Medical image acquisition method and apparatus, computer device and readable storage medium

Abstract

The application relates to a medical image acquisition method and device, computer equipment and a readable storage medium. The method comprises the following steps: acquiring a high-energy image of a detection object and low-energy images collected at different angles; based on the low-energy images, a tomographic sequence image is reconstructed; the tomographic sequence image and the low-energy images are subjected to a synthesis process to obtain a synthesis image; the synthesis image and the high-energy image are subjected to a subtraction process to obtain a subtraction image of the detection object. The method uses the synthesis image obtained from the reconstructed tomographic sequence image and the low-energy images to replace the low-energy images in the traditional subtraction, and the high-energy image is subjected to a subtraction process to obtain a subtraction image, so that the medical image required for the diagnosis of the detection object can be obtained on the basis of reducing the radiation dose of the patient.

Description

Technical Field

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

[0002] With the continuous upgrading of imaging equipment, more and more technologies can be applied to the detection of breast diseases, such as contrast-enhanced spectral mammography (CESM) and digital breast tomosynthesis (DBT).

[0003] In related technologies, breast diseases are generally diagnosed using CESM images, DBT images, and two-dimensional images. This method involves first subjecting the patient to high- and low-energy exposures to obtain a low-energy two-dimensional image and a CESM image, and then subjecting the patient to DBT exposure to obtain a DBT image. This can result in the patient receiving excessive radiation doses. Summary of the Invention

[0004] Therefore, it is necessary to provide a medical image acquisition method, device, computer equipment, computer-readable storage medium, and computer program product to address the technical problem that the above methods may lead to patients receiving excessive radiation doses.

[0005] Firstly, this application provides a method for acquiring medical images. The method includes:

[0006] Acquire high-energy images of the object to be detected and low-energy images acquired from different angles;

[0007] Based on the low-energy image, a tomographic sequence image is reconstructed;

[0008] The tomographic sequence image and the low-energy image are synthesized to obtain a composite image;

[0009] Subtraction processing is performed on the synthetic image and the high-energy image to obtain a subtracted image of the detected object.

[0010] In one embodiment, the step of reconstructing a tomographic sequence image based on the low-energy image includes:

[0011] Reconstruct all low-energy images to obtain the first tomographic sequence images;

[0012] Alternatively, the target low-energy image in the low-energy image can be reconstructed to obtain a second tomographic sequence image; the target low-energy image includes an image with a projection angle near zero degrees.

[0013] The first tomographic sequence image and / or the second tomographic sequence image are used as the tomographic sequence image.

[0014] In one embodiment, the step of synthesizing the tomographic sequence image and the low-energy image to obtain a synthesized image includes:

[0015] The first tomographic sequence image and the second tomographic sequence image are projected respectively to obtain a first projected image and a second projected image;

[0016] The composite image is obtained by combining at least one of the first projected image and the second projected image with at least one of the low-energy images.

[0017] In one embodiment, the step of projecting the first tomographic sequence image and the second tomographic sequence image respectively to obtain a first projected image and a second projected image includes:

[0018] The first tomographic sequence image is obtained by performing maximum density projection on it;

[0019] The second tomographic sequence image is obtained by projecting the average value onto it.

[0020] In one embodiment, the subtraction processing of the synthesized image and the high-energy image to obtain a subtracted image of the detected object includes:

[0021] Obtain a weighting factor for the synthesized image; the weighting factor is used to eliminate normal glandular tissue in the synthesized image to highlight lesion tissue;

[0022] The synthesized image is weighted using the weighting factors to obtain a weighted image;

[0023] The weighted image and the high-energy image are subjected to subtraction processing to obtain the subtracted image.

[0024] In one embodiment, obtaining the weighting factor for the synthesized image includes:

[0025] A first difference image corresponding to the high-energy image and a second difference image corresponding to the synthesized image are obtained; the first difference image is used to characterize the difference between fat and glands in the high-energy image, and the second difference image is used to characterize the difference between fat and glands in the synthesized image;

[0026] The weighting factor is determined based on the comparison results between the first difference image and the second difference image.

[0027] In one embodiment, the high-energy image and the low-energy image are X-ray images, and the tomographic sequence image is a three-dimensional image.

