Image analysis method and related device, equipment, storage medium

Abstract

The present application discloses an image analysis method and related devices, equipment, and storage medium. The image analysis method includes: acquiring a medical image collected for a target object; determining at least one analysis method to be used based on reference information, where the reference information includes the content of the medical image and / or the associated information of the target object; and analyzing the medical image based on the determined analysis method to obtain an image analysis result of the target object. In the above solution, by intelligently determining a matching analysis method for the medical image to analyze the medical image, the efficiency of medical image analysis is improved.

Description

Technical Field

[0001] This application relates to the technical field of image analysis and processing, and in particular to an image analysis method and related devices, equipment, and storage media. Background Art

[0002] Currently, after obtaining the medical images of relevant personnel, doctors still need to manually select the analysis methods for these medical images. For example, doctors select the analysis methods according to the departments that patients registered in. This method still has the following problems. For example, when there are a large number of medical images, due to the limited number of doctors, it takes a lot of time to select the analysis methods for each medical image, resulting in that the analysis equipment can only analyze a small number of medical images within a certain period of time, and the waiting time of the analysis equipment is too long, so that the utilization rate of the analysis equipment is low, that is, the analysis efficiency of medical images is low. Summary of the Invention

[0003] This application provides at least an image analysis method and related devices, equipment, and storage media.

[0004] In a first aspect of this application, an image analysis method is provided, including: obtaining a medical image collected for a target object; determining at least one analysis method to be performed based on reference information, where the reference information includes the content of the medical image and / or the associated information of the target object; analyzing the medical image based on the determined analysis method to be performed to obtain an image analysis result of the target object.

[0005] Therefore, by determining the analysis method to be performed based on the content of the medical image and / or the associated information of the target object, it is not necessary for doctors to manually select the analysis method for each medical image, reducing the waiting time and improving the analysis efficiency of medical images. Moreover, the analysis method determined for the medical image has a high degree of matching with the medical image and the corresponding target object, thereby improving the accuracy of medical image analysis. In addition, determining at least one analysis method to be performed for the medical image, different from that a medical image is only used for one image analysis method, can enrich the types of image analysis methods for medical images and improve the utilization rate of medical images.

[0006] Wherein, the reference information includes the content of the medical image, and based on the reference information, determining at least one analysis method to be performed includes: performing organ recognition on the medical image to obtain an organ recognition result of the medical image, where the organ recognition result includes several recognized organs; selecting at least one recognized organ as the organ to be analyzed; using the analysis method associated with the organ to be analyzed as the first analysis method to be performed.

[0007] Therefore, by selecting at least one of the several identified organs as the organ to be analyzed and identifying the corresponding method for the selected organ, the determined method to be analyzed can specifically analyze the organ. Moreover, selecting the analysis method corresponding to the organ included in the medical image as the method to be analyzed can make the analysis of the medical image effective and improve the efficiency of medical image analysis.

[0008] Among them, selecting at least one identified organ as the organ to be analyzed includes: obtaining the first weight of each identified organ; selecting the identified organs whose first weights meet the first preset selection condition as the organs to be analyzed.

[0009] Therefore, by selecting the identified organ as the organ to be analyzed based on the weight, the determined organ to be analyzed can better reflect the user's intention.

[0010] Among them, the first preset condition is the first first-number of identified organs sorted from high to low in terms of the first weight; and / or, the organ recognition result further includes the probability that each identified organ exists in the medical image; obtaining the first weight of each identified organ includes: using the probability of each identified organ as the first weight of the identified organ.

[0011] Therefore, by using the probability that the identified organ exists in the medical image as the first weight and determining the organ to be analyzed in the order from high to low of the first weight, the analysis result of the organ to be analyzed is more accurate.

[0012] Among them, before selecting the identified organ whose first weight meets the preset selection condition as the organ to be analyzed, the method further includes: if a preset marker is detected in the area where the identified organ is located in the medical image, then increasing the first weight of the identified organ.

[0013] Therefore, the preset marker can be used to indicate that the organ is the key observation object in this image acquisition. By detecting whether a preset marker exists in the area where the identified organ is located to increase the weight of the identified organ, the possibility of analyzing the key observed organ can be improved.

[0014] Among them, the reference information includes the associated information of the target object. Based on the reference information, determining at least one method to be analyzed includes: obtaining the associated location of the target object and determining the second method to be analyzed as the analysis method corresponding to the associated location; and / or, obtaining the personal information of the target object and determining the second method to be analyzed as the analysis method matching the personal information.

[0015] Therefore, by considering the information related to the target object to determine the corresponding method to be analyzed, the types of methods to be analyzed for the medical image can be enriched, and the disease analysis method can be specifically determined for the target object, which can improve the efficiency and accuracy of disease analysis.

[0016] Among them, the associated locations include at least one of the city where the target object is located and the hospital where the target object is located; determining the analysis method corresponding to the associated location as the second analysis method to be determined includes: finding out the preset analysis method configured for the associated location from the preset configuration information, and using the found preset analysis method as the second analysis method to be determined; or analyzing the environment of the associated location to determine the type of disease prone to occur that matches the environment, and selecting the analysis method for determining the type of disease prone to occur as the second analysis method to be determined.

[0017] Therefore, by pre-configuring the corresponding preset analysis method or analyzing the type of disease prone to occur in the environment of the associated location of the target object to determine the corresponding analysis method, the potential diseases of the target object can be analyzed.

[0018] Among them, the personal information includes at least one of medical history and living habits; determining the analysis method that matches the personal information as the second analysis method to be determined includes: analyzing the personal information to determine the predicted disease type of the target object, where the predicted disease type includes the historical disease type in the medical history and / or the disease type associated with the living habits; selecting the analysis method for determining the predicted disease type as the second analysis method to be determined.

[0019] Therefore, due to the medical history and living habits of the target object, it may lead to potential diseases of the target object. Therefore, analyzing the potential diseases of the target object enriches the determination method of the analysis method for medical images.

[0020] Among them, after determining the analysis method corresponding to the associated location as the second analysis method to be determined, or determining the analysis method that matches the personal information as the second analysis method to be determined, the method further includes: determining the first organ that the second analysis method is used to determine, and using the first organ not included in the medical image as the second organ; discarding the second analysis method for determining the second organ.

