CN117808865A

CN117808865A - Medical image processing device, medical image processing method, storage medium and electronic equipment

Info

Publication number: CN117808865A
Application number: CN202311575675.4A
Authority: CN
Inventors: 凌赛广; 穆钰
Original assignee: Yiwei Science And Technology Beijing Co ltd
Current assignee: Yiwei Science And Technology Beijing Co ltd
Priority date: 2023-11-23
Filing date: 2023-11-23
Publication date: 2024-04-02

Abstract

The embodiment of the specification provides a medical image processing device, a medical image processing method, a storage medium and an electronic device, wherein the medical image processing device comprises: the parameter acquisition module is used for acquiring a blood vessel characteristic value from the fundus image; the operation module is used for calculating the probability value of the liver disease of the human body corresponding to the fundus image according to the blood vessel characteristic value; and the determining module is used for generating an evaluation result of the liver of the human body corresponding to the fundus image according to the probability value. According to the embodiment of the specification, the working efficiency of doctors can be improved.

Description

Medical image processing device, medical image processing method, storage medium and electronic equipment

Technical Field

Embodiments in the present specification relate to the field of medical image analysis, and in particular, to a medical image processing apparatus, a medical image processing method, a storage medium, and an electronic device.

Background

In the prior art, diagnosis of diseases can be aided by imaging examinations such as ultrasound or computed tomography (Computed Tomography, CT). These medical images may be evaluated and interpreted by a physician after acquisition, who makes a disease assessment report and corresponding treatment plan after analysis of the images.

In some cases, there may be many patients and the doctor is very busy, so it is necessary to provide better techniques to help the doctor to improve the working efficiency.

Disclosure of Invention

In view of this, various embodiments in the present disclosure provide a medical image processing apparatus, a medical image processing method, a storage medium, and an electronic device, so as to improve the working efficiency of a doctor.

Various embodiments in the present specification provide a medical image processing apparatus including: the parameter acquisition module is used for acquiring a blood vessel characteristic value from the fundus image; the operation module is used for calculating the probability value of the liver disease of the human body corresponding to the fundus image according to the blood vessel characteristic value; and the determining module is used for generating an evaluation result of the liver of the human body corresponding to the fundus image according to the probability value.

One embodiment of the present specification provides a medical image processing method including: acquiring a blood vessel characteristic value from the fundus image; calculating a probability value of liver diseases of the human body corresponding to the fundus image according to the blood vessel characteristic value; and generating an evaluation result of the liver of the human body according to the probability value.

One embodiment of the present specification provides a computer storage medium storing computer program instructions that, when executed by a processor, implement the medical image processing method.

One embodiment of the present specification provides an electronic device including: a processor and a memory storing computer program instructions which integrate means such as medical image processing or which, when executed by the processor, implement a method such as medical image processing.

According to the embodiments provided by the specification, the medical image processing device is provided, firstly, the blood vessel characteristic value is acquired from the fundus image through the parameter acquisition module, and a doctor can be helped to quickly acquire and process relevant information of a patient. And then calculating the probability value of the liver disease of the human body corresponding to the fundus image through an operation module. The module realizes the digital integration of the medical image data by quantifying the medical image data, and provides convenience for doctors to evaluate and read the medical image data. And finally, generating an evaluation result of the liver of the human body corresponding to the fundus image through a determining module. Can help doctors to quickly evaluate the disease risk and predict the disease development. Therefore, the working efficiency of doctors is improved.

Drawings

Fig. 1 is a schematic view of a medical image device according to an embodiment of the present disclosure.

Fig. 2 is a flowchart illustrating a medical image device according to an embodiment of the present disclosure.

Fig. 3 is a schematic diagram of parameter weight setting according to an embodiment of the present disclosure.

Fig. 4 is a schematic flow chart of a medical image processing method according to an embodiment of the present disclosure.

Fig. 5 is a schematic diagram of an electronic device according to an embodiment of the present disclosure.