[0028] Secondly, this application also provides a medical image acquisition device. The device includes:

[0029] The image acquisition module is used to acquire high-energy images of the detected object and low-energy images acquired from different angles;

[0030] An image reconstruction module is used to reconstruct a tomographic sequence image based on the low-energy image;

[0031] An image synthesis module is used to synthesize the tomographic sequence image and the low-energy image to obtain a synthesized image;

[0032] An image subtraction module is used to perform subtraction processing on the synthesized image and the high-energy image to obtain a subtracted image of the detected object.

[0033] 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:

[0034] Acquire high-energy images of the object to be detected and low-energy images acquired from different angles;

[0035] Based on the low-energy image, a tomographic sequence image is reconstructed;

[0036] The tomographic sequence image and the low-energy image are synthesized to obtain a composite image;

[0037] Subtraction processing is performed on the synthetic image and the high-energy image to obtain a subtracted image of the detected object.

[0038] 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:

[0039] Acquire high-energy images of the object to be detected and low-energy images acquired from different angles;

[0040] Based on the low-energy image, a tomographic sequence image is reconstructed;

[0041] The tomographic sequence image and the low-energy image are synthesized to obtain a composite image;

[0042] Subtraction processing is performed on the synthetic image and the high-energy image to obtain a subtracted image of the detected object.

[0043] 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:

[0044] Acquire high-energy images of the object to be detected and low-energy images acquired from different angles;

[0045] Based on the low-energy image, a tomographic sequence image is reconstructed;

[0046] The tomographic sequence image and the low-energy image are synthesized to obtain a composite image;

[0047] Subtraction processing is performed on the synthetic image and the high-energy image to obtain a subtracted image of the detected object.

[0048] The aforementioned medical image acquisition method, apparatus, computer equipment, storage medium, and computer program product acquire high-energy images of the target object and low-energy images acquired from different angles; based on the low-energy images, a tomographic sequence image is reconstructed; the tomographic sequence image and the low-energy image are synthesized to obtain a composite image; and the composite image and the high-energy image are subtracted to obtain a subtracted image of the target object. This method utilizes the composite image obtained from the reconstructed tomographic sequence image and the low-energy image to replace the low-energy image in traditional subtraction, and performs subtraction with the high-energy image to obtain the subtracted image. That is, a CESM image (subtracted image), a DBT image (tomographic sequence image), and a two-dimensional image (composite image) can be obtained from a series of projected low-energy images and a single high-energy image. Therefore, during image acquisition, only one high-energy exposure is needed to obtain the high-energy image, and one DBT exposure is needed to obtain a series of low-energy images, thereby obtaining the medical images required for the diagnosis of the target object while reducing the radiation dose to the patient. Attached Figure Description

[0049] Figure 1 This is a flowchart illustrating a medical image acquisition method in one embodiment;

[0050] Figure 2 This is a flowchart illustrating a medical image acquisition method in another embodiment;

[0051] Figure 3 This is a flowchart illustrating a method for acquiring medical images of the breast in one embodiment;

[0052] Figure 4 This is a schematic diagram of low-energy and high-energy images in one embodiment;

[0053] Figure 5 This is a schematic diagram of a composite image, a tomographic sequence image, and a subtraction image in one embodiment;

[0054] Figure 6 This is a structural block diagram of a medical image acquisition device in one embodiment;

[0055] Figure 7 This is an internal structural diagram of a computer device in one embodiment. Detailed Implementation

[0056] 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.

[0057] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in sequences other than those illustrated or described herein.

[0058] To facilitate understanding of this application, the principles of DBT and CESM technologies are explained below.

[0059] Digital breast tomosynthesis (DBT) is a three-dimensional imaging technique used for the detection of breast diseases. It acquires a series of low-dose images from different angles by moving in an arc around the breast over a short period, and then uses three-dimensional reconstruction technology to obtain high-resolution tomographic images. This technique significantly reduces or even eliminates the influence of tissue overlap, allowing physicians to examine the interior of the breast layer by layer, increasing the visibility of subtle details. DBT has significant clinical value in detecting soft tissue masses, structural distortions, and asymmetric structures, significantly improving the early diagnosis of breast cancer. Furthermore, it effectively eliminates the influence of overlapping glandular tissue, reducing false positive results, allowing doctors to observe the internal structures of the breast more clearly and detect smaller, earlier-stage tumors or lesions.