[0021] Therefore, if the second organ is not included in the medical image and the second analysis method is still used to analyze the medical image, the analysis result may be inaccurate. That is, discarding the second analysis method for determining the second organ helps to reduce the subsequent analysis error.

[0022] Among them, based on the determined analysis method to be analyzed, the medical image is analyzed to obtain the image analysis result of the target object, including: taking the intersection or union of the analysis methods to be analyzed determined based on each reference information as the target analysis method, where the reference information includes at least one of the content of the medical image, the associated location of the target object, and the personal information of the target object; using the target analysis method whose second weight satisfies the second preset condition to analyze the medical image to obtain the image analysis result of the target object; or, determining the priority of each target analysis method based on the second weight of the target analysis method, and analyzing the medical image using each target analysis method in the order of priority to obtain the image analysis result of the target object.

[0023] Therefore, by adopting the intersection or union of the analysis methods to be analyzed determined by each reference information and selecting the analysis method based on the second weight to analyze the medical image, the analysis of the medical image is more focused.

[0024] Among them, the second preset condition includes that the second weight is greater than the preset weight value, or the first second preset number of digits in the descending order of the second weight; and / or, the greater the second weight of the analysis method to be analyzed, the higher the priority of the analysis method to be analyzed.

[0025] Therefore, the greater the weight, the more priority is given to its processing, that is, the disease types that medical staff or the target object need to pay more attention to are analyzed to obtain the analysis result, making the analysis effect better.

[0026] Among them, after obtaining the medical image collected for the target object, the method further includes at least one step: performing normalization processing on the medical image; deleting the medical image whose image quality does not meet the quality requirements, and prompting the collector to collect a new medical image again.

[0027] Therefore, after obtaining the medical image, the medical image is normalized first to unify the style of the medical image, making the analysis more efficient; deleting the medical image whose image quality does not meet the quality requirements reduces the analysis error caused by the medical image quality problem in the follow-up.

[0028] The second aspect of the present application provides an image analysis device, including: an image acquisition module for acquiring the medical image collected for the target object; an analysis method determination module for determining at least one analysis method to be analyzed based on the reference information, where the reference information includes the content of the medical image and / or the associated information of the target object; an image analysis module for analyzing the medical image based on the determined analysis method to be analyzed to obtain the image analysis result of the target object.

[0029] In a third aspect of the present application, an electronic device is provided, including a memory and a processor. The processor is configured to execute program instructions stored in the memory to implement the above-mentioned image analysis method.

[0030] In a fourth aspect of the present application, a computer-readable storage medium is provided, on which program instructions are stored. When the program instructions are executed by a processor, the above-mentioned image analysis method is implemented.

[0031] In the above solution, by determining the analysis method to be used based on the content of the medical image and / or the associated information of the target object, there is no need for a doctor to manually select the analysis method for each medical image, which reduces the waiting time and improves the efficiency of medical image analysis. Moreover, the analysis method determined for the medical image has a high degree of matching with the medical image and the corresponding target object, thereby improving the accuracy of medical image analysis. In addition, determining at least one analysis method to be used for a medical image, different from a single medical image being only used for one image analysis method, can enrich the types of image analysis methods for medical images and improve the utilization rate of medical images.

[0032] It should be understood that the above general description and the following detailed description are only exemplary and explanatory, and do not limit the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] The accompanying drawings herein are incorporated into the specification and constitute a part of this specification. These drawings illustrate embodiments consistent with the present application and, together with the specification, are used to explain the technical solutions of the present application.

[0034] Figure 1 is a first flowchart of an embodiment of the image analysis method of the present application;

[0035] Figure 2 is a second flowchart of an embodiment of the image analysis method of the present application;

[0036] Figure 3 is a schematic structural diagram of an embodiment of the image analysis device of the present application;

[0037] Figure 4 is a schematic structural diagram of an embodiment of the electronic device of the present application;

[0038] Figure 5 is a schematic structural diagram of an embodiment of the computer-readable storage medium of the present application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0039] The solutions of the embodiments of the present application will be described in detail below with reference to the accompanying drawings of the specification.

[0040] In the following description, specific details such as specific system architectures, interfaces, and technologies are presented for the purpose of illustration rather than limitation, in order to provide a thorough understanding of the present application.

[0041] As used herein, the term "and / or" merely describes the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist simultaneously, and B exists alone. In addition, the character " / " in this text generally indicates that the associated objects before and after are in an "or" relationship. In addition, "plurality" in this text means two or more than two. In addition, the term "at least one" in this text means any one of a plurality or any combination of at least two of a plurality. For example, including at least one of A, B, and C can represent any one or more elements selected from the set composed of A, B, and C.

[0042] This application can be applied to devices with image processing capabilities. In addition, the device can have an image acquisition or video acquisition function. For example, the device can include components such as a camera for acquiring images or videos. Or the device can obtain the required video stream or image from other devices by means of data transmission or data interaction with other devices, or access the required video stream or image from the storage resources of other devices. Among them, the other device has an image acquisition or video acquisition function and has a communication connection with the device. For example, the device can perform data transmission or data interaction with other devices through methods such as Bluetooth and wireless networks. Here, the communication method between the two is not limited and can include but is not limited to the above examples. In one implementation, the device can include a mobile phone, a tablet computer, an interactive screen, etc., which is not limited here.

[0043] Please refer to Figure 1 , Figure 1 is the first process schematic diagram of an embodiment of the image analysis method of this application. Specifically, it can include the following steps:

[0044] Step S11: Obtain a medical image collected for a target object.

[0045] Among them, the medical image collected for the target object can be an image taken or scanned by various medical devices. Of course, it can also be an external image of a human body or an animal body taken by the camera of various communication devices. Of course, it can also be an image obtained from other devices, or an image after frame selection, brightness adjustment, resolution adjustment, etc. The target object can be a human body or an animal body. Therefore, the method for obtaining the medical image collected for the target object is not limited. Among them, other devices refer to devices that can only be operated by using different central processing units.

[0046] Step S12: Based on the reference information, determine at least one analysis method to be used, where the reference information includes the content of the medical image and / or the associated information of the target object.

[0047] Among them, the content of the medical image can be the organs contained in the medical image or the parts composed of each organ. For example, the human body can be divided into parts such as the head and neck, chest, abdomen, lower limbs, etc. Among them, the head and neck can further include organs such as the eyes and brain, the chest can include organs such as the lungs and heart, the abdomen can include organs such as the liver and kidneys, and so on. Therefore, the embodiments of the present disclosure do not make specific regulations on the content of the medical image.

