CN113947592A - System for capturing and analyzing image data of target - Google Patents
System for capturing and analyzing image data of target Download PDFInfo
- Publication number
- CN113947592A CN113947592A CN202111284291.8A CN202111284291A CN113947592A CN 113947592 A CN113947592 A CN 113947592A CN 202111284291 A CN202111284291 A CN 202111284291A CN 113947592 A CN113947592 A CN 113947592A
- Authority
- CN
- China
- Prior art keywords
- blood vessel
- interest
- region
- image
- analysis unit
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0012—Biomedical image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/13—Edge detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10004—Still image; Photographic image
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20092—Interactive image processing based on input by user
- G06T2207/20104—Interactive definition of region of interest [ROI]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30004—Biomedical image processing
- G06T2207/30041—Eye; Retina; Ophthalmic
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30004—Biomedical image processing
- G06T2207/30101—Blood vessel; Artery; Vein; Vascular
Landscapes
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Radiology & Medical Imaging (AREA)
- Quality & Reliability (AREA)
- Eye Examination Apparatus (AREA)
Abstract
The invention relates to a system for capturing and analyzing image data of a target, comprising: an image acquisition unit for acquiring fundus color photographs; the image preprocessing unit is used for preprocessing the fundus color photograph; the image analysis unit is used for analyzing whether an interested region exists in the fundus color photograph or not, establishing a coordinate system on the fundus color photograph by the image analysis unit to determine the position of the interested region, and sending the position of the interested region to the focus scanning unit when the position of the interested region is determined; the focus scanning unit is used for scanning the positions of all interest areas in the fundus color photograph to determine all interest areas to scan; the storage unit is used for storing the data of each stage; by the method, whether the region of interest exists can be judged more accurately, the marked region of interest is scanned accurately, accuracy and flexibility of fundus scanning are improved, and scanning time of the system is further saved.
Description
Technical Field
The present invention relates to the field of image recognition technology, and more particularly, to a system for capturing and analyzing image data of a target.
Background
The fundus color photograph is a mode for inspecting the fundus, and can be used for clearly seeing the tissue structure of the fundus, analyzing the normality and abnormality of the fundus structure and judging whether the optic disc, blood vessel, retina or choroid of the fundus is in a problem or not. The existing inspection system can only scan two specific interested places, namely the macula lutea and the papilla of the fundus at fixed points, and can not determine the interested place by scanning other retina areas under the condition of not knowing whether other retina areas have focuses, so that the scanning has blindness and long detection time.
Disclosure of Invention
Therefore, the invention provides a system for capturing and analyzing image data of a target, which is used for overcoming the problems that the position of a region of interest cannot be determined, scanning is blind, and the detection time is long in the prior art.
To achieve the above object, the present invention provides a system for capturing and analyzing image data of a target, comprising:
an image acquisition unit for acquiring fundus color photographs;
the image preprocessing unit is connected with the image processing unit and used for preprocessing the fundus color photo, and when a black frame exists on the outermost side of the fundus color photo, the image processing unit removes the black frame existing on the outermost side of the fundus color photo;
the image analysis unit is connected with the image preprocessing unit and used for analyzing whether an interested region exists in the fundus color photograph according to the definition D of the blood vessel edge in the fundus color photograph, the image analysis unit establishes a coordinate system on the fundus color photograph to determine the position of the interested region, and when the position of the interested region is determined, the image analysis unit sends the position of the interested region to the focus scanning unit;
the focus scanning unit is connected with the image analysis unit and is used for scanning the positions of all interest areas in the fundus color photograph to determine all interest areas to scan;
and the storage unit is connected with the image acquisition unit, the image preprocessing unit, the image analysis unit and the focus scanning unit and is used for storing data of each stage.
Further, when the image analysis unit analyzes the fundus color photograph, the image analysis unit determines a blood vessel edge position coordinate through a coordinate system, obtains a blood vessel edge definition D corresponding to the actual blood vessel edge position coordinate, and compares the D with a preset standard blood vessel edge definition D0 to determine whether an interested region exists in the coordinate;
the preset standard blood vessel edge definition D0 comprises a first preset standard blood vessel edge definition D1 and a second preset standard blood vessel edge definition D2, wherein D1 is less than D2;
when D is less than D1, the image analysis unit judges that the blood vessel edge definition corresponding to the actual blood vessel edge position coordinates meets the standard and no region of interest exists;
when D1 is not less than D2, the image analysis unit judges whether the coordinate has the region of interest according to the blood vessel edge definition D corresponding to the actual blood vessel edge position coordinate;
when D is larger than D2, the image analysis unit judges that the blood vessel edge definition corresponding to the actual blood vessel edge position coordinates does not meet the standard and exists in an interested area; when the judgment is completed, the image analysis unit marks the position of the region of interest and sends the marked position to the focus scanning unit.
