An evaluation method and system for the quality control process of liver cancer.

Abstract

This application relates to an evaluation method and system in the quality control process of liver cancer. The method includes decomposing a set of received three-dimensional ultrasound contrast images according to connection points; grouping objects belonging to different three-dimensional ultrasound contrast images into the same comparison group, with objects in each comparison group generated based on the same structural tissue; sorting multiple objects in a comparison group according to generation time; comparing the degree of change of two adjacent objects belonging to the same comparison group in the time series, and statistically analyzing the number of objects whose degree of change exceeds the allowable degree of change, or calculating the ratio of the sum of the lengths of the parts of the objects whose degree of change exceeds the allowable degree of change to the sum of the lengths of all objects. This application provides an evaluation method and system in the quality control process of liver cancer, which achieves quantitative analysis of local images and provides a comparison of changes in treatment effects before and after treatment by using spatial decomposition and degree of change comparison, thereby providing data reference for subsequent liver cancer quality control processes.

Description

Technical Field

[0001] This application relates to the field of data processing technology, and in particular to an evaluation method and system for the quality control process of liver cancer. Background Technology

[0002] Quality control of liver cancer, within a certain scope, can be described as the standardization of liver cancer treatment. Standardization includes treatment standardization and indicator standardization. A crucial technical approach is to determine treatment methods and related indicator parameters through medical imaging at different stages. Currently, the best method for acquiring medical images is contrast-enhanced ultrasound (CEUS). CEUS uses contrast agents to reflect the actual blood flow within the liver, thereby obtaining relevant liver indicator parameters.

[0003] Contrast-enhanced ultrasound technology mainly includes two-dimensional contrast-enhanced ultrasound technology and three-dimensional contrast-enhanced ultrasound technology. Two-dimensional contrast-enhanced ultrasound technology can only display the enhancement of tumor and vascular conditions on a single plane. If the tumor is more complex, such as heterogeneous lesions, a large number of blood vessels, and tortuous blood vessel courses, the information obtained about the lesion may be incomplete because it is not possible to observe the conditions on other planes at the same time.

[0004] Three-dimensional ultrasound contrast imaging technology needs to extend quantitative analysis from a planar perspective to encompass the entire space occupied by the lesion, providing richer reference data and increasing the comparability of treatment effects before and after treatment. However, for medical images obtained at different time points, the underlying liver condition varies, and the patient's posture during three-dimensional ultrasound contrast imaging cannot be completely consistent. Further research is needed on how to perform spatial quantitative analysis. Summary of the Invention

[0005] This application provides an evaluation method and system for the quality control process of liver cancer. By using spatial decomposition and variability comparison, it achieves quantitative analysis of local images and provides a comparison of changes in treatment effects before and after treatment, thereby providing data reference for the subsequent implementation of the liver cancer quality control process.

[0006] The above-mentioned objective of this application is achieved through the following technical solution:

[0007] Firstly, this application provides an evaluation method for the quality control process of liver cancer, including:

[0008] The received set of three-dimensional ultrasound contrast images is decomposed according to the connection point, and each three-dimensional ultrasound contrast image includes multiple objects;

[0009] Objects belonging to different 3D ultrasound contrast images are grouped into the same comparison group, and objects in each comparison group are generated based on the same structural tissue.

[0010] Sort multiple objects in a comparison group according to their generation time;

[0011] Compare the degree of change of two adjacent objects belonging to the same comparison group in a time series; and

[0012] The number of objects whose variability exceeds the allowable variability, or the ratio of the sum of the lengths of the portions of an object whose variability exceeds the allowable variability to the sum of the lengths of all objects;

[0013] One set of three-dimensional ultrasound contrast images includes two three-dimensional ultrasound contrast images, which were generated at different times.

[0014] In one possible implementation of the first aspect, grouping objects belonging to different three-dimensional ultrasound contrast images into the same comparison group includes:

[0015] Determine the feature relationships between two objects, including connectivity, positional relationships, and shape similarity; and

[0016] When the connectivity, positional relationship, and shape similarity all meet the requirements, objects belonging to different 3D ultrasound contrast images are grouped into the same comparison group.