[0048] The associated information of the target object can be the environment in which the human body or animal body lives, the information preset by the hospital for analyzing the medical image, the previous medical records, and other contents. By using the associated information of the target object to determine the analysis method to be used, it is possible to check for omissions and make up for deficiencies in the content of the medical image, so as to enrich the analysis methods of the medical image, that is, it is possible to perform multiple image analyses on the medical image. That is, only one medical image can be used for multiple image analysis diagnoses, which improves the utilization rate of the medical image to a certain extent.

[0049] Step S13: Based on the determined analysis method to be used, analyze the medical image to obtain the image analysis result of the target object.

[0050] Among them, by analyzing the medical image using at least one analysis method to be used, it is possible to perform at least one image analysis on the medical image. Among them, different analysis methods to be used can all adopt neural networks or decision trees with classification functions, etc. The embodiments of the present disclosure do not limit the specific method adopted by the analysis method to be used.

[0051] In the above solution, by determining the analysis method to be used based on the content of the medical image and / or the associated information of the target object, there is no need for a doctor to manually select the analysis method for each medical image, which reduces the waiting time and improves the efficiency of image analysis. At the same time, by determining at least one analysis method for the medical image, it shows that at least one image analysis can be performed on the medical image, which enriches the analysis content of the medical image and also improves the utilization rate of the medical image.

[0052] In some disclosed embodiments, considering the differences in equipment among various hospitals and the different requirements for medical images, the following solutions are proposed in the disclosed embodiments of the present application to solve this problem: After obtaining the medical image collected from the target object, the medical image is normalized. By normalizing the medical image, the form of the medical image is unified, which facilitates subsequent analysis of the medical image according to the manner to be analyzed. In some disclosed embodiments, the quality of the image can be further detected. If the detection result indicates that the quality of the medical image is too low and sufficient to affect the subsequent analysis result, a prompt is issued to remind doctors and other personnel to re-obtain the medical image collected from the target object. Among them, the detection methods for image quality include, but are not limited to, detecting the clarity of the image, the signal-to-noise ratio of the image, the slice thickness, and other contents. By preliminarily detecting the quality of the image before determining the manner to be analyzed, if the quality of the image is too low, continuing to perform operations such as analysis on it may lead to excessive errors. Therefore, subsequent operations are no longer performed to save computing resources and avoid misdiagnosis problems at the same time.

[0053] In some disclosed embodiments, the reference information includes the content of the medical image. The types of the content of the medical image refer to the above content and will not be elaborated here. Also refer to Figure 2 , Figure 2 is the schematic diagram of the second process in an embodiment of the image analysis method of the present application.

[0054] In step S12, it includes step S121: performing organ recognition on the medical image to obtain the organ recognition result of the medical image, where the organ recognition result includes several recognized organs.

[0055] Optionally, several in the disclosed embodiments of the present application can be one, two, or even more. The method for performing organ recognition on the medical image can be a neural network with a classification function that has been pre-trained. Of course, in addition to the neural network, other methods with classification functions can also be used, such as decision trees, etc. Therefore, the disclosed embodiments of the present application do not overly limit the method for performing organ recognition on the medical image. In some other disclosed embodiments, the organ recognition result further includes the probability that each recognized organ exists in the medical image. That is, the probability that the recognized organ is a real organ. For example, if the probability that the recognized organ is the heart is 95%, the probability that it is the lung is 2.5%, and the probability that it is the kidney is 2.5%, then it is determined that the probability that the recognized heart exists in the medical image is 95%.

[0056] Step S122: Select at least one recognized organ as the organ to be analyzed.

[0057] Optionally, the selection method can be to obtain the first weight of each recognized organ. Among them, the determination method of the first weight can be to use the probability of each recognized organ as the first weight of the recognized organ. For example, if the probability of the recognized organ being the heart is 95%, then the first weight of this organ is 0.95. In some disclosed embodiments, the probability that a recognized organ exists in a medical image is related to the integrity of the recognized organ in the medical image. For example, if only half of the recognized organ is shown in the medical image, the corresponding probability may be 50%.

[0058] Among them, the method of determining the first weight can also be to detect whether there is a preset marker in the area where the recognized organ is located in the medical image. If so, the first weight of the recognized organ is increased. Among them, the area where it is located includes the area occupied by the recognized organ, or the area within a preset radius centered on the organ. The area within the preset radius does not include other recognized organs. If other recognized organs are included within the preset radius of a certain recognized organ, the preset radius is reduced until other recognized organs are not included. The preset marker includes reagents commonly used in the medical field, such as contrast agents, blood enhancers, etc. Any external medical item is the preset marker described in the embodiments of the present disclosure. The method of increasing the first weight can be to increase it according to a preset ratio. Of course, the weight of the recognized organ that does not include the preset marker can also be reduced indirectly to increase the weight of the organ with the preset marker. The preset ratio can be set according to the user's needs. If multiple recognized organs all include the preset marker, then the first weight of the respective organs where they are located can be increased according to the level of the preset marker. By using the preset marker to indicate that the organ is the key observation object in this image acquisition, and by detecting whether there is a preset marker in the area where the recognized organ is located to increase the weight of the recognized organ, the analysis possibility of the key observation organ can be improved.

[0059] Among them, after obtaining the first weight of each recognized organ, the recognized organ whose first weight meets the first preset selection condition is selected as the organ to be analyzed. Optionally, the first preset selection condition includes the first number of recognized organs arranged in descending order of the first weight. Among them, the first number can be greater than the number of recognized organs. If the first number is greater than the number of recognized organs, that is, all recognized organs will be used as the organs to be analyzed.

[0060] Selecting the recognized organ as the organ to be analyzed through the weight makes the determined organ to be analyzed better reflect the user's intention.

[0061] Secondly, by using the probability that the recognized organ exists in the medical image as the first weight and determining the organ to be analyzed in the order from high to low of the first weight, the analysis result of the organ to be analyzed is more accurate.

[0062] Step S123: Take the analysis method associated with the organ to be analyzed as the first analysis method to be analyzed.

[0063] Among them, the analysis methods associated with the organ to be analyzed may include one or more. Of course, all or part of the analysis methods associated with the organ to be analyzed can be used as the first analysis method to be analyzed. When the probability that the organ does not suffer from a certain disease is clearly excluded, the analysis method corresponding to that disease may not be used as the first analysis method. Among them, different analysis methods to be analyzed are used to determine different disease types. By using different analysis methods to be analyzed to determine different disease types, multi-disease analysis of medical images can be carried out, thereby improving the utilization rate of medical images.

