WO2019218118A1

WO2019218118A1 - Fundus oculi lesion area calculation method, apparatus, medical device, and storage medium

Info

Publication number: WO2019218118A1
Application number: PCT/CN2018/086734
Authority: WO
Inventors: 高飞; 黄宏泰
Original assignee: 深圳明眸科技有限公司
Priority date: 2018-05-14
Filing date: 2018-05-14
Publication date: 2019-11-21

Abstract

Provided are a fundus oculi lesion area calculation method, apparatus, medical device, and storage medium, said calculation method comprising the steps: displaying a fundus oculi image on a screen, and receiving an identification operation on the fundus oculi lesion location on the screen according to the fundus oculi image to obtain a corresponding identification path; according to a preset image feature, drawing a target image corresponding to the identification path; obtaining the actual area of the fundus oculi region corresponding to a pixel of the fundus oculi image and obtaining the quantity of pixels corresponding to the target image; according to the actual area and the quantity of pixels, calculating the area of the fundus oculi lesion region.

Description

Method, device, medical device and storage medium for calculating area of fundus lesion area

Technical field

The present application relates to the field of fundus imaging technology, and in particular, to a method, a device, a medical device and a storage medium for calculating a region of a fundus lesion area.

Background technique

Recurrent disease of prematurity, a common disease in premature infants, is prone to blindness due to early neglect and untimely treatment. According to statistics, in China, at least 30,000 to 30,000 children are blind each other because of this disease. There are many factors that lead to this result. For example, there is currently no effective examination and diagnosis device for the disease, mainly because the device currently inspecting the disease has a single function and can only be easily imaged, and the lesion area cannot be calculated. When doctors get pictures of fundus imaging, they can only judge the size of the lesion area by experience, and can not give a quantitative value, which greatly hinders the doctor's diagnosis and also greatly affects the patient. Seeking medical treatment, eventually leading to missed diagnosis, misdiagnosis and loss of treatment opportunities.

Summary of the invention

According to various embodiments provided herein, a method, apparatus, medical device, and storage medium for calculating a region of a fundus lesion area are provided.

A method for calculating the area of a fundus lesion, comprising:

Displaying a fundus image on the screen, receiving an identification operation on the fundus lesion on the screen according to the fundus image, and obtaining a corresponding identification track;

Drawing a target image corresponding to the identified track according to a preset image feature;

Obtaining an actual area of a fundus region corresponding to a pixel point of the fundus image, and acquiring a pixel number of the target image;

Calculating the area of the fundus lesion area according to the actual area and the number of the pixel points.

A computing device for the area of a fundus lesion, comprising:

a display module, configured to display a fundus image on the screen, receive an identification operation on the fundus lesion on the screen according to the fundus image, and obtain a corresponding identification track;

a drawing module, configured to draw a target image corresponding to the identifier track according to a preset image feature;

An area obtaining module, configured to acquire an actual area of a fundus region corresponding to a pixel point of the fundus image, and obtain a number of pixels of the target image;

And a calculating module, configured to calculate an area of the fundus lesion area according to the actual area and the number of the pixel points.

A medical device comprising a memory and a processor, the memory storing computer readable instructions, the computer readable instructions being executed by the processor such that the processor performs the following steps:

One or more non-volatile storage media storing computer readable instructions, when executed by one or more processors, cause one or more processors to perform the following steps:

Details of one or more embodiments of the present application are set forth in the accompanying drawings and description below. Other features, objects, and advantages of the invention will be apparent from the description and appended claims.

DRAWINGS

In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings used in the description of the embodiments will be briefly described below. It is obvious that the drawings in the following description are only some embodiments of the present application. Other drawings may also be obtained from those of ordinary skill in the art in light of the inventive work.

1 is a schematic flow chart showing a method for calculating a region of a fundus lesion area according to an embodiment;

2 is a sub-flow diagram of a method for calculating a region of a fundus lesion area of another embodiment;

3 is a sub-flow diagram showing a method for calculating a region of a fundus lesion area in another embodiment;

4 is a sub-flow diagram showing a method for calculating a region of a fundus lesion area in another embodiment;

FIG. 5 is a schematic diagram of sub-area division according to an embodiment; FIG.

6 is a sub-flow diagram showing a method for calculating a region of a fundus lesion area of another embodiment;

Figure 7 is a block diagram showing a computing device for the area of the fundus lesion area of one embodiment;

8 is a schematic diagram of a sub-module of a computing device for a region of a fundus lesion area according to another embodiment;

9 is a schematic diagram of a sub-module of a computing device for the area of a fundus lesion area of another embodiment;

10 is a schematic diagram of a sub-module of a computing device for a region of a fundus lesion area according to another embodiment;

11 is a schematic diagram of a sub-module of a device for calculating a region of a fundus lesion area according to another embodiment; and

Figure 12 is a block diagram showing the internal structure of a medical device of an embodiment.