Detailed Description

The following description of the embodiments of the present application will be made clearly and fully with reference to the accompanying drawings, in which it is evident that the embodiments described are only some, but not all, of the embodiments of the present application. All other embodiments, which can be made by those skilled in the art based on the embodiments herein without making any inventive effort, are intended to be within the scope of the present application.

In the description of the embodiments of the present application, it should be understood that the terms "first," "second," and the like are used for descriptive purposes only and are not to be construed as indicating or implying a relative importance or an implicit indication of the number of features indicated. Thus, a feature defining "a first" or "a second" may explicitly or implicitly include one or more of the described features. In the description of the embodiments of the present application, the meaning of "a plurality" is two or more, unless explicitly defined otherwise.

In the related art, the liver disease is usually examined by imaging such as ultrasound and CT scan. Specifically, during the examination, the doctor moves the ultrasound probe along the abdomen to observe the morphology, size, structure of the liver, and the presence or absence of abnormal shadows or bumps. CT scanning is the rotation of a scanner around a patient to generate a plurality of tomographic images. The doctor may evaluate the morphology, size, structure of the liver on the image and check for abnormal lesions, bumps, cysts, etc.

However, in some cases, as the population grows, so does the number of people in need of medical services. So that there may be many cases of patients. Further, the workload of doctors is also increased. In particular, in the course of imaging liver disease, doctors need to evaluate or interpret more medical image data. So that the doctor is very busy. Therefore, there is a technical problem in the related art that the working efficiency of doctors is low.

Therefore, it is necessary to provide a medical image processing apparatus, which can help a doctor to quickly acquire and process relevant information of a patient by firstly acquiring a blood vessel characteristic value from a fundus image through a parameter acquisition module. And then calculating the probability value of the liver disease of the human body corresponding to the fundus image through an operation module. The module realizes the digital integration of the medical image data by quantifying the medical image data, and provides convenience for doctors to evaluate and read the medical image data. And finally, generating an evaluation result of the liver of the human body corresponding to the fundus image through a determining module. Can help doctors to quickly evaluate the disease risk and predict the disease development. Therefore, the working efficiency of doctors is improved.

The present specification provides a medical image processing apparatus. The medical image processing apparatus may be applied to a target terminal. The target terminal may be an electronic device having network access capabilities. For example, a graphics processing unit (Graphics Processing Unit, GPU) server, server cluster. Specifically, the environment required for building the algorithm may be on a GPU server, so as to ensure training of the algorithm model. A new technology may also be used to implement a new modality of server. For example: quantum-based computing servers, cloud servers, massively parallel servers, and the like.

The target terminal may also be a desktop computer, a tablet computer, a notebook computer, a smart phone, etc., or the target terminal may also be software that can run in the electronic device.

Please refer to fig. 1. One embodiment of the present specification provides a medical image processing apparatus, which may include: a parameter acquisition module 11, an operation module 22 and a determination module 33.

The parameter acquisition module 11 may be used to acquire a blood vessel feature value from the fundus image.

In the present embodiment, the fundus image may be acquired by a fundus camera. The fundus image is used for acquiring the blood vessel characteristic value. Specifically, for example, after the subject enters a darkroom environment and adapts to the darkroom environment for 2 minutes, the same operator uses the mydriasis-free automatic fundus camera to collect 2 fundus images with 45 degrees centering on the macula, and the person with better image quality is selected for analysis. Alternatively, the fundus image may be a 45 ° fundus image, or may be a 60 ° fundus image, or a wide-angle fundus image, or a fundus image of other angles of view, or even a fundus image of other modes, and the fundus image may be captured with the optic disc as the center, or may be captured with the macula center as the center, or an image of other eye positions, which is not limited in this embodiment.

