Compression coding method, device and equipment for medical image

Through the adaptive compression coding method, the target compression coding parameters are determined based on the actual acquisition parameters of medical images, which solves the problem of poor image quality in the prior art, and achieves better compression effect and diagnostic information retention.

CN119052482APending Publication Date: 2024-11-29WUHAN UNITED IMAGING HEALTHCARE CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411080257.2
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-07
Publication Date
2024-11-29

AI Technical Summary

Technical Problem

The existing medical image compression coding technology is difficult to meet the requirements of clinical scenarios for image quality and key diagnostic information retention, resulting in poor image quality after compression.

Method used

By determining the actual acquisition parameters of medical images and determining matching target compression coding parameters based on these parameters, the adaptive compression coding method, including facet recognition and IDR frame determination, is used to compress and encode the medical images.

Benefits of technology

It achieves better compression effect, retains key diagnostic information in medical imaging, improves the compressed image quality, and adapts to the imaging needs of different clinical scenarios.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119052482A_ABST
    Figure CN119052482A_ABST
Patent Text Reader

Abstract

The invention provides a medical image compression coding method, device and equipment. The compression coding method comprises the following steps: determining actual acquisition parameters of a medical image; determining a target compression coding parameter matched with the actual acquisition parameter according to a corresponding relationship between the acquisition parameter and the compression coding parameter; and performing compression coding on the medical image according to the target compression coding parameter. According to the invention, adaptive compression coding is carried out on the medical image according to the actual acquisition parameter of the medical image, and the target compression coding parameter is determined according to the actual acquisition parameter of the medical image, so that the compression coding process is more in line with the characteristics of the medical image, and key diagnosis information in the medical image can be better reserved; therefore, a better compression effect is obtained, and the quality of medical images obtained through compression coding is better.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present disclosure relates to the field of compression coding technology, and in particular to a compression coding method, device, and equipment for medical images. Background Art

[0002] Medical images, such as ultrasound images, generate a large amount of data per second (about 50 to 300MB per second). If ultrasound images are to be saved to storage media or transmitted to external devices or the cloud via the network, a large amount of storage and network resources will be consumed. Compressing and encoding medical images can alleviate the problem of storage and network resources. However, clinical scenarios have high requirements for image quality and retention of key diagnostic information, and current compression coding technologies are difficult to meet the compression coding requirements of clinical scenarios. Summary of the invention

[0003] The technical problem to be solved by the present disclosure is to overcome the above-mentioned defects in the prior art and to provide a compression encoding method, device and equipment for medical images.

[0004] The present invention solves the above technical problems through the following technical solutions:

[0005] In a first aspect, a compression encoding method for medical images is provided, comprising:

[0006] Determine the actual acquisition parameters of medical images;

[0007] Determining target compression encoding parameters that match the actual acquisition parameters according to the corresponding relationship between the acquisition parameters and the compression encoding parameters;

[0008] The medical image is compressed and encoded according to the target compression encoding parameters.

[0009] Optionally, the corresponding relationship is characterized by a parameter determination model; the parameter determination model is obtained by training a neural network with training samples including acquisition parameters and compression encoding parameters;

[0010] Determining target compression encoding parameters that match the actual acquisition parameters according to the corresponding relationship between the acquisition parameters and the compression encoding parameters includes:

[0011] The actual acquisition parameters are input into the parameter determination model to output the target compression encoding parameters according to the parameter determination model.

[0012] Optionally, the corresponding relationship is obtained by fitting historical acquisition data including acquisition parameters and compression encoding parameters;

[0013] Determining target compression encoding parameters that match the actual acquisition parameters according to the corresponding relationship between the acquisition parameters and the compression encoding parameters includes:

[0014] Substituting the actual acquisition parameters into the fitting results, the target compression encoding parameters are obtained.

[0015] Optionally, the actual acquisition parameter includes at least one of the following: equipment performance of a medical image acquisition device, a type of an acquired object, a section recognition result of an image frame included in the medical image, a running speed of the acquired object, and a frame rate of the medical image;

[0016] And / or, the target compression encoding parameter includes at least one of the following: GOP size, bit rate, IDR frame.