[0017] In one possible implementation of the first aspect, when only the connection relationship and the positional relationship meet the requirements, it also includes:

[0018] Include multiple objects with established spatial relationships that are spatially associated with the object in the scope of the study;

[0019] Calculate the spatial correlation between the object and the matched, already defined relational objects; and

[0020] When the spatial correlation meets the requirements, objects belonging to different 3D ultrasound contrast images are grouped into the same comparison group.

[0021] In one possible implementation of the first aspect, shape similarity includes:

[0022] Include multiple objects with established relationships that are connected to the object in the scope of the study;

[0023] Determine the correspondence between multiple defined relational objects belonging to different objects, and generate multiple defined relational objects belonging to different objects based on the same structure;

[0024] Calculate the degree of deformation of established relational objects with corresponding relationships, obtain multiple degree of deformation values, and calculate the average of the degree of deformation values; and

[0025] The mean of the degree of deformation is used to determine whether two objects have shape similarity.

[0026] In one possible implementation of the first aspect, multiple established relational objects are divided into multiple groups, and the established relational objects in each group have the same connection level with the objects.

[0027] In one possible implementation of the first aspect, comparing the degree of change of two adjacent objects belonging to the same comparison group in the time series includes:

[0028] Use objects to create object-based centerlines;

[0029] Align the first ends of the center lines of the two objects;

[0030] Move the second end of any object to make the two objects overlap as much as possible; and

[0031] The comparison yields the non-overlapping regions of the two objects.

[0032] One possible implementation of the first aspect also includes shape correction of one of the objects, the shape correction including:

[0033] Include multiple objects with established relationships that are connected or spatially related to the first object in the scope of the study;

[0034] Select multiple users from the established relationship objects;

[0035] Calculate the deformation domain of each user object based on the object that matches the user object, and obtain multiple deformation domains;

[0036] The mean deformation domain is obtained by calculating the mean value of multiple deformation domains; and

[0037] The first object is shaped using the mean deformation domain;

[0038] Among them, the object that matches the object used comes from the three-dimensional ultrasound imaging image where the second object is located.

[0039] Secondly, this application provides an evaluation device for the quality control process of liver cancer, comprising:

[0040] The image decomposition unit is used to decompose a set of received three-dimensional ultrasound contrast images according to the connection points. Each three-dimensional ultrasound contrast image includes multiple objects.

[0041] The first grouping unit is used to group objects belonging to different 3D ultrasound contrast images into the same comparison group, and the objects in each comparison group are generated based on the same structural tissue.

[0042] A sorting unit is used to sort multiple objects in a comparison group according to their generation time.

[0043] The first processing unit is used to compare the degree of change of two adjacent objects belonging to the same comparison group in a time series; and

[0044] The second processing unit is used to count the number of objects whose variability exceeds the allowable variability or to calculate the ratio of the sum of the lengths of the parts of an object whose variability exceeds the allowable variability to the sum of the lengths of all objects.

[0045] One set of three-dimensional ultrasound contrast images includes two three-dimensional ultrasound contrast images, which were generated at different times.

[0046] Thirdly, this application provides an evaluation system for the quality control process of liver cancer, the system comprising:

[0047] One or more memories for storing instructions; and

[0048] One or more processors are configured to call and execute the instructions from the memory to perform the methods described in the first aspect and any possible implementation thereof.

[0049] Fourthly, this application provides a computer-readable storage medium, the computer-readable storage medium comprising:

[0050] The program, when run by a processor, is executed as described in the first aspect and any possible implementation thereof.

[0051] Fifthly, this application provides a computer program product, including program instructions that, when run by a computing device, execute the method described in the first aspect and any possible implementation thereof.

[0052] Sixthly, this application provides a chip system including a processor for implementing the functions involved in the foregoing aspects, such as generating, receiving, transmitting, or processing the data and / or information involved in the foregoing methods.