Detailed ways

In order to make the objects, technical solutions, and advantages of the present application more comprehensible, the present application will be further described in detail below with reference to the accompanying drawings and embodiments. It is understood that the specific embodiments described herein are merely illustrative of the application and are not intended to be limiting.

As shown in FIG. 1 , in one embodiment, a method for calculating the area of a fundus lesion area is proposed. The method provided by the embodiment of the present invention can be applied to a medical device, and specifically includes the following steps:

Step S102, displaying a fundus image on the screen, and receiving an identification operation on the fundus lesion on the screen according to the fundus image, to obtain a corresponding identification track.

Specifically, the fundus image may be an image displayed on the screen after being photographed in real time by the medical imaging device when the fundus is diagnosed, or may be an image displayed on the screen after the image obtained by photographing the fundus is saved. After the fundus image is displayed on the screen, the doctor can observe the fundus lesion from the screen, thereby identifying the fundus lesion by sliding or clicking, and the medical device obtains the corresponding marker track. For example, when performing fundus imaging using the fundus imaging system, the contour of the fundus lesion is moved on the fundus image displayed on the screen by the mouse, thereby identifying the fundus lesion and using the movement trajectory of the mouse as the marker trajectory.

Step S104, the target image corresponding to the identification track is drawn according to the preset image feature.

Specifically, the preset image feature may refer to a color feature, for example, may be a color channel value corresponding to each color channel, such as an RGB color channel value, and at the same time, because the identification track is an identifier of a fundus lesion on the screen according to the fundus image. The obtained identification track thus obtained corresponds to the edge position of the fundus lesion portion. Therefore, drawing the target image corresponding to the identification track by using the preset image feature can outline the contour of the fundus lesion.

In one embodiment, when the identification track is a moving track of the mouse, and the identification track is a closed circle, a layer of the same size as the target image may be newly created, and the movement track of the mouse is drawn in the layer as The outline of the target image to obtain the target image. It may be that all of the target images are drawn using the preset image features. It is also possible that the contour of the target image is drawn using the preset image feature, and the portion of the target image other than the contour of the image is the same as the image feature of the layer, for example, when the layer is white, the outline of the target image is Part is white.

Step S106, acquiring the actual area of the fundus region corresponding to the pixel point of the fundus image, and acquiring the number of pixel points of the target image.

Specifically, the actual area of the fundus region corresponding to the pixel point of the fundus image refers to the actual area of the fundus corresponding to the pixel point. For example, the area of the bottom of the eye corresponding to one pixel is 0.2 square millimeters in the human body, and the actual area of the fundus area corresponding to the pixel is 0.2 square millimeter. The actual area of the fundus area corresponding to the pixel of the fundus image may be preset. For example, you can set the actual area in the medical device under the default shooting parameters. The actual area of the fundus region corresponding to the pixel point of the fundus image may also be calculated. For example, the actual area of the fundus region corresponding to the pixel point of the fundus image obtained from the magnification at the time of imaging the fundus image.

The number of pixels of the target image can be obtained by statistical means, for example, when the target image is drawn in the layer, and the outline of the target image is drawn by using the preset image feature, and the portion other than the outline of the target image When the image features of the layer are the same, the recognition start point can be selected within the outline of the target image, and the pixel points of the target image are traversed from the recognition start point. During the traversal process, when the image feature of the identified point is the same as the image feature of the layer, it indicates that the identified point is within the contour of the target image, and when the image feature of the recognized point is the same as the image feature of the contour of the target image, It indicates that the contour of the target image has been recognized. In this way, after traversing all the recognition points in the contour of the target image, the number of recognition points in the contour of the target image can be obtained, and the number of recognition points is taken as the target image. The number of pixels.

In one embodiment, during the traversal of the target image, after the pixel points of the target image are recognized, the repeated recognition may be avoided by changing the image features of the recognized point. For example, when the portion of the image of the target image and the RGB value of the image feature of the layer correspond to white, after the pixel in the outline of the target image is recognized, the pixel may be blacked out (ie, the image feature) The RGB value corresponds to black), so that the blackened pixel points are no longer recognized during the traversal process, thereby avoiding repeated recognition and affecting the pixel point statistical accuracy of the target image.

In step S108, the area of the fundus lesion area is calculated according to the actual area and the number of pixel points.

Specifically, the fundus image may be obtained when the fundus region is imaged in real time during the operation, or may be obtained by photographing the fundus region. Whether the imaging of the fundus region is performed or the photographing is obtained, the size of the fundus region displayed in the fundus image has a corresponding relationship with the actual size of the fundus region. Since the imaging system used has a certain magnification when imaging the fundus image, the portion of the fundus image corresponding to the fundus region is an image effect obtained by enlarging the fundus region, in other words, the pixel point in the fundus image corresponds to the fundus region, thereby The area of the fundus lesion area can be calculated by obtaining the actual area of the fundus region corresponding to the pixel point of the fundus image and the number of pixels of the fundus lesion area imaged to the fundus image, wherein since the target image outlines the contour of the fundus lesion area, The number of pixels in the fundus lesion area imaged to the fundus image is equal to the number of pixel points of the target image, so the area of the fundus lesion area can be calculated according to the actual area and the number of pixel points.