[0017] Optionally, compressing and encoding the medical image according to the target compression encoding parameter includes:

[0018] Performing section recognition on each image frame included in the medical image;

[0019] An image frame whose slice recognition result meets the standard slice requirement is determined as an IDR frame;

[0020] The medical image is compressed and encoded according to the target compression encoding parameters and the IDR frame.

[0021] Optionally, in response to a switching instruction of a clinical scenario, actual acquisition parameters of the medical image are re-determined;

[0022] And / or, the medical image includes an ultrasound image.

[0023] In a second aspect, a compression encoding device for medical images is provided, comprising:

[0024] A first determination module is used to determine actual acquisition parameters of the medical image;

[0025] A second determination module is used to determine a target compression encoding parameter that matches the actual acquisition parameter according to a correspondence between the acquisition parameter and the compression encoding parameter;

[0026] A compression coding module is used to compress and encode the medical image according to the target compression coding parameters.

[0027] Optionally, the compression coding module includes:

[0028] A section recognition unit, used for performing section recognition on each image frame included in the medical image;

[0029] A determination unit, used for determining an image frame whose slice recognition result meets the standard slice requirement as an IDR frame;

[0030] A compression unit is used to compress and encode the medical image according to the target compression encoding parameters and the IDR frame.

[0031] Optionally, the first determination module re-determines the actual acquisition parameters of the medical image in response to a switching indication of the clinical scenario;

[0032] And / or, the medical image includes an ultrasound image.

[0033] In a third aspect, an electronic device is provided, comprising a memory, a processor, and a computer program stored in the memory and used to run on the processor, wherein when the processor executes the computer program, the medical image compression encoding method described in any one of the first aspects is implemented.

[0034] On the basis of being in accordance with the common sense in the art, the above-mentioned preferred conditions can be arbitrarily combined to obtain the preferred embodiments of the present disclosure.

[0035] The positive progressive effect of the present disclosure is that the present disclosure realizes adaptive compression encoding of medical images according to the actual acquisition parameters of the medical images. Since the target compression encoding parameters are determined according to the actual acquisition parameters of the medical images, the compression encoding process is more in line with the characteristics of medical images, and the key diagnostic information in the medical images can be better preserved, thereby obtaining a better compression effect, and the quality of the medical images obtained by compression encoding is better. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] Figure 1 A flowchart of a medical image compression encoding method provided by an exemplary embodiment of the present disclosure;

[0037] Figure 2 A GOP schematic diagram provided for an exemplary embodiment of the present disclosure;

[0038] Figure 3 An exemplary embodiment of the present disclosure provides a Figure 1 The specific flow chart of step 103;

[0039] Figure 4 A schematic diagram of an application scenario of a compression encoding method for medical images provided by an exemplary embodiment of the present disclosure;

[0040] Figure 5 A schematic diagram of a target compression coding parameter before and after adaptive adjustment provided by an exemplary embodiment of the present disclosure;

[0041] Figure 6 A module schematic diagram of a medical image compression encoding device provided by an exemplary embodiment of the present disclosure;

[0042] Figure 7 The present invention provides a schematic structural diagram of an electronic device according to an exemplary embodiment of the present invention. DETAILED DESCRIPTION

[0043] The present disclosure is further described below by way of examples, but the present disclosure is not limited to the scope of the examples.

[0044] Prefixes such as "first" and "second" are used in the embodiments of the present disclosure only to distinguish different description objects, and have no limiting effect on the position, order, priority, quantity or content of the described objects. The use of prefixes such as ordinal numbers to distinguish description objects in the embodiments of the present disclosure does not constitute a limitation on the described objects. For the statement of the described objects, please refer to the description in the context of the claims or embodiments, and no unnecessary limitation should be constituted due to the use of such prefixes. In addition, in the description of the present embodiment, unless otherwise specified, the meaning of "plurality" is two or more.