In this embodiment, the blood vessel characteristic value may be a value of a blood vessel characteristic parameter in the fundus image. The vessel feature values may be used to quantify the features of the vessel. The blood vessel characteristic parameter may be a parameter capable of expressing the state of blood vessels of the eyeball. In particular, for example, the vessel diameter and the vessel tortuosity may be measured in a region between 0.5 and 1.0 disc diameters from the disc rim, the measured values being the average of all vessel diameters and vessel tortuosity in the region, respectively; the blood vessel branch included angle can be a first angle between two sub blood vessels at the bifurcation of the main blood vessel, the first angle can be the included angle between a line segment connecting the main blood vessel and the first sub blood vessel and a line segment connecting the main blood vessel and the second sub blood vessel, and the measured value is the average value of all the branch included angles of the main blood vessel; the fractal dimension of the blood vessel may then be a measure of the complexity of the fundus blood vessel, a higher fractal dimension may indicate a more complex and more branched fundus blood vessel.

In the present embodiment, the blood vessel feature value may be obtained from a fundus image, the fundus image is input to the parameter obtaining module 11, and a function for recognizing the fundus image is integrated in the parameter obtaining module 11. When the parameter acquisition module 11 receives the fundus image, the blood vessel feature value is identified by an internally integrated function. In some embodiments, acquiring vascular feature values from fundus images may also invoke an external automated system. The automated system may be a device capable of fundus image analysis. The fundus image is input to an automation system which analyzes the received fundus image to obtain the blood vessel feature value, and the blood vessel feature value is transmitted to the parameter acquisition module 11 through communication data.

The operation module 22 may be configured to calculate a probability value of liver disease of the human body corresponding to the fundus image according to the blood vessel feature value.

Typically, the vascular characteristic of a healthy human is in a normal threshold interval. And the vascular characteristic value of the liver disease exceeds or falls below the normal threshold interval. Under the influence of various pathophysiological mechanisms such as portal hypertension, liver hypofunction and inflammatory reaction, the retinal vasculature of patients with cirrhosis may be altered. Specifically, when the blood vessel characteristic value exceeds or falls below a normal threshold interval, the human body is prompted to possibly suffer from liver diseases. Specifically, for example, a retinal vessel diameter, a vessel branch angle exceeding a normal threshold, and a retinal vessel fractal dimension below a normal threshold suggests a potential for liver disease.

Please refer to fig. 2. In this embodiment, the probability value of the liver disease of the human body corresponding to the fundus image may be calculated by inputting the blood vessel feature value into a machine learning model. In some embodiments, the means of calculation includes, but is not limited to, inputting the vessel feature values into a deep learning model, or applying a logistic regression model, a nonlinear regression model, a random forest algorithm, etc. Specifically, for example, a fundus camera is used to capture a fundus image, a fundus blood vessel feature value is obtained from the fundus image, the obtained blood vessel feature value is input to a trained deep learning model, and an original prediction score can be converted into a probability value based on the deep learning model through an activation function.

The determining module 33 may be configured to generate an evaluation result of the liver of the human body corresponding to the fundus image according to the probability value.

In the present embodiment, the evaluation result of the liver of the human body corresponding to the fundus image may be obtained from the probability value obtained by the above-described operation module 22. The evaluation can be used to predict the risk of liver disease. Specifically, for example, when the calculated probability value can meet a threshold value, the risk of liver disease is high; if a threshold cannot be met, the risk of liver disease is low.

Please refer to fig. 2. In some embodiments, the medical image processing apparatus may further include: a human body parameter acquisition module; the human body parameter acquisition module is used for acquiring human body biological parameter values corresponding to the fundus image; the operation module 22 is configured to calculate a probability value of liver disease of the human body corresponding to the fundus image according to the blood vessel feature value and the human body biological parameter value.

In some cases, the body parameters may provide important information about the physical state and health condition. When a patient suffers from liver diseases, human body characteristic parameters may change, and the calculated result can be more accurate by calculating the probability value of the liver diseases by combining the human body parameters.

In this embodiment, the human biological parameter value may be a value obtained by quantitatively measuring a human feature. The human biological parameter value is used for evaluating the health condition of the human body.