[0060] Contrast-enhanced Spectral Mammography (CESM) is a relatively new mammographic technique. The technical principle of CESM mainly involves dual-energy imaging and real-time subtraction. The low-energy tube voltage is 25-33 kVp, and the high-energy tube voltage is 45-49 kVp. After intravenous injection of iodine contrast agent into the upper limb, the difference in X-ray absorption rates at high and low energy levels is utilized for high- and low-energy exposure. Lesions are highlighted through image subtraction. CESM technology, based on traditional mammography, combines contrast enhancement with information on anatomical changes. Through high- and low-energy subtraction, it clearly displays areas with high blood perfusion, thus providing a more accurate diagnosis of breast diseases.

[0061] In one embodiment, such as Figure 1 As shown, a method for acquiring medical images is provided. This embodiment illustrates the application of this method to a terminal. It is understood that this method can also be applied to a server, and to a system including both a terminal and a server, and is implemented through interaction between the terminal and the server. The terminal can be, but is not limited to, various personal computers, laptops, smartphones, tablets, IoT devices, and portable wearable devices. IoT devices can include smart speakers, smart TVs, smart air conditioners, smart vehicle devices, etc. Portable wearable devices can include smartwatches, smart bracelets, head-mounted devices, etc. The server can be implemented using a standalone server or a server cluster consisting of multiple servers. In this embodiment, the method includes the following steps:

[0062] Step S110: Acquire high-energy images of the detected object and low-energy images acquired from different angles.

[0063] The test subject can be an organism (such as the human body) or a part or tissue of an organism. For example, the test subject could be the breast.

[0064] Both the high-energy and low-energy images are two-dimensional images (X-ray images). The high-energy tube voltage for acquiring high-energy images is 45~49kVp, and the low-energy tube voltage for acquiring low-energy images is 25~33kVp.

[0065] In practice, the object to be detected can be scanned at different angles using an X-ray tube to obtain projection images at different angles, which serve as low-energy images. Additionally, the object to be detected can be exposed and scanned at 0 degrees to obtain a high-energy image.

[0066] Step S120: Based on the low-energy image, a tomographic sequence image is reconstructed.

[0067] It is understandable that tomographic sequence images are obtained through three-dimensional reconstruction of low-energy images, and therefore are three-dimensional sequence images that can show the anatomical structure of the detected object at a specific level.

[0068] In practice, image reconstruction algorithms can be used to reconstruct at least one low-energy image to obtain a tomographic sequence. For example, 3D reconstruction of low-energy images can be performed using algorithms such as filtered back projection (FBP) and iterative reconstruction.

[0069] For example, when reconstructing a low-energy image using a filtered back-projection algorithm, the low-energy image is first subjected to a one-dimensional Fourier transform, and then convolved with a filter function to obtain the projection data after convolution filtering in each direction; then the filtered projection is back-projected to obtain the density of the low-energy image, and all back-projections are superimposed to obtain the reconstructed projection.

[0070] When reconstructing low-energy images using an iterative reconstruction algorithm, the low-energy image data is treated as an unknown image matrix. Projection data collected at any projection angle is compared with the initial guessed solution for the image. The simulated image is updated based on the comparison results until it approximates the original image. Specifically, a set of simulated image matrices can be set up first, and data is collected from different angles and compared with the actually collected projection data. The simulated image is updated by comparing the results of back projection, and the reconstructed image can be obtained repeatedly until the iteration termination condition is met. Each iteration establishes a set of algebraic equations for the unknown vectors based on the measured projection data, and the unknown image vectors are solved using the system of equations.

[0071] Step S130: The tomographic sequence image and the low-energy image are synthesized to obtain a composite image.

[0072] In practice, after the tomographic sequence image is reconstructed, it can be combined with the low-energy image using a two-dimensional synthesis method to obtain a two-dimensional composite image.

[0073] In some embodiments, since the tomographic sequence images are three-dimensional sequences, while the composite image obtained through synthesis is a two-dimensional image, the tomographic sequence images can be projected before compositing with the two-dimensional low-energy image to obtain a projected image. This projected image is then combined with the low-energy image to obtain the composite image.

[0074] Step S140: Subtraction processing is performed on the synthetic image and the high-energy image to obtain the subtracted image of the detected object.

[0075] Subtraction angiography is an image processing technique that uses the difference between high-energy and low-energy images to highlight lesion areas. In this embodiment, the synthetic image is synthesized from tomographic images and low-energy images. Since the tomographic images are obtained by three-dimensional reconstruction of the low-energy images, they are also low-energy images. Therefore, the synthetic image is actually a low-energy image. Thus, by performing subtraction processing on the synthetic image and the high-energy image, a subtraction image that highlights the lesion can be obtained.

