Three-dimensional medical image construction method, device, equipment and storage medium

Abstract

The present invention relates to the field of medical image processing technology, and discloses a method, apparatus, device, and storage medium for constructing a three-dimensional medical image. The method comprises: acquiring a medical image captured by a medical image acquisition device while rotating around a target object through a preset angle; the preset angle being greater than 360 degrees; comparing the first n frames of the medical image with a continuous n-frame first medical image, where n is an integer greater than zero, and the first medical image is a medical image other than the first n frames; acquiring n consecutive frames of a second medical image, where the n-frame second medical image has the greatest similarity to the first n frames; retaining the medical image preceding the n-frame second medical image; and performing three-dimensional reconstruction based on the retained medical image. The present invention ensures that the two-dimensional medical images used for three-dimensional reconstruction are neither missing nor redundant, thereby guaranteeing the integrity and accuracy of the reconstructed three-dimensional medical image.

Description

Technical Field

[0001] The present invention relates to the technical field of medical image processing, and in particular to a three-dimensional medical image construction method, device, equipment and storage medium. Background Art

[0002] Medical imaging is a medical procedure that uses modern imaging technologies such as X-rays, ultrasound, radionuclides, and magnetic resonance imaging to examine the human body in order to understand its internal structure and function and assist in the diagnosis of diseases. For example, ultrasound, as a non-invasive, radiation-free, and relatively low-cost screening method, has been widely used in medical testing. However, conventional medical imaging produces two-dimensional medical images, which can only display the projection of an object on a certain plane and cannot provide complete information about the object in three-dimensional space. This makes it difficult for doctors to accurately determine the three-dimensional shape, size, and location of lesions during diagnosis. Three-dimensional reconstruction of medical images is an advanced medical image processing technology that converts two-dimensional medical image data into a three-dimensional model. Its core advantage is that it provides more intuitive and three-dimensional anatomical structure and functional information.

[0003] However, the 3D medical image construction process in related technologies has certain shortcomings. For example, the lack of synchronous coding between the image acquisition device (such as an ultrasound probe) and the rotation angle can result in missing or redundant images. Specifically, during one rotation of the image acquisition device (typically 360 degrees), too many or too few image frames may be captured. Directly using these image frames for 3D reconstruction can affect the accuracy of subsequent 3D reconstruction, leading to image distortion and, consequently, the accuracy of disease screening. Summary of the Invention

[0004] In view of this, the present invention provides a three-dimensional medical image construction method, device, equipment and storage medium to solve the problem that three-dimensional medical image reconstruction may result in missing or redundant captured two-dimensional medical image frames, resulting in low accuracy of the reconstructed three-dimensional medical image.

[0005] In a first aspect, the present invention provides a method for constructing a three-dimensional medical image, the method comprising:

[0006] Acquiring a medical image acquired by a medical image acquisition device while rotating around a target object through a preset angle; the preset angle being greater than 360 degrees;

[0007] Comparing first n frames of medical images in the medical image with n consecutive frames of first medical images, where n is an integer greater than zero, and the first medical images are medical images other than the first n frames of medical images;

[0008] Acquire n consecutive frames of second medical images, wherein the n frames of second medical images have the greatest similarity to the first n frames of medical images;

[0009] retaining the n frames of medical images preceding the second medical image;

[0010] Perform three-dimensional reconstruction based on the retained medical image.

[0011] In an optional embodiment, the continuous n frames of first medical images are medical images after the mth frame of medical image, and m is less than or equal to the number of medical image frames that the medical image acquisition device should acquire during a 360-degree rotation around the target object.

[0012] In an optional embodiment, n is an integer greater than 1 and less than 10.

[0013] In an optional embodiment, comparing the first n frames of the medical image with the consecutive n frames of the first medical image includes:

[0014] Selecting the n frames of the first medical image until the last frame of the medical image using a sliding window, where the length of the sliding window is n and the sliding step is s, where s is an integer greater than zero;

[0015] The first n frames of medical images in the medical image are compared with the currently selected n frames of first medical image.

[0016] In an optional embodiment, comparing the first n frames of the medical image with the consecutive n frames of the first medical image includes:

[0017] performing similarity comparison on each medical image in the first n frames of medical images and the first medical image in the same order as the n frames of first medical images to obtain n similarity values;

[0018] An average similarity value of the n similarity values is calculated as the similarity value between the n frames of medical images and the n frames of first medical images.