[0064] Therefore, by selecting at least one of the several identified organs as the organ to be analyzed and selecting the corresponding method according to the identified organ, the analysis method to be analyzed determined can perform targeted analysis on the organ. Moreover, selecting the analysis method corresponding to the organ included in the medical image as the analysis method to be analyzed can make the analysis of the medical image effective and improve the efficiency of medical image analysis.

[0065] In some disclosed embodiments, the reference information includes the associated information of the target object. Based on the reference information, determining at least one analysis method to be analyzed includes obtaining the associated location of the target object and taking the analysis method corresponding to the associated location as the second analysis method to be analyzed. By considering the information related to the target object to determine the corresponding analysis method to be analyzed, the types of analysis methods to be analyzed for medical images can be enriched, and the disease analysis method can be determined specifically for the target object, which can improve the efficiency and accuracy of disease analysis. Among them, the associated location includes at least one of the city where the target object is located and the hospital where the target object is located. Optionally, the city where the target object is located includes the city where the target object lives (usual place of residence), and the hospital where the target object is located includes the hospital where the target object seeks medical treatment.

[0066] Optionally, the way to obtain the city information in the associated location of the target object can be to call the previous medical records of the target object or the oral or written statements of the target object and the people related to the target object. Among them, the way to obtain the associated information of the target object through the oral statement of the target object or the people related to the target object can be to obtain the keywords of the oral content and match the keywords with the preset content to obtain the final associated information. For example, the target person orally states "I am from Chongqing", the keyword is extracted as "Chongqing", and the preset content includes the living city. After matching, "Living city: Chongqing" is obtained. The information about the hospital where the target object is located in the associated location of the target object can be set in advance. Specifically, it can be set in the preset configuration information in advance.

[0067] Find out the preset analysis methods configured for the associated locations from the preset configuration information. Optionally, in the preset configuration information, there may be more than one preset analysis method configured for each associated location. For example, in the preset configuration information, the hospital where the target object is located is Hospital A, and the preset analysis methods configured for Hospital A include Method B, C, D, and so on. For example, nowadays, with the prevalence of COVID-19, the COVID-19 analysis method is configured for Hospital A in the preset configuration information, and so on. The methods of configuring the preset analysis methods for the associated locations include specifying according to the hospital, determining according to the main business of the hospital, and / or determining at least one corresponding preset analysis method based on the air quality, cultural habits, water quality, etc. of each city. For example, if the air quality of a city is poor, it may cause lung diseases. Therefore, the preset analysis methods configured for this city include the preset analysis methods corresponding to the lungs. Take the found preset analysis methods as the second analysis methods to be analyzed. Among them, the found preset analysis methods can be the same or different. Different analysis methods to be analyzed are used to determine different disease types. If two or more preset analysis methods are found, then some or all of the analysis methods to be analyzed can be selected for analysis.

[0068] Optionally, the found preset analysis methods can determine the corresponding weights. The reference factors for setting the weights include the mortality rate, heritability, infection rate, etc. of the diseases corresponding to the previous preset analysis. Set the corresponding weights for the found preset analysis methods according to these reference factors. For example, the higher the mortality rate, heritability, or infection rate of the corresponding disease, the greater the weight is set. If the corresponding disease is common and easy to treat, a smaller weight is set. Therefore, the found preset analysis methods can be sorted according to the corresponding weights, and it is acceptable to select all or part of the preset analysis methods as the second analysis methods to be analyzed. The way of setting the weights can be set by the hospital itself.

[0069] Optionally, determining the analysis method corresponding to the associated location as the second analysis method to be analyzed also includes analyzing the environment of the associated location, determining the disease types prone to occur that match the environment, and selecting the analysis method used to determine the disease types prone to occur as the second analysis method to be analyzed. Among them, the associated location is the living location corresponding to the target object, for example, the city where the target object lives. The way to obtain the associated location of the target object can be through the oral statement of the target object or other people or by providing written explanatory materials. For example, the oral statement of the target object is as follows: "The air in the city where I live is poor. I generally need to wear a mask when going out. By the way, a COVID-19 patient was recently detected in our area." In this regard, extract the keywords including "air", "poor", "COVID-19". Through keyword matching analysis, the following conclusions are drawn: The air quality of the associated location of the target object is poor and there is a COVID-19 disease. Select the analysis method corresponding to the lung disease as the second analysis method to be analyzed, which includes the analysis method for COVID-19.

[0070] By pre-configuring the corresponding preset analysis method or determining the corresponding analysis method according to the types of diseases prone to occur in the environment associated with the location of the target object, the potential diseases of the target object can be analyzed.

[0071] In some disclosed embodiments, considering that the target object may have potential diseases due to its own reasons, the following solutions are proposed in the disclosed embodiments: Obtain the personal information of the target object, and determine the analysis method matching the personal information as the second analysis method to be determined. Optionally, the personal information includes at least one of medical history and living habits. Specifically, determining the analysis method matching the personal information as the second analysis method to be determined includes analyzing the personal information to determine the predicted disease type of the target object. Among them, the predicted disease type includes the historical disease type in the medical history and / or the disease type associated with the living habits. Living habits include eating habits, exercise habits, and so on. The method of obtaining the medical history of the target object includes retrieving the target object's previous medical records online and / or the target object or others providing them offline. Living habits are mainly provided offline by the target object or others. Select the analysis method used to determine the predicted disease type as the second analysis method to be determined. Each second analysis method determined through personal information can have different weights. For example, the weight is determined according to the severity of the disease type corresponding to the second analysis method. The higher the severity, the greater the weight. Conversely, the lower the severity, the smaller the weight. If there are restrictions on the number of second analysis methods, the final second analysis method can be determined according to the corresponding weights.

[0072] For example, the target object orally states, "I usually love to eat chili peppers very much, and I occasionally feel a little uncomfortable in my heart. I don't know what the reason is." The keywords include "love to eat chili peppers" and "uncomfortable in the heart". After analysis, the following conclusions are drawn: Loving to eat chili peppers may indicate stomach problems, and select the analysis method used to determine stomach problems as the second analysis method to be determined. Feeling uncomfortable in the heart may indicate heart problems, and select the analysis method used to determine heart problems as the second analysis method to be determined.