[0053] This chip system can consist of chips or include chips and other discrete components.

[0054] In one possible design, the chip system also includes a memory for storing necessary program instructions and data. The processor and the memory can be decoupled and located on different devices, connected via wired or wireless means, or the processor and the memory can be coupled to the same device.

[0055] Compared with existing technologies, the beneficial effects are:

[0056] Overall, the evaluation method and system for the quality control process of liver cancer provided in this application can analyze and compare images generated using three-dimensional ultrasound contrast imaging technology. By using spatial decomposition and variability comparison, it can achieve quantitative analysis of local images and provide a comparison of changes in treatment effects before and after treatment. The comparison process can identify local and overall abnormalities, allowing doctors to further understand the treatment effect and providing a reference for subsequent treatment. Attached Figure Description

[0057] Figure 1 This is a flowchart illustrating the steps of an evaluation method provided in this application.

[0058] Figure 2 This application provides a flowchart illustrating the steps for grouping two objects into the same comparison group.

[0059] Figure 3 This is a schematic diagram illustrating a shape similarity processing procedure provided in this application.

[0060] Figure 4 This is a schematic diagram illustrating a process for shape correction of one of two objects provided in this application. Detailed Implementation

[0061] The technical solutions in this application will be further described in detail below with reference to the accompanying drawings.

[0062] This application discloses an evaluation method in the quality control process of liver cancer. Please refer to [link / reference]. Figure 1 In some examples, the evaluation method includes the following steps:

[0063] S101, decompose a set of received three-dimensional ultrasound contrast images according to the connection point, each three-dimensional ultrasound contrast image includes multiple objects;

[0064] S102, objects belonging to different three-dimensional ultrasound contrast images are grouped into the same comparison group, and objects in each comparison group are generated based on the same structural tissue;

[0065] S103, Sort multiple objects in a comparison group according to their generation time;

[0066] S104, compare the degree of change of two adjacent objects belonging to the same comparison group in the time series; and

[0067] S105, Count the number of objects whose variability exceeds the allowable variability or calculate the ratio of the sum of the lengths of the parts of an object whose variability exceeds the allowable variability to the sum of the lengths of all objects;

[0068] One set of three-dimensional ultrasound contrast images includes two three-dimensional ultrasound contrast images, which were generated at different times.

[0069] This application discloses an evaluation method in the quality control process of liver cancer, which is applied to a computer, processing terminal, server or cloud server, hereinafter collectively referred to as a server.

[0070] In step S101, the server receives a set of three-dimensional ultrasound contrast images. Generally, a set of three-dimensional ultrasound contrast images includes two three-dimensional ultrasound contrast images. These two three-dimensional ultrasound contrast images are generated at different times. They can be an initial three-dimensional ultrasound contrast image and a final three-dimensional ultrasound contrast image of a treatment stage, or they can be three-dimensional ultrasound contrast images generated during two examinations.

[0071] Processing three-dimensional ultrasound contrast images requires decomposition. After decomposition, each three-dimensional ultrasound contrast image comprises multiple objects. It should be understood that the three-dimensional ultrasound contrast images obtained using ultrasound contrast technology in this application represent the influence of blood vessels and related tissues in the liver. The contrast agent in the blood is used to reflect the condition of blood vessels and related tissues in the liver, and then the changes in the condition of blood vessels and related tissues are used to determine the before-and-after comparison of treatment effects.

[0072] The liver has the function of storing blood and regulating blood volume. When lesions (cancer) occur inside the liver, the blood flow or blood storage in the lesion (cancer) area will change. By observing these changes and trends, we can infer the changes in the treatment effect before and after.

[0073] The decomposition process is generally based on the connection nodes. Through these connection nodes, a three-dimensional ultrasound contrast image can be decomposed into multiple objects, each corresponding to a segment of blood vessel or a related tissue.

