distance between these two points can be calculated, and this spatial distance can be considered as the interlayer spacing between the two adjacent image slices. That is:

[0108]

[0109] Here, [x1, y1, z1] and [x2, y2, z2] respectively identify the image positions corresponding to the two image slices.

[0110] ⑥ Recognition of scanning windows

[0111] The scanning window, also known as the 3D scan image reconstruction algorithm, includes common algorithms such as soft tissue reconstruction, lung reconstruction, and bone reconstruction. Among these, CT scan reconstruction algorithms are clinically significant. For example, lung or bone reconstruction algorithms help visualize high-contrast, high-resolution images of the lung lobes, enabling faster and earlier diagnosis of lung lesions. Soft tissue reconstruction algorithms offer better contrast and resolution for observing lesions in soft tissues such as blood vessels, the brain, and the liver.

[0112] Specifically, the scanning reconstruction algorithm involves setting the window width and window level. The window width refers to the range of CT values ​​displayed in the CT scan image. Within this range, tissue structures are divided into 16 gray levels from white to black according to their density. For example, if the window width is set to 100 HU, the human eye can distinguish a CT value of 100 / 16 = 6.25 HU, meaning that two tissues with a CT value difference of more than 6.25 HU can be recognized by the human eye. Therefore, the width of the window directly affects the image clarity and contrast. If a narrow window width is used, the displayed CT value range is small, each gray level represents a small CT value amplitude, and the contrast is strong, suitable for observing tissue structures with similar densities (such as brain tissue). Conversely, if a wide window width is used, the displayed CT value range is large, each gray level represents a large CT value amplitude, the image contrast is poor, but the density is uniform, suitable for observing structures with large density differences.

[0113] Window level (window center) refers to the average or central value within the window width. For example, if a CT scan image has a window width of 100 HU and a window level of 0 HU, then with the window level as the center (0 HU), the area above includes +50 HU and below includes -50 HU. All tissues within this 100 HU range can be displayed and recognized by the human eye. For ground, tissues greater than +50 HU are displayed as white, and tissues less than -50 HU are displayed as black; their density differences cannot be displayed. The human eye can only recognize CT values ​​within a ±50 HU range, and the CT value range for each grayscale level is 100 / 16 = 6.25 HU.

[0114] As mentioned above, the scanning reconstruction algorithm achieves different contrasts and resolutions for different tissues by setting different window widths and window levels.

[0115] In the identification of scanning windows, a baseline noise value can be calculated using the grayscale values ​​of air regions in the image slice, and this baseline noise value can be corrected using scanning information from the CT scan image (such as slice thickness, reconstructed field of view, scanning current, single-slice scanning time, scanning voltage, etc.). Due to the differences in noise levels corresponding to different scanning windows, the scanning window of the image slice can be finally determined by comparing a reference noise threshold with the obtained corrected noise value.

[0116] In one embodiment, the formula for calculating the corrected noise value is:

[0117]

[0118] Where Noise_corrected is the corrected noise value, Noise is the reference noise value, and slice thickness , where fov is the layer thickness, current is the reconstructed field of view, time is the single-layer scan time, and voltage is the scan voltage.

[0119] ⑦ Identification during the scanning period

[0120] Plain CT scans and enhanced CT scans are two important categories of CT examinations. Plain CT scans, also known as standard scans, refer to scans performed intravenously without the administration of iodine-containing contrast agents. Under a plain CT scan, the absorption capacity of blood vessels, soft tissues, and common organs such as the liver, kidneys, and spleen is relatively similar. According to the principles of CT imaging, these tissues or organs have similar grayscale values ​​on a plain CT scan. Therefore, if observing lesions, a plain CT scan does not provide good contrast.

[0121] Enhanced CT scans involve injecting a contrast agent (a liquid with a stronger ability to absorb X-rays than human tissue) intravenously. During the examination, the contrast agent circulates through the bloodstream, entering arteries, veins, hepatic artery, hepatic vein, renal artery, renal vein, and eventually the ureters. Because cancerous or diseased tissues have a very active blood supply, the contrast agent follows the blood circulation to reach the lesion area. Therefore, the use of contrast agents enhances the contrast of the diseased tissue, making it easier to accurately observe the location and size of the lesion on CT images.