[0045] In the embodiments of the present disclosure, the collection, storage, use, processing, transmission, provision and disclosure of medical images and actual acquisition parameters involved are in compliance with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0046] Figure 1 This is a flowchart of a compression coding method for medical images provided by an exemplary embodiment of the present disclosure. The compression coding method is applicable to the storage, transmission, wireless probe and other scenarios of medical images. Figure 1 , the compression encoding method comprises the following steps:

[0047] Step 101: Determine actual acquisition parameters of medical images.

[0048] Medical images are images that can be produced in real time, such as ultrasound images.

[0049] The actual acquisition parameters are related to the clinical scenario and imaging quality, and include at least one of the following: the equipment performance of the medical image acquisition equipment, the type of the object being acquired, the section recognition results of the image frames contained in the medical image, the movement speed of the object being acquired, and the frame rate of the medical image.

[0050] For different clinical scenarios, at least one of the sampled object, the device performance of the medical imaging device, and the section type is different.

[0051] Step 102: According to the correspondence between the acquisition parameters and the compression encoding parameters, target compression encoding parameters matching the actual acquisition parameters are determined.

[0052] In one embodiment, the target compression encoding parameter includes at least one of the following: GOP (Group of Pictures) size, bit rate, and IDR (Instantaneous Decoder Refresh) frame.

[0053] When the actual acquisition parameters include device performance, the bit rate is positively correlated with the device performance, that is, the higher the device performance, the higher the bit rate. Device performance can be characterized by, but not limited to, the following parameters: processing speed, memory capacity, storage capacity and speed, image processing capability, network card performance\bandwidth, etc.

[0054] In the case where the actual acquisition parameters include the type of the acquired object, the target compression encoding parameters can be set according to the characteristics of the acquired object type, and the acquired object type can include but is not limited to anatomical structures such as the heart, liver, and brain. For example, the movement speed of the heart is faster than that of the liver, and the GOP corresponding to the medical image of the heart should be set larger than that of the medical image of the liver, and the bit rate corresponding to the medical image of the heart should be set larger than that of the medical image of the liver.

[0055] The slice recognition result included in the actual acquisition parameters includes the type of object to be collected and / or the image quality. In the case where the slice recognition result includes the type of object to be collected, the relationship between the slice recognition result and the target compression encoding parameters is similar to the relationship between the type of object to be collected and the target compression encoding parameters, and will not be repeated here. In the case where the slice recognition result includes the image quality, the IDR frame (Immediately refreshed I frame) can also be filtered according to the result of the slice recognition, which plays an immediate refresh role. At the same time, the details of the I frame are retained most completely, so when the standard slice is identified based on the image quality, it is immediately used as an IDR frame. The specific implementation process is described below.

[0056] When the actual acquisition parameters include the moving speed of the object being acquired, the GOP is positively correlated with the moving speed of the object being acquired, that is, the faster the moving speed, the larger the GOP. The bit rate is positively correlated with the moving speed, that is, the faster the moving speed, the larger the bit rate. The moving speed of the object being acquired can be, for example, the blood flow speed in the blood vessels, the beating speed of the heart, the peristalsis speed of the intestines, etc.

[0057] When the actual acquisition parameters include the frame rate of medical images, GOP is positively correlated with the frame rate, that is, the higher the frame rate, the larger the GOP. Bit rate is positively correlated with the frame rate, that is, the higher the frame rate, the larger the bit rate.

[0058] In one embodiment, an IDR frame is an image frame with good image quality in a medical image, that is, an image frame with image quality exceeding a quality threshold is recorded as an IDR frame. Image quality can be determined by, but is not limited to, at least one of spatial resolution, density resolution, artifact rate, contrast, noise, frame rate, and other parameters. Image quality can be determined based on the section recognition result.

[0059] In one embodiment, when the actual acquisition parameters change, the IDR frames are re-marked.

[0060] Step 103: compress and encode the medical image according to the target compression encoding parameters.

[0061] In the prior art, when compressing a video, the first frame of the video is used as an I frame (Intra-coded picture), and the video is compressed with a specific GOP size and a specific bit rate. Figure 2 , taking a GOP contained in a video as an example to briefly introduce the compression process:

[0062] Figure 2 The square filled with diagonal lines represents an I frame 21, and the square without filling represents a P frame 22 (predictive-frame).

