Medical image processing system

Abstract

The application relates to a medical image processing system. The system comprises a medical imaging device and a report generation device; the medical imaging device is used for collecting a first image and a second image of a target part, and transmitting the first image and the second image to the report generation device; the first image is used for describing a part structure of the target part, and the second image is used for describing a part condition of the target part; the report generation device is used for identifying a first region of interest on the first image, and performing registration on the first image and the second image to obtain a second region of interest on the second image; the second region of interest on the second image is associated with the first region of interest on the first image; and the report generation device is further used for generating text report data of the target part according to part condition information corresponding to the second region of interest on the second image. The method can simplify medical image processing.

Description

Technical Field

[0001] This application relates to the field of computer technology, and in particular to a medical image processing system. Background Technology

[0002] With the development of magnetic resonance imaging (MRI) technology, MRI scans of the liver can not only obtain qualitative images, providing rich contrast information on the liver's anatomical structure to facilitate lesion identification, but also obtain multidimensional quantitative images, providing multidimensional diagnostic information for liver diseases.

[0003] Currently, for lesion regions in qualitative and quantitative images, the method involves manually outlining the region of interest for each image, processing the region of interest, and then generating text report data for each image. This method of generating text report data is cumbersome, and the diagnostic information is scattered, making it inconvenient to use multidimensional diagnostic information for disease diagnosis.

[0004] Therefore, existing medical image processing technologies suffer from cumbersome operation. Summary of the Invention

[0005] Therefore, it is necessary to provide a medical image processing system, method, computer device, computer-readable storage medium, and computer program product that is easy to operate, in response to the above-mentioned technical problems.

[0006] In a first aspect, this application provides a medical image processing system. The system includes a medical imaging device and a report generation device;

[0007] The medical imaging device is used to acquire a first image and a second image of the target area, and send the first image and the second image to the report generation device; the first image is used to describe the structure of the target area, and the second image is used to describe the condition of the target area.

[0008] The report generation device is used to identify a first region of interest on the first image and register the first image and the second image to obtain a second region of interest on the second image; the second region of interest on the second image is associated with the first region of interest on the first image.

[0009] The report generation device is further configured to generate text report data for the target location based on the location status information corresponding to the second region of interest on the second image.

[0010] In one embodiment, the report generation device is further configured to register the first image and the second image to obtain a mapping relationship between the first image and the second image; and to determine, based on the mapping relationship, an image region on the second image associated with the first region of interest as the second region of interest.

[0011] In one embodiment, the report generating device is further configured to: determine first location information of the first region of interest on the first image; determine second location information of the second image associated with the first location information according to the mapping relationship; and determine the second region of interest on the second image according to the second location information.

[0012] In one embodiment, the second image is at least one, and the second image has at least one second region of interest. Each second image is used to describe the condition of the target part in different dimensions. The report generation device is further used to generate text report data of the target part based on the first image, each second image, and the condition information corresponding to each second region of interest.

[0013] In one embodiment, the report generating device is further configured to acquire information reference values ​​corresponding to the location condition information; generate an information anomaly identifier if the location condition information does not conform to the information reference values; and generate the text report data based on the first image, each of the second images, each of the location condition information, each of the information reference values, and the information anomaly identifier.

[0014] In one embodiment, the report generating device is further configured to display a second image display window in response to a trigger operation on the target location condition information in the text report data, the second image display window displaying a target second image corresponding to the target location condition information.

[0015] In one embodiment, the report generating device is further configured to, in response to a region selection operation on the target second image in the second image display window, determine a third region of interest on the target second image; determine a fourth region of interest associated with the third region of interest on each of the second images other than the target second image; and update the text report data according to the location status information corresponding to the third region of interest and the location status information corresponding to the fourth region of interest.

[0016] In one embodiment, the report generating device is further configured to, in response to a first triggering operation on a second image in the text report data, display an enlarged second image in the text report data; and, in response to a second triggering operation on the enlarged second image, reduce the size of the enlarged second image.

[0017] In one embodiment, the report generating device is further configured to delete the part status information corresponding to the target second region of interest in the text report data in response to a region deletion operation on the target second region of interest in the second image in the text report data.

[0018] In one embodiment, the report generation device is further configured to determine a region recognition model corresponding to the target part; input the first image into the region recognition model corresponding to the target part to obtain a first region of interest on the first image.

[0019] Secondly, this application provides a medical image processing method. The method includes:

[0020] Acquire a first image and a second image of the target area using a medical imaging device; the first image is used to describe the structure of the target area, and the second image is used to describe the condition of the target area.

[0021] Identify the first region of interest in the first image;

[0022] The first image and the second image are registered to obtain a second region of interest on the second image; the second region of interest on the second image is associated with the first region of interest on the first image.

[0023] Based on the location information corresponding to the second region of interest in the second image, a text report data of the target location is generated.