[0122] In contrast-enhanced CT scans, the scanning phase corresponds to the period when the contrast agent reaches different parts of the body, facilitating the observation of lesions in different locations. For example, in the arterial phase of the scanning phase, the contrast agent fills the arterial system, enhancing arterial vessels and organs with rich blood supply; in the venous phase, which is later than the arterial phase, the portal vein is enhanced by the contrast agent, making it very useful for observing lesions in the liver; in the equilibrium phase, the contrast agent redistributes to the portal vein, inferior vena cava, and abdominal aorta, allowing the filling of the contrast agent to be seen in both the venous and arterial systems; in the delayed phase, the contrast agent in the blood vessels decreases, but if there are highly vascularized tissues such as tumors, the contrast agent decays more slowly, making it useful for observing these highly vascularized tissues.

[0123] Plain CT scans and enhanced CT scans are widely used in various examination scenarios. Identifying different scan phases in enhanced CT scans is crucial for selecting the appropriate timing to observe lesions in specific locations. Therefore, in the embodiments of this application, the scan phase mentioned may refer to plain and enhanced scans, different scan phases within plain and enhanced scans, or only different scan phases within enhanced scans.

[0124] In the identification of scan periods, different scan period identification methods can be applied based on different scan tissue information. For example, for the identification of CT scan sequences of the head, neck, and head and neck, the scan period can be identified directly using images of reference sites selected in the CT scan sequence; for the identification of CT scan sequences other than the head and neck, each image in the CT scan sequence can be projected into a two-dimensional tissue region image. Image information from different locations can corroborate each other and influence the judgment, providing scan period identification results with high reliability.

[0125] Exemplary, the specific identification during the scanning period can rely on a trained neural network model or other suitable machine learning models or combinations thereof.

[0126] ⑧ Identification of scanned areas

[0127] In the identification of scanned areas, each image in the CT scan sequence can be projected into a two-dimensional tissue region image. Depending on the classification of the scanned areas output, a neural network model or a modified neural network model can be used for identification.

[0128] For example, if the goal is to identify the scanned body parts "head," "neck," "chest," "abdomen," and "pelvis," a trained neural network model can receive image input and output using its built-in 5-class classifier. Of course, it's understandable that if more types of scanned body parts need to be identified, the neural network model can be modified and a corresponding number of classifiers added; this will not be elaborated upon here.

[0129] ⑨ Identification of missing slices

[0130] Slice missingness can be determined by the instance number in the label. A continuous sequence of instance numbers indicates that the image slice is not missing. For example, an instance number sequence of [1,2,3,4,5,7] indicates that the image slice of page six is ​​missing in this sequence.

[0131] In the process of identifying target CT quality parameters, the medical image slices corresponding to each CT quality parameter can be classified or labeled accordingly, so that the medical image slices corresponding to the corresponding category of CT quality parameters can be called later.

[0132] The layer thickness, interlayer spacing, scanning window, scanning period, and scanning location mentioned above can be considered as scanning information of image slices. In the embodiments of this application, the pre-stitched image slices can be further used for stitching different scanning locations to obtain a two-dimensional image that simultaneously includes multiple scanning locations, which will be described in detail in the following embodiments.

[0133] S13. Project the access image sequence into a two-dimensional image.

[0134] Two-dimensional images can include at least one of the following: head, neck, chest, abdomen, pelvis, head and neck, head and neck chest, head and neck chest and abdomen, head and neck chest and abdomen pelvis, neck and chest, neck and chest and abdomen, neck and chest and abdomen pelvis, chest and abdomen, chest and abdomen pelvis, and abdominal pelvis. Head, neck, chest, abdomen, and pelvis can be understood as single body parts, while head and neck, head and neck chest, head and neck chest and abdomen, head and neck chest and abdomen pelvis, neck and chest, neck and chest and abdomen, neck and chest and abdomen pelvis, chest and abdomen, chest and abdomen pelvis, and abdominal pelvis can be understood as composite body parts consisting of multiple body parts.

[0135] The sequence of images (e.g., pre-stitched image slices) can be projected into two-dimensional coronal and two-dimensional sagittal images. Depending on the number of body parts, the two-dimensional images can be projected onto a single body part or onto multiple body parts, which are then sutured to obtain the sutured image.

[0136] In this embodiment, two-dimensional images of different scanned regions belonging to the same scan period and scan window can be stitched together. For example, two-dimensional images of the chest, abdomen, and pelvis belonging to the same scan period and scan window can be registered and stitched together to obtain stitched two-dimensional sagittal and coronal images of the chest, abdomen, and pelvis. The stitched two-dimensional images will help determine the integrity of the scanned region.