In this embodiment, a probability value of liver disease of the human body corresponding to the fundus image is calculated from the blood vessel characteristic value and the human body biological parameter value. Specifically, for example, the vessel diameter increases abnormally, and the patient ages older, which may indicate that cirrhosis is occurring. The vascular characteristic value and the human biological parameter value are utilized to obtain more comprehensive and accurate liver disease assessment.

In this embodiment, the operation module 22 is configured to calculate the probability value of liver disease of the human body corresponding to the fundus image according to the blood vessel feature value and the human body biological parameter value, which may be implemented based on a deep learning model. Specifically, for example, training a deep learning model by using a large number of known medical image samples and human biological parameters corresponding to the medical image samples to obtain a liver function assessment model; inputting the blood vessel characteristic value and the human body biological parameter value into the liver function evaluation model for prediction; outputting the probability value of liver disease. In this way, the risk of liver disease is assessed.

In some embodiments, the medical image processing apparatus may further include: the parameter obtaining module 11 is further configured to obtain an external eye parameter value from an external eye image corresponding to an eyeball in the fundus image; the operation module 22 is configured to calculate a probability value of liver disease of the human body corresponding to the fundus image according to the blood vessel feature value, the human body biological parameter value and the external eye parameter value.

In some cases, the external ocular characteristics of a patient with liver disease have a certain difference from the external ocular characteristics of a healthy human body. Thus, assessing liver disease in combination with external ocular features may improve the reliability of the assessment to some extent.

In the present embodiment, a blood vessel characteristic value is acquired after quality evaluation is passed on the basis of fundus images photographed by different photographing centers. And calculating the probability value of liver diseases of the human body corresponding to the fundus image according to the human body biological parameters corresponding to the fundus image and the external eye parameters corresponding to the eyeball. In some embodiments, fundus image quality assessment may cull out images that are not fundus, as well as overexposed fundus images. So that the quality of the fundus image is qualified for evaluation.

In this embodiment, the external ocular parameter value may be a value recorded for an external ocular feature. The values of the external ocular parameters are used to aid in the assessment of liver disease. In some embodiments, liver disease may be associated with symptoms associated with the eye. Specifically, for example, one of the symptoms of jaundice is yellow staining of the eyeball. In this case, the external eye image may be observed to check whether there is evidence of jaundice.

In this embodiment, the operation module 22 is configured to calculate the probability value of liver disease of the human body corresponding to the fundus image according to the blood vessel feature value, the human body biological parameter value and the external eye parameter value, and may be implemented based on a deep learning model. Specifically, for example, the deep learning model is trained using a large number of known medical image samples, human biological parameters corresponding to the medical image samples, and external eye parameters of a human body corresponding to the medical image samples, so as to obtain a liver function assessment model. Inputting the blood vessel characteristic value, the human body biological parameter value and the external eye parameter value into the liver function evaluation model for prediction, and outputting a probability value of liver disease illness. In this way, the risk of liver disease is assessed.

Please refer to fig. 3. In some embodiments, the medical image processing apparatus may further include: the blood vessel characteristic value is a value of a blood vessel characteristic parameter, and the blood vessel characteristic parameter comprises at least one of a blood vessel diameter, an artery-vein ratio, a fractal dimension, a blood vessel density, a branch included angle and a blood vessel curvature; the human body biological parameter value is a value of a human body biological parameter, and the human body characteristic parameter comprises at least one of age, sex, height and weight; the external eye parameter value is a value of an external eye parameter, and the external eye parameter comprises at least one of color and brightness.

In some cases, more vascular feature parameters, human biological parameters, and external ocular parameters may be employed in order to improve the reliability of the results. With the increase of the parameters, the reliability and the accuracy of the result are improved. Furthermore, the working efficiency of doctors can be improved.

In this embodiment, the blood vessel characteristic parameters may include vessel caliber, arterial-venous ratio, fractal dimension, vessel density, and branch included angle. The vascular characteristic parameter may be used to assess liver disease.