[0019] In an optional embodiment, the target object is breast tissue.

[0020] In a second aspect, the present invention provides a three-dimensional medical image construction device, the device comprising:

[0021] A first acquisition module is configured to acquire a medical image acquired by the medical image acquisition device during a process of rotating the target object around a preset angle; the preset angle is greater than 360 degrees;

[0022] a comparing module, configured to compare first n frames of medical images in the medical image with n consecutive frames of first medical images, where n is an integer greater than zero, and the first medical images are medical images other than the first n frames of medical images;

[0023] A second acquisition module is configured to acquire n consecutive frames of second medical images, wherein the n frames of second medical images have the greatest similarity to the first n frames of medical images;

[0024] a screening module, configured to retain the medical images preceding the n frames of the second medical image;

[0025] A reconstruction module is used to perform three-dimensional reconstruction based on the retained medical image.

[0026] In a third aspect, the present invention provides a medical device comprising: a memory and a processor, the memory and the processor being communicatively connected to each other, the memory storing computer instructions, and the processor executing the three-dimensional medical image construction method of the first aspect or any corresponding embodiment thereof by executing the computer instructions.

[0027] In a fourth aspect, the present invention provides a computer-readable storage medium having computer instructions stored thereon, the computer instructions being used to enable a computer to execute the three-dimensional medical image construction method of the first aspect or any corresponding embodiment thereof.

[0028] In a fifth aspect, the present invention provides a computer program product comprising computer instructions for causing a computer to execute the three-dimensional medical image construction method of the first aspect or any corresponding embodiment thereof.

[0029] The 3D medical image construction method, apparatus, device, and storage medium provided by embodiments of the present invention prevent the loss of captured 2D medical image frames due to insufficient rotation by setting the rotation angle of the medical image acquisition device to slightly greater than 360 degrees, thereby ensuring that all 2D medical images used for 3D reconstruction are present. Furthermore, embodiments of the present invention use similarity comparison to determine the last frame or frames of 2D medical images captured by the medical image acquisition device in a 360-degree scan, thereby removing redundant 2D medical images. This ensures that neither missing nor redundant 2D medical images are present for 3D reconstruction, thereby guaranteeing the integrity and accuracy of the reconstructed 3D medical images. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] In order to more clearly illustrate the specific embodiments of the present invention or the technical solutions in related technologies, the following briefly introduces the drawings required for use in the specific embodiments or related technical descriptions. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0031] Figure 1 is a flow chart of a method for constructing a three-dimensional medical image according to an embodiment of the present invention;

[0032] Figure 2 is a schematic diagram of a process for acquiring two-dimensional ultrasound images using an ultrasound probe according to an embodiment of the present invention;

[0033] Figure 3 is a schematic diagram of average similarity values corresponding to n frames of first medical images selected sequentially using a sliding window according to an embodiment of the present invention;

[0034] Figure 4 It is one of the top view schematic diagrams of a three-dimensional medical image constructed using a three-dimensional medical image construction method in the related art;

[0035] Figure 5 is one of the schematic top views of a three-dimensional medical image constructed using the three-dimensional medical image construction method provided by an embodiment of the present invention;

[0036] Figure 6 This is a second schematic top view of a three-dimensional medical image constructed using a three-dimensional medical image construction method in related art;

[0037] Figure 7 This is a second schematic top view of a three-dimensional medical image constructed using the three-dimensional medical image construction method provided by an embodiment of the present invention;

[0038] Figure 8 is a structural block diagram of a three-dimensional medical image construction device according to an embodiment of the present invention;

[0039] Figure 9 Schematic diagram of the hardware structure of the medical device according to the embodiment of the present invention. DETAILED DESCRIPTION

[0040] To make the purpose, technical solutions, and advantages of the embodiments of the present invention more clear, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without making creative efforts shall fall within the scope of protection of the present invention.