[0074] In step S102, objects belonging to different 3D ultrasound contrast images need to be grouped into the same comparison group, and objects in each comparison group are generated based on the same structural tissue. This can also be described as follows: a blood vessel or a related tissue corresponds to one object in each of two 3D ultrasound contrast images, and in step S102, these two objects need to be placed in a comparison group.

[0075] In step S103, multiple objects in a comparison group are sorted according to the generation time. The purpose of sorting is to prepare for obtaining the degree of change of a blood vessel or a related tissue corresponding to a comparison group in the time dimension.

[0076] The comparison of variability is performed in step S104, which compares the variability of two adjacent objects that belong to the same comparison group in the time series. Here, variability refers to the difference between two adjacent objects that belong to the same comparison group in the time dimension.

[0077] The quantitative calculation of the difference is performed in step S105, which provides two methods:

[0078] The first method involves counting the number of objects whose variability exceeds the allowable variability.

[0079] The second method is to calculate the ratio of the sum of the lengths of the portions of the object whose variability exceeds the allowable variability to the sum of the lengths of the entire object.

[0080] The first method describes the quantity, while the second method describes the overall picture. Both methods have their advantages, and the specific choice depends on the actual judgment needs. Alternatively, both methods can be used simultaneously to provide the results.

[0081] In addition, for objects whose variability exceeds the allowable variability, this application can also use the method of clustering degree, which is represented by displaying it in a three-dimensional ultrasound contrast image and is an extension of the first method. The advantage of clustering degree representation is that it can detect regional anomalies.

[0082] In some cases, grouping objects belonging to different 3D ultrasound contrast images into the same contrast group includes the following steps:

[0083] S201, determine the feature relationship between the two objects, including connection relationship, positional relationship, and shape similarity; and

[0084] S202, When the connectivity, positional relationship and shape similarity all meet the requirements, objects belonging to different three-dimensional ultrasound contrast images are grouped into the same comparison group.

[0085] In step S201, the feature relationship between the two objects is determined first. There are three types of feature relationships: connection relationship, positional relationship, and shape similarity. Specifically, the connection relationship determines which remaining objects the two objects are connected to, and this connection relationship can be determined by the connection nodes in step S101. Then, the positional relationship is determined, which refers to the relative positional relationship with other objects that are determined to have a connection relationship. Finally, the shape similarity is used, which refers to the degree of similarity between the two objects in shape. As mentioned earlier, the two objects should be generated based on a blood vessel or a related tissue, so their shapes should also match.

[0086] When the connectivity, positional relationship and shape similarity all meet the requirements, objects belonging to different three-dimensional ultrasound contrast images are grouped into the same comparison group, which is the content of step S202.

[0087] Please see Figure 2 When only connection and positional relationships meet the requirements, the following method should be used:

[0088] S301, include multiple objects with established spatial relationships with the object in the scope of consideration;

[0089] S302, calculate the spatial correlation between the object and the matched, already determined relational objects; and

[0090] S303, when the spatial correlation meets the requirements, objects belonging to different three-dimensional ultrasound contrast images are grouped into the same comparison group.

[0091] Steps S301 to S303 involve using multiple established relational objects to determine whether two objects whose relationship needs to be determined can be grouped into the same comparison group. This requires the use of spatial correlation. Spatial correlation here refers to multiple established relational objects that have direct and indirect connections (through objects with direct connections) with the object. These established relational objects are distributed around the object whose relationship needs to be determined. For example, assuming there are six established relational objects, the object whose relationship needs to be determined is located within the area enclosed by these six objects.

[0092] Alternatively, a spatial graph can be constructed using established relational objects and objects with direct connections, and then the similarity between the two spatial graphs can be compared to determine whether objects belonging to different 3D ultrasound contrast images should be grouped into the same comparison group.

[0093] At this point, it can be assumed that one of the objects has developed a disease or obvious recovery, resulting in only the connection and position relationships meeting the requirements.