In one embodiment, the pixel area of the fundus image corresponding to the actual area of the fundus area can be calculated from the magnification at the time of imaging of the fundus image and the side length of the pixel.

Specifically, since the magnification of the fundus image is optically magnified when the fundus imaging system images the fundus region, the magnification of the pixel side and the fundus image on the fundus image can be calculated, and the magnification can be calculated. The pixel of the fundus image corresponds to the actual area of the fundus area. For example, the length of the pixel on the fundus image is i, and the magnification of the fundus image when imaging is α (ie, the fundus region is magnified by α times when imaging the fundus image), so that the actual side length of the pixel corresponding to the fundus region can be obtained. L=i/α, and thus the actual area of the fundus corresponding to the fundus region S=L*L=i ² /α ² can be obtained, wherein the pixel size of the fundus image is determined by the image acquisition sensor itself, that is, When performing fundus imaging, the fundus images obtained with different image acquisition sensors have different pixel spot sizes. The image acquisition sensor may be a CCD or CMOS image sensor. For example, when a fundus image is imaged by using a CMOS image sensor, the image quality (ie, resolution) of the fundus image obtained depends on the CMOS image sensor, specifically, when high resolution is used. When the CMOS image sensor is used, the obtained fundus image is clearer, that is, the resolution is higher. The magnification at the time of imaging the fundus image can be obtained by means of optical path analysis or the like.

In another embodiment, the actual area of the fundus region corresponding to the pixel point of the fundus image can also be obtained by the following steps:

The S- _area- f _{object focal length} function or the S- _area- x _{lens group displacement} function is obtained by fitting the optical path simulation data.

Specifically, by means of optical path simulation, a large amount of simulation data is used to fit a functional mapping relationship between the actual area of the fundus region corresponding to the pixel point of the fundus image and the object focal length or the wafer group displacement when the fundus image is imaged. For example, when the fundus image is imaged, by adjusting the lens group displacement x of the fundus imaging system, the same region of the fundus is displayed on the fundus image in different sizes. Since the number and area of the pixel points of the fundus image can be obtained according to image recognition and the like, In the process of the lens group displacement x change, the relationship between the area of the fundus area and the lens group displacement x, that is, the S _area- x _{lens group displacement} function, can be obtained according to the change of the area of the fundus area corresponding to the pixel area of the same area of the fundus image.

The pixel area of the fundus image corresponds to the actual area of the fundus area according to the S _area- f _{object focal length} function or the S _area- x _{lens group displacement} function and the object focal length f or the lens group displacement x when the fundus image is imaged.

Since the object focal length f or the lens group displacement x when the fundus image is imaged can be obtained by the optical path analysis of the fundus imaging system, the pixels of the fundus image can be obtained by the S _area- f _{object focal length} function or the S _area- x _{lens group displacement} function. The point corresponds to the actual area of the fundus area. In addition, for the fundus imaging system, the focus position of the object focal length f is achieved by adjusting the lens group displacement x, that is, by adjusting the lens group displacement x when imaging the fundus, the object focus is focused on the fundus region. Therefore, there is a correlation between the object focal length f and the lens group displacement x. Therefore, it is only necessary to obtain one of the object focal length f and the lens group displacement x when the fundus image is imaged, and the S- _area- f _object can be passed _. S or _a function _{of focus} _{lens group} -x _{_area} _displacement function to obtain the fundus image corresponding to the actual area of the pixel area of the fundus.

Specifically, when the fundus image is imaged, each position of the fundus lesion area is imaged to a pixel point corresponding to the target image on the fundus image, so that the pixel area of the fundus image corresponds to the actual area of the fundus area and the target image. The area of the fundus lesion area can be obtained by the number of pixels.

In an embodiment, as shown in FIG. 2, step S104 is to draw a target image corresponding to the identifier track according to the preset image feature, including:

Step S202: Generate a target layer according to the size of the fundus image, and obtain a preset image feature, where the preset image feature is different from the background image feature corresponding to the background of the target layer.

Specifically, the size of the target layer is obtained according to the size of the fundus image. The size of the target layer may be the same as the size of the fundus image, or the size of the fundus image may be multiplied by the corresponding zoom factor to obtain the size of the target layer. The preset image feature is different from the background image feature corresponding to the background of the target layer. For example, when the target layer is white, the color channel value of the preset image feature is different from white to match the target layer with The target image is distinguished.

Step S204: Draw a target image corresponding to the identification track on the target layer according to the preset image feature.