[0137] S14. In response to quality control instructions, select target data from preprocessed data to generate a quality monitoring report.

[0138] Quality control instructions can be input by quality control personnel based on clinical imaging control guidelines. For example, a clinical imaging control guideline might require a chest soft tissue reconstruction scan and a lung reconstruction scan for a particular visit. Quality control personnel can simultaneously request both chest soft tissue reconstruction and lung reconstruction scans; if successful, the image collection for that visit meets the requirements. Accordingly, this request for image acquisition by the quality control personnel can be considered a "quality control instruction" as described above.

[0139] Of course, in some embodiments, the quality control instructions can also be pre-defined. For example, taking the clinical imaging control guidelines that require a certain visit's scan sequence to include soft tissue reconstruction scans of the chest and lung reconstruction scans as an example, this requirement of the guidelines is pre-defined as "Quality Control Instruction-A". During quality control, the quality control personnel can send this "Quality Control Instruction-A" to simultaneously trigger the acquisition of soft tissue reconstruction scans of the chest and lung reconstruction scans.

[0140] These pre-defined quality control instructions can be used by quality control personnel or other users to associate and edit requests related to various types of quality control instructions according to actual quality control needs; or, these quality control instructions can be pre-defined in medical image quality monitoring devices.

[0141] The following examples of quality control in various scenarios will be used to illustrate this step in detail.

[0142] Scene 1

[0143] S21. In response to quality control instructions, target data is selected from target CT quality parameters and two-dimensional images and assembled into a data table.

[0144] S22. Output a quality control display interface including a data table, wherein the quality control display interface includes a two-dimensional image call-up control.

[0145] S23. In response to the display operation of the two-dimensional image call-up control, output the corresponding two-dimensional image to the quality control display interface.

[0146] Coordination Figure 5 and Figure 6 , in this scenario, the quality control instruction requires the output of some required target CT quality parameters and the corresponding two-dimensional images. When receiving the quality control instruction, the corresponding target data is screened from the target CT quality parameters and two-dimensional images identified and processed in the above steps, and assembled in the form of a data table.

[0147] In a schematic quality control display interface A1, it includes target CT quality parameters such as scan type, section direction, scan window, metal artifacts, etc., and two-dimensional images. These target data are assembled in a data table S1. The two-dimensional images can be in a default state of not being called out initially, and each row of data in the data table can correspond to a two-dimensional image call-out control B1 for the corresponding two-dimensional image.

[0148] When the quality control personnel need to view the two-dimensional image corresponding to a certain row of data in the data table, they can perform a display operation on the two-dimensional image call-out control B1 of that row, and then the two-dimensional image is called out to the quality control display interface. The quality control personnel can perform quality control on the medical image sequence by combining the two-dimensional image and the CT quality parameters of the corresponding row.

[0149] Refer Figure 7 , when the quality control personnel perform quality control by combining the two-dimensional image, they may find that some of the target CT quality parameters in the quality control display interface A1 are misidentified. For example, after the quality control personnel open some visit images, they find that the scanned part identified in a certain row of the data table is misidentified. The scanned part currently shown as "thorax, neck, abdomen, pelvis" should be "abdomen, pelvis".

[0150] In this scenario, the quality control display interface A1 can also include a quality parameter input control B2, and the quality control personnel can perform an input operation on the quality parameter input control B2. For example, modify the "thorax" in this row of the data table S1 in the quality control display interface A1 to "abdomen, pelvis". In response to the input operation on the quality parameter input control, the data table in the quality control display interface can be updated.

[0151] Among the target CT quality parameters, it includes motion artifacts, metal artifacts, external markers, externally added text, etc., which can all be regarded as having a preset type of image identifier. Correspondingly, refer Figure 8 , the quality control display interface A1 can also include an identifier image call-out control B3 corresponding to these preset type of image identifiers.

[0152] For example, if the image slice of a certain row shown in the data table S1 of the quality control display interface A1 has metal artifacts, the quality control personnel can perform a display operation on the corresponding identifier image call-out control B3. In response to the display operation on the identifier image call-out control B3, the corresponding identifier image (metal artifact image slice) is output to the quality control display interface.