[0073] Because the medical history and living habits of the target object may lead to potential diseases of the target object, analyzing the potential diseases of the target object enriches the determination method of the analysis method for medical images.

[0074] Considering that the second analysis method determined by associating location or personal information is not applicable to the current medical image. For example, the second analysis method is the analysis method corresponding to heart disease, but the medical image does not include the heart organ. Therefore, to prevent incorrect analysis, the embodiments of the present disclosure provide the following technical solutions: After determining the second analysis method to be analyzed, determine the first organ that the second analysis method to be analyzed is used to determine, and use the first organ not included in the medical image as the second organ. For example, the first organ that the second analysis method to be analyzed is used to determine is the heart, but the heart is not included in the medical image. Therefore, the heart is used as the second organ. Discard the second analysis method to be analyzed used to determine the second organ. Continuing with the above example, if the heart is used as the second organ, then the second analysis method used to determine the heart needs to be discarded, that is, the heart will not be analyzed subsequently.

[0075] If the medical image does not include the second organ and the second analysis method to be analyzed is still used to analyze the medical image, then the analysis result may have errors. That is, discarding the second analysis method to be analyzed used to determine the second organ helps to reduce subsequent analysis errors.

[0076] In some disclosed embodiments, when the reference information for determining the analysis method to be analyzed includes at least one of the content of the medical image, the associated location of the target object, and the personal information of the target object, there may be more than one determined analysis method to be analyzed, and even many analysis methods to be analyzed. Therefore, after obtaining each analysis method to be analyzed, based on the determined analysis method to be analyzed, the method for analyzing the medical image to obtain the image analysis result of the target object may include: using the intersection or union of the analysis methods to be analyzed determined based on each reference information as the target analysis method. For example, the first analysis method to be analyzed determined by the content of the medical image includes methods A and B, the second analysis method to be analyzed determined by the associated location of the target object includes methods B and C, and the analysis method to be analyzed determined by the personal information of the target object includes methods B, C, and D. Among them, the intersection of the analysis methods to be analyzed determined by each reference information is method B. Therefore, B is the target analysis method. Or the union of the analysis methods to be analyzed determined based on each reference information is methods A, B, C, and D, that is, the target analysis method includes methods A, B, C, and D.

[0077] After obtaining the target analysis method, use the target analysis method whose second weight meets the second preset condition to analyze the medical image, and obtain the image analysis result of the target object. Among them, the image analysis result can specifically be the physical examination situation of the target object. For example, it can include the diseases that the target object may have and the probabilities of suffering from these diseases, etc., and can also include the health status of organs, etc. Optionally, the second preset condition can be that the second weight is greater than the preset weight value, or the first second preset number of digits in the descending order of the second weight. Among them, in the embodiments of the present disclosure, the second weight can be the sum of the first weight determined by the content of the medical image for the same analysis method to be analyzed, the weight determined according to the associated location of the target object, and the weight determined by the personal information of the target object. For example, if the first weight corresponding to analysis method A determined by the content of the medical image is 0.5 and the first weight corresponding to analysis method A determined according to the associated location of the target object is 0.6, then the second weight corresponding to the target analysis method A is 1.1. In some other embodiments, a larger weight is given to the analysis method determined according to the associated location of the target object, so that the analysis method determined according to the associated location of the target object meets the second preset condition. Or regardless of whether the weight of the analysis method determined according to the associated location of the target object meets the second preset condition, it is used to analyze the medical image.

[0078] In some other disclosed embodiments, weights can be set for the analysis methods to be analyzed determined by the content of the medical image, the associated location of the target object, and the personal information of the target object. For example, the weight corresponding to the method of the analysis method to be analyzed determined by the content of the medical image is 0.5, while the analysis methods to be analyzed determined by the associated location of the target object and the personal information of the target object each account for 0.25. That is, not only different weights will be determined for the analysis methods to be analyzed determined in each method, but also weights will be determined for the methods of determining the analysis methods to be analyzed using different reference information. Continuing with the above example, if the weight corresponding to the method of the analysis method to be analyzed determined by the content of the medical image is 0.5, while the analysis methods to be analyzed determined by the associated location of the target object and the personal information of the target object each account for 0.25. Among them, the first weight corresponding to analysis method A determined by the content of the medical image is 0.5, the first weight corresponding to analysis method A determined according to the associated location of the target object is 0.6, and the first weight corresponding to analysis method B is 0.4. Then the second weight corresponding to the target analysis method B is 0.25 * 0.4 + 0 = 0.1, and the second weight corresponding to the target analysis method A is 0.5 * 0.5 + 0.25 * 0.6 = 0.4. Among them, a larger weight can be set for the method of determining the second analysis method by the target associated location, so that the second analysis method determined by the target associated location can give priority to analyzing the medical image. Of course, this is only an example of the weight calculation method, and the method of calculating the weight is not limited to this.

[0079] In some other disclosed embodiments, after obtaining the target analysis methods, the priority of each target analysis method is determined based on the second weight of the target analysis, and each target analysis method is used to analyze the medical image in the order of priority to obtain the image analysis result of the target object. Similarly, the image analysis result can be the physical examination condition of the target object. Among them, the greater the second weight of the analysis method to be analyzed, the higher the priority of the analysis method to be analyzed. At this time, regardless of the level of the second weight of the target analysis method, the target analysis method can be used to analyze the medical image to obtain the physical examination condition of the target object. Among them, the physical examination condition obtained by a single target analysis method includes the conclusion of whether the target object has the corresponding disease and the probability of having the corresponding disease, and can even give subsequent physical conditioning methods, or matters that should be noted, etc.

[0080] By adopting the intersection or union of the analysis methods to be analyzed determined by each reference information, and selecting the analysis methods to be analyzed based on the second weight to analyze the medical image, the analysis of the medical image is made more focused.

