Liver eight-segment segmentation model based on deep learning and training method and segmentation method thereof

Abstract

The invention provides a liver eight-segment segmentation model based on deep learning and a training method and segmentation method thereof, and the model comprises an input layer which is used for receiving input data to obtain a target sequence; the normalization layer is used for normalizing the target sequence; the linear layer is used for changing the dimension of intermediate processing data of the current model; the convolution layer is used for carrying out feature extraction on intermediate processing data of the current model; the activation layer is used for performing nonlinear conversion on the output of the convolution layer by using an activation function; and the output layer is used for calculating and processing the model according to a preset loss function and outputting a model segmentation result. According to the liver eight-segment segmentation model based on deep learning and the training method and the segmentation method thereof, the deep learning algorithm is adopted, different data features and changes can be better adapted, automatic segmentation is achieved, the segmentation accuracy is improved, large-scale medical image data can be rapidly processed and analyzed, and the segmentation efficiency is improved. And the liver eight-segment segmentation efficiency is improved.

Description

Technical Field

[0001] The present invention belongs to the technical field of image processing, and in particular relates to a deep learning-based liver eight-segment segmentation model and a training method and a segmentation method thereof. Background Art

[0002] In medical imaging, liver segmentation is a key clinical task that can help doctors accurately diagnose liver lesions and develop treatment plans. Traditionally, the main method used by doctors is the Couinaud segmentation method, but in practical application, it has the following disadvantages:

[0003] (1) The traditional Couinaud segmentation method is based on standard anatomical structures and does not adequately address the variability of liver anatomy between individuals;

[0004] (2) Traditional segmentation methods rely on the doctor's experience and manual operation, which is subjective and complex. Different doctors may have different segmentation results, which affects the consistency of diagnosis and treatment. Summary of the invention

[0005] In view of the above-mentioned shortcomings of the prior art, the object of the present invention is to provide a deep learning-based liver eight-segment segmentation model and its training method and segmentation method, so as to solve the above-mentioned problems.

[0006] In a first aspect, the present invention provides a deep learning-based liver eight-segment segmentation model, comprising:

[0007] The input layer is used to receive input data to obtain the target sequence;

[0008] A normalization layer, used to normalize the target sequence;

[0009] Linear layer, used to change the dimension of the intermediate processed data of the current model;

[0010] Convolutional layer, used to extract features from the intermediate processing data of the current model;

[0011] The activation layer is used to perform nonlinear transformation on the output of the convolutional layer using the activation function;

[0012] The output layer is used to calculate the model using the preset loss function and output the model segmentation results.

[0013] In a first aspect, the present invention provides a training method for a deep learning-based liver eight-segment segmentation model, which is applied to the deep learning-based liver eight-segment segmentation model, and the method comprises:

[0014] Acquire input images to obtain a training set and a validation set, wherein the input images include liver images with data labels;

[0015] Inputting the training set into the liver eight-segment segmentation model for testing, and using the validation set for validation to perform iterative training, wherein the iteration is stopped when the number of iterations reaches a target iteration value, or the iteration is stopped when the loss function reaches a target loss value;

[0016] After the iteration is completed, the finally trained liver eight-segment segmentation model is output based on the optimal model.

[0017] In a possible implementation of the present application, training a liver eight-segment segmentation model specifically includes:

[0018] Performing image processing based on the input image to obtain a target sequence, wherein the image processing method at least includes a block operation and an addition operation;

[0019] When performing a block operation, the input image is divided into blocks according to a preset format, and each block image is converted into a one-dimensional vector using a serialization operation;

[0020] During the addition operation, the target sequence is obtained by performing an addition operation based on the position information of each block image and the one-dimensional vector sequence.

[0021] In a possible implementation of the present application, when performing block operations, the following steps are specifically included:

[0022] Get the image specifications of the input image, where the input image specifications are H*W, where H is the input image height and W is the input image width;

[0023] Performing a block operation on the input image to obtain a block image, wherein the block image is a square image, the block image specification is P*P, and N=H*W / (P*P), P is the side length of the block image, and N is the number of block images;

[0024] The block image is converted into a one-dimensional vector N*D, where D is the length of the sequence after serialization.