[0024] Thirdly, this application also provides a computer device. The computer device includes a memory and a processor, the memory storing a computer program, and the processor executing the computer program to perform the following steps:

[0025] Acquire a first image and a second image of the target area using a medical imaging device; the first image is used to describe the structure of the target area, and the second image is used to describe the condition of the target area.

[0026] Identify the first region of interest in the first image;

[0027] The first image and the second image are registered to obtain a second region of interest on the second image; the second region of interest on the second image is associated with the first region of interest on the first image.

[0028] Based on the location information corresponding to the second region of interest in the second image, a text report data of the target location is generated.

[0029] Fourthly, this application also provides a computer-readable storage medium. The computer-readable storage medium stores a computer program thereon, which, when executed by a processor, performs the following steps:

[0030] Acquire a first image and a second image of the target area using a medical imaging device; the first image is used to describe the structure of the target area, and the second image is used to describe the condition of the target area.

[0031] Identify the first region of interest in the first image;

[0032] The first image and the second image are registered to obtain a second region of interest on the second image; the second region of interest on the second image is associated with the first region of interest on the first image.

[0033] Based on the location information corresponding to the second region of interest in the second image, a text report data of the target location is generated.

[0034] Fifthly, this application also provides a computer program product. The computer program product includes a computer program that, when executed by a processor, performs the following steps:

[0035] Acquire a first image and a second image of the target area using a medical imaging device; the first image is used to describe the structure of the target area, and the second image is used to describe the condition of the target area.

[0036] Identify the first region of interest in the first image;

[0037] The first image and the second image are registered to obtain a second region of interest on the second image; the second region of interest on the second image is associated with the first region of interest on the first image.

[0038] Based on the location information corresponding to the second region of interest in the second image, a text report data of the target location is generated.

[0039] The aforementioned medical image processing system, method, computer equipment, storage medium, and computer program product acquire a first image and a second image of a target area using a medical imaging device, and send the first and second images to a report generation device. The report generation device identifies a first region of interest (ROI) on the first image, registers the second image to the first image, determines a second ROI on the second image, and generates text report data for the target area based on the site condition information corresponding to the second ROI on the second image. This allows for the synchronous updating of the ROI to the second image through image registration, reducing the complexity of obtaining the second ROI on the second image and simplifying medical image processing for the second ROI on the second image, while facilitating the identification of the first ROI from the first image. Attached Figure Description

[0040] Figure 1 This is a block diagram of a medical image processing system in one embodiment;

[0041] Figure 2 This is a schematic diagram of the application environment of medical image processing in one embodiment;

[0042] Figure 3 This is a schematic diagram of the process for generating comprehensive liver text report data in one embodiment;

[0043] Figure 4 This is a schematic diagram of qualitative and quantitative images in one embodiment;

[0044] Figure 5 This is a schematic diagram of comprehensive liver text report data in one embodiment;

[0045] Figure 6 This is a schematic diagram of a quantitative image magnification in one embodiment;

[0046] Figure 7 This is a schematic diagram illustrating the synchronous update of the region of interest in one embodiment;

[0047] Figure 8 This is a flowchart illustrating a medical image processing method in one embodiment;

[0048] Figure 9 This is an internal structural diagram of a computer device in one embodiment. Detailed Implementation

[0049] 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.

[0050] In one embodiment, such as Figure 1 As shown, a medical image processing system is provided, which may include a medical imaging device 102 and a report generation device 104. The medical imaging device 102 may be, but is not limited to, various magnetic resonance imaging (MRI) devices, positron emission tomography (PET) devices, and combined PET-MR devices. The report generation device 104 may be, but is not limited to, various personal computers, laptops, smartphones, tablets, IoT devices, and portable wearable devices. IoT devices may include smart speakers, smart TVs, smart air conditioners, smart in-vehicle devices, etc., and portable wearable devices may include smartwatches, smart bracelets, head-mounted devices, etc.

[0051] The medical imaging device 102 is used to acquire and generate a first image and a second image of the target area, and send the first image and the second image to the report generation device 104; the first image is used to describe the structure of the target area, and the second image is used to describe the condition of the target area.

[0052] The report generation device 104 is used to identify a first region of interest on a first image and to register the first image and the second image to obtain a second region of interest on the second image; the second region of interest on the second image is associated with the first region of interest on the first image.

[0053] The report generation device 104 is also used to generate text report data of the target part based on the part condition information corresponding to the second region of interest on the second image.

[0054] The target site can be any part of the human body that is to be diagnosed.

[0055] The first image can be a qualitative image, i.e., a structural image, used to describe the anatomical structure of the part of the human body to be diagnosed. The first image can be a longitudinal relaxation time contrast (T1 contrast) image, a transverse relaxation time contrast (T2 contrast) image, or a diffusion-weighted imaging (DWI) image acquired by MRI equipment.