[0076] Specifically, a weighting factor can be determined between the synthesized image and the high-energy image. Subtraction processing is then performed between the synthesized image and the high-energy image using this weighting factor to obtain a subtracted image. In another embodiment, the subtracted image can also be obtained directly by subtracting the high-energy image from the synthesized image. This subtraction removes background signals from normal tissue and enhances the signal display of the lesion area.

[0077] In some embodiments, a subtraction algorithm can be performed between any image in the low-energy image and the high-energy image to obtain a subtracted image.

[0078] Furthermore, after obtaining the synthetic image, tomographic sequence image, and subtraction image, they can be output and displayed to facilitate the diagnosis and detection of the target object by combining these three types of images.

[0079] In some embodiments, before performing subtraction processing on the synthetic image and the high-energy image, the two images can be preprocessed with denoising, correction, enhancement, etc., to optimize the two images and make the subsequent subtraction process more accurate.

[0080] In some embodiments, after subtracting the synthetic image and the high-energy image to obtain the subtracted image, post-processing can be performed on the generated subtracted image, such as smoothing, denoising, and contrast enhancement, to improve the visualization effect. Filters can also be used to preserve edge features and further highlight the lesion area.

[0081] In the aforementioned medical image acquisition method, high-energy images of the target object and low-energy images acquired from different angles are obtained. Based on the low-energy images, a tomographic sequence image is reconstructed. The tomographic sequence image and the low-energy image are then synthesized to obtain a composite image. Finally, the composite image and the high-energy image are subtracted to obtain a subtracted image of the target object. This method uses a composite image obtained from the reconstructed tomographic sequence image and the low-energy image to replace the low-energy image in traditional subtraction. Subtraction is performed between the composite image and the high-energy image to obtain the subtracted image. In other words, a CESM image (subtracted image), a DBT image (tomographic sequence image), and a two-dimensional image (composite image) can be obtained from a series of projected low-energy images and a single high-energy image. Therefore, during image acquisition, only one high-energy exposure is needed to obtain the high-energy image, and one DBT exposure is needed to obtain a series of low-energy images. This allows for obtaining the medical images required for the diagnosis of the target object while reducing the radiation dose to the patient.

[0082] In an exemplary embodiment, step S120 above, which reconstructs a tomographic sequence image based on a low-energy image, includes: reconstructing all low-energy images to obtain a first tomographic sequence image; or, reconstructing a target low-energy image in the low-energy images to obtain a second tomographic sequence image; the target low-energy image includes an image whose projection angle is near zero degrees; and using the first tomographic sequence image and / or the second tomographic sequence image as the tomographic sequence image.

[0083] In practical implementation, 3D reconstruction based on low-energy images can be performed on all low-energy images to obtain a tomographic sequence, or it can be performed on a subset of low-energy images. Since the tomographic sequence needs to be synthesized with the low-energy images to obtain a two-dimensional composite image, this composite image replaces the low-energy image in traditional subtraction, which needs to be a projection image in the 0-degree direction. Therefore, when performing 3D reconstruction on a subset of low-energy images, this subset needs to include images with projection angles near zero degrees to make the composite image approximate the effect of a zero-degree projection.

[0084] More specifically, the tomographic sequence image obtained by reconstructing all low-energy images can be denoted as the first tomographic sequence image, and the tomographic sequence image obtained by reconstructing the target low-energy image from the low-energy images can be denoted as the second tomographic sequence image; the target low-energy image includes images with a projection angle near zero degrees. Further, at least one of the first and second tomographic sequence images is used as the tomographic sequence image obtained by the above reconstruction.

[0085] In this embodiment, when performing three-dimensional reconstruction of low-energy images, all low-energy images can be selected for reconstruction, or only some low-energy images can be selected for reconstruction. However, the selected images need to include images with projection angles near zero degrees to ensure that the subsequent synthetic images obtained based on tomographic sequence images have an effect close to zero-degree projection, so as to facilitate the subtraction of high-energy images to obtain subtracted images.

[0086] In an exemplary embodiment, step S130, which involves synthesizing a tomographic sequence image and a low-energy image to obtain a synthesized image, includes: projecting a first tomographic sequence image and a second tomographic sequence image to obtain a first projected image and a second projected image; and synthesizing at least one of the first projected image and the second projected image with at least one low-energy image to obtain a synthesized image.