Further, when the image analysis unit determines that whether the coordinate has the region of interest cannot be determined according to the blood vessel edge definition D corresponding to the actual blood vessel edge position coordinate, the image analysis unit calculates an actual user health score R to correct the actual blood vessel edge definition D, and the image analysis unit records the corrected actual blood vessel edge definition as Da, and sets Da ═ D × (R/R0), wherein R0 is a preset user health score.
Further, the user health score R is calculated using the following formula:
R＝(Q/25)/(W×0.43+P)；
wherein Q is the age of the user, W is the tobacco age of the user, and P is the number of diabetes stages of the user.
Further, when the image analysis unit judges that the blood vessel edge definition corresponding to the actual blood vessel edge position coordinate does not meet the standard and an area of interest exists, the image analysis unit calculates an actual blood vessel edge definition difference Δ D, sets the actual blood vessel edge definition difference Δ D to D-D2, and when the calculation is completed, the image analysis unit compares the Δ D with a preset blood vessel edge definition difference to classify the area of interest;
the preset blood vessel edge definition difference comprises a first preset blood vessel edge definition difference delta D1, a second preset blood vessel edge definition difference delta D2 and a third preset blood vessel edge definition difference delta D3, wherein delta D1 is smaller than delta D2 is smaller than delta D3;
when Δ D < Δd1, the image analysis unit determines that the region of interest is a primary region of interest;
when Δ D1 ≦ Δ D <. Δ D2, the image analysis unit determines the region of interest as a secondary region of interest;
when Δ D2 ≦ Δ D <. Δ D3, the image analysis unit determines that the region of interest is a tertiary region of interest;
when Δ D ≧ Δ D3, the image analysis unit determines that the region of interest is a four-level region of interest;
when the focus scanning unit scans the interested region, the interested region is scanned according to a priority order, wherein the priority order is that the fourth-level interested region is larger than the third-level interested region, and the second-level interested region is larger than the first-level interested region.
Further, when the image analysis unit judges that the blood vessel edge definition corresponding to the actual blood vessel edge position coordinate meets the standard and no region of interest exists, the image analysis unit calculates the blood vessel width a according to the blood vessel edge coordinate, and compares the a with the preset blood vessel width a0 to determine whether the blood vessel width meets the standard or not;
when A is larger than A0, the image analysis unit judges that the width of the blood vessel does not meet the standard, and acquires the coordinate mark of the position as a region of interest;
when A is less than or equal to A0, the image analysis unit judges that the width of the blood vessel meets the standard and no region of interest exists.
Further, when the image processing unit calculates the blood vessel width, the image processing unit acquires a user myopia degree F, and compares the user myopia degree F with a preset myopia degree F0 to determine whether to correct the blood vessel width A;
when F is less than or equal to F0, the image processing unit judges that the blood vessel width A does not need to be corrected;
when F > F0, the image processing unit determines that the blood vessel width a needs to be corrected, and sets the corrected blood vessel width as Aa, which is a × (1+ (F/F0) × 0.015).
Further, when the image analysis unit judges that the blood vessel width does not meet the standard and acquires the coordinate mark of the position as the region of interest, the image analysis unit calculates a blood vessel width difference value delta A, sets the blood vessel width difference value delta A to be A-A0, and when the calculation is finished, the image analysis unit compares the delta A with a preset blood vessel width difference value to classify the region of interest;
the preset blood vessel width difference values comprise a first preset blood vessel width difference value delta A1, a second preset blood vessel width difference value delta A2 and a third preset blood vessel width difference value delta A3, wherein delta A1 is less than delta A2 is less than delta A3;
when Δ a < Δa1, the image analysis unit determines that the region of interest is a primary region of interest;
when the area of interest is more than or equal to delta A1 and less than delta A2, the image analysis unit judges the area of interest as a secondary area of interest;
when the area of interest is more than or equal to delta A2 and less than delta A3, the image analysis unit judges the area of interest to be a three-level area of interest;
when the delta A is not less than the delta A3, the image analysis unit judges that the region of interest is a four-level region of interest;
when the focus scanning unit scans the interested region, the interested region is scanned according to a priority order, wherein the priority order is that the fourth-level interested region is larger than the third-level interested region, and the second-level interested region is larger than the first-level interested region.