[0025] In a possible implementation of the present application, training the liver eight-segment segmentation model specifically includes:

[0026] Normalizing the target sequence and then changing its dimension to obtain first processed data;

[0027] Performing a convolution operation and an activation function processing on the first processed data to obtain second processed data;

[0028] Processing the second processed data using a structured state space model to obtain third processed data;

[0029] Processing the first processed data by using an activation function, multiplying the data with the third processed data, and performing dimension change to obtain fourth processed data;

[0030] Performing feature map dimension restoration based on the fourth processed data to obtain fifth processed data;

[0031] Upsampling and convolution operations are performed based on the fifth processed data to restore the feature map and the target mask.

[0032] In a possible implementation of the present application, the loss function used when training the eight-segment liver segmentation model is the Dice-CE Loss loss function, and the ratio of the training set to the validation set is 4:1.

[0033] In a third aspect, the present invention provides a training system for a liver eight-segment segmentation model based on deep learning, the system comprising:

[0034] An acquisition module, used for acquiring input images to obtain a training set and a validation set, wherein the input images include liver images with data labels;

[0035] A training module, used for inputting the training set into the liver eight-segment segmentation model for testing, and using the validation set for validation, and performing iterative training, wherein the iteration is stopped when the number of iterations reaches a target iteration value, or the iteration is stopped when the loss function reaches a target loss value;

[0036] The output module is used to output the finally trained liver eight-segment segmentation model based on the optimal model after the iteration is completed.

[0037] In a fourth aspect, the present invention provides an electronic device, the electronic device comprising: a processor and a memory;

[0038] The memory is used to store computer programs;

[0039] The processor is used to execute the computer program stored in the memory so that the electronic device executes the above-mentioned training method of the eight-segment liver segmentation model based on deep learning.

[0040] In a fifth aspect, the present invention provides a computer-readable storage medium having a computer program stored thereon, which, when executed by an electronic device, implements the above-mentioned training method for the deep learning-based eight-segment liver segmentation model.

[0041] In a sixth aspect, the present invention provides a segmentation method of an eight-segment liver segmentation model based on deep learning, characterized in that the eight-segment liver segmentation model trained by any one of the training methods for the eight-segment liver segmentation model based on deep learning is applied, wherein the segmentation method comprises:

[0042] Obtain the image to be segmented;

[0043] Inputting the image to be segmented into a trained liver eight-segment segmentation model for processing to obtain a segmentation result;

[0044] A target segmented image is output based on the segmentation result.

[0045] As described above, the deep learning-based liver eight-segment segmentation model and its training method and segmentation method described in the present invention have the following beneficial effects:

[0046] (1) Improved accuracy: The present invention can extract more accurate features from a large amount of medical imaging data in liver segmentation, thereby achieving more accurate liver segmentation. Compared with traditional rule-based or feature engineering methods, it can better adapt to different data features and changes, thereby improving the accuracy of segmentation.

[0047] (2) Improved automation: The present invention can realize automatic analysis and processing of medical images, thereby reducing the workload of doctors. Traditional liver segmentation requires doctors to manually draw areas or perform complex calculations, while the deep learning-based liver eight-segment segmentation model of the present invention can realize automatic segmentation, saving doctors' time and reducing the impact of human factors on the results.

[0048] (3) Enhanced applicability: The deep learning-based algorithm used in the present invention has strong generalization ability and can adapt to medical imaging data of different types and qualities. Therefore, it can be applied to various clinical scenarios. Whether it is different types of medical imaging data such as MRI, CT or ultrasound, the deep learning algorithm can achieve better liver segmentation effect, thereby improving the applicability of the algorithm;

[0049] (4) Speed ​​improvement: Liver segmentation is a complex and time-consuming task, and the present invention can take advantage of parallel computing to achieve rapid processing and analysis of large-scale medical imaging data, thereby improving the speed and efficiency of segmentation. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] Figure 1 Shown is a schematic diagram of a scene of an electronic device in an embodiment of the present invention;

[0051] Figure 2 It is a schematic diagram showing the steps of a training method of a liver eight-segment segmentation model based on deep learning in one embodiment of the present invention;

[0052] Figure 3 Shown is a schematic diagram of the structure of the liver eight-segment segmentation model based on deep learning of the present invention;

[0053] Figure 4Shown is a schematic diagram of the steps of a training method for a deep learning-based liver eight-segment segmentation model in one embodiment of the present invention;