[0087] In a specific implementation, when the tomographic sequence image includes a first tomographic sequence image reconstructed from all low-energy images and a second tomographic sequence image reconstructed from some low-energy images, the first tomographic sequence image and the second tomographic sequence image can be projected respectively. The projected image obtained by projecting the first tomographic sequence image is denoted as the first projected image, and the projected image obtained by projecting the second tomographic sequence image is denoted as the second projected image.

[0088] Further, at least one of the first and second projected images is combined with at least one low-energy image to obtain a composite image. That is, in some embodiments, the first projected image can be combined with at least one low-energy image to obtain a composite image. In other embodiments, the second projected image can be combined with at least one low-energy image to obtain a composite image. In still other embodiments, the first projected image, the second projected image, and at least one low-energy image can be combined to obtain a composite image.

[0089] In some embodiments, after obtaining the first projected image and the second projected image, the first projected image and the second projected image can be filtered respectively to obtain a first filtered image corresponding to the first projected image and a second filtered image corresponding to the second projected image. At least one of the first filtered image and the second filtered image is combined with at least one low-energy image to obtain a composite image. The filtering method can be a high-pass filter to achieve image enhancement of the first projected image and the second projected image, thereby improving the image quality of the composite image obtained based on the first projected image and the second projected image.

[0090] In this embodiment, at least one of the images obtained by projecting the first tomographic sequence image and / or the second tomographic sequence image is combined with at least one low-energy image to obtain a composite image, which enriches the generation methods of composite images and facilitates selection according to actual needs.

[0091] In an exemplary embodiment, the steps of projecting the first tomographic sequence image and the second tomographic sequence image to obtain the first projected image and the second projected image respectively include: performing maximum density projection on the first tomographic sequence image to obtain the first projected image; and performing average value projection on the second tomographic sequence image to obtain the second projected image.

[0092] In the specific implementation, since the first tomographic sequence image is reconstructed from all low-energy images at different angles, the purpose of projecting the first tomographic sequence image is to extract the features with high attenuation in the image. Therefore, the maximum density projection method is used to project the first tomographic sequence image to extract the high-attenuation tissue structures in the image, such as calcification points and some edges of detailed structures.

[0093] Since the second tomographic sequence image is reconstructed from an image with a projection angle near zero degrees, the structural information of each layer of the second tomographic sequence image is very similar. Therefore, the second tomographic sequence image can be projected using the average value method (equivalent to denoising) to extract the glandular structure that is similar to the low-energy two-dimensional image.

[0094] In this embodiment, considering the difference in low-energy images on which the reconstruction of the first tomographic sequence image and the second tomographic sequence image are based, different projection methods are used for projection to ensure the effectiveness and accuracy of the obtained projected images.

[0095] In an exemplary embodiment, step S140 above performs subtraction processing on the synthetic image and the high-energy image to obtain a subtracted image of the detected object, including: obtaining a weighting factor for the synthetic image; using the weighting factor to eliminate normal glandular tissue in the synthetic image to highlight lesion tissue; weighting the synthetic image using the weighting factor to obtain a weighted image; and performing subtraction processing on the weighted image and the high-energy image to obtain a subtracted image.

[0096] In practice, a weighting factor can be determined based on the differences between fat and glands in the synthesized image and the high-energy image to reduce the influence of normal glandular tissue on the synthesized image. After obtaining the weighting factor, it is multiplied by the synthesized image to achieve weighting, resulting in a weighted image. Further, a subtraction process is performed on the weighted image and the high-energy image; specifically, the high-energy image is subtracted from the weighted image to obtain the subtracted image.

[0097] In some embodiments, considering that medical images typically have a large dynamic range and pixel values ​​may vary significantly, when performing subtraction on synthetic and high-energy images, logarithmic processing can be performed on both images first, and then subtraction can be performed on the resulting logarithmic synthetic and high-energy images. Logarithmic processing effectively reduces this dynamic range and decreases the differences between pixel values, thus simplifying subsequent processing. After logarithmic processing, low-intensity areas (such as background and normal tissue) are magnified, while high-intensity areas (such as lesions or regions of interest) are relatively smaller, thus highlighting defects or lesions. This enhanced contrast helps in better identifying lesion areas.

[0098] For example, let the synthesized image be... High-energy images are The weighting factor is The method for subtracting synthetic and high-energy images can be expressed as:

[0099]

[0100] in, This represents the resulting subtractive image.

[0101] In this embodiment, by applying a weighting factor to the synthesized image and then subtracting it from the high-energy image, the signal of the lesion tissue can be enhanced while the signal of the normal glandular tissue is weakened, thereby making it easier to identify and locate the lesion tissue and improving the lesion recognition rate and accuracy.