Further, the image processing unit acquires the brightness S of each coordinate point in the fundus color photograph, compares S with a preset brightness S0 to determine whether or not a region of interest exists;
when S is larger than or equal to S0, the image processing unit judges that an area of interest exists and sends the coordinates of the area of interest to the focus scanning unit;
when S < S0, the image processing unit determines that there is no region of interest.
Further, the lesion scanning unit is an OCT scanning device.
Compared with the prior art, the system has the advantages that the acquired fundus color photographs are analyzed in advance through the image analysis unit to determine whether the region of interest exists in the fundus reference, the coordinate system is established in the image acquisition unit to determine the position of the region of interest and mark the position, and the position of the region of interest is quickly marked through the image analysis unit, so that the focus scanning unit can accurately scan the marked region of interest, the accuracy and flexibility of the system for scanning the fundus are improved, and the scanning time of the system is further saved.
Furthermore, the image analysis unit of the invention is preset with a standard blood vessel edge definition D0, when the image analysis unit analyzes the fundus color photograph, the image analysis unit acquires the definition of each blood vessel edge in real time, and compares the actual blood vessel edge definition with a preset standard blood vessel edge definition D0 to quickly determine whether the blood vessel edge definition meets the preset standard, when the definition of the blood vessel edge does not meet the preset standard, the image analysis unit marks the coordinates of the blood vessel edge position and sends the coordinates to the focus scanning unit to scan the position, to determine whether a lesion occurs at the location, rapidly marking the location of interest by the image analysis unit, the focus scanning unit can accurately scan the marked region of interest, so that the accuracy and flexibility of fundus scanning of the system are improved, and the scanning time of the system is further saved.
Furthermore, the image analysis unit of the invention also presets a blood vessel edge definition difference value, the image acquisition unit calculates the actual blood vessel edge definition difference value by the real-time blood vessel edge definition, and compares the delta D with the preset blood vessel edge definition difference value to classify the regions of interest, thereby enabling the focus scanning unit to more accurately scan each region of interest, improving the accuracy and flexibility of the system for scanning the eyeground, and further saving the scanning time of the system.
Furthermore, the image scanning unit of the invention also presets a blood vessel width A0, when the image analysis unit judges that the blood vessel edge definition corresponding to the actual blood vessel edge position coordinate meets the standard and no region of interest exists, the image analysis unit calculates the blood vessel width A according to the blood vessel edge coordinate, compares the A with the preset blood vessel width A0 to determine whether the blood vessel width meets the standard, and by judging the blood vessel width, the position of the region of interest can be determined more accurately, so that the focus scanning unit can accurately scan the marked region of interest, the accuracy and flexibility of the fundus scanning of the system of the invention are improved, and the scanning time of the system of the invention is further saved.
Furthermore, the image processing unit is preset with myopia degree F0, when the image processing unit calculates the blood vessel width, the image processing unit acquires the myopia degree F of the user, compares the myopia degree F with the preset myopia degree F0 to judge whether the blood vessel width A is corrected, and acquires the myopia degree of the user through the image processing unit, so that the blood vessel width can be grasped more accurately, whether an interested region exists can be judged more accurately, the focus scanning unit can accurately scan the marked interested region, the accuracy and flexibility of the fundus scanning of the system are improved, and the scanning time of the system is further saved.
Furthermore, the image analysis unit of the invention also presets a blood vessel width difference value, calculates the actual blood vessel width difference value by the real-time blood vessel width of the image acquisition unit, and compares the delta A with the preset blood vessel width difference value to classify the regions of interest, thereby enabling the focus scanning unit to more accurately scan each region of interest, improving the accuracy and flexibility of the fundus scanning of the system of the invention, and further saving the scanning time of the system of the invention.