Specifically, the size of the target layer may be the same as the size of the fundus image, and the preset image feature may refer to a color feature or an attribute feature. Since the preset image feature is different from the background image feature corresponding to the background of the target layer, the image of the preset image feature on the target layer can be obtained by the recognition of the image feature, and in this embodiment, The target image drawn corresponds to the identification track. Therefore, the preset image feature will be drawn on the target layer along the identified track, and correspondingly, according to the difference between the preset image feature and the background image feature of the target layer The identification track can be stored with preset image features and the target image can be obtained. For example, if the preset image feature is black and the background of the target layer is white, since the identification track is an operation of marking the fundus lesion on the screen according to the fundus image, the preset image feature in the target image is formed along the identification track. The target image corresponds to the contour of the fundus lesion corresponding to the fundus lesion area.

As shown in FIG. 3, the calculation method of the area of the fundus lesion area may further include the following steps:

Step S302, extracting an outline of the target image according to the image feature of the target image and the background image feature.

Specifically, since the image feature of the target image is different from the background image feature, and the contour of the target image is drawn on the target layer by the preset image feature, the outline of the target image can be obtained by determining the image feature. For example, when the layer is a white background, since the target image is drawn with a preset image feature different from the background image feature, the image feature of the target image is a color other than white, so that the target image can be traversed through Judging the color of the pixel to obtain the outline of the target image.

Step S304, obtaining an image region corresponding to the contour on the fundus image according to the size of the target layer and the size of the fundus image.

Specifically, the size of the target layer is obtained according to the size of the fundus image. The size of the target layer may be the same as the size of the fundus image, or the size of the fundus image may be multiplied by the corresponding zoom factor to obtain the size of the target layer. Since the contour of the target image is drawn on the target layer, and the contour of the target image corresponds to the identification trajectory when the fundus lesion is marked in the fundus image, the relationship between the target layer and the fundus image size and the target are determined. The contour of the image is such that an image region corresponding to the contour on the fundus image is obtained, which is the fundus avoidance portion presented on the fundus image.

Step S306, the image area is identified on the fundus image.

Specifically, when an image region corresponding to the contour of the target image on the fundus image is obtained, it can be presented on the fundus image by identifying the image region. For example, when the fundus lesion area is circular, the contour of the fundus lesion image presented on the fundus image is also circular. Correspondingly, since the target image is obtained by identifying the fundus lesion portion of the fundus image, the target image is The contour is the same as the contour of the fundus lesion on the fundus image, so that after the image region is identified on the fundus image, the image corresponding to the fundus lesion region can be identified on the fundus image.

As shown in FIG. 4, the calculation method of the area of the fundus lesion area may further include the following steps:

Step S402, acquiring a trajectory image area corresponding to the identified trajectory on the fundus image.

Specifically, the trajectory image area corresponding to the identification trajectory refers to an image area included in the identification trajectory. For example, when the identification track is a sliding track, the image area within the sliding track is taken as the track image area. Since the identification trajectory is obtained according to the identification operation of the fundus image on the screen for the fundus lesion, the trajectory image region corresponding to the trajectory on the fundus image identifies the image of the fundus lesion in the fundus image, specifically, the marker trajectory The corresponding trajectory image area is an image area corresponding to the fundus lesion part in the fundus image.

Step S404, acquiring a focus center when the fundus image is imaged, and dividing the track image area into a plurality of sub-areas according to the distance from the focus center.

Specifically, the focus center refers to the position where the focus point is located when the fundus image is imaged. Since the fundus image is imaged, the field of view of the image is centered on the focus point, and the different distances from the focus point have different magnifications due to imaging. That is to say, when the fundus image is imaged, the actual area of the fundus region corresponding to the pixel point at different distances from the focus point will change, and this change will affect the accuracy of the area of the fundus lesion area. Therefore, the trajectory image area is divided into a plurality of sub-areas according to the distance from the focus center. It can be understood that the sub-area where the focus point is located is a circular area centered on the focus point, and the other sub-areas are annular areas surrounding the sub-area where the focus point is located. . When the fundus image is imaged, the pixels with the same distance from the focus point have the same magnification when imaging the fundus region, so that the magnification of each pixel in each sub-area is relatively close, and this method is effectively avoided. When calculating the actual area of the fundus image corresponding to the actual area of the fundus region, the pixel point farther from the focus point and the closer pixel point have a larger difference in magnification during imaging, which causes a larger error, thereby increasing the area of the fundus lesion area. calculation accuracy.

Step S406, obtaining the actual area of the fundus region corresponding to the pixel points of the respective sub-regions according to the magnification ratio corresponding to each sub-region and the side length of the pixel.

Specifically, for the same sub-area, since the distance between each pixel point and the focus point is not large, the pixel points of the same sub-area are substantially equal when the image is viewed on the fundus area. It should be noted that the radius of the sub-area can be planned such that when the pixel of the sub-area is imaged to the fundus area, the change of the magnification is likely to be small, thereby effectively improving the actual pixel area of the sub-area corresponding to the fundus area. The accuracy of the area.