[0094] Please see Figure 3 The following steps are used to process shape similarity:

[0095] S401, include multiple objects with established relationships that are connected to the object in the scope of consideration;

[0096] S402, determine the correspondence of multiple determined relational objects belonging to different objects, and generate multiple determined relational objects belonging to different objects based on the same structure;

[0097] S403, calculate the degree of deformation of the corresponding objects with established relationships, obtain multiple degree of deformation values, calculate the average of the degree of deformation values; and

[0098] S404 uses the mean of the degree of deformation to determine whether two objects have shape similarity.

[0099] Steps S401 to S404 primarily address the issue of uncertain shape similarity caused by localized overall shape changes. In such cases, it's necessary to utilize multiple objects with established connections to the objects, and then use the variations in these established objects to inversely determine whether two objects possess shape similarity.

[0100] For example, by obtaining deformation values ​​of shortening, lengthening, or bending under pressure at both ends from multiple objects with established relationships that are connected to the object, and if two objects whose relationship needs to be determined happen to match these deformation values, then it can be determined that the two objects have shape similarity.

[0101] In some possible implementations, multiple defined relational objects are divided into multiple groups. The defined relational objects in each group have the same connection level with the objects. The connection level includes direct connection and indirect connection. Indirect connection includes first-level connection (connected through a direct connection) and second-level connection (connected through a direct connection and an indirect connection).

[0102] The purpose of using connection levels is to determine whether multiple established relational objects within a region have similar trends in shape change. For example, the deformation values ​​of multiple established relational objects at a connection level should tend to be consistent.

[0103] By using multiple sets of deformation values, the trend of change of the latter object can be inferred. Then, the shape of the latter object is changed using this trend, and finally, it is determined whether the two objects have shape similarity.

[0104] Please see Figure 4 The specific process is as follows:

[0105] S501, include multiple objects with established relationships that are connected or spatially associated with the first object into the scope of consideration;

[0106] S502, Select multiple user objects from the established relationship objects;

[0107] S503, calculate the deformation domain of each user object based on the object that matches the user object, and obtain multiple deformation domains;

[0108] S504, calculate the mean value of multiple deformation domains to obtain the mean deformation domain; and

[0109] S505, use the mean deformation domain to perform shape correction on the first object;

[0110] Among them, the object that matches the object used comes from the three-dimensional ultrasound imaging image where the second object is located.

[0111] The mean deformation domain in steps S501 to S505 is obtained by calculating the mean, or it can be obtained by using the changing trends of multiple sets of deformation domains obtained by the connection level.

[0112] In some possible implementations, the deformation domain includes multiple vectors, each with a direction and a vector, representing the trend of change.

[0113] In some cases, comparing the degree of change of two adjacent objects belonging to the same comparison group in a time series includes the following steps:

[0114] S601, Use objects to create object-based centerlines;

[0115] S602, align the first ends of the center lines of the two objects;

[0116] S603, move the second end of any object to make the two objects overlap as much as possible; and

[0117] S604 compares and obtains the non-overlapping regions of the two objects.

[0118] In steps S601 to S604, the center line is first used for overlap processing, and then the non-overlapping areas of the two objects are obtained by comparing the center line after overlap processing. The non-overlapping areas here refer to the non-overlapping areas of the objects in space.

[0119] To determine the non-overlapping regions, a cross-sectional method can be used. Specifically, a cross-section is created, and the cross-sectional images of the two objects are obtained on this cross-section. These two cross-sectional images are then moved to maximize the overlap. Finally, the area ratio of the non-overlapping region to the overlapping region is calculated. For example, a threshold of 0.03 is set. If the area ratio is less than 0.03, the two cross-sectional images are considered to overlap; otherwise, they are considered to be non-overlapping. The non-overlapping region corresponds to the non-overlapping area of ​​the two objects.

[0120] This application also provides an evaluation device for the quality control process of liver cancer, including:

[0121] The image decomposition unit is used to decompose a set of received three-dimensional ultrasound contrast images according to the connection points. Each three-dimensional ultrasound contrast image includes multiple objects.

[0122] The first grouping unit is used to group objects belonging to different 3D ultrasound contrast images into the same comparison group, and the objects in each comparison group are generated based on the same structural tissue.