[0063] The I frame is the starting frame of each GOP, contains a complete frame of image information, and uses intra-frame compression.

[0064] The P frame is a forward predicted frame, that is, the frame after the I frame in the GOP. It is predictively encoded with reference to other frames before the P frame, and has a relatively high compression ratio.

[0065] IDR frame is a special I frame. IDR frame can be transmitted independently with less information loss after compression. It plays an important role in refreshing the decoder status in the video stream.

[0066] Currently, when performing video compression, changes in clinical scenarios and different requirements for imaging quality are not taken into consideration. Directly applying existing video compression algorithms to medical image compression cannot meet the requirements of clinical scenarios.

[0067] Based on this, in the process of compressing and encoding medical images in this embodiment, the clinical scene and imaging quality of ultrasound images are taken into consideration. In step 103, the medical images are compressed and encoded according to at least one of the GOP size, bit rate, and IDR frame that match the actual acquisition parameters, so that the compression encoding process is more in line with the characteristics of medical images, and can reduce the loss of key diagnostic information in medical images during compression, so that the key diagnostic information in medical images can be better preserved. The specific implementation method of compressing and encoding medical images according to the target compression encoding parameters can refer to the relevant technical description, which will not be repeated here.

[0068] In this embodiment, adaptive compression encoding of medical images is implemented according to the actual acquisition parameters of the medical images. Since the target compression encoding parameters are determined according to the actual acquisition parameters of the medical images, the compression encoding process is more in line with the characteristics of medical images, and can reduce the loss of key diagnostic information in the medical images during compression, ensuring that the key diagnostic information can be better preserved, thereby obtaining a better compression effect, and the quality of the medical images obtained by compression encoding is better.

[0069] In one embodiment, the corresponding relationship is characterized by a parameter determination model. The parameter determination model is obtained by training a neural network with training samples including acquisition parameters and compression encoding parameters. The neural network can be, but is not limited to, a convolutional neural network. The training process of the neural network can refer to the description of the relevant technology, which will not be repeated here. The training sample can be clinical data or experimental data.

[0070] In step 102, the actual acquisition parameters are input into the parameter determination model, so as to output the target compression coding parameters according to the parameter determination model. A parameter determination model can be set for each target compression coding parameter, so that the corresponding target compression coding parameter is determined by the parameter determination model; or a parameter determination model can be set, and all target compression coding parameters are output by the parameter determination model; this is not particularly limited in the embodiments of the present disclosure.

[0071] In this embodiment, the target compression coding parameters are determined by the trained neural network, which can improve the accuracy and effectiveness of the target compression coding parameters, make them compatible with the characteristics of medical images, and further improve the compression coding effect.

[0072] In one embodiment, the corresponding relationship is obtained by fitting the historical acquisition data including acquisition parameters and compression encoding parameters. The fitting function can be set according to actual needs, and can use a linear function or a nonlinear function, which is not particularly limited in the embodiment of the present disclosure. The historical acquisition data can be clinical data or experimental data.

[0073] In step 102, the actual acquisition parameters are substituted into the fitting results to obtain the target compression coding parameters. A function can be fitted for each target compression coding parameter to determine the corresponding target compression coding parameter by the function; or a function can be fitted, the function including the variables corresponding to all target compression coding parameters, and all target compression coding parameters can be determined by the function; this is not particularly limited in the embodiments of the present disclosure.

[0074] In this embodiment, the target compression coding parameter is determined by the function obtained by fitting, which reduces the amount of calculation and can improve the rate of the target compression coding parameter, thereby improving the overall rate of compression coding.

[0075] In one embodiment, the corresponding relationship can also be represented by a list, and step 102 obtains the target compression encoding parameters matching the actual acquisition parameters by searching the list. In this embodiment, the amount of calculation is small, and the rate of the target compression encoding parameters can be increased, thereby improving the overall compression encoding rate.

[0076] In one embodiment, see Figure 3 , step 103 comprises:

[0077] Step 103 - 1 , performing section recognition on each image frame included in the medical image.