[0153] As can be seen, in Scenario 1, the target CT quality parameters and images are integrated in the form of data table S1. Quality control personnel can review the contents of the data table in the quality control display interface in an intuitive way; furthermore, for some two-dimensional images, labeled images, etc., that need to be viewed for quality control, they can be brought up by operating the corresponding controls, improving quality control efficiency. At the same time, errors in CT quality parameters caused by automatic recognition can also be modified through the corresponding controls.

[0154] Scene 2

[0155] S31. In response to the quality control command, the selected two-dimensional images are annotated using at least one preset CT quality parameter;

[0156] S31. Output a quality control display interface including the labeled 2D image.

[0157] Coordination Figure 9 and Figure 10 In this scenario, the quality control instruction can also require the output to include some necessary target CT quality parameters and corresponding two-dimensional images. The difference from scenario 1 is that when the quality control instruction is received, the target CT quality parameters and the corresponding target data in the two-dimensional images identified and processed in the above steps are matched and assembled using image annotation.

[0158] In a schematic quality control display interface A2, the "neck, chest, abdomen, and hip" region is projected as a two-dimensional image. The two-dimensional image is labeled with information such as: plain scan or enhanced scan (CT contrast agent), and slice spacing or slice thickness. The types of two-dimensional images shown in quality control display interface A2 include images stitched together from two-dimensional images of different body parts, and images corresponding to different scanning windows to highlight the projection results of bones (bone windows) or soft tissues (soft tissue windows).

[0159] Based on quality control requirements, the quality control display interface A2 can also output image slices from the access image sequence to assist in determining the integrity of the scanned area. Simultaneously, the quality control display interface A2 can also include a summary data table S2 of the aforementioned quality control-related information, thereby helping quality control personnel to gain an overview of all quality control-related information.

[0160] Based on the quality control display interface A2, quality control personnel can intuitively judge, for example, the integrity of the scanned area, whether it contains artifacts and privacy information, thus improving the efficiency and reliability of quality control.

[0161] Scene 3

[0162] S41. In response to the quality control command, select two-dimensional images of the scan type that correspond to the scan type quality control information;

[0163] S42. Based on the selected two-dimensional images, determine whether the visit image sequence meets the quality control requirements.

[0164] Reference Figure 11 , in this scenario, the quality control instructions include scanning site quality control information. For example, it is required that a certain visit image sequence includes soft tissue reconstruction scan images and lung reconstruction scan images of the chest.

[0165] Correspondingly, the images of the chest can be screened from the two-dimensional images projected by the visit image sequence. If both of these two scanning techniques are included in the selected two-dimensional images, the collection of this visit image sequence meets the quality control requirements. If one or both of the scanning techniques are missing in the selected two-dimensional images, the collection of this visit image sequence does not meet the quality control requirements.

[0166] Reference Figure 12 , on the quality control display interface A3, the process of screening the two-dimensional images above may not be shown, but directly output the final quality control results, such as: "Lung reconstruction scan image missing", "Soft tissue reconstruction scan image missing", "Not missing", etc.

[0167] Scenario 4

[0168] S51. In response to the quality control instructions, screen out the coronal plane projection images and / or sagittal plane projection images of the scanning site corresponding to the scanning site quality control information;

[0169] S52. Based on the selected coronal plane projection images and / or sagittal plane projection images, determine whether the visit image sequence meets the quality control requirements.

[0170] Reference Figure 13 , in this scenario, the quality control instructions include scanning site quality control information. For example, it is required that a certain visit image sequence includes images of the chest, abdomen and pelvis under soft tissue window.

[0171] Correspondingly, the images of the soft tissue window can be screened from the two-dimensional images projected by the visit image sequence. The two-dimensional images screened here can include coronal plane projection images and / or sagittal plane projection images. If the two-dimensional images selected include the three parts of the chest, abdomen and pelvis, the collection of this visit image sequence meets the quality control requirements. If some of these parts are missing in the selected two-dimensional images, the collection of this visit image sequence does not meet the quality control requirements.

[0172] Reference Figure 14 , similarly, on the quality control display interface A4, the process of screening the two-dimensional images above may not be shown, but directly output the final quality control results, such as: "Chest soft tissue reconstruction scan image missing", "Abdomen soft tissue reconstruction scan image missing", "Pelvis soft tissue reconstruction scan image missing", "Not missing", etc.