[0102] In one exemplary embodiment, obtaining a weighting factor for a synthesized image includes: obtaining a first difference image corresponding to a high-energy image and a second difference image corresponding to the synthesized image; and determining a weighting factor based on the comparison result between the first difference image and the second difference image.

[0103] The first difference image is used to characterize the differences between fat and glands in the high-energy image, and the second difference image is used to characterize the differences between fat and glands in the synthesized image.

[0104] In a specific implementation, for high-energy images, a first fat region and a first gland region can be extracted from the high-energy image, and the difference between the two can be calculated to obtain a first difference image. For example, the first difference image can be obtained by calculating the difference between the pixel values ​​of the first fat region and the pixel values ​​of the first gland region.

[0105] Similarly, for a synthesized image, a second fat region and a second glandular region can be extracted from the synthesized image, and the difference between them can be calculated to obtain a second difference image. For example, the second difference image can be obtained by calculating the difference between the pixel values ​​of the second fat region and the pixel values ​​of the second glandular region.

[0106] Furthermore, the weighting factor is determined by comparing the similarity between the first difference image and the second difference image. Specifically, the similarity between the first difference image and the second difference image can be obtained through mathematical statistical methods. For example, the ratio between the first difference image and the second difference image can be obtained to obtain the weighting factor.

[0107] In some embodiments, similar to the image processing when acquiring a subtraction image, when calculating the weighting factor based on the fat and gland regions of the high-energy image and the synthetic image, the pixel values ​​of the fat and gland regions of the high-energy image and the synthetic image can be logarithmically processed separately to facilitate the calculation.

[0108] For example, let the first fat region in the high-energy image be represented as... The first gland region is represented as The second fat region in the synthesized image is represented as... The second gland region is represented as Then the weighting factor The calculation process can be expressed as:

[0109]

[0110] In this embodiment, the weighting factor is determined by the high-energy image to be subtracted and the synthesized image, realizing the dynamic generation of the weighting factor based on the image content. This makes the weighting factor highly adaptable and can effectively cope with different imaging conditions and pathological states.

[0111] refer to Figure 2 This is a flowchart illustrating a medical image acquisition method provided for another exemplary embodiment. In this embodiment, the method includes the following steps:

[0112] (1) Acquire high-energy images of the object to be detected and low-energy images acquired from different angles.

[0113] (2) Reconstruct all low-energy images to obtain the first tomographic sequence image.

[0114] (3) Reconstruct the target low-energy image in the low-energy image to obtain the second tomographic sequence image; the target low-energy image includes images with a projection angle near zero degrees.

[0115] (4) Perform maximum density projection on the first fault sequence image to obtain the first projection image.

[0116] (5) Project the average value of the second fault sequence image to obtain the second projected image.

[0117] (6) Combine at least one of the first projection image and the second projection image with at least one low-energy image to obtain a composite image.

[0118] (7) The composite image is weighted by a weighting factor to obtain a weighted image.

[0119] The weighting factor is determined based on the first difference image corresponding to the high-energy image and the second difference image corresponding to the synthetic image; the first difference image is used to characterize the difference between fat and glands in the high-energy image, and the second difference image is used to characterize the difference between fat and glands in the synthetic image.

[0120] (8) Subtract the weighted image and the high-energy image to obtain the subtracted image.

[0121] (9) Output tomographic sequence images, composite images and subtraction images.

[0122] This method utilizes a composite image obtained from reconstructed tomographic sequences and low-energy images to replace the low-energy image in traditional subtraction. Subtraction is then performed with a high-energy image to obtain a subtracted image. In other words, a CESM image (subtraction image), a DBT image (tomographic sequence image), and a two-dimensional image (composite image) can be obtained from a series of projected low-energy images and a single high-energy image. Therefore, during image acquisition, only one high-energy exposure is needed to obtain a high-energy image, and one DBT exposure is needed to obtain a series of low-energy images. This allows for obtaining the medical images required for diagnosis of the subject while reducing the radiation dose to the patient.

[0123] In one embodiment, to facilitate understanding of the embodiments of this application by those skilled in the art, the following uses the breast as the detection object to specifically describe the medical image acquisition method provided in this application. Reference Figure 3 The diagram illustrates a flowchart of a method for acquiring medical images of the breast, including the following steps:

[0124] Step S310: Scan the breast at different angles using an X-ray tube to obtain low-energy images projected at different angles. High-energy images are obtained by exposing the breast to X-rays at 0 degrees using an X-ray tube. .