[0078] The purpose of section recognition is to identify the clarity and completeness of each image frame. For section recognition, please refer to the relevant technical description, which will not be repeated here.

[0079] Step 103 - 2 : Determine the image frame whose slice recognition result meets the standard slice requirement as an IDR frame.

[0080] The standard section requirements can be set according to the actual situation. The purpose of screening through the standard section requirements is to select image frames with good integrity and high clarity from medical images. Such image frames have high diagnostic value and are determined as IDR frames, that is, they are used as reference frames for other image frames in the GOP, so that the entire GOP can obtain better compression effects.

[0081] Step 103 - 3 , compress and encode the medical image according to the target compression encoding parameters and the IDR frame.

[0082] In this embodiment, during the real-time ultrasound scanning process, IDR frames are automatically selected based on the section recognition results, and compression encoding parameters that are compatible with the clinical scenario are automatically adjusted to achieve adaptive compression encoding, which has a good compression effect and a better quality of medical images obtained by compression encoding.

[0083] In one embodiment, in response to a switching instruction of a clinical scenario, actual acquisition parameters of the medical image are re-determined.

[0084] The switching instructions of the clinical scene can be manually triggered by medical staff, or they can be automatically generated when changes are detected in actual acquisition parameters that can characterize the clinical scene. For example, the switching instructions of the clinical scene are automatically generated when at least one of the actual acquisition parameters, such as the type of object being acquired, the section recognition result, the movement speed of the object being acquired, and the frame rate of the medical image, changes.

[0085] In this embodiment, after the clinical scene is switched, steps 101 to 103 are re-executed to automatically adjust the target compression encoding parameters to match the switched clinical scene, and then the medical images collected after the clinical scene is switched are compressed and encoded.

[0086] Combine the following Figure 4 and Figure 5 , taking ultrasound images as an example of medical imaging, the compression encoding process is further explained.

[0087] After the ultrasound probe collects ultrasound data, the ultrasound imaging link outputs the ultrasound image. Medical staff can trigger the switching of clinical scenes through the clinical scene switching interface and generate clinical scene switching instructions. For example, Figure 4 The object to be sampled in the image is switched from the heart to the liver, and the ultrasound imaging link will generate ultrasound images in the clinical scenario according to the preset parameters of the switched clinical scenario. The ultrasound images in different clinical scenarios have different frame rates and image details.

[0088] After receiving the switching instruction of the clinical scene, it is necessary to re-determine the actual acquisition parameters of the medical image, and determine the GOP size and bit rate that match the actual acquisition parameters. It is also necessary to perform section recognition on the ultrasound image and mark the image frames whose section recognition results meet the standard section requirements as IDR frames. See Figure 5 The frame sequence after self-adaptive adjustment is obtained (the figure also shows the frame sequence comparison before and after the adjustment), triggering the subsequent compression encoding of the ultrasound image based on the re-determined new GOP size, bit rate and IDR frame 23. The specific implementation process of compression encoding is described in the relevant technology, which will not be repeated here.

[0089] Corresponding to the aforementioned embodiment of the compression encoding method of medical images, the present disclosure also provides an embodiment of the compression encoding device of medical images.

[0090] Figure 6 A schematic diagram of a module of a medical image compression encoding device provided by an exemplary embodiment of the present disclosure, the device comprising:

[0091] A first determination module 61 is used to determine actual acquisition parameters of the medical image;

[0092] A second determination module 62 is used to determine a target compression encoding parameter that matches the actual acquisition parameter according to the corresponding relationship between the acquisition parameter and the compression encoding parameter;

[0093] The compression coding module 63 is used to compress and code the medical image according to the target compression coding parameters.

[0094] Optionally, the corresponding relationship is characterized by a parameter determination model; the parameter determination model is obtained by training a neural network with training samples including acquisition parameters and compression encoding parameters;

[0095] The second determining module 62 is specifically used for:

[0096] The actual acquisition parameters are input into the parameter determination model to output the target compression encoding parameters according to the parameter determination model.