[0054] Figure 5 It is a schematic diagram showing the steps of a training method of a liver eight-segment segmentation model based on deep learning in one embodiment of the present invention;

[0055] Figure 6 Shown is a schematic structural diagram of a training system for a deep learning-based liver eight-segment segmentation model in one embodiment of the present invention;

[0056] Figure 7 Shown is a schematic diagram of the structure of an electronic device of the present invention in one embodiment;

[0057] Figure 8 It is a schematic diagram showing the steps of a segmentation method of the liver eight-segment segmentation model based on deep learning in one embodiment of the present invention;

[0058] Fig. 9 A schematic diagram showing an input image of an embodiment of a deep learning-based liver eight-segment segmentation model of the present invention;

[0059] Fig. 10A A cross-sectional view showing the segmentation result of the liver eight-segment segmentation model based on the depth school in one embodiment of the present invention;

[0060] Fig. 10B Shown is a front view of the segmentation result of the liver eight-segment segmentation model based on the deep learning system in one embodiment of the present invention;

[0061] Fig. 10C A side view showing the segmentation result of the liver eight-segment segmentation model based on the depth school in one embodiment of the present invention;

[0062] Fig.11 Shown is a cross-sectional view of an input image of an eight-segment liver segmentation model based on depth learning in one embodiment of the present invention. DETAILED DESCRIPTION

[0063] The following describes the embodiments of the present invention by specific examples, and those skilled in the art can easily understand other advantages and effects of the present invention from the contents disclosed in this specification. The present invention can also be implemented or applied through other different specific embodiments, and the details in this specification can also be modified or changed in various ways based on different viewpoints and applications without departing from the spirit of the present invention. It should be noted that the following embodiments and features in the embodiments can be combined with each other without conflict.

[0064] It should be noted that the illustrations provided in the following embodiments are only schematic illustrations of the basic concept of the present invention, and thus the drawings only show components related to the present invention rather than being drawn according to the number, shape and size of components in actual implementation. In actual implementation, the type, quantity and proportion of each component may be changed arbitrarily, and the component layout may also be more complicated.

[0065] The following embodiments of the present invention provide a training method for a liver eight-segment segmentation model based on deep learning, which can be applied to Figure 1 The electronic device shown. The electronic device described in the present invention may include a mobile phone 11 with a wireless charging function, a tablet computer 12, a laptop computer 13, a wearable device, a vehicle-mounted device, an augmented reality (AR) / virtual reality (VR) device, an ultra-mobile personal computer (UMPC), a netbook, a personal digital assistant (PDA), etc. The embodiment of the present invention does not impose any restrictions on the specific type of the electronic device.

[0066] For example, the electronic device may be a station (STAION, ST) in a WLAN with a wireless charging function, a cellular phone, a cordless phone, a Session Initiation Protocol (SIP) phone, a Wireless Local Loop (WLL) station, a Personal Digital Assistant (PDA) device, a handheld device with a wireless charging function, a computing device or other processing device, a computer, a laptop computer, a handheld communication device, a handheld computing device, and / or other devices for communicating on a wireless system and a next generation communication system, such as a mobile terminal in a 5G network, a mobile terminal in a future evolved Public Land Mobile Network (PLMN), or a mobile terminal in a future evolved Non-terrestrial Network (NTN), etc.

[0067] For example, the electronic device can communicate with the network and other devices through wireless communication. The above wireless communication can use any communication standard or protocol, including but not limited to Global System of Mobilecommunication (GSM), General Packet Radio Service (GPRS), Code Division Multiple Access (CDMA), Wideband Code Division Multiple Access (WCDMA), Long Term Evolution (LTE), email, Short Messaging Service (SMS), BT, GNSS, WLAN, NFC, FM, and / or IR technology. The GNSS can include Global Positioning System (GPS), Global Navigation Satellite System (GLONASS), BeiDou navigation Satellite System (BDS), Quasi-Zenith Satellite System (QZSS) and / or Satellite Based Augmentation Systems (SBAS).

[0068] The technical solutions in the embodiments of the present invention will be described in detail below in conjunction with the accompanying drawings in the embodiments of the present invention.