[0125] refer to Figure 4 This is a schematic diagram of low-energy and high-energy images provided in one embodiment. Figure 4 In the image (a), we see a series of low-energy images obtained by projecting from different angles. Figure 4 (b) in the image represents a high-energy image obtained by exposure scanning at 0 degrees.

[0126] Step S320: For low-energy images at different angles, reconstruct tomographic sequence images using a reconstruction algorithm. .

[0127] Specifically, a reconstruction algorithm can be performed on all low-energy images at different angles to obtain the first tomographic sequence image Volume1; alternatively, a reconstruction algorithm can be performed on a subset of low-energy images (images with projection angles near 0 degrees) to obtain the second tomographic sequence image Volume2. Volume1 and / or Volume2 are then used as the tomographic sequence images. .

[0128] Step S330: Using a 2D synthesis method, at least one low-energy image is... With tomographic sequence images Synthesize a 2D image .

[0129] Specifically, maximum density projection is performed on the first tomographic sequence image Volume1 to obtain the projected image. and the projected image Perform high-pass filtering to obtain the filtered image. .

[0130] Performing mean projection on Volume2 of the second tomographic sequence image yields... The image is then high-pass filtered to obtain the filtered image. .

[0131] Will and / or The image is synthesized by combining it with at least one low-energy image to obtain a composite image. .

[0132] Step S340, synthesize the image With high-energy images Subtraction is performed to obtain a subtracted image. .

[0133] Specifically, the subtraction is performed using the following two formulas:

[0134]

[0135]

[0136] Step S350, generate the composite image Tomographic sequence images and subtraction image Output display; specifically, the composite image can be displayed. Tomographic sequence images and subtraction image It can be output to the same monitor for display; it can also be output to two or three monitors for display.

[0137] refer to Figure 5This is a schematic diagram of a synthetic image, a tomographic sequence image, and a subtraction image provided in one embodiment. Figure 5 In the image, (a) represents a synthetic image, (b) represents a DBT tomographic sequence image, and (c) represents a subtraction image.

[0138] This method utilizes a composite image obtained from reconstructed tomographic sequences and low-energy images to replace the low-energy image in traditional subtraction. Subtraction is then performed with a high-energy image to obtain a subtracted image. In other words, a CESM image (subtraction image), a DBT image (tomographic sequence image), and a two-dimensional image (composite image) can be obtained from a series of projected low-energy images and a single high-energy image. Therefore, during image acquisition, only one high-energy exposure is needed to obtain a high-energy image, and one DBT exposure is needed to obtain a series of low-energy images. This allows for obtaining the medical images required for diagnosis of the subject while reducing the radiation dose to the patient.

[0139] 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.

[0140] Based on the same inventive concept, this application also provides a medical image acquisition device for implementing the medical image acquisition method described above. The solution provided by this device is similar to the solution described in the above method; therefore, the specific limitations in one or more embodiments of the medical image acquisition device provided below can be found in the limitations of the medical image acquisition method described above, and will not be repeated here.

[0141] In one embodiment, such as Figure 6 As shown, a medical image acquisition device is provided, comprising:

[0142] The image acquisition module 610 is used to acquire high-energy images of the detected object and low-energy images acquired from different angles;

[0143] Image reconstruction module 620 is used to reconstruct tomographic sequence images based on low-energy images;

[0144] The image synthesis module 630 is used to synthesize tomographic sequence images and low-energy images to obtain a synthesized image;

[0145] The image subtraction module 640 is used to perform subtraction processing on synthetic images and high-energy images to obtain subtracted images of the detected object.

[0146] In one embodiment, the image reconstruction module 620 is further configured to reconstruct all low-energy images to obtain a first tomographic sequence image; or, to reconstruct a target low-energy image in the low-energy images to obtain a second tomographic sequence image; the target low-energy image includes an image with a projection angle near zero degrees; and to use the first tomographic sequence image and / or the second tomographic sequence image as the tomographic sequence image.

[0147] In one embodiment, the image synthesis module 630 is further configured to project the first tomographic sequence image and the second tomographic sequence image respectively to obtain a first projected image and a second projected image; and to perform a synthesis process on at least one of the first projected image and the second projected image with at least one low-energy image to obtain a synthesized image.

[0148] In one embodiment, the image synthesis module 630 is further configured to perform maximum density projection on the first tomographic sequence image to obtain a first projected image; and to perform average value projection on the second tomographic sequence image to obtain a second projected image.