Furthermore, by setting the preset brightness S0, when fundus color photograph analysis is performed, the image processing unit acquires the brightness S of each coordinate point in the fundus color photograph, compares the brightness S with the preset brightness S0 to see whether a region of interest exists, and by marking a high-brightness area, the focus scanning unit can more accurately scan each region of interest, so that the accuracy and flexibility of fundus scanning of the system of the invention are improved, and the scanning time of the system of the invention is further saved.
Drawings
Fig. 1 is a block diagram of a system for capturing and analyzing image data of a target according to the present invention.
Detailed Description
In order that the objects and advantages of the invention will be more clearly understood, the invention is further described below with reference to examples; it should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
Preferred embodiments of the present invention are described below with reference to the accompanying drawings. It should be understood by those skilled in the art that these embodiments are only for explaining the technical principle of the present invention, and do not limit the scope of the present invention.
It should be noted that in the description of the present invention, the terms of direction or positional relationship indicated by the terms "upper", "lower", "left", "right", "inner", "outer", etc. are based on the directions or positional relationships shown in the drawings, which are only for convenience of description, and do not indicate or imply that the device or element must have a specific orientation, be constructed in a specific orientation, and be operated, and thus, should not be construed as limiting the present invention.
Furthermore, it should be noted that, in the description of the present invention, unless otherwise explicitly specified or limited, the terms "mounted," "connected," and "connected" are to be construed broadly, and may be, for example, fixedly connected, detachably connected, or integrally connected; can be mechanically or electrically connected; they may be connected directly or indirectly through intervening media, or they may be interconnected between two elements. The specific meanings of the above terms in the present invention can be understood by those skilled in the art according to specific situations.
Referring to fig. 1, a block diagram of a system for capturing and analyzing image data of a target according to the present invention is shown, including:
an image acquisition unit for acquiring fundus color photographs;
the image preprocessing unit is connected with the image processing unit and used for preprocessing the fundus color photo, and when a black frame exists on the outermost side of the fundus color photo, the image processing unit removes the black frame existing on the outermost side of the fundus color photo;
the image analysis unit is connected with the image preprocessing unit and used for analyzing whether an interested region exists in the fundus color photograph according to the definition D of the blood vessel edge in the fundus color photograph, the image analysis unit establishes a coordinate system on the fundus color photograph to determine the position of the interested region, and when the position of the interested region is determined, the image analysis unit sends the position of the interested region to the focus scanning unit;
specifically, when the image analysis unit analyzes the fundus oculi color photograph, the image analysis unit marks the blood vessels sequentially in a clockwise direction as the 1 st blood vessel, the 2 nd blood vessel, and the n th blood vessel, and after the marking is completed, the image analysis unit establishes a blood vessel upper edge starting point coordinate n (x1, y1), a blood vessel upper edge end point coordinate n (xj, yj), a blood vessel lower edge starting point coordinate n '(x' 1, y '1), and a blood vessel lower edge end point coordinate n' (x 'j, y' j +1) from the growth position of the n th blood vessel along the growth direction of the blood vessel.
Specifically, the image analysis unit acquires actual blood vessel edge definition corresponding to each actual blood vessel edge coordinate corresponding to the edge coordinate from the starting point edge coordinate of the 1 st blood vessel to the end point edge coordinate of the 1 st blood vessel to analyze whether an area of interest exists in the fundus color photograph;
the image analysis unit acquires actual blood vessel edge definition corresponding to each actual blood vessel edge coordinate corresponding to the edge coordinate from the starting point edge coordinate of the 2 nd blood vessel to the end point edge coordinate of the 2 nd blood vessel so as to analyze whether an area of interest exists in the fundus color photograph;
the image analysis unit acquires actual blood vessel edge definition corresponding to each actual blood vessel edge coordinate corresponding to the edge coordinate from the starting point edge coordinate of the nth blood vessel to the end point edge coordinate of the nth blood vessel so as to analyze whether an area of interest exists in the fundus color photograph.
The focus scanning unit is connected with the image analysis unit and is used for scanning the positions of all interest areas in the fundus color photograph to determine all interest areas to scan; wherein, the focus scanning unit can be an OCT scanning device, and can also be other scanning devices which can identify pathological changes;
and the storage unit is connected with the image acquisition unit, the image preprocessing unit, the image analysis unit and the focus scanning unit and is used for storing data of each stage.