[0173] Cooperation parameter Figure 15 As can be seen from the medical image quality monitoring method of the embodiments of the present application demonstrated in the above Scenarios 1 to 4, through the cyclic input of the visit image sequence, the target CT quality parameters in the visit image sequence can be obtained by using, for example, an AI detection module, and the visit image sequence can be projected into a two-dimensional image. The output of the AI detection module can be used as the target data source of the quality monitoring report and displayed in the form of a UI to assist quality control personnel in quality control. Moreover, according to the input of the clinical quality guidelines, the target data required can be automatically screened from the output of the AI detection module, and a prompt indicating whether it meets the quality control requirements can be directly output according to the screening result.

[0174] Parameter Figure 16 Figure 16 Introduce an embodiment of the medical image quality monitoring device of the present application. In this embodiment, the medical image quality monitoring device includes an acquisition module 21, an identification module 22, a projection module 23, and a generation module 24.

[0175] The acquisition module 21 is used to acquire a visit image sequence, and the visit image sequence includes multiple medical image slices; the identification module 22 is used to identify the target CT quality parameters of the visit image sequence; the projection module 23 is used to project the visit image sequence into a two-dimensional image; the generation module 24 is used to, in response to a quality control instruction, screen out target data from the preprocessed data to generate a quality monitoring report, where the preprocessed data includes one or a combination of the target CT quality parameters, the medical image slices corresponding to the target CT quality parameters, and the two-dimensional image.

[0176] In one embodiment, the generation module 24 is specifically used for: in response to a quality control instruction, screening out target data from the target CT quality parameters and the two-dimensional image and assembling them into a data table; outputting a quality control display interface including the data table, where the quality control display interface includes a two-dimensional image call-out control; in response to a display operation on the two-dimensional image call-out control, outputting the corresponding two-dimensional image to the quality control display interface.

[0177] In one embodiment, the quality control display interface further includes a quality parameter input control;

[0178] The medical image quality monitoring device further includes an update module 25, which is used to update the data table in the quality control display interface in response to an input operation on the quality parameter input control.

[0179] In one embodiment, the target CT quality parameter includes a preset type image identifier, and the quality control display interface further includes an identifier image call-out control corresponding to the preset type image identifier;

[0180] The medical image quality monitoring device also includes a display module 26, which is used to output the corresponding label image to the quality control display interface in response to the display operation of the label image call-up control.

[0181] In one embodiment, the generation module 24 is specifically used to: in response to a quality control instruction, annotate the selected two-dimensional image using at least one of the target CT quality parameters; and output a quality control display interface including the annotated two-dimensional image.

[0182] In one embodiment, the quality control instruction includes scan type quality control information, and the target CT quality parameter includes scan type;

[0183] The medical image quality monitoring device also includes a quality control module 27, which is used to respond to quality control instructions, filter out two-dimensional images of the scan type corresponding to the scan type quality control information, and determine whether the visited image sequence meets the quality control requirements based on the filtered two-dimensional images.

[0184] In one embodiment, the quality control instruction includes quality control information for the scanned area, the target CT quality parameters include the scanned area, and the two-dimensional image includes a coronal projection image and a sagittal projection image;

[0185] The quality control module 27 is further configured to respond to quality control instructions by selecting coronal projection images and / or sagittal projection images of the scanned area corresponding to the quality control information of the scanned area; and based on the selected coronal projection images and / or sagittal projection images, to determine whether the access image sequence meets the quality control requirements.

[0186] In one embodiment, the projection module 23 is further configured to stitch together two-dimensional images of different scanning regions belonging to the same scanning period and scanning window.

[0187] In one embodiment, the target CT quality parameters include at least one of scan type, scan period, scan window, slice spacing, slice thickness, cross-sectional orientation, slice missing, scan location, motion artifacts, metal artifacts, external markers, and externally added text.

[0188] In one embodiment, the identification module 22 is specifically used to: identify the scan type of the access image sequence and calculate the cross-sectional orientation of each image slice in the CT scan sequence to filter out cross-sectional image slices; identify image identifiers in the cross-sectional image slices to filter out corresponding image slices, and identify image channels of the cross-sectional image slices to filter out VR image slices, to obtain pre-stitched image slices, wherein the image identifiers include at least one of external markers, externally added text, metal artifacts, and motion artifacts; and identify the scan information of the pre-stitched image slices, wherein the scan information includes at least one of slice thickness, slice spacing, scan window, scan period, and scan location.

[0189] As referred above Figures 1 to 15 This specification describes a medical image quality monitoring method according to embodiments thereof. The details mentioned in the above description of the method embodiments also apply to the medical image quality monitoring device according to embodiments thereof. The above-described medical image quality monitoring device can be implemented in hardware, software, or a combination of hardware and software.