For example, as shown in FIG. 5, the radius of a circle in which the trajectory image area can be included around the focus point is R, and the sum of the areas of the plurality of sub-areas formed by dividing the trajectory image area in the above-described manner is Is the area of the circle of radius R. In some embodiments, the trajectory image area is divided into a first sub-region, a second sub-region, and a third sub-region, the first sub-region being a circular region having a center of the focus center and a radius of R/3; The area is an annular area centered on the focus center, having an inner diameter of R/3 and an outer diameter of 5R/6; the third sub-area is an annular area centered on the focus center, having an inner diameter of 5R/6 and an outer diameter R. Through the optical path analysis, the magnifications of the first sub-region, the second sub-region, and the third sub-region pixel point when imaging the lesion region can be respectively obtained, thereby utilizing the magnification of each sub-region and the side length of the pixel. The actual area of the fundus region corresponding to the pixel points of each sub-region can be obtained.

Correspondingly, in this embodiment, the number of pixels of the target image acquired in step S106 includes the number of pixels of the target image in each sub-region.

Specifically, the number of pixels of the target image is also the number of pixels corresponding to the fundus lesion region when the fundus image is imaged, and the sub-region is divided according to the distance from the focus center to the trajectory image region corresponding to the marker track on the fundus image. Thus, the sum of the pixel points of each sub-area is equal to the number of pixels of the target image.

Therefore, the number of pixel points of the target image in each sub-region can be obtained according to the ratio of each sub-region to the trajectory image region corresponding to the trajectory on the fundus image, and specifically, the size determination according to each sub-region when dividing the trajectory image region The number of pixels of the target image in each sub-area. For example, in some embodiments, the trajectory image area is divided into a first sub-area, a second sub-area, and a third sub-area, the first sub-area being a circular area having a center of the focus center and a radius of R/3; The two sub-regions are annular regions with a center of focus, an inner diameter of R/3, and an outer diameter of 5R/6; the third sub-region is an annular region with a center of focus, an inner diameter of 5R/6, and an outer diameter of R. . Therefore, the number of pixels of the target image falling into the circular area with the center of the focus and the radius of R/3 is the number of pixels of the target image in the first sub-area, and correspondingly, the target image falls into the focus center. The number of pixels in the annular region with the center of the circle, the inner diameter of R/3, and the outer diameter of 5R/6 is the number of pixels of the target image in the second sub-region, and the target image falls into the center of the focus center, and the inner diameter is The number of pixel points of the ring region of 5R/6 and outer diameter R is the number of pixel points of the target image in the third sub-region. Certainly, the number of pixels of the fundus lesion image in the corresponding fundus image in each sub-region can be obtained by traversing, so that the number of pixels of the fundus lesion image in the fundus image corresponding to each sub-region can be summed, and The number of pixels of the target image is obtained, and details are not described herein again.

As shown in FIG. 6, in one embodiment, step S108 calculates the area of the fundus lesion area according to the actual area and the number of pixel points, including:

Step S602, calculating the area of the fundus lesion region corresponding to each sub-region according to the actual area of the fundus region corresponding to the pixel point of each sub-region and the corresponding number of pixel points.

Specifically, since the pixel points of the target image all correspond to the corresponding fundus lesion area, after dividing into a plurality of sub-areas, the number of pixels in each sub-area according to the target image and the fundus corresponding to the pixel points of each sub-area With the actual area of the area, it is possible to obtain the area of each sub-area corresponding to the fundus lesion area.

In step S604, the area of the fundus lesion area is obtained according to the area of the fundus lesion area corresponding to each sub-area.

Specifically, since the trajectory image area corresponding to the trajectory on the fundus image is divided into a plurality of sub-areas, the number of the pixel points and the area of the pixel point corresponding to the fundus lesion area are not affected by the area segmentation, and the pixel points of each sub-area The sum of the pixel points of the trajectory image area corresponding to the fundus image identification trajectory is equal, so that after obtaining the area corresponding to the fundus lesion area of each sub-area, summation can be performed to obtain the area of the fundus lesion area.

As shown in FIG. 7 , the present invention further provides a computing device for a region of a fundus lesion area, which can be applied to a medical device, and the computing device includes:

The display module 702 is configured to display a fundus image on the screen, and receive an identification operation on the screen of the fundus lesion according to the fundus image to obtain a corresponding identification track;

a drawing module 704, configured to draw a target image corresponding to the identifier track according to the preset image feature;

The area obtaining module 706 is configured to acquire an actual area of a fundus area corresponding to a pixel point of the fundus image, and obtain a number of pixel points of the target image;

The calculating module 708 is configured to calculate the area of the fundus lesion area according to the actual area and the number of pixel points.

In one embodiment, the area obtaining module 706 is further configured to calculate the actual area of the fundus region of the fundus image corresponding to the magnification of the fundus image and the side length of the pixel.