[0123] A sorting unit is used to sort multiple objects in a comparison group according to their generation time.

[0124] The first processing unit is used to compare the degree of change of two adjacent objects belonging to the same comparison group in a time series; and

[0125] The second processing unit is used to count the number of objects whose variability exceeds the allowable variability or to calculate the ratio of the sum of the lengths of the parts of an object whose variability exceeds the allowable variability to the sum of the lengths of all objects.

[0126] One set of three-dimensional ultrasound contrast images includes two three-dimensional ultrasound contrast images, which were generated at different times.

[0127] Furthermore, it also includes:

[0128] The first relationship determination unit is used to determine the feature relationship between two objects, including connection relationship, positional relationship, and shape similarity; and

[0129] The second grouping unit is used to group objects belonging to different 3D ultrasound contrast images into the same comparison group when the connection relationship, positional relationship and shape similarity all meet the requirements.

[0130] Furthermore, it also includes:

[0131] The first scope determination unit is used to include multiple objects with established spatial relationships with the object into the scope of investigation;

[0132] The first relation calculation unit is used to calculate the spatial correlation between an object and a matched, already determined relation object; and

[0133] The third grouping unit is used to group objects belonging to different 3D ultrasound contrast images into the same comparison group when the spatial correlation meets the requirements.

[0134] Furthermore, it also includes:

[0135] The second scope determination unit is used to include multiple objects with established relationships that are connected to the object into the scope of consideration;

[0136] The second relation calculation unit is used to determine the corresponding relationship of multiple determined relation objects belonging to different objects. The multiple determined relation objects belonging to different objects are generated based on the same structure.

[0137] The first numerical calculation unit is used to calculate the degree of deformation of objects with a defined relationship, obtain multiple deformation degree values, calculate the average value of the deformation degree values, and obtain the mean value of the deformation degree values; and

[0138] The second relationship determination unit is used to determine whether two objects have shape similarity using the mean value of the degree of deformation.

[0139] Furthermore, multiple established relational objects are divided into multiple groups, and the established relational objects in each group have the same connection level with the objects.

[0140] Furthermore, it also includes:

[0141] The first image processing unit is used to create object-based centerlines using objects;

[0142] The second image processing unit is used to make the first ends of the center lines of the two objects coincide.

[0143] The third image processing unit is used to move the second end of any object so that the two objects overlap as much as possible; and

[0144] The image comparison unit is used to compare the non-overlapping regions of two objects.

[0145] Furthermore, it also includes:

[0146] The third scope determination unit is used to include multiple objects with established relationships that are connected or spatially associated with the first object into the scope of investigation;

[0147] The object filtering unit is used to filter out multiple objects for use from the established relationship objects;

[0148] The second numerical calculation unit is used to calculate the deformation domain of each user object based on the object that matches the user object, and obtain multiple deformation domains.

[0149] The third numerical calculation unit is used to calculate the mean value of multiple deformation domains to obtain the mean deformation domain; and

[0150] A correction unit is used to perform shape correction on the first object using the mean deformation domain;

[0151] Among them, the object that matches the object used comes from the three-dimensional ultrasound imaging image where the second object is located.

[0152] In one example, the unit in any of the above devices may be one or more integrated circuits configured to implement the above methods, such as one or more application-specific integrated circuits (ASICs), or one or more digital signal processors (DSPs), or one or more field-programmable gate arrays (FPGAs), or a combination of at least two of these integrated circuit forms.

[0153] For example, when the units in the device can be implemented through a processing element scheduler, the processing element can be a general-purpose processor, such as a central processing unit (CPU) or other processor capable of calling programs. Alternatively, these units can be integrated together to form a system-on-a-chip (SOC).

[0154] In this application, various objects such as messages / information / devices / network elements / systems / apparatus / actions / operations / processes / concepts may be named. It is understood that these specific names do not constitute a limitation on the relevant objects. The names may be changed depending on the scenario, context, or usage habits. The understanding of the technical meaning of the technical terms in this application should be mainly determined from their functions and technical effects embodied / performed in the technical solution.