[0190] Figure 17 A hardware structure diagram of an electronic device according to an embodiment of this specification is shown. Figure 17 As shown, the electronic device 30 may include at least one processor 31, a memory 32 (e.g., non-volatile memory), a memory 33, and a communication interface 34, and the at least one processor 31, memory 32, memory 33, and communication interface 34 are connected together via an internal bus 35. The at least one processor 31 executes at least one computer-readable instruction stored or encoded in the memory 32.

[0191] It should be understood that the computer-executable instructions stored in memory 32, when executed, cause at least one processor 31 to perform the above-described combinations in the various embodiments of this specification. Figures 1 to 15 The description includes various operations and functions.

[0192] In the embodiments of this specification, electronic device 30 may include, but is not limited to: personal computer, server computer, workstation, desktop computer, laptop computer, notebook computer, mobile electronic device, smartphone, tablet computer, cellular phone, personal digital assistant (PDA), handheld device, messaging device, wearable electronic device, consumer electronic device, etc.

[0193] According to one embodiment, a program product, such as a machine-readable medium, is provided. The machine-readable medium may have instructions (i.e., the elements implemented in software as described above), which, when executed by a machine, cause the machine to perform the above-described combinations of the various embodiments of this specification. Figures 1-15 The various operations and functions described. Specifically, a system or apparatus equipped with a readable storage medium storing software program code that implements the functions of any of the embodiments described above, and enabling the computer or processor of the system or apparatus to read and execute the instructions stored in the readable storage medium.

[0194] In this case, the program code read from the readable medium itself can perform the functions of any of the above embodiments, and therefore the machine-readable code and the readable storage medium storing the machine-readable code constitute a part of this specification.

[0195] Examples of readable storage media include floppy disks, hard disks, magneto-optical disks, optical disks (such as CD-ROM, CD-R, CD-RW, DVD-ROM, DVD-RAM, DVD-RW, DVD-RW), magnetic tapes, non-volatile memory cards, and ROMs. Alternatively, program code can be downloaded from a server computer or the cloud via a communication network.

[0196] Those skilled in the art will understand that the various embodiments disclosed above can be modified and varied without departing from the spirit of the invention. Therefore, the scope of protection of this specification should be defined by the appended claims.

[0197] It should be noted that not all steps and units in the above process and system structure diagrams are mandatory; some steps or units can be omitted according to actual needs. The execution order of each step is not fixed and can be determined as needed. The device structure described in the above embodiments can be a physical structure or a logical structure. That is, some units may be implemented by the same physical client, or some units may be implemented by multiple physical clients, or they may be jointly implemented by certain components in multiple independent devices.

[0198] In the above embodiments, the hardware units or modules can be implemented mechanically or electrically. For example, a hardware unit, module, or processor may include permanent dedicated circuitry or logic (such as a dedicated processor, FPGA, or ASIC) to perform the corresponding operation. The hardware unit or processor may also include programmable logic or circuitry (such as a general-purpose processor or other programmable processor), which can be temporarily configured by software to perform the corresponding operation. The specific implementation method (mechanical, dedicated permanent circuitry, or temporarily configured circuitry) can be determined based on cost and time considerations.

[0199] The specific embodiments described above with reference to the accompanying drawings are exemplary embodiments, but do not represent all embodiments that can be implemented or fall within the scope of the claims. The term "exemplary" as used throughout this specification means "serving as an example, instance, or illustration" and does not imply that it is "preferred" or "advantageous" compared to other embodiments. Specific details are included to provide an understanding of the described techniques. However, these techniques can be practiced without these specific details. In some instances, well-known structures and apparatuses are shown in block diagram form to avoid obscuring the concepts of the described embodiments.

[0200] The foregoing description of this disclosure is provided to enable any person skilled in the art to implement or use this disclosure. Various modifications to this disclosure will be apparent to those skilled in the art, and the general principles applicable herein can be applied to other variations without departing from the scope of this disclosure. Therefore, this disclosure is not limited to the examples and designs described herein, but is consistent with the widest scope of the principles and novel features disclosed herein.