[0041] According to an embodiment of the present invention, an embodiment of a three-dimensional medical image construction method is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of executable computer instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0042] In this embodiment, a three-dimensional medical image construction method is provided, which can be used in various computer devices, including medical devices or other medical devices. Figure 1 FIG. 1 is a flow chart of a method for constructing a three-dimensional medical image according to an embodiment of the present invention. Figure 1 As shown, the process includes the following steps:

[0043] Step S101 involves acquiring a medical image (i.e., a medical image) captured by a medical image acquisition device while rotating around a target object through a preset angle; the preset angle is greater than 360 degrees. The medical image acquisition device is a sensor or other device closely related to image acquisition, and may not include a processor or memory. For example, the device may be an ultrasound probe or an X-ray sensor.

[0044] Specifically, the acquired medical images are a sequence of 2D medical images arranged in chronological order. The preset angle is generally slightly larger than 360 degrees, but can be slightly larger, such as 365 or 370 degrees. This prevents the loss of 2D medical images and also prevents excessive 2D images from significantly increasing subsequent computational complexity and affecting the efficiency of 3D medical image construction.

[0045] The three-dimensional medical image construction method provided in the embodiment of the present invention can be applied to construct a three-dimensional ultrasound image of breast tissue, that is, the target object is breast tissue. When the target object is breast tissue, the patient usually lies prone on the ultrasound device, and the ultrasound probe rotates and scans around the breast area to obtain ultrasound image data at different angles. Specifically, the process of using the ultrasound probe to collect two-dimensional ultrasound images is as follows: Figure 2 As shown (where 201 is an ultrasound probe and 202 is breast tissue).

[0046] Step S102 : comparing the first n frames of medical images in the medical image with n consecutive frames of first medical images, where n is an integer greater than zero, and the first medical images are medical images other than the first n frames of medical images.

[0047] Specifically, n is an integer greater than 1 and less than 10. For example, n is 3 or 5. In order to avoid inaccurate comparison results due to errors in image comparison, thereby causing an error in determining the most similar medical image, it is not recommended that n be 1.

[0048] In some optional specific embodiments, the continuous n frames of first medical images are medical images after the mth frame of medical image, and m is less than or equal to the number of medical image frames that the medical image acquisition device should acquire during a 360-degree rotation around the target object.

[0049] Because the two-dimensional medical image with the highest similarity must be the one captured by the medical image acquisition device at the same position, the medical image with the highest similarity to the previous n frames must be the n frames captured by the medical image acquisition device during a 360-degree rotation. Therefore, based on the rotation speed and image acquisition frequency of the medical image acquisition device, it can be determined that the medical image with the highest similarity to the previous n frames must be after a certain frame (e.g., the 1200th frame). Similarity calculations with the n frames can then be performed starting from the frames after that frame. This significantly reduces the computational effort involved in the similarity calculation process, shortens comparison time, and improves comparison efficiency. Furthermore, to ensure that the medical image with the highest similarity to the previous n frames is not missed, after determining the theoretical number of medical image frames corresponding to a 360-degree rotation of the medical image acquisition device, this number can be appropriately reduced to form the value of m.

[0050] In some optional specific implementations, step S102, i.e., comparing the first n frames of the medical image with the consecutive n frames of the first medical image, includes:

[0051] Step S1021 : Select the n frames of the first medical image by using a sliding window until the last frame of the medical image, wherein the length of the sliding window is n, the sliding step is s, and s is an integer greater than zero.

[0052] Specifically, the sliding step size can be 1, 2, or 3, etc. A sliding step size of 1 ensures accurate retrieval of the last medical image frame (i.e., the medical image captured when the medical image acquisition device rotates 360 degrees), thereby ensuring the accuracy of the constructed 3D medical image. A sliding step size greater than 1 improves comparison efficiency, but there is a possibility that the last medical image frame found is not the true last frame (i.e., the medical image captured when the medical image acquisition device rotates 360 degrees), but rather an adjacent medical image to the last frame.

[0053] Step S1022 : comparing the first n frames of medical images in the medical image with the currently selected n frames of first medical image.

[0054] In the embodiment of the present invention, a sliding window is used to select n frames of the first medical image for comparison with the previous n frames of medical images, thereby avoiding omissions in image comparison.

[0055] In some optional specific implementations, step S102, i.e., comparing the first n frames of the medical image with the consecutive n frames of the first medical image, includes:

[0056] Step S102a compares each of the first n medical image frames with the first medical image frames of the same order as the n first medical image frames to obtain n similarity values. That is, the i-th (i=1, 2, ..., n) medical image frame in the first n medical image frames is compared with the i-th medical image frame in the n (i=1, 2, ..., n) first medical image frames.