[0081] Considering that the requirements for image quality of each analysis method are different, therefore, to reduce the subsequent analysis error, the following technical solution is proposed in the disclosed embodiments of the present disclosure: after obtaining the target analysis method, before using the target analysis method to analyze the medical image, delete the medical images whose image quality does not meet the quality requirements of each target analysis method. At the same time, the acquisition personnel can also be prompted to re-acquire new medical images. Among them, the influencing factors of image quality include signal-to-noise ratio, slice thickness, and clarity. If one of the influencing parameters does not meet the conditions, it can be considered that the image quality does not meet the requirements, or when the image quality of the combination of influencing factors does not meet the requirements, the medical image is deleted. In the disclosed embodiments of the present disclosure, different image quality requirements can be formulated for different organs or analysis methods. In some cases, even if the image quality does not meet the requirements, it can still be analyzed. For example, if there are multiple target analysis methods, but the image quality does not meet the requirements of one or more target analysis methods, only the target analysis method corresponding to the image quality that meets the requirements is used to analyze the medical image. For example, if the obtained target analysis methods include method A, B, and C, but the medical image quality does not meet the image quality requirements corresponding to method B and C, therefore, only analysis method A is used to analyze the medical image.

[0082] By deleting the medical images whose image quality does not meet the quality requirements, the subsequent analysis error caused by the medical image quality problem is reduced.

[0083] In the above solution, the analysis method to be used is determined based on the content of the medical image and / or the associated information of the target object. There is no need for a doctor to manually select the analysis method for each medical image, which reduces the waiting time and improves the efficiency of medical image analysis. Moreover, the analysis method determined for the medical image has a high degree of matching with the medical image and the corresponding target object, thereby improving the accuracy of medical image analysis. In addition, determining at least one analysis method to be used for the medical image, as opposed to a single medical image being only used for one type of image analysis method, can enrich the types of image analysis methods for medical images and improve the utilization rate of medical images.

[0084] Among them, the execution subject of the image analysis method can be an image analysis device. For example, the image analysis method can be executed by a terminal device, a server, or other processing devices. Among them, the terminal device can be a medical device, a user equipment (UE), a mobile device, a user terminal, a terminal, a cellular phone, a cordless phone, a personal digital assistant (PDA), a handheld device, a computing device, a vehicle-mounted device, a wearable device, etc. In some possible implementation manners, the image analysis method can be implemented by a processor calling computer-readable instructions stored in a memory.

[0085] Please refer to Figure 3 , Figure 3 which is a schematic structural diagram of an embodiment of the image analysis device of the present application. The image analysis device 30 includes an image acquisition module 31, an analysis method determination module 32, and an image analysis module 33. The image acquisition module 31 is configured to acquire medical images collected for a target object; the analysis method determination module 32 is configured to determine at least one analysis method to be used based on reference information, where the reference information includes the content of the medical image and / or the associated information of the target object; the image analysis module 33 is configured to analyze the medical image based on the determined analysis method to be used to obtain an image analysis result of the target object.

[0086] In the above solution, the analysis method to be used is determined based on the content of the medical image and / or the associated information of the target object. There is no need for a doctor to manually select the analysis method for each medical image, which reduces the waiting time and improves the efficiency of medical image analysis. Moreover, the analysis method determined for the medical image has a high degree of matching with the medical image and the corresponding target object, thereby improving the accuracy of medical image analysis. In addition, determining at least one analysis method to be used for the medical image, as opposed to a single medical image being only used for one type of image analysis method, can enrich the types of image analysis methods for medical images and improve the utilization rate of medical images.

[0087] In some disclosed embodiments, the reference information includes the content of a medical image. Based on the reference information, the analysis method determination module 32 determines at least one analysis method to be performed, including: performing organ recognition on the medical image to obtain an organ recognition result of the medical image, where the organ recognition result includes several recognized organs; selecting at least one recognized organ as the organ to be analyzed; and using the analysis method associated with the organ to be analyzed as the first analysis method to be performed.

[0088] In the above solution, by selecting at least one of the several recognized organs as the organ to be analyzed and selecting the corresponding method based on the recognized organ, the determined analysis method to be performed can perform targeted analysis on the organ. Moreover, selecting the analysis method corresponding to the organ included in the medical image as the analysis method to be performed can make the analysis of the medical image effective and improve the efficiency of medical image analysis.

[0089] In some disclosed embodiments, when the analysis method determination module 32 selects at least one recognized organ as the organ to be analyzed, it includes: obtaining a first weight for each recognized organ; and selecting the recognized organs whose first weights meet a first preset selection condition as the organs to be analyzed.

[0090] In the above solution, by selecting the recognized organ as the organ to be analyzed based on the weight, the determined organ to be analyzed can better reflect the intention of the user.

[0091] In some disclosed embodiments, the first preset condition is the first several recognized organs sorted in descending order of the first weight; and / or, the organ recognition result further includes the probability of each recognized organ existing in the medical image; when the analysis method determination module 32 obtains the first weight for each recognized organ, it includes: using the probability of each recognized organ as the first weight of the recognized organ.

[0092] In the above solution, by using the probability of the recognized organ existing in the medical image as the first weight and determining the organ to be analyzed in the order of the first weight from high to low, the analysis result of the organ to be analyzed is more accurate.

[0093] In some disclosed embodiments, before selecting the recognized organs whose first weights meet the preset selection condition as the organs to be analyzed, the analysis method determination module 32 is further configured to: if a preset marker is detected in the region where the recognized organ is located in the medical image, increase the first weight of the recognized organ.

[0094] In the above solution, the preset marker can be used to indicate that the organ is a key observation object in the current image acquisition. By detecting whether a preset marker exists in the region where the recognized organ is located to increase the weight of the recognized organ, the possibility of analyzing the key observation organ can be improved.

[0095] In some disclosed embodiments, the reference information includes the associated information of the target object. Based on the reference information, the analysis method determination module 32 determines at least one analysis method to be performed, including: obtaining the associated location of the target object, and determining the analysis method corresponding to the associated location as the second analysis method to be performed; and / or, obtaining the personal information of the target object, and determining the analysis method matching the personal information as the second analysis method to be performed.

[0096] In the above solution, by considering the information related to the target object to determine the corresponding analysis method to be performed, the types of analysis methods to be performed on the medical image can be enriched, and the disease analysis method can be specifically determined for the target object, which can improve the efficiency and accuracy of disease analysis.

[0097] In some disclosed embodiments, the associated location includes at least one of the city where the target object is located and the hospital where the target object is located. When the analysis method determination module 32 determines the analysis method corresponding to the associated location as the second analysis method to be performed, it includes: searching for the preset analysis method configured for the associated location from the preset configuration information, and using the found preset analysis method as the second analysis method to be performed; or, analyzing the environment of the associated location to determine the type of disease prone to occur that matches the environment, and selecting the analysis method for determining the type of disease prone to occur as the second analysis method to be performed.