In this embodiment, the blood vessel characteristic parameter may further include an arterial-venous ratio. The arteriovenous ratio can be used as an index for evaluating liver diseases. In some embodiments, the parameter acquisition module 11 may calculate the arteriovenous ratio by the number, diameter, or area of arterial and venous vessels of the fundus. Specifically, the ratio of the number of arteries to the number of veins may be calculated as a result of calculation of the ratio of arteries to veins, or may be calculated based on the ratio between the diameters of arteries and veins. In particular, for example, for certain liver diseases, such as cirrhosis, the arteriovenous ratio may change, the ratio may be biased toward veins or arteries, or the ratio may increase or decrease. Based on the values of the arteriovenous ratios, the state of the liver blood vessel and the degree of liver disease can be evaluated.

In this embodiment, the blood vessel characteristic parameter may further include a blood vessel density. The vessel density may be used as an index for assessing liver disease. In some embodiments, the parameter acquisition module 11 may acquire the number of fundus blood vessels and the distribution of the blood vessels, and measure the length, area, or density of the blood vessels, etc. with specific software or algorithms. From the acquired data, the vessel density of the liver can be calculated. Specifically, the total length or area of the liver blood vessels may be divided by the total volume of the liver to obtain the blood vessel density, and the blood vessel density may be calculated from the number of blood vessels per unit area or unit volume of the liver. In particular, for example, in a cirrhosis lesion, blood vessels in liver tissue may decrease, and blood vessel density may decrease. Based on the values of the vessel density, the status of the hepatic vessels and the extent of liver disease can be assessed.

In this embodiment, the blood vessel characteristic parameter may further include a blood vessel curvature. The tortuosity of the blood vessel can be used as an index for evaluating liver diseases. Specifically, for example, a patient suffering from a liver disease, particularly a patient suffering from a late stage of a liver disease, causes a series of changes in ocular fundus angiogenesis such as vein dilation, bending, arterial thinning, etc., and thus the degree of curvature of the blood vessel can be an important index for evaluating a liver disease. In particular, it may be shown that the greater the degree of curvature, the higher the risk.

In this embodiment, the blood vessel characteristic parameter may further include a fractal dimension and a branch angle. In some embodiments, the parameter acquisition module 11 may calculate the fractal dimension and branch angle within a specific vascular structure region by acquiring that region and using a fractal analysis algorithm. Based on the fractal dimension and the values of the branch angles, the complexity and the change condition of the liver vascular structure and the possible liver disease condition can be evaluated. In particular, diseases such as cirrhosis or liver tumors may lead to changes in vascular structure, affecting the fractal dimension and the value of the branch angle.

In this embodiment, the human body characteristic parameter may be age. The age may increase the specificity of the model. Specifically, for example, the disease incidence increases with age, the model specificity increases with age, and the model accuracy and specificity further increases with the addition of the external ocular feature.

In this embodiment, the human body characteristic parameter may also be sex. The gender may allow for more accurate model discrimination. In some embodiments, the disease has different criteria for men and women. In particular, for example, primary biliary hepatitis is more common in women, while autoimmune hepatitis is more common in men. Accordingly, in judging and evaluating these liver diseases, it may be necessary to consider the corresponding results according to the difference in sex.

In this embodiment, the external eye parameter may be color, or brightness. The color or brightness may make the obtained fundus image clearer. Thus, the blood vessel characteristic parameters can be better acquired.

In some embodiments, the medical image processing apparatus may further include: the operation module 22 is integrated with a liver function evaluation model, and the operation module 22 inputs the blood vessel characteristic value, the human body biological parameter value and the external eye parameter value into the liver function evaluation model to obtain a probability value output by the liver function evaluation model.

In some cases, the liver function assessment model can help doctors and patients to more accurately understand liver disease states and predict liver disease risks by using technical means such as big data and machine learning. Specifically, training is performed in conjunction with a large-scale case database to predict whether a patient is at risk for a liver disease. This is of great importance for early detection of potential liver disease and for efficient screening.

In this embodiment, the liver function assessment model may be one or more of a deep learning model, a logistic regression model, a nonlinear regression model, and a random forest algorithm. The liver function assessment model is used to predict the risk of liver disease. Specifically, for example, it is assumed that a prediction result a is output by using the a model, and a prediction result B is output by using the B model. The combination of the two models may be a weighted processing of a and b to form a new predicted value p.