[0057] Step S102b: Calculate an average similarity value of the n similarity values as the similarity value between the n frames of medical images and the n frames of first medical images.

[0058] In an embodiment of the present invention, a sliding window is used to select n frames of first medical images for comparison with the previous n frames of medical images, and n similarity values are obtained. Finally, an average similarity value of the n similarity values is calculated as the similarity value between the n frames of medical images and the n frames of first medical images. This can avoid accidental similarity calculation errors that lead to errors in determining the last frame of image (i.e., the medical image acquired when the medical image acquisition device rotates 360 degrees), thereby affecting the accuracy of the constructed three-dimensional medical image.

[0059] Specifically, deep learning compression coding can be used for medical image comparison. First, a deep learning model can be used to compress the medical images to be compared, obtaining their corresponding low-dimensional representations. This is the compressed result. These low-dimensional representations are essentially highly abstract versions of the original images, retaining the most important feature information. With the compressed feature representation, similarity can be calculated. Common similarity calculation methods include Euclidean distance, cosine similarity, and more complex metric learning methods. Euclidean distance directly calculates the Euclidean distance between the feature vectors of two medical images. A smaller distance indicates greater similarity. Cosine similarity calculates the cosine of the angle between the feature vectors of two medical images. A value closer to 1 indicates greater similarity. Metric learning involves training a specialized metric network to learn how to better measure the similarity between two medical images. This method can consider more contextual information, resulting in more accurate results. The deep learning model can be a neural network based on an autoencoder or stacked autoencoder (SAE) architecture. The model consists of two parts: an encoder and a decoder. The encoder converts the input high-dimensional medical image into a low-dimensional representation (i.e., a compressed feature vector), while the decoder restores the original image from this low-dimensional representation. Furthermore, a variational autoencoder (VAE) or a generative adversarial network (GAN) can be introduced to further optimize model performance.

[0060] In other embodiments, medical image comparison can also be performed using the following method: First, key points in the medical image are detected using algorithms such as SIFT (Scale-Invariant Feature Transform) and SURF (Speeded-Up Robust Features), and descriptors, such as SIFT descriptors, are generated for each key point. Next, feature points of the two medical images are matched using algorithms such as KNN (K-Nearest Neighbors) and FLANN (Fast Library for Approximate Nearest Neighbors). Finally, metrics such as the number of matching points, Euclidean distance, and cosine similarity are calculated.

[0061] Step S103 : acquiring n consecutive frames of second medical images, wherein the n frames of second medical images have the greatest similarity to the first n frames of medical images.

[0062] For example, using a sliding window of size 3, n frames of the first medical image are selected in turn to compare with the previous n frames of medical images. The average similarity value obtained is as follows: Figure 3 As shown (in the figure, the middle frame first medical image among the n frames of first medical images is the horizontal axis).

[0063] Step S104: retain the n frames of medical images preceding the second medical image.

[0064] That is, n frames of second medical images and medical images subsequent to the n frames of second medical images are deleted.

[0065] Step S105, perform three-dimensional reconstruction based on the retained medical image. The specific reconstruction process is: first, map the pixel points on the two-dimensional medical image sequence to the corresponding position in the three-dimensional imaging space through coordinate transformation, and assign the pixel value to the voxel. Then, traverse the entire three-dimensional voxel grid, and perform interpolation calculations on the empty voxels that are not directly mapped. Commonly used methods include nearest neighbor interpolation, bilinear interpolation, trilinear interpolation, etc. Finally, you can choose the pixel method (PBM), voxel method (VBM) or function method (FBM) to perform the final volume reconstruction. In addition, after completing the three-dimensional medical image reconstruction, the generated three-dimensional data set can also be appropriately rendered to facilitate intuitive observation and analysis by clinicians.