[0069] Furthermore, Couinaud's method of segmentation is an important technique based on the anatomical structure of the liver. It is based on the distribution of the Glisson system in the liver. Couinaud is the surname of French anatomist Pierre Couinaud, which is used to describe the anatomical structure of the liver. Specifically, the Glisson system is a duct system composed of the branches of the portal vein, hepatic artery and bile duct in the liver, which is distributed in the liver in a tree-like manner. According to Couinaud's method, the liver is divided into "2" hemilivers, "4" regions and "8" liver segments. This division is based on specific anatomical structures formed by the portal fissure, the middle fissure and the left and right interlobar fissure, which divide the liver into different functional areas. Specifically, the portal fissure divides the liver into "4" sectors, and each sector is further divided into upper and lower segments by the horizontal section of the left and right branches of the portal vein. The caudate lobe is classified as segment I and exists as an autonomous segment. The median hepatic fissure divides the liver into left and right hemilivers, and the left interlobar fissure and the right interlobar fissure further subdivide the left and right hemilivers into left outer sector, left inner sector, right anterior sector, and right posterior sector.

[0070] This method of liver segmentation based on the Glisson system has important guiding significance in liver surgery. Since each liver segment receives a branch from the Glisson system, especially the branch of the portal vein system, clinicians can perform minimal resection according to the condition of the lesion to preserve normal liver tissue as much as possible. In medical imaging, this method can also accurately locate liver segments by identifying the hepatic vein, portal vein and other structures. Therefore, Couinaud's liver segmentation method not only provides an important theoretical basis for liver anatomy, but also provides practical guidance for clinical diagnosis and surgery.

[0071] However, with further research on the anatomical structure of intrahepatic ducts, people have found that there are significant anatomical variations in the vascular structure inside the liver. These anatomical variations may cause the traditional Couinaud segmentation method to be unable to accurately reflect the liver anatomical structure of some individuals. Therefore, the research and improvement of the background technology of the liver segmentation method becomes crucial. In response to this situation, the present invention begins to explore the use of high-resolution medical imaging and deep learning technology to improve the liver segmentation method. By utilizing a large amount of medical imaging data, the deep learning model is used to learn from the image and accurately segment the various functional areas of the liver. This deep learning-based liver segmentation method can better cope with the variation of the liver's anatomical structure and provide more accurate anatomical guidance for clinical imaging diagnosis and liver surgery. The development of this technology will bring important progress to the diagnosis and treatment of liver diseases and provide better medical services for patients, thereby proposing the deep learning-based liver eight-segment segmentation model and its training method and segmentation method of the present invention.

[0072] Specifically, see Figure 2 In one embodiment of the invention, the training method of the deep learning-based liver eight-segment segmentation model of the present invention comprises the following steps:

[0073] Step S202, acquiring input images to obtain a training set and a validation set, wherein the input images include liver images with data labels;

[0074] Step S204, inputting the training set into the liver eight-segment segmentation model for testing, and using the validation set for validation to perform iterative training, wherein the iteration is stopped when the number of iterations reaches a target iteration value, or when the loss function reaches a target loss value;

[0075] Step S206: after the iteration is completed, the finally trained liver eight-segment segmentation model is output based on the optimal model.

[0076] It should be noted that, in this embodiment, the training method of the liver eight-segment segmentation model specifically described is applied to the liver eight-segment segmentation model based on deep learning, wherein, Figure 3 As shown, in one embodiment of the invention, the deep learning-based liver eight-segment segmentation model 30 specifically includes: an input layer 31, used to receive input data to obtain a target sequence; a normalization layer 32, used to normalize the target sequence; a linear layer 33, used to change the dimension of the intermediate processing data of the current model; a convolutional layer 34, used to extract features from the intermediate processing data of the current model; an activation layer 35, used to perform nonlinear transformation on the output of the convolutional layer using an activation function; and an output layer 36, used to calculate and process the model using a preset loss function and output the model segmentation result.