[0056] The second image can be a quantitative image used to describe the physiological condition of the area to be diagnosed in the human body. The second image can be a fat quantitative analysis and calculation technology (FACT) image, a susceptibility weighted imaging (SWI) image, a spin lattice relaxation time (T1ρ) image, a relaxation time mapping (T1 / T2 / T2*Mapping) image, a magnetic resonance elastography (MRE) image, or a fluid attenuated inversion recovery (FLAIR) image acquired by an MRI device. The second image can also be a PET image acquired by a PET or PET-MR device.

[0057] During FACT image acquisition, an R2* parameter map is generated simultaneously. For example, during FACT quantitative image scanning, multiple parameters are output, including water map, fat map, in-phase (IP) image, out-of-phase (OP) image, and fat fraction (FF) map.

[0058] The first and second images differ in the quantitative parameters, structural parameters, or contrast of the same tissue at the target site. Taking magnetic resonance imaging (MRI) as an example, the first and second images can be obtained by exciting the target site using different imaging sequences. For instance, if the target site is cerebrospinal fluid in the brain, the first image uses a T1WI (T1-weighted imaging) sequence, and the second image uses a T2WI (T2-weighted imaging) sequence. The corresponding cerebrospinal fluid region appears as a high signal in the second image and a low signal in the first image. As another example, the first image might be a DWI image obtained using a diffusion-weighted imaging (DWI) sequence, while the second image is an apparent diffusion coefficient (ADC) map created by mathematically removing the T2 effect from the DWI image. By comparing the DWI image and the ADC map, it's possible to determine whether diffusion is restricted. Furthermore, combining the ADC map can identify T2 penetration, T2 clearing, and T2 darkening effects observed on the DWI image.

[0059] Among them, the first region of interest and the second region of interest can be the lesion area of ​​the human body to be diagnosed.

[0060] Among them, the location status information can be the measured values ​​of physiological indicators of the lesion area, such as the degree of iron deposition, fat content, or SUV value (Standard Uptake Value) in the liver lesion area.

[0061] The text report data can be a readable text report, a text report with accompanying digital images, or a text report with accompanying information such as subsequent medical treatment or examination recommendations.

[0062] In practice, medical imaging equipment can acquire qualitative and quantitative images of the body site to be diagnosed, and send both images to a report generation device. Upon receiving the qualitative and quantitative images, the report generation device can intelligently identify lesion regions from the qualitative images, designating these lesion regions as the first region of interest (ROI). The report generation device can also register the qualitative and quantitative images, establishing a mapping relationship between the pixel coordinates of the qualitative and quantitative images. Based on this mapping, a second region of interest corresponding to the first ROI is determined on the quantitative image. This second ROI may correspond to the same lesion region as the first ROI. Furthermore, the report generation device can acquire measurements of human physiological indicators from the second ROI on the quantitative image and generate a comprehensive text report of the body site to be diagnosed based on these measurements.

[0063] Figure 2 A schematic diagram of an application environment for medical image processing is provided, in which medical imaging device 102 communicates with report generation device 104 via a wired or wireless link. Figure 3 A flowchart illustrating the generation process of comprehensive liver text report data is provided, based on... Figure 3 The generation of comprehensive liver text report data may include the following steps:

[0064] Step S210: Based on the patient's condition, plan a scanning protocol for the patient. The scanning protocol may include a structural qualitative protocol and a quantitative protocol. The structural qualitative protocol may include scanning protocols for images such as T1 contrast, T2 contrast, and DWI, while the quantitative protocol may include scanning protocols for images such as FACT FF (FF), FACT R2* (R2*), SWI, T1ρ, Mapping (T1 / T2 / T2*), MRE, and FLAIR.

[0065] Step S220 involves synchronously updating the regions of interest (ROIs) identified from the qualitative images onto the multidimensional quantitative images. Specifically, according to the planned scanning protocol, one qualitative image and multiple quantitative images of the patient's liver can be acquired. Lesion regions are intelligently identified from the qualitative images, and these identified lesion regions are designated as ROIs. The qualitative images and multiple quantitative images are then registered to establish a mapping relationship between the pixel coordinates of the qualitative images and the pixel coordinates of each quantitative image. Based on this mapping relationship, the ROIs on the qualitative images are synchronized onto each quantitative image, resulting in the ROIs on each quantitative image.

[0066] Step S230: Generate comprehensive liver text report data based on the regions of interest (ROIs) on the quantitative images. Specifically, the ROIs on each quantitative image can correspond to the same lesion area. Measurement values ​​of the ROIs on each quantitative image are obtained. Different measurement values ​​can reflect different physiological indicators of the same lesion area. Integrating these measurement values ​​into a single text report data can generate comprehensive liver text report data. The comprehensive text report data can display both qualitative and quantitative images. If the user is not satisfied with the current results displayed in the text report data, they can manually select new ROIs from the qualitative or quantitative images displayed in the text report data. The measurement values ​​corresponding to the new ROIs can be synchronously updated in the text report data.