[0097] Optionally, the corresponding relationship is obtained by fitting historical acquisition data including acquisition parameters and compression encoding parameters;

[0098] The second determining module 62 is specifically used for:

[0099] Substituting the actual acquisition parameters into the fitting results, the target compression encoding parameters are obtained.

[0100] Optionally, the actual acquisition parameter includes at least one of the following: equipment performance of a medical image acquisition device, a type of an acquired object, a section recognition result of an image frame included in the medical image, a movement speed of the acquired object, and a frame rate of the medical image;

[0101] And / or, the target compression encoding parameter includes at least one of the following: GOP size, bit rate, IDR frame.

[0102] Optionally, the compression coding module includes:

[0103] A section recognition unit, used for performing section recognition on each image frame included in the medical image;

[0104] A determination unit, used for determining an image frame whose slice recognition result meets the standard slice requirement as an IDR frame;

[0105] A compression unit is used to compress and encode the medical image according to the target compression encoding parameters and the IDR frame.

[0106] Optionally, the first determination module re-determines the actual acquisition parameters of the medical image in response to a switching indication of the clinical scenario;

[0107] And / or, the medical image includes an ultrasound image.

[0108] For the device embodiment, since it basically corresponds to the method embodiment, the relevant parts can refer to the partial description of the method embodiment. The device embodiment described above is only illustrative, wherein the units described as separate components may or may not be physically separated, and the components as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the disclosed solution.

[0109] Figure 7 This is a structural schematic diagram of an electronic device shown in an example embodiment of the present disclosure, the electronic device includes a memory, a processor, and a computer program stored in the memory and used to run on the processor, and when the processor executes the computer program, the compression encoding method of medical images described in any of the above embodiments is implemented. Figure 7 The electronic device 70 shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present disclosure.

[0110] like Figure 7As shown, the electronic device 70 may be in the form of a general-purpose computing device, for example, it may be a server device. The components of the electronic device 70 may include, but are not limited to: at least one processor 71, at least one memory 72, and a bus 73 connecting different system components (including the memory 72 and the processor 71).

[0111] The bus 73 includes a data bus, an address bus, and a control bus.

[0112] The memory 72 may include a volatile memory, such as a random access memory (RAM) 721 and / or a cache memory 722 , and may further include a read-only memory (ROM) 723 .

[0113] The memory 72 may also include a program tool 725 (or utility) having a set (at least one) of program modules 724, such program modules 724 including but not limited to: an operating system, one or more application programs, other program modules and program data, each of which or some combination may include an implementation of a network environment.

[0114] The processor 71 executes various functional applications and data processing by running the computer program stored in the memory 72, such as the compression encoding method of medical images provided in any of the above embodiments.

[0115] The electronic device 70 may also communicate with one or more external devices 74 (e.g., keyboards, pointing devices, etc.). Such communication may be performed via an input / output (I / O) interface 75. Furthermore, the electronic device 70 may also communicate with one or more networks (e.g., local area networks (LANs), wide area networks (WANs), and / or public networks, such as the Internet) via a network adapter 76. As shown, the network adapter 76 communicates with other modules of the electronic device 70 via a bus 73. It should be understood that, although not shown in the figure, other hardware and / or software modules may be used in conjunction with the electronic device 70, including but not limited to: microcode, device drivers, redundant processors, external disk drive arrays, RAID (disk array) systems, tape drives, and data backup storage systems, etc.

[0116] It should be noted that although several units / modules or sub-units / modules of the electronic device are mentioned in the above detailed description, this division is merely exemplary and not mandatory. In fact, according to the embodiments of the present disclosure, the features and functions of two or more units / modules described above can be embodied in one unit / module. Conversely, the features and functions of one unit / module described above can be further divided into multiple units / modules to be embodied.

[0117] The embodiments of the present disclosure further provide a computer-readable storage medium having a computer program stored thereon, and when the program is executed by a processor, the medical image compression encoding method provided in any of the above embodiments is implemented.

[0118] The readable storage medium may include but is not limited to: a portable disk, a hard disk, a random access memory, a read-only memory, an erasable programmable read-only memory, an optical storage device, a magnetic storage device or any suitable combination of the above.