[0155] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0156] In the several embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0157] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0158] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0159] It should also be understood that in the various embodiments of this application, the terms "first," "second," etc., are merely to indicate that multiple objects are different. For example, a first time window and a second time window are only to indicate different time windows. They should not have any effect on the time windows themselves, and the aforementioned terms "first," "second," etc., should not impose any limitations on the embodiments of this application.

[0160] It should also be understood that, in the various embodiments of this application, unless otherwise specified or in case of logical conflict, the terms and / or descriptions between different embodiments are consistent and can be referenced by each other, and the technical features in different embodiments can be combined to form new embodiments according to their inherent logical relationships.

[0161] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a computer-readable storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned computer-readable storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0162] This application also provides an evaluation system for the quality control process of liver cancer, the system comprising:

[0163] One or more memories for storing instructions; and

[0164] One or more processors are configured to retrieve and execute the instructions from the memory, performing the methods described above.

[0165] This application also provides a computer program product including instructions that, when executed, cause the evaluation system in the liver cancer quality control process to perform operations corresponding to the above-described method.

[0166] This application also provides a chip system including a processor for implementing the functions involved in the above description, such as generating, receiving, transmitting, or processing the data and / or information involved in the above methods.

[0167] This chip system can consist of chips or include chips and other discrete components.

[0168] The processor mentioned above can be a CPU, a microprocessor, an ASIC, or one or more integrated circuits that execute a program to control the method of transmitting the feedback information described above.

[0169] In one possible design, the chip system also includes a memory for storing necessary program instructions and data. The processor and the memory can be decoupled and located on different devices, connected via wired or wireless means to support the chip system in implementing the various functions described in the above embodiments. Alternatively, the processor and the memory can also be coupled to the same device.

[0170] Optionally, the computer instructions are stored in memory.

[0171] Optionally, the memory can be a storage unit within the chip, such as a register or cache. Alternatively, the memory can be a storage unit located outside the chip within the terminal, such as a ROM or other types of static storage devices that can store static information and instructions, such as RAM.

[0172] It is understood that the memory in this application may be volatile memory or non-volatile memory, or may include both volatile and non-volatile memory.

[0173] Non-volatile memory can be ROM, programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), or flash memory.

[0174] Volatile memory can be RAM, which is used as an external cache. There are many different types of RAM, such as static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link dynamic random access memory (SLDRAM), and direct memory bus random access memory.

[0175] The embodiments described in this specific implementation are preferred embodiments of this application and are not intended to limit the scope of protection of this application. Therefore, all equivalent changes made in accordance with the structure, shape and principle of this application should be covered within the scope of protection of this application.

Claims

1. An evaluation method in a liver cancer quality control process, characterized by, include: The received set of three-dimensional ultrasound contrast images is decomposed according to the connection point, and each three-dimensional ultrasound contrast image includes multiple objects; Objects belonging to different 3D ultrasound contrast images are grouped into the same comparison group, and objects in each comparison group are generated based on the same structural tissue. Sort multiple objects in a comparison group according to their generation time; Compare the degree of change of two adjacent objects belonging to the same comparison group in a time series; and The number of objects whose variability exceeds the allowable variability, or the ratio of the sum of the lengths of the portions of an object whose variability exceeds the allowable variability to the sum of the lengths of all objects; One set of three-dimensional ultrasound contrast images includes two three-dimensional ultrasound contrast images, which are generated at different times. Objects belonging to different 3D ultrasound contrast images are grouped into the same comparison group, including: Determine the feature relationships between two objects, including connectivity, positional relationships, and shape similarity; and When the connectivity, positional relationship and shape similarity all meet the requirements, objects belonging to different 3D ultrasound contrast images are grouped into the same comparison group. When only connectivity and positional relationships meet the requirements, it also includes: Include multiple objects with established spatial relationships that are spatially associated with the object in the scope of the study; Calculate the spatial correlation between the object and the matched, already defined relational objects; and When the spatial correlation meets the requirements, objects belonging to different 3D ultrasound contrast images are grouped into the same comparison group; Shape similarity includes: Include multiple objects with established relationships that are connected to the object in the scope of the study; Determine the correspondence between multiple defined relational objects belonging to different objects, and generate multiple defined relational objects belonging to different objects based on the same structure; Calculate the degree of deformation of established relational objects with corresponding relationships, obtain multiple degree of deformation values, and calculate the average of the degree of deformation values; and The mean of the degree of deformation is used to determine whether two objects have shape similarity.