[0098] In the above solution, by pre-configuring the corresponding preset analysis method or analyzing the type of disease prone to occur in the environment of the associated location of the target object to determine the corresponding analysis method, the potential diseases of the target object can be analyzed.

[0099] In some disclosed embodiments, the personal information includes at least one of medical history and living habits. When the analysis method determination module 32 determines the analysis method matching the personal information as the second analysis method to be performed, it includes: analyzing the personal information to determine the predicted disease type of the target object, where the predicted disease type includes the historical disease type in the medical history and / or the disease type associated with the living habits; and selecting the analysis method for determining the predicted disease type as the second analysis method to be performed.

[0100] In the above solution, since the medical history and living habits of the target object may lead to potential diseases of the target object, analyzing the potential diseases of the target object enriches the method for determining the analysis method of the medical image.

[0101] In some disclosed embodiments, after the analysis method determination module 32 determines the analysis method corresponding to the associated location as the second analysis method to be performed, or determines the analysis method matching the personal information as the second analysis method to be performed, the analysis method determination module 32 is further configured to: determine the first organ for which the second analysis method to be performed is used, and use the first organ not included in the medical image as the second organ; and discard the second analysis method to be performed for determining the second organ.

[0102] In the above solution, if the second organ is not included in the medical image and the second analysis method to be analyzed is still used for the medical analysis, there may be errors in the analysis results. That is, discarding the second analysis method for determining the second organ helps reduce subsequent analysis errors.

[0103] In some disclosed embodiments, the image analysis module 33 analyzes the medical image based on the determined analysis method to be analyzed, and obtains the image analysis result of the target object, including: using the intersection or union of the analysis methods to be analyzed determined based on each reference information as the target analysis method, where the reference information includes at least one of three types of information: the content of the medical image, the associated location of the target object, and the personal information of the target object; analyzing the medical image using the target analysis method whose second weight satisfies the second preset condition to obtain the image analysis result of the target object; or, determining the priority of each target analysis method based on the second weight of the target analysis method, and analyzing the medical image using each target analysis method in the order of priority to obtain the image analysis result of the target object.

[0104] In the above solution, by using the intersection or union of the analysis methods to be analyzed determined based on each reference information and selecting the analysis method based on the second weight to analyze the medical image, the analysis of the medical image is more focused.

[0105] In some disclosed embodiments, the second preset condition includes that the second weight is greater than the preset weight value, or the first second preset number of digits in the descending order of the second weight; and / or, the greater the second weight of the analysis method to be analyzed, the higher the priority of the analysis method to be analyzed.

[0106] In the above solution, the greater the weight, the more priority is given to processing it. That is, the analysis result is obtained by analyzing the disease type that medical staff or the target object needs to pay more attention to, making the analysis effect better.

[0107] In some disclosed embodiments, after the image acquisition module 31 acquires the medical image collected for the target object, the image acquisition module 31 is further configured to perform at least one of the following steps: performing normalization processing on the medical image; deleting the medical image whose image quality does not meet the quality requirements, and prompting the collector to collect a new medical image again.

[0108] In the above solution, after obtaining the medical image, the medical image is first normalized to unify the style of the medical image, making the analysis more efficient; deleting the medical image whose image quality does not meet the quality requirements reduces the subsequent analysis errors caused by the medical image quality problems.

[0109] In the above solution, the analysis method to be used is determined based on the content of the medical image and / or the associated information of the target object, eliminating the need for doctors to manually select the analysis method for each medical image, reducing the waiting time, and improving the efficiency of medical image analysis. Moreover, the analysis method determined for the medical image has a high degree of matching with the medical image and the corresponding target object, thereby improving the accuracy of medical image analysis. In addition, determining at least one analysis method to be used for a medical image, different from a single medical image being only used for one type of image analysis method, can enrich the types of image analysis methods for medical images and improve the utilization rate of medical images.

[0110] Please refer to Figure 4 , Figure 4 which is a schematic structural diagram of an embodiment of an electronic device according to the present application. The electronic device 40 includes a memory 41 and a processor 42. The processor 42 is configured to execute program instructions stored in the memory 41 to implement the steps in any of the above embodiments of the image analysis method. In a specific implementation scenario, the electronic device 40 may include, but is not limited to: medical devices, microcomputers, desktop computers, servers. In addition, the electronic device 40 may also include mobile devices such as laptop computers and tablet computers, which are not limited herein.

[0111] Specifically, the processor 42 is configured to control itself and the memory 41 to implement the steps in any of the above embodiments of the image analysis method. The processor 42 may also be referred to as a CPU (Central Processing Unit). The processor 42 may be an integrated circuit chip with signal processing capabilities. The processor 42 may also be a general-purpose processor, a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc. In addition, the processor 42 may be implemented jointly by integrated circuit chips.

[0112] In the above solution, the analysis method to be used is determined based on the content of the medical image and / or the associated information of the target object, eliminating the need for doctors to manually select the analysis method for each medical image, reducing the waiting time, and improving the efficiency of medical image analysis. Moreover, the analysis method determined for the medical image has a high degree of matching with the medical image and the corresponding target object, thereby improving the accuracy of medical image analysis. In addition, determining at least one analysis method to be used for a medical image, as opposed to a single medical image being only used for one type of image analysis method, can enrich the types of image analysis methods for medical images and improve the utilization rate of medical images.

[0113] Please refer to Figure 5 , Figure 5 which is a schematic structural diagram of an embodiment of the computer-readable storage medium of the present application. The computer-readable storage medium 50 stores program instructions 51 that can be run by a processor, and the program instructions 51 are used to implement the steps in any of the above-described embodiments of the image analysis method.

[0114] In the above solution, the analysis method to be used is determined based on the content of the medical image and / or the associated information of the target object, eliminating the need for doctors to manually select the analysis method for each medical image, reducing the waiting time, and improving the efficiency of medical image analysis. Moreover, the analysis method determined for the medical image has a high degree of matching with the medical image and the corresponding target object, thereby improving the accuracy of medical image analysis. In addition, determining at least one analysis method to be used for a medical image, as opposed to a single medical image being only used for one type of image analysis method, can enrich the types of image analysis methods for medical images and improve the utilization rate of medical images.