[0119] The present disclosure also provides a computer program product, including a computer program, which implements any of the above-mentioned medical image compression encoding methods when executed by a processor.

[0120] Among them, the program code for executing the computer program product of the present disclosure can be written in any combination of one or more programming languages, and the program code can be executed completely on the user device, partially on the user device, as an independent software package, partially on the user device and partially on a remote device, or completely on the remote device.

[0121] Although the specific embodiments of the present disclosure are described above, those skilled in the art should understand that this is only an example, and the protection scope of the present disclosure is defined by the appended claims. Those skilled in the art may make various changes or modifications to these embodiments without departing from the principles and essence of the present disclosure, but these changes and modifications all fall within the protection scope of the present disclosure.

Claims

1. A compression coding method for medical images, It is characterized in that include: Determine the actual acquisition parameters of medical images; Determining target compression encoding parameters that match the actual acquisition parameters according to the corresponding relationship between the acquisition parameters and the compression encoding parameters; The medical image is compressed and encoded according to the target compression encoding parameters.

2. The method for compressing and encoding medical images according to claim 1, It is characterized in that The corresponding relationship is characterized by a parameter determination model; the parameter determination model is obtained by training a neural network with training samples including acquisition parameters and compression encoding parameters; Determining target compression encoding parameters that match the actual acquisition parameters according to the corresponding relationship between the acquisition parameters and the compression encoding parameters includes: The actual acquisition parameters are input into the parameter determination model to output the target compression encoding parameters according to the parameter determination model.

3. The medical image compression encoding method according to claim 1, It is characterized in that The corresponding relationship is obtained by fitting the historical acquisition data including acquisition parameters and compression encoding parameters; Determining target compression encoding parameters that match the actual acquisition parameters according to the corresponding relationship between the acquisition parameters and the compression encoding parameters includes: Substituting the actual acquisition parameters into the fitting results, the target compression encoding parameters are obtained.

4. The method for compressing and encoding medical images according to claim 1, It is characterized in that The actual acquisition parameters include at least one of the following: equipment performance of the medical image acquisition equipment, the type of the acquired object, the section recognition result of the image frame included in the medical image, the movement speed of the acquired object, and the frame rate of the medical image; And / or, the target compression encoding parameter includes at least one of the following: GOP size, bit rate, IDR frame.

5. The medical image compression encoding method according to claim 1, It is characterized in that Compression encoding the medical image according to the target compression encoding parameter includes: Performing section recognition on each image frame included in the medical image; An image frame whose slice recognition result meets the standard slice requirement is determined as an IDR frame; The medical image is compressed and encoded according to the target compression encoding parameters and the IDR frame.

6. The medical image compression encoding method according to any one of claims 1 to 5, It is characterized in that In response to a switching instruction of a clinical scenario, re-determining actual acquisition parameters of the medical image; And / or, the medical image includes an ultrasound image.

7. A compression encoding device for medical images, It is characterized in that include: A first determination module is used to determine actual acquisition parameters of the medical image; A second determination module is used to determine a target compression encoding parameter that matches the actual acquisition parameter according to a correspondence between the acquisition parameter and the compression encoding parameter; A compression coding module is used to compress and encode the medical image according to the target compression coding parameters.

8. The medical image compression encoding device according to claim 7, It is characterized in that The compression coding module comprises: A section recognition unit, used for performing section recognition on each image frame included in the medical image; A determination unit, used for determining an image frame whose slice recognition result meets the standard slice requirement as an IDR frame; A compression unit is used to compress and encode the medical image according to the target compression encoding parameters and the IDR frame.

9. The medical image compression encoding device according to claim 7 or 8, It is characterized in that The first determination module re-determines the actual acquisition parameters of the medical image in response to the switching indication of the clinical scenario; And / or, the medical image includes an ultrasound image.

10. An electronic device comprising a memory, a processor, and a computer program stored in the memory and for running on the processor, It is characterized in that When the processor executes the computer program, the medical image compression encoding method according to any one of claims 1 to 6 is implemented.