[0067] Figure 4 A schematic diagram of qualitative and quantitative images is provided. According to... Figure 4 Qualitative images can be T2-contrast images, while quantitative images can be FF, R2*, SWI, etc. A lesion region A can be intelligently identified from the T2-contrast image as a region of interest (ROI). Multidimensional registration is then performed on the qualitative and quantitative images, and the ROI is simultaneously applied to the quantitative image, resulting in ROIs A1, A2, and A3 on the FF, R2*, and SWI images, respectively. A, A1, A2, and A3 can correspond to the same lesion region of interest, and each qualitative or quantitative image can contain multiple ROIs.

[0068] Figure 5 A schematic diagram of comprehensive liver text report data is provided. According to... Figure 5This system can acquire measurement values ​​of regions of interest (ROIs) on various quantitative images and integrate these values ​​into a single text report, generating a comprehensive text report of liver data. The comprehensive text report displays qualitative images, quantitative images, measurement values ​​of ROIs within each quantitative image, and the corresponding standard values ​​for each measurement. It also shows comparisons between measured values ​​and standard values. If a measured value does not match the standard value, it is displayed in red. If the measured value is larger than the standard value, a "larger" flag is added; if the measured value is smaller than the standard value, a "smaller" flag is added. For example... Figure 5 In the diagram, ↑ indicates that the measured value is larger than the standard value, and ↓ indicates that the measured value is smaller than the standard value. In the comprehensive text report data, the standard value and multiple measured values ​​corresponding to the same quantitative image can be located in the same row, and multiple measured values ​​corresponding to the same lesion region of interest can be located in the same column. For example, the measured values ​​of regions of interest ROI1, ROI2, ROI3, and ROI4 in the FF image, as well as the standard value of FF, can be located in the same row, and the measured values ​​of region of interest ROI1 in the FF, R2*, SWI, T1 / T2 / T2*Mapping, and T1ρ images can be located in the same column.

[0069] Figure 6 A schematic diagram of a quantitative image magnification is provided. According to... Figure 6 This can trigger a qualitative or quantitative image in the comprehensive text report data, magnifying it and restoring it to its original state upon re-triggering. For example, double-clicking the FF image in the comprehensive text report data will produce a magnified FF image. Figure 6 As shown, double-clicking the enlarged FF image again will shrink it back to its original size, restoring the data from the integrated text report.

[0070] Figure 7 A schematic diagram illustrating the synchronous updates of the region of interest is provided. According to... Figure 7This process can trigger any measurement value in the comprehensive text report data, open the quantitative image corresponding to that measurement value, and by outlining a new region of interest (ROI) in that quantitative image, the new ROI can be synchronously updated on other quantitative images. The measurement values ​​corresponding to the new ROIs in all quantitative images are then obtained and added to the comprehensive text report data. For example, if the current text report data provides the measurement values ​​for ROI4 of four ROIs (ROI1, ROI2, ROI3), and the doctor is not satisfied with the results shown in the current text report data, they can trigger any measurement value corresponding to the FF image, open the FF image, and manually outline a new ROI5 on the opened FF image. ROI5 can then be synchronously updated on R2*, SWI, T1 / T2 / T2*Mapping, and T1ρ images, respectively. The measurement values ​​of ROI5 on the FF, R2*, SWI, T1 / T2 / T2*Mapping, and T1ρ images are then obtained, forming a new column of ROI5 measurement results, which are added to the comprehensive text report data.

[0071] The aforementioned medical image processing system acquires a first image and a second image of the target area using medical imaging equipment, and sends the first and second images to a report generation device. The report generation device identifies a first region of interest (ROI) on the first image, registers the second image to the first image, determines a second ROI on the second image, and generates text report data for the target area based on the site condition information corresponding to the second ROI on the second image. This system allows for easy identification of the first ROI from the first image, and through image registration, the ROI can be synchronously updated to the second image, reducing the complexity of obtaining the second ROI on the second image and making medical image processing of the second ROI on the second image simpler.

[0072] In one embodiment, the report generation device is further configured to register the first image and the second image to obtain a mapping relationship between the first image and the second image; and to determine, based on the mapping relationship, an image region on the second image associated with the first region of interest as the second region of interest.

[0073] In specific implementation, the report generation device can select marker points on the first image and the second image respectively for the same anatomical location of the human body, to obtain the first marker point on the first image and the second marker point on the second image. The mapping relationship between the spatial coordinates of the first marker point and the spatial coordinates of the second marker point is used as the mapping relationship between the first image and the second image. After determining the first region of interest on the first image, the coordinates of the points corresponding to the first region of interest can be obtained. According to the mapping relationship, the coordinates of the second region of interest points corresponding to the coordinates of the first region of interest points are determined on the second image. The region on the second image containing the coordinates of the second region of interest points is used as the second region of interest.