Specifically, the acquired fundus color photographs are analyzed in advance through the image analysis unit to determine whether an interested region exists in fundus reference, a coordinate system is established in the image acquisition unit to determine the position of the interested region and mark the interested region, and the position of the interested region is quickly marked through the image analysis unit, so that the focus scanning unit can accurately scan the marked interested region, the accuracy and flexibility of fundus scanning of the system are improved, and the scanning time of the system is further saved.
Specifically, when the image analysis unit analyzes the fundus color photograph, the image analysis unit determines a blood vessel edge position coordinate through a coordinate system, obtains a blood vessel edge definition D corresponding to the actual blood vessel edge position coordinate, and compares the D with a preset standard blood vessel edge definition D0 to determine whether an interested region exists in the coordinate;
the preset standard blood vessel edge definition D0 comprises a first preset standard blood vessel edge definition D1 and a second preset standard blood vessel edge definition D2, wherein D1 is less than D2;
when D is less than D1, the image analysis unit judges that the blood vessel edge definition corresponding to the actual blood vessel edge position coordinates meets the standard and no region of interest exists;
when D1 is not less than D2, the image analysis unit judges whether the coordinate has the region of interest according to the blood vessel edge definition D corresponding to the actual blood vessel edge position coordinate;
when D is larger than D2, the image analysis unit judges that the blood vessel edge definition corresponding to the actual blood vessel edge position coordinates does not meet the standard and exists in an interested area; when the judgment is completed, the image analysis unit marks the position of the region of interest and sends the marked position to the focus scanning unit.
Specifically, the image analysis unit of the invention is preset with a standard blood vessel edge definition D0, when the image analysis unit analyzes the fundus color photograph, the image analysis unit acquires the definition of each blood vessel edge in real time, and compares the actual blood vessel edge definition with a preset standard blood vessel edge definition D0 to quickly determine whether the blood vessel edge definition meets the preset standard, when the definition of the blood vessel edge does not meet the preset standard, the image analysis unit marks the coordinates of the blood vessel edge position and sends the coordinates to the focus scanning unit to scan the position, to determine whether a lesion occurs at the location, rapidly marking the location of interest by the image analysis unit, the focus scanning unit can accurately scan the marked region of interest, so that the accuracy and flexibility of fundus scanning of the system are improved, and the scanning time of the system is further saved.
Specifically, when the image analysis unit determines that whether a region of interest exists in the coordinate according to the blood vessel edge definition D corresponding to the actual blood vessel edge position coordinate cannot be determined, the image analysis unit calculates an actual user health score R to correct the actual blood vessel edge definition D, and the image analysis unit records the corrected actual blood vessel edge definition as Da, and sets the Da as D x (R/R0), wherein R0 is a preset user health score.
Specifically, the image analysis unit of the invention is also preset with a user health score R0, when the region of interest is determined, the image analysis unit obtains previous diagnosis information of the user to determine the age, the tobacco age, the severity of diabetes or other information of the user, and calculates the user health score according to the previous diagnosis information of the user, so as to further determine whether the blood vessel edge definition meets the preset standard, and by correcting the actual blood vessel edge definition D, the presence of the region of interest can be more accurately determined, so that the focus scanning unit can accurately scan the marked region of interest, thereby improving the accuracy and flexibility of the fundus scanning of the system of the invention, and further saving the scanning time of the system of the invention.
Specifically, the user health score R is calculated using the following formula:
R＝(Q/25)/(W×0.43+P)；
wherein Q is the age of the user, W is the tobacco age of the user, and P is the number of diabetes stages of the user.
Specifically, when the image analysis unit judges that the blood vessel edge definition corresponding to the actual blood vessel edge position coordinate does not meet the standard and a region of interest exists, the image analysis unit calculates an actual blood vessel edge definition difference Δ D, sets the difference Δ D to D-D2, and when the calculation is completed, the image analysis unit compares the difference Δ D with a preset blood vessel edge definition difference to classify the region of interest;
the preset blood vessel edge definition difference comprises a first preset blood vessel edge definition difference delta D1, a second preset blood vessel edge definition difference delta D2 and a third preset blood vessel edge definition difference delta D3, wherein delta D1 is smaller than delta D2 is smaller than delta D3;
when Δ D < Δd1, the image analysis unit determines that the region of interest is a primary region of interest;
when Δ D1 ≦ Δ D <. Δ D2, the image analysis unit determines the region of interest as a secondary region of interest;
when Δ D2 ≦ Δ D <. Δ D3, the image analysis unit determines that the region of interest is a tertiary region of interest;
when Δ D ≧ Δ D3, the image analysis unit determines that the region of interest is a four-level region of interest;
when the focus scanning unit scans the interested region, the interested region is scanned according to a priority order, wherein the priority order is that the fourth-level interested region is larger than the third-level interested region, and the second-level interested region is larger than the first-level interested region.