[0077] Furthermore, after constructing the liver eight-segment segmentation model based on deep learning, it needs to be trained, wherein first, an input image is obtained, wherein the input image is a liver image with a data label, and the input image is classified to obtain a training set and a validation set, specifically distinguished according to a ratio of "4:1". After obtaining the training set and the validation set, the liver eight-segment segmentation model is tested based on the training set, and the validation set is used for verification to perform multiple iterations of training, wherein stopping the iteration can be divided into two situations, one is to stop the iteration when the number of iterations reaches the target iteration value, such as stopping the iteration when the iteration reaches "400" times; the other is to stop the iteration when the loss function reaches the target loss value, such as stopping the iteration when the target loss value reaches "0.05" or less. Accordingly, the loss function used in training the liver eight-segment segmentation model is the Dice-CE Loss loss function, wherein Dice Loss is a loss function for image segmentation tasks, which has been widely used in fields such as medical image segmentation. It can solve the problem of poor performance of cross entropy loss function on unbalanced data sets, and CELoss is also a commonly used function in classification tasks. It is a measure of the cross entropy between the predicted probability distribution and the true label probability distribution. Therefore, in this embodiment, the two are combined as the loss function of the liver eight-segment segmentation model. Since it is a specific application of the prior art in this embodiment, the details are not repeated.

[0078] Furthermore, after the iteration is completed, the final trained liver eight-segment segmentation model is output based on the optimal model, wherein a model will be obtained after each iteration of training and verification, and the optimal model is selected from the models of each iteration as the final target model, which corresponds to the trained liver eight-segment segmentation model.

[0079] Further, in one embodiment of the invention, if Figure 4 As shown, training the liver eight-segment segmentation model specifically includes the following steps:

[0080] Step S402, performing image processing based on the input image to obtain a target sequence, wherein the image processing method at least includes a block operation and an addition operation;

[0081] Step S404, during the block operation, the input image is divided into blocks according to a preset format, and each block image is converted into a one-dimensional vector by using a serialization operation;

[0082] Step S406 , during the summing operation, the target sequence is obtained by performing a summing operation based on the position information of each block image and the one-dimensional vector sequence.

[0083] It should be noted that, in this embodiment, after the input image is obtained, image processing is performed on it to obtain the target sequence, wherein the processing process includes first dividing into blocks, then converting the dimension, and finally performing a sum operation to obtain the target sequence. Specifically, the input image is first divided into blocks, wherein, in one embodiment of the invention, the picture specifications of the input image are first obtained, wherein the input image specifications are H*W, wherein H is the input image height and W is the input image width; then the input image is divided into blocks to obtain a block image, wherein the block image is a square image, the block image specification is P*P, and N=H*W / (P*P), P is the side length of the block image, and N is the number of block images; further, after obtaining the block image, it is dimensional converted, specifically, the block image is converted into a one-dimensional vector N*D, wherein D is the sequence length value after serialization.

[0084] Furthermore, after completing the block operation, a summation operation is performed, wherein the position of each block image in the original image (input image) is first obtained to obtain the corresponding position information, and then the position information of each block image is summed with the one-dimensional vector sequence to obtain the target sequence.

[0085] Further, in one embodiment of the invention, if Figure 5 As shown, the training of the liver eight-segment segmentation model specifically includes the following steps:

[0086] Step S502, normalizing the target sequence and then changing the dimension to obtain first processed data;

[0087] Step S504, performing a convolution operation and an activation function processing on the first processed data to obtain second processed data;

[0088] Step S506, processing the second processed data using a structured state space model to obtain third processed data;

[0089] Step S508, processing the first processed data using an activation function, multiplying the result with the third processed data, and performing dimension change to obtain fourth processed data;

[0090] Step S510, performing feature map dimension restoration based on the fourth processed data to obtain fifth processed data;

[0091] Step S512: performing upsampling and convolution operations based on the fifth processed data to restore a feature map and a target mask.

[0092] It should be noted that, in this embodiment, since the above embodiment illustrates that the liver eight-segment segmentation model based on deep learning includes a normalization layer, a linear layer, a convolutional layer and an activation layer in addition to an input layer and an output layer, each layer processes the data in a different manner. Specifically, after obtaining the target sequence, the target sequence is normalized (RMS Norm) and the dimension is changed (upgraded to three times the original dimension) to obtain the first processed data X1 (N*3D), and then the first processed data is convolved (a 2d convolution operation with padding "1" and kernelsize "3") and an activation function (silu) is performed to obtain the second processed data X2 (N*3D); the second processed data is processed using a structured state space model (Selective State Space Model) to obtain third processed data X3 (N*3D); the first processed data is processed by using an activation function and then multiplied with the third processed data, and the dimension is changed (reduced to one time) to obtain fourth processed data X4 (N*D); based on the fourth processed data, the feature map dimension is restored to obtain fifth processed data X5 (H / P*W / P*D); based on the fifth processed data, upsampling and convolution operations are performed to restore the feature map (H*W*K) and the target mask (Mask).