[0074] For example, for the same anatomical location on the human body, a marker point x can be selected on the qualitative image and a marker point y can be selected on the quantitative image. The mapping relationship y = f(x) between marker points x and y can be used as the mapping relationship between the qualitative and quantitative images. After determining the first region of interest on the qualitative image, the coordinates of the points x1, x2, ..., xy on the boundary of the first region of interest can be obtained. N Substituting the mapping relation y = f(x), we get y1, y2, ..., y N Connect y1, y2, ..., y on the quantitative image. N This allows us to obtain the boundary of the second region of interest, which can be the boundary itself or the area inside the boundary.

[0075] In this embodiment, by registering the first image and the second image, a mapping relationship between the first image and the second image is obtained. Based on the mapping relationship, an image region on the second image associated with the first region of interest is determined as the second region of interest. Based on the registration of the first image and the second image, the region of interest on the first image can be synchronously updated to the second image, increasing the convenience of obtaining the second region of interest.

[0076] In one embodiment, the report generating device is further configured to: determine first location information of a first region of interest on a first image; determine second location information of a second image associated with the first location information based on a mapping relationship; and determine a second region of interest on the second image based on the second location information.

[0077] In practice, the report generation device can select a point to be matched in the first region of interest on the first image, use the position coordinates of the point to be matched as the first position information, determine the second position information corresponding to the first position information according to the mapping relationship, determine the target point in the second image according to the second position information, and use the area corresponding to the target point as the second region of interest.

[0078] For example, the boundary points of the first region of interest can be selected as the points to be matched, thus obtaining the first location information x1, x2, ..., x N Substituting the first position information into the mapping relation y = f(x), we obtain the second position information y1, y2, ..., y N y1, y2, ..., y N The corresponding point is the target point. Connecting the target point on the second image yields the boundary of the second region of interest, which can be the boundary and the interior of the boundary.

[0079] In this embodiment, by determining the first location information of the first region of interest on the first image, and determining the second location information associated with the first location information on the second image according to the mapping relationship, and determining the second region of interest on the second image according to the second location information, the region of interest can be determined on the first image and the second image respectively for the same lesion, thereby obtaining multi-dimensional information of the same lesion, so as to accurately identify the lesion condition.

[0080] In one embodiment, there is at least one second image, and at least one second region of interest on each second image. Each second image is used to describe the condition of the target part in different dimensions. The report generation device is also used to generate text report data of the target part based on the first image, each second image, and the condition information corresponding to each second region of interest.

[0081] In practice, one or more quantitative images can be acquired, each containing one or more regions of interest (ROIs), and each quantitative image can correspond to different human physiological indicators. The report generation device can acquire the measurement values ​​of human physiological indicators in each ROI of each quantitative image and display the qualitative image, one or more quantitative images, and the measurement values ​​of each ROI on each quantitative image in the generated text report data.

[0082] In this embodiment, by generating text report data of the target area based on the first image, each second image, and the location information corresponding to each second region of interest, the human physiological indicators can be displayed in multiple dimensions in the generated text report data, enabling accurate identification of lesions.

[0083] In one embodiment, the report generation device is further configured to acquire information reference values ​​corresponding to the location status information; generate an information anomaly identifier when the location status information does not conform to the information reference values; and generate text report data based on the first image, each second image, each location status information, each information reference value, and the information anomaly identifier.

[0084] In practice, the standard values ​​corresponding to the measured values ​​of human physiological indicators can be pre-stored in the report generation device. If the report generation device detects that the measured value does not match the standard value, it can generate an information anomaly indicator and display qualitative images, one or more quantitative images, the measured values ​​of each region of interest on each quantitative image, the standard values ​​corresponding to each region of interest on each quantitative image, and the information anomaly indicator on the generated text report data.

[0085] For example, the standard value can be a numerical value or a range of numerical values. If the measured value is not equal to the standard value, or if the measured value does not fall within the standard value range, the measured value can be marked in red. If the measured value is larger than the standard value, a larger indicator can be added to the measured value. If the measured value is smaller than the standard value, a smaller indicator can be added to the measured value. Finally, the qualitative image, quantitative image, measured value, standard value, red measured value, larger indicator, and smaller indicator can be displayed in the comprehensive text report data.

[0086] In this embodiment, by obtaining information reference values ​​corresponding to the condition information of the body part, an information anomaly identifier is generated when the condition information of the body part does not conform to the information reference value. Based on the first image, each second image, each body part condition information, each information reference value, and the information anomaly identifier, text report data is generated. This can provide reminders when the condition information of the body part does not conform to the reference value, enabling timely detection of abnormalities in body parts and improving the efficiency of lesion identification.

[0087] In one embodiment, the report generating device is further configured to display a second image display window in response to a trigger operation on the target location status information in the text report data; the second image display window displays a target second image corresponding to the target location status information.

[0088] In practice, users can select target measurement values ​​from text report data. The report generation device responds to the user's trigger operation on the target measurement value by generating a new image display window to display the quantitative image corresponding to the target measurement value.