As shown in FIG. 8, the rendering module 704 includes:

The image feature acquiring unit 704A is configured to generate a target layer according to the size of the fundus image, and acquire a preset image feature, where the preset image feature is different from the background image feature corresponding to the background of the target layer;

The drawing unit 704B is configured to draw a target image corresponding to the identification track on the target layer according to the preset image feature.

As shown in FIG. 9, the calculation device for the area of the fundus lesion area further includes:

An extraction module 802, configured to extract an outline of the target image according to the image feature of the target image and the background image feature;

The image area obtaining module 804 is configured to obtain an image area corresponding to the contour on the fundus image according to the size of the target layer and the size of the fundus image;

The identification module 806 identifies the image area on the fundus image.

As shown in FIG. 10, in one embodiment, the device for calculating the area of the fundus lesion area further includes:

The trajectory image region obtaining module 902 is configured to acquire a trajectory image region corresponding to the identified trajectory on the fundus image;

The sub-area dividing module 904 is configured to acquire a focus center when the fundus image is imaged, and divide the track image area into a plurality of sub-areas according to the distance from the focus center;

The sub-area calculation module 906 is configured to obtain, according to the magnification ratio corresponding to each sub-area and the side length of the pixel point, the actual area of the fundus area corresponding to the pixel point of each sub-area;

In this embodiment, the area obtaining module 706 is further configured to acquire the number of pixels of the target image in each sub-area;

As shown in FIG. 11, the calculation module 708 includes:

The sub-region calculating unit 708A is configured to calculate, according to the actual area of the fundus region corresponding to the pixel point of each sub-region and the corresponding number of pixel points, the area of the fundus lesion region corresponding to each sub-region;

The obtaining unit 708B is configured to obtain the area of the fundus lesion area according to the area of the fundus lesion area corresponding to each sub-area.

For the specific definition of the calculation device for the area of the fundus lesion area, reference may be made to the above definition of the calculation method of the area of the fundus lesion area, and details are not described herein again. The various modules in the computing device for the area of the fundus lesion area described above may be implemented in whole or in part by software, hardware, and combinations thereof. Each of the above modules may be embedded in or independent of the processor in the computer device in hardware, or may be stored in a memory in the computer device in software form, so that the processor calls to perform operations corresponding to the above modules.

Figure 12 is a diagram showing the internal structure of a medical device in one embodiment. As shown in FIG. 12, the medical device includes a processor, a memory, a network interface, an input device, and a display screen connected by a system bus. Wherein, the memory comprises a non-volatile storage medium and an internal memory. The non-volatile storage medium of the medical device stores an operating system, and can also store computer readable instructions that, when executed by the processor, enable the processor to implement a method of calculating the area of the fundus lesion area. The internal memory can also store computer readable instructions that, when executed by the processor, cause the processor to perform a method of calculating the area of the fundus lesion area. The display of the medical device may be a liquid crystal display or an electronic ink display. The input device of the medical device may be a touch layer covered on the display, or a button, a trackball or a touchpad provided on the casing of the medical device. It can be an external keyboard, trackpad or mouse.

It should be understood that although the various steps in the flowcharts of the various embodiments of the present invention are sequentially displayed as indicated by the arrows, these steps are not necessarily performed in the order indicated by the arrows. Except as explicitly stated herein, the execution of these steps is not strictly limited, and the steps may be performed in other orders. Moreover, at least some of the steps in the various embodiments may include multiple sub-steps or multiple stages, which are not necessarily performed at the same time, but may be performed at different times, and these sub-steps or stages The order of execution is not necessarily performed sequentially, but may be performed alternately or alternately with at least a portion of other steps or sub-steps or stages of other steps.

One of ordinary skill in the art can understand that all or part of the process of implementing the above embodiments can be completed by a computer program to instruct related hardware, and the program can be stored in a non-volatile computer readable storage medium. Wherein, the program, when executed, may include the flow of an embodiment of the methods as described above. Any reference to a memory, storage, database or other medium used in the various embodiments provided herein may include non-volatile and/or volatile memory. Non-volatile memory can include read only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of formats, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronization chain. Synchlink DRAM (SLDRAM), Memory Bus (Rambus) Direct RAM (RDRAM), Direct Memory Bus Dynamic RAM (DRDRAM), and Memory Bus Dynamic RAM (RDRAM).

The technical features of the above embodiments may be arbitrarily combined. For the sake of brevity of description, all possible combinations of the technical features in the above embodiments are not described. However, as long as there is no contradiction in the combination of these technical features, It is considered to be the range described in this specification.

The above embodiments are merely illustrative of several embodiments of the present application, and the description thereof is more specific and detailed, but is not to be construed as limiting the scope of the invention. It should be noted that a number of variations and modifications may be made by those skilled in the art without departing from the spirit and scope of the present application. Therefore, the scope of the invention should be determined by the appended claims.