In this embodiment, the effect of the liver function evaluation model may be explained with reference to the embodiment of the medical image processing apparatus in this specification, and will not be described herein.

Please refer to fig. 3. In some embodiments, the medical image processing apparatus may further include: the operation module 22 is respectively provided with a parameter weight value corresponding to the blood vessel characteristic parameters; a human body biological parameter weight value is set corresponding to the human body biological parameter, and an external eye parameter weight value is set corresponding to the external eye parameter; wherein the parameter weight values of the blood vessel characteristic parameters include first parameter weight values of the blood vessel characteristic parameters obtained from a fundus image centering on a macula lutea; or, a second parameter weight value of a blood vessel characteristic parameter obtained from a fundus image centering on the optic disc; wherein the first parameter weight value is different from the second parameter weight value.

In some cases, in order to adjust the degree of influence of different parameters on the model, weight values of the parameters are set. The weight value of the parameter is used for representing the importance degree of the parameter in the calculation process.

In this embodiment, setting the parameter weight value may be a weight-based calculation method. Methods for quantifying the importance of different factors or variables. The parameter weight value can be set according to the professional experience of a doctor. Specifically, the value of each factor or variable may be multiplied by a corresponding weight, and weighted and combined to obtain a final result.

In the present embodiment, the first parameter weight value is set based on a blood vessel characteristic parameter obtained from a fundus image centering on macula lutea. Specifically, the vascular caliber of the fundus image taking the macula as the center is the most important vascular characteristic parameter, so that the parameter weight value of the vascular caliber is larger; the second parameter weight value is set according to a blood vessel characteristic parameter obtained from a fundus image centered on the optic disc. Specifically, the importance degree of the blood vessel characteristic parameter, namely the blood vessel diameter of the fundus image taking the optic disc as the center is light, so that the parameter weight value of the blood vessel diameter occupies a small space.

In some embodiments, the medical image processing apparatus may further include: the determining module 33 integrates a specified threshold value, and generates an evaluation result indicating that the liver disease risk of the human body is high if the probability value is greater than the specified threshold value; or, in the case where the probability value is smaller than the specified threshold, generating an evaluation result indicating that the risk of liver disease of the human body is low.

In some cases, by setting appropriate thresholds, it is convenient to identify high risk individuals and take corresponding precautions and therapeutic measures.

In this embodiment, the specified threshold may be a threshold empirically set by a doctor. The specified threshold is used for judging the liver disease risk degree of the human body. In some embodiments, the probability value may be calculated based on a model. Specifically, for example, for a deep learning model, or a random deep forest algorithm, the probability value is calculated to be greater than a certain probability, which indicates that the liver disease risk is high. For the linear regression model, a value obtained by weighting each index is calculated, and the larger or smaller value indicates the higher or lower risk of suffering from liver diseases.

Please refer to fig. 4. The embodiment of the specification also provides a medical image processing method, which comprises the following steps.

Step S110: blood vessel characteristic values are acquired from fundus images.

Step S120: and calculating the probability value of the liver disease of the human body corresponding to the fundus image according to the blood vessel characteristic value.

Step S130: and generating an evaluation result of the liver of the human body according to the probability value.

The medical image processing method may be explained in contrast with reference to the embodiment of the medical image processing apparatus part, and is not described in detail here.

The present specification embodiment also provides a computer storage medium having stored thereon a computer program which, when executed by a computer, causes the computer to perform the medical image processing method in the above embodiment.

The present description also provides a computer program product comprising instructions which, when executed by a computer, cause the computer to perform the medical image processing apparatus of any of the above embodiments, or which, when executed by the processor, implement a medical image processing method.

Please refer to fig. 5. The present description may provide an electronic device including: a memory, and one or more processors communicatively coupled to the memory; the memory stores instructions executable by the one or more processors to cause the one or more processors to implement the medical image processing method of any of the above embodiments.