[0089] For example, according to Figure 7 If the user is not satisfied with the results currently displayed in the text report, they can double-click any measurement value corresponding to the FF image. The report generation device will respond to the double-click operation by generating a new window to display the FF image.

[0090] In this embodiment, by responding to a trigger operation on the target part status information in the text report data, a second image display window is displayed, which makes it convenient for users to open the second image corresponding to the target part status information and view the second image, thus increasing the convenience of use.

[0091] In one embodiment, the report generation device is further configured to, in response to a region selection operation on a target second image in a second image display window, determine a third region of interest on the target second image; determine a fourth region of interest associated with the third region of interest on each of the second images other than the target second image; and update the text report data based on the location information corresponding to the third region of interest and the location information corresponding to the fourth region of interest.

[0092] In practice, after the report generation device responds to the user's trigger operation on the target measurement value and generates a new image display window to display the quantitative image corresponding to the target measurement value, the user can select a new region of interest on the quantitative image displayed in the new image display window. In response to the user's selection of the new region of interest, the report generation device generates a third region of interest on the quantitative image displayed in the new image display window and synchronously updates the third region of interest to other quantitative images to form a fourth region of interest. The report generation device can also obtain the measurement values ​​of the third region of interest and the fourth region of interest and update each measurement value in the text report data.

[0093] For example, according to Figure 7 After the report generation device responds to the user's double-click operation and generates a new window to display the FF image, the user can also select a new region of interest (ROI5) from the displayed FF image by dragging the mouse. The report generation device can synchronously update the new ROI5 to the R2*, SWI, T1 / T2 / T2*Mapping, and T1ρ images, and obtain the measurement value corresponding to ROI5 in each of the FF, R2*, SWI, T1 / T2 / T2*Mapping, and T1ρ images. By adding a column to the text report data, the measurement value of ROI5 can be updated in the text report data.

[0094] In this embodiment, in response to a region selection operation on the target second image in the second image display window, a third region of interest is determined on the target second image, and a fourth region of interest associated with the third region of interest is determined on each second image other than the target second image. Based on the location information corresponding to the third region of interest and the location information corresponding to the fourth region of interest, the text report data is updated. This allows the measurement values ​​of other regions of interest to be synchronously updated in the text report data when the user needs to view the results of other regions of interest, increasing the convenience of operation.

[0095] In one embodiment, the report generating device is further configured to, in response to a first triggering operation on a second image in text report data, display an enlarged second image in the text report data; and, in response to a second triggering operation on the enlarged second image, reduce the size of the enlarged second image.

[0096] In practice, users can trigger the quantitative image in the text report data, and the report generation device can respond to the user's trigger operation by displaying the magnified quantitative image in the text report data. Users can also trigger the magnified quantitative image, and the report generation device can respond to the user's trigger operation by reducing the size of the magnified quantitative image.

[0097] For example, according to Figure 6 Users can double-click the FF image in the text report data to generate an enlarged FF image in the text report data. Users can also double-click the enlarged FF image to reduce the enlarged FF image to its original size and restore the text report data.

[0098] In this embodiment, by responding to a first trigger operation on the second image in the text report data, an enlarged second image is displayed in the text report data, and by responding to a second trigger operation on the enlarged second image, the enlarged second image is reduced. This allows the quantitative image displayed in the text report data to be enlarged and restored, making it easier for users to view.

[0099] In one embodiment, the report generation device is further configured to delete the part status information corresponding to the target second region of interest in the text report data in response to a region deletion operation on the target second region of interest in the second image of the text report data.

[0100] In practice, users can perform a region deletion operation on any region of interest on the quantitative image in the text report data. In response to the user's region deletion operation, the report generation device can delete the measurement value corresponding to the region of interest in the text report data.

[0101] For example, according to Figure 5 Users can first click to select the region of interest (ROI1) on the FF image, and then press the Delete button on the keyboard to perform a region deletion operation. The report generation device responds to the user's region deletion operation by deleting the column corresponding to ROI1 in the text report data measurement values.

[0102] In this embodiment, by responding to the region deletion operation on the second region of interest of the target on the second image in the text report data, the part status information corresponding to the second region of interest of the target in the text report data is deleted, which allows the user to flexibly set the items in the text report data and increase the flexibility of text report data generation.

[0103] In one embodiment, the report generation device is further configured to determine a region recognition model corresponding to the target part; input the first image into the region recognition model corresponding to the target part to obtain a first region of interest on the first image.

[0104] Among them, the region identification model can be a machine learning model.

[0105] In practice, the report generation device can determine a machine learning model that is appropriate for the part of the human body to be diagnosed, input the quantitative image into the machine learning model, and identify the lesion area of ​​interest on the quantitative image.

[0106] In this embodiment, by determining the region recognition model corresponding to the target part, the first image is input into the region recognition model corresponding to the target part to obtain the first region of interest on the first image. Since the first image is convenient for describing the anatomical structure of the part of the human body to be diagnosed, the lesion area of ​​the part to be diagnosed can be quickly and accurately identified, ensuring the efficiency and accuracy of the region of interest determination.