Specifically, the image analysis unit of the invention also presets a blood vessel edge definition difference value, the image acquisition unit calculates the actual blood vessel edge definition difference value by real-time blood vessel edge definition, and compares the delta D with the preset blood vessel edge definition difference value to classify the regions of interest, so that the focus scanning unit can more accurately scan each region of interest, the accuracy and flexibility of fundus scanning of the system of the invention are improved, and the scanning time of the system of the invention is further saved.
Specifically, when the image analysis unit determines that the blood vessel edge definition corresponding to the actual blood vessel edge position coordinate meets the standard and no region of interest exists, the image analysis unit calculates the blood vessel width a according to the blood vessel edge coordinate, and compares the a with a preset blood vessel width a0 to determine whether the blood vessel width meets the standard or not;
when A is larger than A0, the image analysis unit judges that the width of the blood vessel does not meet the standard, and acquires the coordinate mark of the position as a region of interest;
when A is less than or equal to A0, the image analysis unit judges that the width of the blood vessel meets the standard and no region of interest exists.
Specifically, the image scanning unit of the invention further presets a blood vessel width a0, when the image analysis unit judges that the blood vessel edge definition corresponding to the actual blood vessel edge position coordinate meets the standard and no region of interest exists, the image analysis unit calculates the blood vessel width a according to the blood vessel edge coordinate, compares the blood vessel width a with the preset blood vessel width a0 to determine whether the blood vessel width meets the standard, and by judging the blood vessel width, the position of the region of interest can be determined more accurately, so that the focus scanning unit can accurately scan the marked region of interest, the accuracy and flexibility of fundus scanning of the system of the invention are improved, and the scanning time of the system of the invention is further saved.
Specifically, when the image processing unit calculates the blood vessel width, the image processing unit acquires a user myopia degree F, and compares the myopia degree F with a preset myopia degree F0 to determine whether to correct the blood vessel width A;
when F is less than or equal to F0, the image processing unit judges that the blood vessel width A does not need to be corrected;
when F > F0, the image processing unit determines that the blood vessel width a needs to be corrected, and sets the corrected blood vessel width as Aa, which is a × (1+ (F/F0) × 0.015).
Specifically, the image processing unit is preset with a myopia degree F0, when the image processing unit calculates the blood vessel width, the image processing unit acquires the myopia degree F of the user, compares the myopia degree F with the preset myopia degree F0 to judge whether the blood vessel width A is corrected, and acquires the myopia degree of the user through the image processing unit, so that the blood vessel width can be grasped more accurately, whether an interested region exists can be judged more accurately, the focus scanning unit can accurately scan the marked interested region, the accuracy and flexibility of fundus scanning of the system are improved, and the scanning time of the system is further saved.
Specifically, when the image analysis unit judges that the blood vessel width does not meet the standard and acquires the coordinate mark of the position as the region of interest, the image analysis unit calculates a blood vessel width difference value delta A, sets the blood vessel width difference value delta A to A-A0, and when the calculation is completed, the image analysis unit compares the delta A with a preset blood vessel width difference value to classify the region of interest;
the preset blood vessel width difference values comprise a first preset blood vessel width difference value delta A1, a second preset blood vessel width difference value delta A2 and a third preset blood vessel width difference value delta A3, wherein delta A1 is less than delta A2 is less than delta A3;
when Δ a < Δa1, the image analysis unit determines that the region of interest is a primary region of interest;
when the area of interest is more than or equal to delta A1 and less than delta A2, the image analysis unit judges the area of interest as a secondary area of interest;
when the area of interest is more than or equal to delta A2 and less than delta A3, the image analysis unit judges the area of interest to be a three-level area of interest;
when the delta A is not less than the delta A3, the image analysis unit judges that the region of interest is a four-level region of interest;
when the focus scanning unit scans the interested region, the interested region is scanned according to a priority order, wherein the priority order is that the fourth-level interested region is larger than the third-level interested region, and the second-level interested region is larger than the first-level interested region.