Claims

A method for calculating the area of a fundus lesion, comprising:

Displaying a fundus image on the screen, receiving an identification operation on the fundus lesion on the screen according to the fundus image, and obtaining a corresponding identification track;

Drawing a target image corresponding to the identified track according to a preset image feature;

Obtaining an actual area of a fundus region corresponding to a pixel point of the fundus image, and acquiring a pixel number of the target image;

Calculating the area of the fundus lesion area according to the actual area and the number of the pixel points.
The method for calculating the area of the fundus lesion area according to claim 1, wherein the drawing the target image corresponding to the identification track according to the preset image feature comprises:

Generating a target layer according to a size of the fundus image, and acquiring the preset image feature, where the preset image feature is different from a background image feature corresponding to a background of the target layer;

And mapping a target image corresponding to the identified track on the target layer according to the preset image feature.
The method of calculating the area of the fundus lesion area according to claim 2, wherein the calculating method further comprises:

Extracting an outline of the target image according to image features of the target image and the background image feature;

Obtaining an image region corresponding to the contour on the fundus image according to a size of the target layer and a size of the fundus image;

The image area is identified on the fundus image.
The method for calculating a region of a fundus lesion area according to claim 1, wherein the actual area of the fundus region corresponding to the pixel point at which the fundus image is acquired comprises:

The pixel area of the fundus image corresponds to the actual area of the fundus area according to the magnification at the time of imaging the fundus image and the side length of the pixel.
The method of calculating the area of the fundus lesion area according to claim 1, wherein the calculating method further comprises:

Obtaining a trajectory image area corresponding to the identified trajectory on the fundus image;

Obtaining a focus center when the fundus image is imaged, and dividing the track image region into a plurality of sub-regions according to a distance from the focus center;

Obtaining, according to the magnification ratio corresponding to each sub-region and the side length of the pixel point, the actual area of the fundus region corresponding to the pixel point of each sub-region;

The obtaining the number of pixels of the target image includes:

Obtaining a number of pixel points of the target image in each of the sub-regions;

Calculating the area of the fundus lesion area according to the actual area and the number of pixel points includes:

Calculating, according to the actual area of the fundus region corresponding to the pixel points of the respective sub-regions and the corresponding number of pixel points, the area of the respective sub-region corresponding to the fundus lesion region;

The area of the fundus lesion area is obtained according to the area of each of the sub-regions corresponding to the fundus lesion area.
A computing device for the area of a fundus lesion, comprising:

a display module, configured to display a fundus image on the screen, receive an identification operation on the fundus lesion on the screen according to the fundus image, and obtain a corresponding identification track;

a drawing module, configured to draw a target image corresponding to the identifier track according to a preset image feature;

An area obtaining module, configured to acquire an actual area of a fundus region corresponding to a pixel point of the fundus image, and obtain a number of pixels of the target image;

And a calculating module, configured to calculate an area of the fundus lesion area according to the actual area and the number of the pixel points.
The apparatus for calculating the area of the fundus lesion area according to claim 6, wherein the drawing module comprises:

An image feature acquiring unit, configured to generate a target layer according to a size of the fundus image, and acquire the preset image feature, where the preset image feature is different from a background image feature corresponding to a background of the target layer;

And a drawing unit, configured to draw a target image corresponding to the identification track on the target layer according to the preset image feature.
The device for calculating the area of the fundus lesion area according to claim 7, wherein the computing device further comprises:

An extracting module, configured to extract an outline of the target image according to the image feature of the target image and the background image feature;

An image area obtaining module, configured to obtain an image area corresponding to the contour on the fundus image according to a size of the target layer and a size of the fundus image;

An identification module that identifies the image area on the fundus image.
The device for calculating the area of the fundus lesion area according to claim 6, wherein the area obtaining module is further configured to calculate the pixel of the fundus image according to the magnification of the fundus image and the side length of the pixel The point corresponds to the actual area of the fundus area.
The device for calculating the area of the fundus lesion area according to claim 6, wherein the computing device further comprises:

a trajectory image area acquiring module, configured to acquire a trajectory image area corresponding to the identification trajectory on the fundus image;

a sub-area dividing module, configured to acquire a focus center when the fundus image is imaged, and divide the track image area into a plurality of sub-areas according to a distance from the focus center;

a sub-area calculation module, configured to obtain, according to the magnification ratio corresponding to each sub-region and the side length of the pixel, the actual area of the fundus region corresponding to the pixel point of each sub-region;

The area obtaining module is further configured to acquire the number of pixels of the target image in each of the sub-regions;

The calculation module includes:

a sub-region calculating unit, configured to calculate, according to an actual area of the fundus region corresponding to the pixel points of the respective sub-regions and a corresponding number of pixel points, an area of the respective sub-region corresponding to the fundus lesion region;