[0066] The three-dimensional medical image construction method provided in this embodiment avoids the loss of captured two-dimensional medical image frames due to insufficient rotation angle by setting the rotation angle of the medical image acquisition device to slightly greater than 360 degrees, thereby ensuring that the two-dimensional medical images used for three-dimensional reconstruction are not missing. In addition, in the embodiment of the present invention, similarity comparison is also used to determine the last frame or frames of two-dimensional medical images scanned by the medical image acquisition device at 360 degrees, and to remove redundant two-dimensional medical images. This ensures that the two-dimensional medical images used for three-dimensional reconstruction are neither missing nor redundant, thereby ensuring the integrity and accuracy of the reconstructed three-dimensional medical images. For example, Figure 4 is a schematic top view of a three-dimensional medical image constructed without using the three-dimensional medical image construction method provided by the embodiment of the present invention. Figure 5 This is a top view schematic diagram of a three-dimensional medical image constructed using the three-dimensional medical image construction method provided by an embodiment of the present invention. Figure 4 and Figure 5 It can be seen that Figure 4 The accuracy of 3D medical images is not as good as Figure 5 The accuracy of the three-dimensional medical image shown. For example, Figure 6 is a schematic top view of another three-dimensional medical image constructed without using the three-dimensional medical image construction method provided by the embodiment of the present invention (due to the presence of redundant repeated two-dimensional medical image frames). Figure 7This is a top view schematic diagram of another three-dimensional medical image constructed using the three-dimensional medical image construction method provided by the embodiment of the present invention. Figure 6 and Figure 7 It can be seen that Figure 6 The accuracy of 3D medical images is not as good as Figure 7 The accuracy of the three-dimensional medical images shown.

[0067] This embodiment also provides a 3D medical image construction device for implementing the above-described embodiments and preferred implementations. Details already described will not be repeated. As used below, the term "module" may refer to a combination of software and / or hardware that implements a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, implementation using hardware, or a combination of software and hardware, is also possible and contemplated.

[0068] This embodiment provides a three-dimensional medical image construction device, such as Figure 8 As shown, including:

[0069] The first acquisition module 801 is configured to acquire a medical image acquired by a medical image acquisition device while rotating around a target object at a preset angle; the preset angle being greater than 360 degrees;

[0070] a comparing module 802 configured to compare first n frames of medical images in the medical image with n consecutive frames of first medical images, where n is an integer greater than zero, and the first medical images are medical images other than the first n frames of medical images;

[0071] A second acquisition module 803 is configured to acquire n consecutive frames of second medical images, wherein the n frames of second medical images have the greatest similarity to the first n frames of medical images;

[0072] A screening module 804 is configured to retain the medical images preceding the n frames of the second medical image;

[0073] The reconstruction module 805 is configured to perform three-dimensional reconstruction based on the retained medical image.

[0074] In some optional embodiments, the continuous n frames of first medical images are medical images following the mth frame of medical image, and m is less than or equal to the number of medical image frames that should be captured during the 360-degree rotation of the medical image acquisition device.

[0075] In some optional embodiments, n is an integer greater than 1 and less than 10.

[0076] In some optional implementations, the comparison module 802 includes:

[0077] a sliding selection unit, configured to select the n frames of the first medical image until the last frame of the medical image using a sliding window, wherein the length of the sliding window is n and the sliding step is s, where s is an integer greater than zero;

[0078] A comparing unit is used to compare the first n frames of medical images in the medical image with the currently selected n frames of first medical image.

[0079] In some optional implementations, the comparison module 802 includes:

[0080] a similarity calculation unit, configured to perform similarity comparison between each medical image in the first n frames of medical images and the first medical image in the n frames of first medical images having the same order as the first medical image, to obtain n similarity values;

[0081] The mean value calculation unit is used to calculate an average similarity value of the n similarity values as the similarity value between the n frames of medical images and the n frames of first medical images.

[0082] In some optional embodiments, the target object is breast tissue.

[0083] The further functional description of each of the above modules and units is the same as that of the above corresponding embodiments and will not be repeated here.

[0084] The three-dimensional medical image construction device in this embodiment is presented in the form of a functional unit, where the unit refers to an ASIC (Application Specific Integrated Circuit) circuit, a processor and memory that executes one or more software or fixed programs, and / or other devices that can provide the above functions.

[0085] The embodiment of the present invention also provides a medical device having the above Figure 8 The three-dimensional medical image construction device shown.