[0115] In some embodiments, the functions or modules included in the device provided by the embodiments of the present disclosure can be used to execute the methods described in the above method embodiments. The specific implementation can refer to the description of the above method embodiments. For the sake of brevity, it will not be repeated here.

[0116] The descriptions of the above embodiments tend to emphasize the differences between the embodiments. The similarities or identical parts can be referred to each other. For the sake of brevity, they will not be repeated in this article.

[0117] In several embodiments provided in the present application, it should be understood that the disclosed methods and apparatuses can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative. For example, the division of modules or units is only a logical function division. In actual implementation, there may be other division methods. For example, units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed coupling or direct coupling or communication connection between each other can be through some interfaces. The indirect coupling or communication connection of devices or units can be in electrical, mechanical or other forms.

[0118] In addition, each functional unit in various embodiments of the present application can be integrated in a processing unit, or each unit can exist physically alone, or two or more units can be integrated in one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of a software functional unit. If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on such an understanding, the technical solution of the present application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) or a processor to execute all or part of the steps of the methods in various embodiments of the present application. The foregoing storage medium includes: various media such as USB flash drives, mobile hard disks, read-only memories (ROMs), random access memories (RAMs), magnetic disks, or optical discs that can store program codes.

Claims

1. An image analysis method, characterized in that, Including: Obtaining a medical image collected for a target object; Determining at least one analysis method to be performed based on reference information, where the reference information includes the content of the medical image and / or the associated information of the target object; Analyzing the medical image based on the determined analysis method to be performed to obtain an image analysis result of the target object, including: using the intersection or union of the analysis methods to be performed determined based on each piece of the reference information as the target analysis method; analyzing the medical image using the target analysis method whose second weight satisfies a second preset condition to obtain the image analysis result of the target object; or determining the priority of each target analysis method based on the second weight of the target analysis method, and analyzing the medical image using each target analysis method in the order of the priority to obtain the image analysis result of the target object.

2. The method according to claim 1, wherein The reference information includes the content of the medical image, and determining at least one analysis method to be performed based on the reference information includes: Performing organ recognition on the medical image to obtain an organ recognition result of the medical image, where the organ recognition result includes several recognized organs; Selecting at least one of the recognized organs as an organ to be analyzed; Using the analysis method associated with the organ to be analyzed as the first analysis method to be performed.

3. The method according to claim 2, wherein The selecting at least one of the recognized organs as an organ to be analyzed includes: Obtaining a first weight of each recognized organ; Selecting the recognized organs whose first weight satisfies a first preset selection condition as the organs to be analyzed.

4. The method according to claim 3, wherein The first preset selection condition is the first several recognized organs sorted in descending order of the first weight; and / or The organ recognition result further includes the probability that each recognized organ exists in the medical image; the obtaining a first weight of each recognized organ includes: Using the probability of each recognized organ as the first weight of the recognized organ.

5. The method according to claim 3 or 4, characterized in that Before the selecting the recognized organs whose first weight satisfies a preset selection condition as the organs to be analyzed, the method further includes: If it is detected that a preset marker exists in the region where the recognized organ is located in the medical image, increasing the first weight of the recognized organ.

6. The method according to any one of claims 1 to 4, characterized in that, The reference information includes the associated information of the target object, and determining at least one analysis method to be performed based on the reference information includes: Obtaining the associated location of the target object, and determining the analysis method corresponding to the associated location as the second analysis method to be performed; and / or Obtaining the personal information of the target object, and determining the analysis method matching the personal information as the second analysis method to be performed.

7. The method according to claim 6, wherein The associated location includes at least one of the city where the target object is located and the hospital where the target object is located; The determining the analysis method corresponding to the associated location as the second analysis method to be performed includes: Searching for a preset analysis method configured for the associated location from preset configuration information, and using the found preset analysis method as the second analysis method to be performed; Or Analyze the environment of the associated location to determine the type of disease prone to match the environment, and select the analysis method for determining the type of disease prone to as the second analysis method to be analyzed.

8. The method according to claim 6, wherein The personal information includes at least one of medical history and living habits; Determining the analysis method matching the personal information as the second analysis method to be analyzed includes: Analyze the personal information to determine the predicted disease type of the target object, where the predicted disease type includes the historical disease type in the medical history and / or the disease type associated with the living habits; Select the analysis method for determining the predicted disease type as the second analysis method to be analyzed.

9. The method according to claim 6, wherein After determining the analysis method corresponding to the associated location as the second analysis method to be analyzed, or determining the analysis method matching the personal information as the second analysis method to be analyzed, the method further includes: Determine the first organ that the second analysis method to be analyzed is used to determine, and use the first organ not included in the medical image as the second organ; Discard the second analysis method to be analyzed for determining the second organ.

10. The method according to any one of claims 1 to 4, characterized in that Wherein, The reference information includes at least one of the content of the medical image, the associated location of the target object, and the personal information of the target object.

11. The method according to claim 10, wherein The second preset condition includes that the second weight is greater than the preset weight value, or the first second preset number of digits in the order from high to low of the second weight; And / or, the greater the second weight of the analysis method to be analyzed, the higher the priority of the analysis method to be analyzed.

12. The method according to any one of claims 1 to 4, characterized in that, After acquiring the medical image collected for the target object, the method further includes at least one step: Perform normalization processing on the medical image; Delete the medical image whose image quality does not meet the quality requirements, and prompt the collector to re-collect a new medical image.

13. An image analysis device, characterized in that, Including: An image acquisition module for acquiring a medical image collected for a target object; An analysis method determination module for determining at least one analysis method to be analyzed based on reference information, where the reference information includes the content of the medical image and / or the associated information of the target object; An image analysis module for analyzing the medical image based on the determined analysis method to be analyzed to obtain an image analysis result of the target object, including: using the intersection or union of the analysis methods to be analyzed determined based on each reference information as the target analysis method; using the target analysis method whose second weight meets the second preset condition to analyze the medical image to obtain an image analysis result of the target object; or determining the priority of each target analysis method based on the second weight of the target analysis method, and analyzing the medical image using each target analysis method in the order of the priority to obtain an image analysis result of the target object.

14. An electronic device, characterized in that, Including a memory and a processor, the processor is used to execute the program instructions stored in the memory to implement the method according to any one of claims 1 to 12.

15. A computer-readable storage medium having program instructions stored thereon, characterized in that, When the program instructions are executed by the processor, the method according to any one of claims 1 to 12 is implemented.

Images