[0093] Furthermore, by continuously iteratively optimizing the liver eight-segment segmentation model for the input images (training set and validation set), a trained optimal liver eight-segment segmentation model can be finally obtained for subsequent applications. Therefore, in actual applications, an image to be segmented can be directly input, and after being processed by the trained liver eight-segment segmentation model in this embodiment, the corresponding segmentation result can be obtained based on the model output.

[0094] An embodiment of the present application also provides a training system for an eight-segment liver segmentation model based on deep learning. The training system for an eight-segment liver segmentation model based on deep learning can implement the training method for an eight-segment liver segmentation model based on deep learning described in the present application. However, the implementation device of the training method for an eight-segment liver segmentation model based on deep learning described in the present application includes but is not limited to the structure of the training system for an eight-segment liver segmentation model based on deep learning listed in the present embodiment. All structural deformations and replacements of the prior art made according to the principles of the present application are included in the protection scope of the present application.

[0095] See also Figure 6 In one embodiment, this embodiment provides a training system 60 for a deep learning-based liver eight-segment segmentation model, the system comprising:

[0096] An acquisition module 61 is used to acquire input images to obtain a training set and a validation set, wherein the input images include liver images with data labels;

[0097] A training module 62 is used to input the training set into the liver eight-segment segmentation model for testing, and use the validation set for validation, and perform iterative training, wherein the iteration is stopped when the number of iterations reaches a target iteration value, or the iteration is stopped when the loss function reaches a target loss value;

[0098] The output module 63 is used to output the finally trained liver eight-segment segmentation model based on the optimal model after the iteration is completed.

[0099] Since the specific implementation of this embodiment corresponds to the aforementioned method embodiment, the same details will not be repeated here, and those skilled in the art should also understand that Figure 6 The division of the modules in the embodiment is merely a division of logical functions, and in actual implementation, all or part of them can be integrated into one or more physical entities, and these modules can be implemented entirely in the form of software called by processing elements, or entirely in the form of hardware, or some modules can be implemented in the form of software called by processing elements, and some modules can be implemented in the form of hardware.

[0100] In the several embodiments provided by the present invention, it should be understood that the disclosed system, device or method can be implemented in other ways. For example, the device embodiments described above are only schematic, for example, the division of modules / units is only a logical function division, and there may be other division methods in actual implementation, such as multiple modules or units can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or modules or units, which can be electrical, mechanical or other forms.

[0101] The modules / units described as separate components may or may not be physically separated, and the components displayed as modules / units may or may not be physical modules, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules / units may be selected according to actual needs to achieve the purpose of the embodiments of the present invention. For example, the functional modules / units in the various embodiments of the present invention may be integrated into one processing module, or each module / unit may exist physically separately, or two or more modules / units may be integrated into one module / unit.

[0102] Those of ordinary skill in the art should further appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in terms of function in the above description. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0103] The embodiment of the present invention also provides a computer-readable storage medium. A person of ordinary skill in the art can understand that all or part of the steps in the method for implementing the above embodiment can be completed by instructing the processor through a program, and the program can be stored in a computer-readable storage medium, and the storage medium is a non-transitory medium, such as a random access memory, a read-only memory, a flash memory, a hard disk, a solid-state hard disk, a magnetic tape, a floppy disk, an optical disc, and any combination thereof. The above storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or a data center that includes one or more available media integrated. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a digital video disc (DVD)), or a semiconductor medium (e.g., a solid-state disk (SSD)), etc.

[0104] An embodiment of the present invention further provides an electronic device, which includes a processor and a memory.

[0105] The memory is used to store computer programs.

[0106] The memory includes: ROM, RAM, disk, USB flash drive, memory card or CD and other media that can store program codes.

[0107] The processor is connected to the memory and is used to execute the computer program stored in the memory so that the electronic device executes the above-mentioned training method of the eight-segment liver segmentation model based on deep learning.

[0108] Preferably, the processor can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components.