[0149] In one embodiment, the image subtraction module 640 is further configured to obtain a weighting factor for the synthesized image; the weighting factor is used to eliminate normal glandular tissue in the synthesized image to highlight lesion tissue; the synthesized image is weighted by the weighting factor to obtain a weighted image; and the weighted image and the high-energy image are subjected to subtraction processing to obtain a subtracted image.

[0150] In one embodiment, the image subtraction module 640 is further configured to acquire a first difference image corresponding to the high-energy image and a second difference image corresponding to the synthesized image; the first difference image is used to characterize the difference between fat and glands in the high-energy image, and the second difference image is used to characterize the difference between fat and glands in the synthesized image; a weighting factor is determined based on the comparison result of the first difference image and the second difference image.

[0151] In one embodiment, the high-energy image and the low-energy image are X-ray images, and the tomographic sequence image is a three-dimensional image.

[0152] Each module in the aforementioned medical image acquisition device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device, or stored in the memory of a computer device as software, so that the processor can call and execute the operations corresponding to each module.

[0153] In one embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram may be as follows: Figure 7 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 acquisition 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 on the computer device's casing, or an external keyboard, touchpad, or mouse.

[0154] Those skilled in the art will understand that Figure 7 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0155] 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.

[0156] 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.

[0157] 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.

[0158] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of related data must comply with the relevant laws, regulations and standards of the relevant countries and regions.

[0159] Those skilled in the art will understand that all or part of the processes in 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. When executed, the computer program can include the processes of the embodiments described above. 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.

[0160] 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.

[0161] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A method for acquiring medical images, characterized in that, The method includes: Acquire high-energy images of the object to be detected and low-energy images acquired from different angles; Based on the low-energy image, a tomographic sequence image is reconstructed; The tomographic sequence image and the low-energy image are synthesized to obtain a composite image; Subtraction processing is performed on the synthetic image and the high-energy image to obtain a subtracted image of the detected object.

2. The method according to claim 1, characterized in that, The process of reconstructing a tomographic sequence image based on the low-energy image includes: Reconstruct all low-energy images to obtain the first tomographic sequence images; Alternatively, the target low-energy image in the low-energy image can be reconstructed to obtain a second tomographic sequence image; the target low-energy image includes an image with a projection angle near zero degrees. The first tomographic sequence image and / or the second tomographic sequence image are used as the tomographic sequence image.

3. The method according to claim 2, characterized in that, The process of synthesizing the tomographic sequence image and the low-energy image to obtain a synthesized image includes: The first tomographic sequence image and the second tomographic sequence image are projected respectively to obtain a first projected image and a second projected image; The composite image is obtained by combining at least one of the first projected image and the second projected image with at least one of the low-energy images.

4. The method according to claim 3, characterized in that, The step of projecting the first tomographic sequence image and the second tomographic sequence image respectively to obtain a first projected image and a second projected image includes: The first tomographic sequence image is obtained by performing maximum density projection on it; The second tomographic sequence image is obtained by projecting the average value onto it.

5. The method according to claim 1, characterized in that, The subtraction processing of the synthesized image and the high-energy image to obtain the subtracted image of the detected object includes: Obtain the weighting factors for the synthesized image; The synthesized image is weighted using the weighting factors to obtain a weighted image; The weighted image and the high-energy image are subjected to subtraction processing to obtain the subtracted image.

6. The method according to claim 5, characterized in that, The step of obtaining the weighting factor for the synthesized image includes: Obtain the first difference image corresponding to the high-energy image and the second difference image corresponding to the synthesized image; The weighting factor is determined based on the comparison results between the first difference image and the second difference image.

7. The method according to any one of claims 1-6, characterized in that, The high-energy image and the low-energy image are X-ray images, and the tomographic sequence image is a three-dimensional image.

8. A medical image acquisition device, characterized in that, The device includes: The image acquisition module is used to acquire high-energy images of the detected object and low-energy images acquired from different angles; An image reconstruction module is used to reconstruct a tomographic sequence image based on the low-energy image; An image synthesis module is used to synthesize the tomographic sequence image and the low-energy image to obtain a synthesized image; An image subtraction module is used to perform subtraction processing on the synthesized image and the high-energy image to obtain a subtracted image of the detected object.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the medical image acquisition method according to any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the steps of the medical image acquisition method according to any one of claims 1 to 7.

Images