And obtaining a unit for obtaining an area of the fundus lesion area according to an area of the respective sub-region corresponding to the fundus lesion area.
A medical device comprising a memory and a processor, the memory storing computer readable instructions, the computer readable instructions being executed by the processor such that the processor performs the following steps:

Displaying a fundus image on the screen, receiving an identification operation on the fundus lesion on the screen according to the fundus image, and obtaining a corresponding identification track;

Drawing a target image corresponding to the identified track according to a preset image feature;

Obtaining an actual area of a fundus region corresponding to a pixel point of the fundus image, and acquiring a pixel number of the target image;

Calculating the area of the fundus lesion area according to the actual area and the number of the pixel points.
The medical device according to claim 11, wherein the mapping of the target image corresponding to the identification track according to the preset image feature performed by the processor comprises:

Generating a target layer according to a size of the fundus image, and acquiring the preset image feature, where the preset image feature is different from a background image feature corresponding to a background of the target layer;

And mapping a target image corresponding to the identified track on the target layer according to the preset image feature.
The medical device of claim 12, wherein the computer readable instructions further cause the processor to perform the following steps:

Extracting an outline of the target image according to image features of the target image and the background image feature;

Obtaining an image region corresponding to the contour on the fundus image according to a size of the target layer and a size of the fundus image;

The image area is identified on the fundus image.
The medical device according to claim 11, wherein the actual area of the fundus region corresponding to the pixel point at which the fundus image is acquired by the processor comprises:

The pixel area of the fundus image corresponds to the actual area of the fundus area according to the magnification at the time of imaging the fundus image and the side length of the pixel.
The medical device of claim 11 wherein said computer readable instructions further cause said processor to perform the following steps:

Obtaining a trajectory image area corresponding to the identified trajectory on the fundus image;

Obtaining a focus center when the fundus image is imaged, and dividing the track image region into a plurality of sub-regions according to a distance from the focus center;

Obtaining, according to the magnification ratio corresponding to each sub-region and the side length of the pixel point, the actual area of the fundus region corresponding to the pixel point of each sub-region;

The obtaining the number of pixels of the target image includes:

Obtaining a number of pixel points of the target image in each of the sub-regions;

Calculating the area of the fundus lesion area according to the actual area and the number of pixel points includes:

Calculating, according to the actual area of the fundus region corresponding to the pixel points of the respective sub-regions and the corresponding number of pixel points, the area of the respective sub-region corresponding to the fundus lesion region;

The area of the fundus lesion area is obtained according to the area of each of the sub-regions corresponding to the fundus lesion area.
One or more non-volatile storage media storing computer readable instructions, when executed by one or more processors, cause one or more processors to perform the following steps:

Displaying a fundus image on the screen, receiving an identification operation on the fundus lesion on the screen according to the fundus image, and obtaining a corresponding identification track;

Drawing a target image corresponding to the identified track according to a preset image feature;

Obtaining an actual area of a fundus region corresponding to a pixel point of the fundus image, and acquiring a pixel number of the target image;

Calculating the area of the fundus lesion area according to the actual area and the number of the pixel points.
The medical device according to claim 16, wherein the mapping, by the processor, the mapping of the target image corresponding to the identification track according to the preset image feature comprises:

Generating a target layer according to a size of the fundus image, and acquiring the preset image feature, where the preset image feature is different from a background image feature corresponding to a background of the target layer;

And mapping a target image corresponding to the identified track on the target layer according to the preset image feature.
The medical device of claim 17, wherein the computer readable instructions further cause the processor to perform the following steps:

Extracting an outline of the target image according to image features of the target image and the background image feature;

Obtaining an image region corresponding to the contour on the fundus image according to a size of the target layer and a size of the fundus image;

The image area is identified on the fundus image.
The medical device according to claim 16, wherein the actual area of the fundus region corresponding to the pixel point at which the fundus image is acquired by the processor comprises:

The pixel area of the fundus image corresponds to the actual area of the fundus area according to the magnification at the time of imaging the fundus image and the side length of the pixel.
The medical device of claim 16 wherein said computer readable instructions further cause said processor to perform the following steps:

Obtaining a trajectory image area corresponding to the identified trajectory on the fundus image;

Obtaining a focus center when the fundus image is imaged, and dividing the track image region into a plurality of sub-regions according to a distance from the focus center;

Obtaining, according to the magnification ratio corresponding to each sub-region and the side length of the pixel point, the actual area of the fundus region corresponding to the pixel point of each sub-region;

The obtaining the number of pixels of the target image includes:

Obtaining a number of pixel points of the target image in each of the sub-regions;

Calculating the area of the fundus lesion area according to the actual area and the number of pixel points includes:

Calculating, according to the actual area of the fundus region corresponding to the pixel points of the respective sub-regions and the corresponding number of pixel points, the area of the respective sub-region corresponding to the fundus lesion region;

The area of the fundus lesion area is obtained according to the area of the respective sub-region corresponding to the fundus lesion area.