[0109] like Figure 7 As shown, the electronic device of the present invention is in the form of a general computing device. The components of the electronic device may include but are not limited to: one or more processors or processing units 71, a memory 72, and a bus 73 connecting different system components (including the memory 72 and the processing unit 71).

[0110] Bus 73 represents one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, a processor or a local bus using any of a variety of bus architectures. By way of example, these architectures include, but are not limited to, an Industry Standard Architecture (ISA) bus, a Micro Channel Architecture (MAC) bus, an Enhanced ISA bus, a Video Electronics Standards Association (VESA) local bus, and a Peripheral Component Interconnect (PCI) bus.

[0111] Electronic devices typically include a variety of computer system readable media. These media can be any available media that can be accessed by the electronic device, including volatile and non-volatile media, removable and non-removable media.

[0112] The memory 72 may include computer system readable media in the form of volatile memory, such as random access memory (RAM) 721 and / or cache memory 722. The electronic device may further include other removable / non-removable, volatile / non-volatile computer system storage media. By way of example only, the storage system 723 may be used to read and write non-removable, non-volatile magnetic media ( Figure 7 not shown, usually called a "hard drive"). Although Figure 7Not shown, a disk drive for reading and writing to a removable non-volatile disk (e.g., a "floppy disk"), and an optical disk drive for reading and writing to a removable non-volatile optical disk (e.g., a CD-ROM, a DVD-ROM, or other optical media) may be provided. In these cases, each drive may be connected to the bus 73 via one or more data medium interfaces. The memory 72 may include at least one program product having a set (e.g., at least one) of program modules that are configured to perform the functions of the various embodiments of the present invention.

[0113] A program / utility 724 having a set (at least one) of program modules 7241 may be stored, for example, in the memory 72, such program modules 7241 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. The program modules 7241 generally perform the functions and / or methods of the embodiments described herein.

[0114] The electronic device may also communicate with one or more external devices (e.g., keyboards, pointing devices, displays, etc.), one or more devices that enable a user to interact with the electronic device, and / or any device that enables the electronic device to communicate with one or more other computing devices (e.g., network cards, modems, etc.). Such communication may be performed via input / output (I / O) interface 74. Furthermore, the electronic device 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 network adapter 75. Figure 7 As shown, the network adapter 75 communicates with other modules of the electronic device via the bus 73. It should be understood that, although not shown in the figure, other hardware and / or software modules can be used in conjunction with the electronic device, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0115] Furthermore, in one embodiment of the invention, the present invention also provides a segmentation method of an eight-segment liver segmentation model based on deep learning, which is applied to the eight-segment liver segmentation model trained by the training method of an eight-segment liver segmentation model based on deep learning as claimed in any one of the claims, wherein, Figure 8 As shown, the segmentation method comprises the following steps:

[0116] Step S802, obtaining an image to be segmented;

[0117] Step S804, inputting the image to be segmented into the trained liver eight-segment segmentation model for processing to obtain a segmentation result;

[0118] Step S806: output a target segmented image based on the segmentation result.

[0119] It should be noted that in this embodiment, the practical application of the trained liver eight-segment segmentation model is specifically described, wherein reference is made to Fig. 9 ,in, Fig. 9 The input image to be segmented is a stereogram. The image to be segmented is input into the trained liver eight-segment segmentation model for processing to obtain the segmentation result, and then the corresponding target segmentation image is output based on the segmentation result, such as Figures 10A-10C As shown, Fig. 10A The cross-sectional view of the segmentation result is shown. Fig. 10B The front view of the segmentation result is shown. Fig. 10C The side view of the segmentation result is shown. It should be noted that in order to better show the front and back, Fig.11 The cross-sectional view of the image to be segmented is shown. Fig. 10A and Fig.11 It can be seen from the comparison that the front and back segmentation of the liver eight-segment segmentation model trained in this embodiment can well distinguish the segmentation results after image segmentation of the liver area.

[0120] The above embodiments are merely illustrative of the principles and effects of the present invention, and are not intended to limit the present invention. Anyone familiar with the art may modify or alter the above embodiments without departing from the spirit and scope of the present invention. Therefore, all equivalent modifications or alterations made by a person of ordinary skill in the art without departing from the spirit and technical concept disclosed by the present invention shall still be covered by the claims of the present invention.