In some embodiments, the electronic device may include a processor, a non-volatile storage medium, an internal memory, a communication interface, a display device, and an input device connected by a system bus. The non-volatile storage medium may store an operating system and associated computer programs.

User information or user account information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, etc.) referred to in various embodiments of the present description are information and data that are authorized by the user or sufficiently authorized by the parties, and the collection, use, and processing of relevant data requires compliance with relevant legal regulations and standards of the relevant countries and regions, and is provided with corresponding operation portals for the user to select authorization or denial.

It will be appreciated that the specific examples herein are intended only to assist those skilled in the art in better understanding the embodiments of the present disclosure and are not intended to limit the scope of the present invention.

It should be understood that, in various embodiments of the present disclosure, the sequence number of each process does not mean that the execution sequence of each process should be determined by the function and the internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present disclosure.

It will be appreciated that the various embodiments described in this specification may be implemented either alone or in combination, and are not limited in this regard.

Unless defined otherwise, all technical and scientific terms used in the embodiments of this specification have the same meaning as commonly understood by one of ordinary skill in the art to which this specification belongs. The terminology used in the description is for the purpose of describing particular embodiments only and is not intended to limit the scope of the description. The term "and/or" as used in this specification includes any and all combinations of one or more of the associated listed items. As used in this specification and the appended claims, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise.

It will be appreciated that the processor of the embodiments of the present description may be an integrated circuit chip having signal processing capabilities. In implementation, the steps of the above method embodiments may be implemented by integrated logic circuits of hardware in a processor or instructions in software form. The processor may be a general purpose processor, a Digital signal processor (Digital SignalProcessor, DSP), an application specific integrated circuit (Application Specific Integrated Circuit, ASIC), an off-the-shelf programmable gate array (Field Programmable Gate Array, FPGA) or other programmable logic device, discrete gate or transistor logic device, discrete hardware components. The methods, steps and logic blocks disclosed in the embodiments of the present specification may be implemented or performed. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like. The steps of a method disclosed in connection with the embodiments of the present specification may be embodied directly in hardware, in a decoded processor, or in a combination of hardware and software modules in a decoded processor. The software modules may be located in a random access memory, flash memory, read only memory, programmable read only memory, or electrically erasable programmable memory, registers, etc. as well known in the art. The storage medium is located in a memory, and the processor reads the information in the memory and, in combination with its hardware, performs the steps of the above method.

It will be appreciated that the memory in the embodiments of this specification may be either volatile memory or nonvolatile memory, or may include both volatile and nonvolatile memory. The nonvolatile memory may be a read-only memory (ROM), a Programmable ROM (PROM), an Erasable Programmable ROM (EPROM), an Electrically Erasable Programmable ROM (EEPROM), or a flash memory, among others. The volatile memory may be Random Access Memory (RAM). It should be noted that the memory of the systems and methods described herein is intended to comprise, without being limited to, these and any other suitable types of memory.

Those of ordinary skill in the art will appreciate that the elements and algorithm steps described in connection with the embodiments disclosed herein can be implemented as electronic hardware, or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present specification.

It will be clear to those skilled in the art that, for convenience and brevity of description, specific working procedures of the above-described system, apparatus and unit may refer to corresponding procedures in the foregoing method embodiments, and are not repeated herein.

In the several embodiments provided in this specification, it should be understood that the disclosed systems, apparatuses, and methods may be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative, e.g., the division of the units is merely a logical function division, and there may be additional divisions when actually implemented, e.g., multiple units or components may be combined or integrated into another system, or some features may be omitted or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed with each other may be an indirect coupling or communication connection via some interfaces, devices or units, which may be in electrical, mechanical or other form.

The units described as separate units may or may not be physically separate, and units shown as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the embodiment.

In addition, each functional unit in each embodiment of the present specification may be integrated into one processing unit, each unit may exist alone physically, or two or more units may be integrated into one unit.