Claims

1. A method for monitoring the quality of medical images, characterized in that, The method includes: Obtain a sequence of medical images, which includes multiple slices of medical images; Identify the target CT quality parameters of the visited image sequence; The access image sequence is projected into a two-dimensional image, and two-dimensional images of different scan sites belonging to the same scan period and scan window are stitched together; In response to a quality control instruction, target data is selected from the preprocessed data to generate a quality monitoring report. The preprocessed data includes one or a combination of the target CT quality parameters, medical image slices corresponding to the target CT quality parameters, and two-dimensional images.

2. The medical image quality monitoring method according to claim 1, characterized in that, In response to quality control instructions, target data is selected from preprocessed data to generate a quality monitoring report, specifically including: In response to quality control instructions, target data is filtered from the target CT quality parameters and two-dimensional images and assembled into a data table; The output includes a quality control display interface for the data table, wherein the quality control display interface includes a two-dimensional image call-up control; In response to the display operation of the two-dimensional image call-up control, the corresponding two-dimensional image is output to the quality control display interface.

3. The medical image quality monitoring method according to claim 2, characterized in that, The quality control display interface also includes quality parameter input controls; The method further includes: In response to an input operation to the quality parameter input control, the data table in the quality control display interface is updated.

4. The medical image quality monitoring method according to claim 2, characterized in that, The target CT quality parameters include preset type image identifiers, and the quality control display interface also includes an identifier image call-up control corresponding to the preset type image identifiers; The method further includes: In response to the display operation of the control that brings up the identification image, the corresponding identification image is output to the quality control display interface.

5. The medical image quality monitoring method according to claim 1, characterized in that, In response to quality control instructions, target data is selected from preprocessed data to generate a quality monitoring report, specifically including: In response to quality control instructions, the selected two-dimensional images are labeled using at least one of the target CT quality parameters; The output includes a quality control display interface for the annotated two-dimensional image.

6. The medical image quality monitoring method according to claim 1, characterized in that, The quality control instructions include scan type quality control information, and the target CT quality parameters include scan type; The method further includes: In response to quality control instructions, two-dimensional images of the scan type corresponding to the scan type quality control information are selected; Based on the selected two-dimensional images, determine whether the visited image sequence meets the quality control requirements.

7. The medical image quality monitoring method according to claim 1, characterized in that, The quality control instructions include quality control information for the scanned area, the target CT quality parameters include the scanned area, and the two-dimensional images include coronal projection images and sagittal projection images; The method further includes: In response to the quality control command, the coronal projection image and / or sagittal projection image of the scanned part corresponding to the quality control information of the scanned part are selected. Based on the selected coronal and / or sagittal projection images, determine whether the visited image sequence meets the quality control requirements.

8. The medical image quality monitoring method according to claim 1, characterized in that, The target CT quality parameters include at least one of the following: scan type, scan period, scan window, slice spacing, slice thickness, cross-sectional direction, slice missing, scan location, motion artifacts, metal artifacts, external markers, and externally added text.

9. The medical image quality monitoring method according to claim 8, characterized in that, Identifying the target CT quality parameters of the visited image sequence specifically includes: Identify the scan type of the visited image sequence and calculate the cross-sectional orientation of each image slice in the CT scan sequence to filter out cross-sectional image slices. The image identifiers in the cross-sectional image slices are identified to filter out the corresponding image slices, and the image channels of the cross-sectional image slices are identified to filter out VR image slices, resulting in pre-stitched image slices. The image identifiers include at least one of external markers, externally added text, metal artifacts, and motion artifacts. Identify the scanning information of the pre-stitched image slice, wherein the scanning information includes at least one of layer thickness, interlayer spacing, scanning window, scanning period, and scanning location.

10. A medical image quality monitoring device, characterized in that, include: The acquisition module is used to acquire a sequence of medical images, which includes multiple medical image slices. The identification module is used to identify the target CT quality parameters of the visited image sequence; The projection module is used to project the access image sequence into a two-dimensional image and stitch together two-dimensional images of different scan parts belonging to the same scan period and scan window; The generation module is used to filter target data from preprocessed data in response to quality control instructions to generate a quality monitoring report. The preprocessed data includes one or a combination of the target CT quality parameters, medical image slices corresponding to the target CT quality parameters, and two-dimensional images.

11. An electronic device, comprising: At least one processor; as well as A memory that stores instructions, which, when executed by the at least one processor, cause the at least one processor to perform the medical image quality monitoring method as described in any one of claims 1 to 9.

12. A machine-readable storage medium storing executable instructions that, when executed, cause the machine to perform the medical image quality monitoring method as claimed in any one of claims 1 to 9.

Images