Claims

1. A deep learning-based liver segmentation model, characterized in that: include: The input layer is used to receive input data to obtain the target sequence; A normalization layer, used to normalize the target sequence; Linear layer, used to change the dimension of the intermediate processed data of the current model; Convolutional layer, used to extract features from the intermediate processing data of the current model; The activation layer is used to perform nonlinear transformation on the output of the convolutional layer using the activation function; The output layer is used to calculate the model using the preset loss function and output the model segmentation results.

2. A training method for a liver eight-segment segmentation model based on deep learning, characterized in that: Applied to the deep learning-based liver eight-segment segmentation model of claim 1, the method comprises: Acquire input images to obtain a training set and a validation set, wherein the input images include liver images with data labels; Inputting the training set into the liver eight-segment segmentation model for testing, and using the validation set for validation to perform iterative training, wherein the iteration is stopped when the number of iterations reaches a target iteration value, or the iteration is stopped when the loss function reaches a target loss value; After the iteration is completed, the finally trained liver eight-segment segmentation model is output based on the optimal model.

3. The training method of the deep learning-based liver eight-segment segmentation model according to claim 2, characterized in that: Training the liver eight-segment segmentation model includes: Performing image processing based on the input image to obtain a target sequence, wherein the image processing method at least includes a block operation and an addition operation; When performing a block operation, the input image is divided into blocks according to a preset format, and each block image is converted into a one-dimensional vector using a serialization operation; During the addition operation, the target sequence is obtained by performing an addition operation based on the position information of each block image and the one-dimensional vector sequence.

4. The training method of the deep learning-based liver eight-segment segmentation model according to claim 3, characterized in that: When working in blocks, it specifically includes: Get the image specifications of the input image, where the input image specifications are H*W, where H is the input image height and W is the input image width; Performing a block operation on the input image to obtain a block image, wherein the block image is a square image, the block image specification is P*P, and N=H*W / (P*P), P is the side length of the block image, and N is the number of block images; The block image is converted into a one-dimensional vector N*D, where D is the length of the sequence after serialization.

5. The training method of the deep learning-based liver eight-segment segmentation model according to claim 4, characterized in that: Training the liver eight-segment segmentation model includes: Normalizing the target sequence and then changing its dimension to obtain first processed data; Performing a convolution operation and an activation function processing on the first processed data to obtain second processed data; Processing the second processed data using a structured state space model to obtain third processed data; Processing the first processed data by using an activation function, multiplying the data with the third processed data, and performing dimension change to obtain fourth processed data; Performing feature map dimension restoration based on the fourth processed data to obtain fifth processed data; Upsampling and convolution operations are performed based on the fifth processed data to restore the feature map and the target mask.

6. The training method of the deep learning-based liver eight-segment segmentation model according to claim 2, characterized in that: The loss function used in training the liver eight-segment segmentation model is the Dice-CE Loss loss function, and the ratio of the training set to the validation set is 4:

1.

7. A training system for a liver eight-segment segmentation model based on deep learning, characterized in that: include: An acquisition module, used for acquiring input images to obtain a training set and a validation set, wherein the input images include liver images with data labels; A training module, used for inputting the training set into the liver eight-segment segmentation model for testing, and using the validation set for validation, and performing iterative training, wherein the iteration is stopped when the number of iterations reaches a target iteration value, or the iteration is stopped when the loss function reaches a target loss value; The output module is used to output the finally trained liver eight-segment segmentation model based on the optimal model after the iteration is completed.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, it implements the training method of the deep learning-based liver eight-segment segmentation model described in any one of claims 2 to 6.

9. An electronic device, characterized in that: The electronic device comprises: a processor and a memory; wherein the memory is used to store a computer program, and the processor is used to execute the computer program stored in the memory, so that the electronic device executes the training method of the deep learning-based liver eight-segment segmentation model as described in any one of claims 2 to 6.

10. A segmentation method of the liver eight-segment segmentation model based on deep learning, characterized in that: The eight-segment liver segmentation model obtained by training the eight-segment liver segmentation model training method based on deep learning as described in any one of claims 2 to 6, wherein: The segmentation method comprises: Obtain the image to be segmented; Inputting the image to be segmented into a trained liver eight-segment segmentation model for processing to obtain a segmentation result; A target segmented image is output based on the segmentation result.

Images