The functions, if implemented in the form of software functional units and sold or used as a stand-alone product, may be stored in a computer-readable storage medium. Based on this understanding, the technical solutions of the present specification may be essentially or portions contributing to the prior art or portions of the technical solutions may be embodied in the form of a software product stored in a storage medium, including several instructions to cause a computer device (which may be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in the embodiments of the present specification. And the aforementioned storage medium includes: a usb disk, a removable hard disk, a read-only memory (ROM), a random-access memory (RAM), a magnetic disk, or an optical disk, etc.

The foregoing is merely specific embodiments of the present disclosure, but the scope of the present disclosure is not limited thereto, and any person skilled in the art can easily think about changes or substitutions within the technical scope disclosed in the present disclosure, and should be covered by the scope of the present disclosure. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.

Claims

1. A medical image processing apparatus, comprising:

the parameter acquisition module is used for acquiring a blood vessel characteristic value from the fundus image;

the operation module is used for calculating the probability value of the liver disease of the human body corresponding to the fundus image according to the blood vessel characteristic value;

and the determining module is used for generating an evaluation result of the liver of the human body corresponding to the fundus image according to the probability value.

2. The apparatus of claim 1, further comprising a human parameter acquisition module; the human body parameter acquisition module is used for acquiring human body biological parameter values corresponding to the fundus image;

the operation module is used for calculating the probability value of the liver disease of the human body corresponding to the fundus image according to the blood vessel characteristic value and the human body biological parameter value.

3. The apparatus according to claim 2, wherein the parameter acquisition module is further configured to acquire an external eye parameter value from an external eye image of the eye ball corresponding to the fundus image;

the operation module is used for calculating a probability value of liver diseases of the human body corresponding to the fundus image according to the blood vessel characteristic value, the human body biological parameter value and the external eye parameter value.

4. The device of claim 3, wherein the vessel characteristic value is a value of a vessel characteristic parameter, the vessel characteristic parameter including at least one of vessel caliber, arterial-venous ratio, fractal dimension, vessel density, branch angle, and vessel tortuosity;

the human body biological parameter value is a value of a human body biological parameter, and the human body characteristic parameter comprises at least one of age, sex, height and weight;

the external eye parameter value is a value of an external eye parameter, and the external eye parameter comprises at least one of color and brightness.

5. The apparatus of claim 4, wherein a liver function assessment model is integrated in the operation module, and the operation module inputs the blood vessel characteristic value, the human body biological parameter value and the external eye parameter value into the liver function assessment model to obtain a probability value output by the liver function assessment model.

6. The device according to claim 4, wherein the operation module is provided with parameter weight values corresponding to the blood vessel characteristic parameters, respectively; a human body biological parameter weight value is set corresponding to the human body biological parameter, and an external eye parameter weight value is set corresponding to the external eye parameter; wherein the parameter weight values of the blood vessel characteristic parameters include first parameter weight values of the blood vessel characteristic parameters obtained from a fundus image centering on a macula lutea; or, a second parameter weight value of a blood vessel characteristic parameter obtained from a fundus image centering on the optic disc; wherein the first parameter weight value is different from the second parameter weight value.

7. The apparatus according to claim 1, wherein the determining module is integrated with a specified threshold and generates an evaluation result representing that the human body has a high risk of liver disease if the probability value is greater than the specified threshold; or, in the case where the probability value is smaller than the specified threshold, generating an evaluation result indicating that the risk of liver disease of the human body is low.

8. A medical image processing method, comprising:

obtaining a blood vessel characteristic value from the fundus image;

calculating a probability value of liver diseases of the human body corresponding to the fundus image according to the blood vessel characteristic value;

and generating an evaluation result of the liver of the human body according to the probability value.

9. A computer storage medium storing computer program instructions which, when executed by a processor, implement the method of claim 8.

10. An electronic device, comprising: a processor and a memory storing computer program instructions, characterized in that the electronic device is integrated with an apparatus according to any one of claims 1 to 7, or that the computer program instructions, when executed by the processor, implement the method according to claim 8.