[0086] See also Figure 9 , Figure 9 is a structural diagram of a medical device provided by an optional embodiment of the present invention, such as Figure 9As shown, the medical device includes: one or more processors 10, a memory 20, and interfaces for connecting various components, including high-speed interfaces and low-speed interfaces. The various components utilize different buses to communicate with each other and can be installed on a common mainboard or installed in other ways as needed. The processor can process instructions executed in the medical device, including instructions stored in or on the memory to display graphical information of a GUI on an external input / output device (such as a display device coupled to the interface). In some optional embodiments, if necessary, multiple processors and / or multiple buses can be used together with multiple memories and multiple memories. Similarly, multiple medical devices can be connected, and each device provides some necessary operations (for example, as a server array, a group of blade servers, or a multi-processor system). Figure 9 A processor 10 is taken as an example.

[0087] The processor 10 may be a central processing unit, a network processor, or a combination thereof. The processor 10 may further include a hardware chip. The hardware chip may be an application-specific integrated circuit, a programmable logic device, or a combination thereof. The programmable logic device may be a complex programmable logic device, a field programmable gate array, a general purpose array logic, or any combination thereof.

[0088] The memory 20 stores instructions that can be executed by at least one processor 10, so that the at least one processor 10 executes the method shown in the above embodiment.

[0089] The memory 20 may include a program storage area and a data storage area, wherein the program storage area may store an operating system and application programs required for at least one function; the data storage area may store data created based on the use of the medical device, etc. In addition, the memory 20 may include a high-speed random access memory and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some optional embodiments, the memory 20 may optionally include a memory remotely located relative to the processor 10, and these remote memories may be connected to the medical device via a network. Examples of the aforementioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0090] The memory 20 may include a volatile memory, such as a random access memory; the memory may also include a non-volatile memory, such as a flash memory, a hard disk or a solid-state drive; the memory 20 may also include a combination of the above types of memory.

[0091] The medical device further includes an input device 30 and an output device 40. The processor 10, the memory 20, the input device 30 and the output device 40 may be connected via a bus or other means. Figure 9 The bus connection is taken as an example.

[0092] The input device 30 can receive input numeric or character information and generate key input signals related to user settings and function control of the medical device. Examples include a touch screen, keypad, mouse, trackpad, touchpad, pointer, one or more mouse buttons, trackball, joystick, etc. The output device 40 can include a display device, auxiliary lighting devices (e.g., LEDs), and tactile feedback devices (e.g., vibration motors). Such display devices include, but are not limited to, liquid crystal displays, light-emitting diodes, monitors, and plasma displays. In some optional embodiments, the display device can be a touch screen.

[0093] The medical device also includes a communication interface for the medical device to communicate with other devices or a communication network.

[0094] The embodiment of the present invention also provides a computer-readable storage medium. The above-mentioned method according to the embodiment of the present invention can be implemented in hardware, firmware, or implemented as a computer code that can be recorded in a storage medium, or implemented as a computer code that is originally stored in a remote storage medium or a non-temporary machine-readable storage medium and downloaded through a network and will be stored in a local storage medium, so that the method described herein can be stored in such software processing on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. Among them, the storage medium can be a magnetic disk, an optical disk, a read-only storage memory, a random access memory, a flash memory, a hard disk or a solid-state drive, etc.; further, the storage medium can also include a combination of the above-mentioned types of memory. It can be understood that a computer, a processor, a microprocessor controller or programmable hardware includes a storage component that can store or receive software or computer code. When the software or computer code is accessed and executed by a computer, a processor or hardware, the method shown in the above embodiment is implemented.

[0095] A portion of the present invention may be applied as a computer program product, such as a computer program instruction, which, when executed by a computer, can call or provide the method and / or technical solution according to the present invention through the operation of the computer. Those skilled in the art should understand that the form in which the computer program instruction exists in a computer-readable medium includes, but is not limited to, a source file, an executable file, an installation package file, etc. Accordingly, the way in which the computer program instruction is executed by the computer includes, but is not limited to: the computer directly executes the instruction, or the computer compiles the instruction and then executes the corresponding compiled program, or the computer reads and executes the instruction, or the computer reads and installs the instruction and then executes the corresponding installed program. Here, the computer-readable medium may be any available computer-readable storage medium or communication medium that can be accessed by the computer.