[0107] In one embodiment, the first image includes at least one of a longitudinal relaxation time contrast image, a transverse relaxation time contrast image, and a diffusion-weighted image; the second image includes at least one of a fat quantification image, a magnetic susceptibility-weighted image, a spin lattice relaxation time image, a relaxation time mapping image, a magnetic resonance elastography image, and a positron emission tomography (PET) image.

[0108] In specific implementations, the first image can be a longitudinal relaxation time contrast (T1 contrast) image, a transverse relaxation time contrast (T2 contrast) image, or a diffusion-weighted imaging (DWI) image acquired by an MRI device. The second image can be a fat quantification (FACT FF or FACT R2*) image, a susceptibility-weighted imaging (SWI) image, a spin lattice relaxation time (T1ρ) image, a relaxation time mapping (T1 / T2 / T2*Mapping) image, a magnetic resonance elastography (MRE) image, or a fluid attenuated inversion recovery (FLAIR) image acquired by an MRI device. The second image can also be a PET image acquired by a PET or PET-MR device.

[0109] In this embodiment, by setting a first image and a second image, the region of interest on the second image can be quickly and accurately determined based on the first image that accurately describes the human anatomical structure, ensuring the efficiency and accuracy of the region of interest determination.

[0110] To facilitate a deeper understanding of the embodiments of this application by those skilled in the art, a specific example will be used for illustration below.

[0111] With the development of magnetic resonance imaging (MRI) technology, MRI scans of the liver can now provide not only multi-contrast qualitative diagnosis but also multi-dimensional quantitative diagnosis. Therefore, qualitatively locating lesions and synthesizing quantitative data to form a comprehensive text report has become a crucial technology. Current techniques involve manually outlining the region of interest (ROI) and then processing each region individually to generate multiple text reports. This process is cumbersome, inconvenient for subsequent review, and results in fragmented diagnostic information, hindering users from synthesizing information for comprehensive disease diagnosis. Therefore, this paper proposes a method for intelligent lesion identification that ensures all multi-dimensional data originates from the same ROI and that all dimensions are cross-registered, generating a rapid online, multi-dimensional, comparable, and quantitative comprehensive report. This method reduces manual operations, saves time, and facilitates doctors' review of text reports, improving work efficiency.

[0112] Specifically, regions of interest (ROIs) can be intelligently identified from qualitative images. After multidimensional registration, these ROIs are synchronously applied to quantitative images. Based on the measurements on the quantitative images, unified comprehensive text report data is generated, such as... Figure 5 As shown, the text report data can reflect the different quantitative results corresponding to each region of interest, and includes a standard value explanation. If the quantitative result is not within the standard value range, the quantitative result can be displayed in red and marked with a downward or upward arrow.

[0113] The text report data can display qualitative or quantitative images as reference images. Double-clicking any reference image will enlarge its display. Figure 6 As shown, double-clicking again will restore the enlarged reference image.

[0114] Users can also manually double-click any value in the text report data to open the corresponding image. On this image, users can manually select the region of interest, which will be synchronously updated across all quantitative images, and the text report data will also be updated accordingly. The final report can be displayed as follows: Figure 7 As shown.

[0115] It should be noted that, for PET-MR, the same technical solution in the above embodiments of this application can be used to treat the MR image as a qualitative image and the PET image as a quantitative image, and the PET image and MR image can be highly registered. The SUV value of the region of interest in the PET image can be synchronously updated to the comprehensive text report data.

[0116] In this embodiment, by intelligently identifying regions of interest, multidimensional quantitative applications can share a unified region of interest; by integrating multidimensional quantitative data, quantitative comprehensive liver text report data can be generated; moreover, it also supports users to adjust, add or delete regions of interest, dynamically update comprehensive report data, and improve the flexibility of report generation.

[0117] In one embodiment, such as Figure 8 As shown, a medical image processing method is provided, which can be applied to... Figure 1 Taking the report generation device 104 as an example, the following steps are included:

[0118] Step S310: Acquire a first image and a second image of the target area obtained by a medical imaging device; the first image is used to describe the structure of the target area, and the second image is used to describe the condition of the target area.

[0119] Step S320: Identify the first region of interest on the first image.

[0120] Step S330: Register the first image and the second image to obtain a second region of interest on the second image; the second region of interest on the second image is associated with the first region of interest on the first image.

[0121] Step S340: Generate text report data for the target area based on the location information corresponding to the second region of interest on the second image.

[0122] In practice, medical imaging equipment can acquire qualitative and quantitative images of the body site to be diagnosed, and send both images to a report generation device. Upon receiving the qualitative and quantitative images, the report generation device can intelligently identify lesion regions from the qualitative images, designating these lesion regions as the first region of interest (ROI). The report generation device can also register the qualitative and quantitative images, establishing a mapping relationship between the pixel coordinates of the qualitative and quantitative images. Based on this mapping, a second region of interest corresponding to the first ROI is determined on the quantitative image. This second ROI may correspond to the same lesion region as the first ROI. Furthermore, the report generation device can acquire measurements of human physiological indicators from the second ROI on the quantitative image and generate a comprehensive text report of the body site to be diagnosed based on these measurements.