2. The evaluation method in the quality control process of liver cancer according to claim 1, characterized in that, Multiple established relational objects are divided into multiple groups, and the established relational objects in each group have the same connection level with the objects.

3. The evaluation method in the quality control process of liver cancer according to claim 1, characterized in that, Comparing the degree of change between two adjacent objects belonging to the same comparison group in a time series includes: Use objects to create object-based centerlines; Align the first ends of the center lines of the two objects; Move the second end of any object to make the two objects overlap as much as possible; and The comparison yields the non-overlapping regions of the two objects.

4. The evaluation method in the quality control process of liver cancer according to claim 3, characterized in that, It also includes shape correction of one of the objects, the shape correction including: Include multiple objects with established relationships that are connected or spatially related to the first object in the scope of the study; Select multiple users from the established relationship objects; Calculate the deformation domain of each user object based on the object that matches the user object, and obtain multiple deformation domains; The mean deformation domain is obtained by calculating the mean value of multiple deformation domains; and The first object is shaped using the mean deformation domain; Among them, the object that matches the object used comes from the three-dimensional ultrasound imaging image where the second object is located.

5. An evaluation device for the quality control process of liver cancer, characterized in that, include: The image decomposition unit is used to decompose a set of received three-dimensional ultrasound contrast images according to the connection points. Each three-dimensional ultrasound contrast image includes multiple objects. The first grouping unit is used to group objects belonging to different 3D ultrasound contrast images into the same comparison group, and the objects in each comparison group are generated based on the same structural tissue. A sorting unit is used to sort multiple objects in a comparison group according to their generation time. The first processing unit is used to compare the degree of change of two adjacent objects belonging to the same comparison group in the time series. as well as The second processing unit is used to count the number of objects whose variability exceeds the allowable variability or to calculate the ratio of the sum of the lengths of the parts of an object whose variability exceeds the allowable variability to the sum of the lengths of all objects. One set of three-dimensional ultrasound contrast images includes two three-dimensional ultrasound contrast images, which are generated at different times. Objects belonging to different 3D ultrasound contrast images are grouped into the same comparison group, including: Determine the feature relationships between two objects, including connectivity, positional relationships, and shape similarity; and When the connectivity, positional relationship and shape similarity all meet the requirements, objects belonging to different 3D ultrasound contrast images are grouped into the same comparison group. When only connectivity and positional relationships meet the requirements, it also includes: Include multiple objects with established spatial relationships that are spatially associated with the object in the scope of the study; Calculate the spatial correlation between the object and the matched, already defined relational objects; and When the spatial correlation meets the requirements, objects belonging to different 3D ultrasound contrast images are grouped into the same comparison group; Shape similarity includes: Include multiple objects with established relationships that are connected to the object in the scope of the study; Determine the correspondence between multiple defined relational objects belonging to different objects, and generate multiple defined relational objects belonging to different objects based on the same structure; Calculate the degree of deformation of established relational objects with corresponding relationships, obtain multiple degree of deformation values, and calculate the average of the degree of deformation values; and The mean of the degree of deformation is used to determine whether two objects have shape similarity.

6. An evaluation system for the quality control process of liver cancer, characterized in that, The system includes: One or more memories for storing instructions; and One or more processors are configured to retrieve and execute the instructions from the memory to perform the method as described in any one of claims 1 to 4.

7. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes: The program, when run by the processor, executes the method as described in any one of claims 1 to 4.

Images