[0096] Although the embodiments of the present invention have been described with reference to the accompanying drawings, those skilled in the art may make various modifications and variations without departing from the spirit and scope of the present invention. Such modifications and variations are all within the scope defined by the appended claims.

Claims

1. A three-dimensional medical image construction method, characterized in that: The method comprises: Acquiring a medical image acquired by a medical image acquisition device while rotating around a target object through a preset angle; the preset angle being greater than 360 degrees; Comparing first n frames of medical images in the medical image with n consecutive frames of first medical images, where n is an integer greater than 1, the first medical images are medical images other than the first n frames of medical images, and the n consecutive frames of first medical images are medical images subsequent to the m-th frame of medical image, where m is less than or equal to the number of medical image frames that should be captured by the medical image acquisition device during a 360-degree rotation around the target object; The comparing the first n frames of medical images in the medical image with the consecutive n frames of first medical images specifically includes: selecting the n frames of first medical images until the last frame of the medical image using a sliding window, where the length of the sliding window is n and the sliding step is s, where s is an integer greater than zero; and comparing the first n frames of medical images in the medical image with the currently selected n frames of first medical images; Acquire n consecutive frames of second medical images, wherein the n frames of second medical images have the greatest similarity to the first n frames of medical images; retaining the n frames of medical images preceding the second medical image; Performing three-dimensional reconstruction based on the retained medical image; The comparing the first n frames of medical images in the medical image with the consecutive n frames of first medical images includes: performing similarity comparison on each medical image in the first n frames of medical images and the first medical image in the same order as the n frames of first medical images to obtain n similarity values; An average similarity value of the n similarity values is calculated as the similarity value between the n frames of medical images and the n frames of first medical images.

2. The method according to claim 1, characterized in that The n is an integer greater than 1 and less than 10.

3. The method according to any one of claims 1 to 2, characterized in that The comparing the first n frames of medical images in the medical image with the consecutive n frames of first medical images includes: Using a deep learning model to compress the first n frames of medical images and the n frames of first medical images to obtain corresponding low-dimensional representations; Based on the low-dimensional representations of the first n frames of medical images and the n frames of first medical images, similarities between the first n frames of medical images and the n frames of first medical images are calculated.

4. The method according to any one of claims 1 to 2, characterized in that The target object is breast tissue.

5. A three-dimensional medical image construction device, characterized in that: The device comprises: A first acquisition module is configured to acquire a medical image acquired by the medical image acquisition device during a process of rotating the target object around a preset angle; the preset angle is greater than 360 degrees; a comparison module, configured to compare first n frames of medical images in the medical image with n consecutive frames of first medical images, where n is an integer greater than 1, the first medical images are medical images other than the first n frames of medical images, and the n consecutive frames of first medical images are medical images subsequent to the m-th frame of medical image, where m is less than or equal to the number of medical image frames that the medical image acquisition device should acquire during a 360-degree rotation around the target object; The comparison module specifically includes: a sliding selection unit, configured to select the n frames of the first medical image using a sliding window until the last frame of the medical image, wherein the length of the sliding window is n and the sliding step is s, where s is an integer greater than zero; a comparison unit, configured to compare the first n frames of the medical image with the currently selected n frames of the first medical image; A second acquisition module is configured to acquire n consecutive frames of second medical images, wherein the n frames of second medical images have the greatest similarity to the first n frames of medical images; a screening module, configured to retain the medical images preceding the n frames of the second medical image; A reconstruction module, configured to perform three-dimensional reconstruction based on the retained medical image; Wherein, the comparison module includes: a similarity calculation unit, configured to perform similarity comparison between each medical image in the first n frames of medical images and the first medical image in the n frames of first medical images having the same order as the first medical image, to obtain n similarity values; The mean value calculation unit is used to calculate an average similarity value of the n similarity values as the similarity value between the n frames of medical images and the n frames of first medical images.

6. A medical device, characterized in that: include: A memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the three-dimensional medical image construction method according to any one of claims 1 to 4 by executing the computer instructions.

7. A computer-readable storage medium, characterized in that The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a computer to execute the three-dimensional medical image construction method according to any one of claims 1 to 4.

8. A computer program product, characterized in that The method comprises computer instructions for causing a computer to execute the three-dimensional medical image construction method according to any one of claims 1 to 4.

Images