[0123] Since the processing procedure of the report generation device 104 has been described in detail in the foregoing embodiments, it will not be repeated here.

[0124] In this embodiment, by acquiring a first image and a second image of the target area through a medical imaging device, a first region of interest (ROI) on the first image is identified, the second image is registered to the first image, a second ROI on the second image is determined, and text report data of the target area is generated based on the site condition information corresponding to the second ROI on the second image. This approach allows for the synchronous updating of the ROI to the second image through image registration, reducing the complexity of acquiring the second ROI on the second image and facilitating medical image processing of the second ROI on the second image, while ensuring easy identification of the first ROI from the first image.

[0125] 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.

[0126] In one embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram may 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 the computer program is executed by the processor, it implements a medical image processing method. 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 located on the computer device's casing, or an external keyboard, touchpad, or mouse.

[0127] Those skilled in the art will understand that Figure 9The 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.

[0128] In one embodiment, a computer device is also provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps in the above method embodiments.

[0129] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon that, when executed by a processor, implements the steps in the above method embodiments.

[0130] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps in the above method embodiments.

[0131] 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.

[0132] 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.

[0133] 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 medical image processing system, characterized in that, The system includes medical imaging equipment and report generation equipment; The medical imaging device is used to acquire a first image and a second image of the target area, and send the first image and the second image to the report generation device; the first image is a qualitative image used to describe the structure of the target area, and the second image is a plurality of quantitative images used to describe the condition of the target area in different dimensions. The report generation device is used to identify a first region of interest on the first image and to register the first image and the second image to obtain a second region of interest on each of the second images; the second region of interest on the second image is associated with the first region of interest on the first image. The report generation device is also used to generate text report data of the target part based on the part status information corresponding to the second region of interest on each of the second images; The report generation device is further configured to, in response to a trigger operation on target location status information in the text report data, display a second image display window, the second image display window displaying a target second image corresponding to the target location status information; in response to a region selection operation on the target second image, determine a third region of interest on the target second image; determine a fourth region of interest associated with the third region of interest on each of the second images other than the target second image; and update the measurement values ​​of the third region of interest and the fourth region of interest in the text report data. The report generation device is also configured to, in response to a trigger operation for any measurement value in the text report data, open the quantitative image corresponding to the measurement value, synchronously update the new region of interest (ROI) to other quantitative images based on the new ROI delineated in the quantitative image, obtain the measurement values ​​corresponding to the new ROI in all quantitative images, and add the measurement values ​​corresponding to the new ROI in all quantitative images to the text report data.

2. The system according to claim 1, characterized in that, The report generation device is further configured to register the first image and the second image to obtain a mapping relationship between the first image and the second image; and to determine, based on the mapping relationship, an image region on the second image associated with the first region of interest as the second region of interest.

3. The system according to claim 2, characterized in that, The report generation device is further configured to determine first location information of the first region of interest on the first image; and determine second location information on the second image associated with the first location information according to the mapping relationship; Based on the second location information, the second region of interest on the second image is determined.

4. The system according to claim 1, characterized in that, Each of the second images has at least one second region of interest, and each of the second images is used to describe the condition of the target part in different dimensions; the report generation device is also used to generate text report data of the target part based on the first image, each of the second images and the condition information corresponding to each of the second regions of interest.

5. The system according to claim 4, characterized in that, The report generation device is further configured to acquire information reference values ​​corresponding to the location status information; generate an information anomaly identifier when the location status information does not conform to the information reference values; and generate the text report data based on the first image, each of the second images, each of the location status information, each of the information reference values, and the information anomaly identifier.

6. The system according to claim 5, characterized in that, The report generating device is further configured to, in response to a first trigger operation on a second image in the text report data, display an enlarged second image in the text report data; and, in response to a second trigger operation on the enlarged second image, reduce the size of the enlarged second image.

7. The system according to claim 5, characterized in that, The report generation device is further configured to, in response to a region deletion operation on the second target region of interest in the second image in the text report data, delete the part status information corresponding to the second target region of interest in the text report data.

8. The system according to claim 1, characterized in that, The first image includes a T1 contrast image, a T2 contrast image, or a DWI image.

9. The system according to claim 1, characterized in that, The second image includes a FACT image, a SWI image, a T1p image, a relaxation time mapping image, an MRE image, or a FLAIR image.

10. The system according to any one of claims 1 to 9, characterized in that, The report generation device is further configured to determine a region recognition model corresponding to the target part; input the first image into the region recognition model corresponding to the target part to obtain a first region of interest on the first image.

Images