Specifically, the image analysis unit of the invention also presets a blood vessel width difference value, calculates an actual blood vessel width difference value through the real-time blood vessel width of the image acquisition unit, and compares the delta A with the preset blood vessel width difference value to classify the regions of interest, so that the focus scanning unit can more accurately scan each region of interest, the accuracy and the flexibility of the system for scanning the eyeground are improved, and the scanning time of the system is further saved.
Specifically, the image processing unit acquires the brightness S of each coordinate point in fundus color photography, compares S with a preset brightness S0 to determine whether or not a region of interest exists;
when S is larger than or equal to S0, the image processing unit judges that an area of interest exists and sends the coordinates of the area of interest to the focus scanning unit;
when S < S0, the image processing unit determines that there is no region of interest.
Specifically, by setting the preset brightness S0, when fundus color photograph analysis is performed, the image processing unit acquires the brightness S of each coordinate point in the fundus color photograph, compares the brightness S with the preset brightness S0 to see whether a region of interest exists, and by marking a high-brightness region, the focus scanning unit can more accurately scan each region of interest, so that the accuracy and flexibility of fundus scanning by the system of the invention are improved, and the scanning time of the system of the invention is further saved.
So far, the technical solutions of the present invention have been described in connection with the preferred embodiments shown in the drawings, but it is easily understood by those skilled in the art that the scope of the present invention is obviously not limited to these specific embodiments. Equivalent changes or substitutions of related technical features can be made by those skilled in the art without departing from the principle of the invention, and the technical scheme after the changes or substitutions can fall into the protection scope of the invention.
The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention; various modifications and alterations to this invention will become apparent to those skilled in the art. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (10)
1. A system for capturing and analyzing image data of a target, comprising:
an image acquisition unit for acquiring fundus color photographs;
the image preprocessing unit is connected with the image processing unit and used for preprocessing the fundus color photo, and when a black frame exists on the outermost side of the fundus color photo, the image processing unit removes the black frame existing on the outermost side of the fundus color photo;
the image analysis unit is connected with the image preprocessing unit and used for analyzing whether an interested region exists in the fundus color photograph according to the definition D of the blood vessel edge in the fundus color photograph, the image analysis unit establishes a coordinate system on the fundus color photograph to determine the position of the interested region, and when the position of the interested region is determined, the image analysis unit sends the position of the interested region to the focus scanning unit;
the focus scanning unit is connected with the image analysis unit and is used for scanning the positions of all interest areas in the fundus color photograph to determine all interest areas to scan;
and the storage unit is connected with the image acquisition unit, the image preprocessing unit, the image analysis unit and the focus scanning unit and is used for storing data of each stage.
2. The system for capturing and analyzing image data of a target according to claim 1, wherein when the image analyzing unit analyzes the fundus color photograph, the image analyzing unit determines a blood vessel edge position coordinate through a coordinate system, and acquires a blood vessel edge definition D corresponding to the actual blood vessel edge position coordinate, compares D with a preset standard blood vessel edge definition D0 to determine whether a region of interest exists at the coordinate;
the preset standard blood vessel edge definition D0 comprises a first preset standard blood vessel edge definition D1 and a second preset standard blood vessel edge definition D2, wherein D1 is less than D2;
when D is less than D1, the image analysis unit judges that the blood vessel edge definition corresponding to the actual blood vessel edge position coordinates meets the standard and no region of interest exists;
when D1 is not less than D2, the image analysis unit judges whether the coordinate has the region of interest according to the blood vessel edge definition D corresponding to the actual blood vessel edge position coordinate;
when D is larger than D2, the image analysis unit judges that the blood vessel edge definition corresponding to the actual blood vessel edge position coordinates does not meet the standard and exists in an interested area; when the judgment is completed, the image analysis unit marks the position of the region of interest and sends the marked position to the focus scanning unit.
3. The system for capturing and analyzing image data of a target according to claim 2, wherein when the image analysis unit determines that it is impossible to determine whether there is a region of interest in an actual blood vessel edge position coordinate from a blood vessel edge definition D corresponding to the coordinate, the image analysis unit calculates an actual user health score R to correct the actual blood vessel edge definition D, and the image analysis unit records the corrected actual blood vessel edge definition as Da, and sets Da ═ D × (R/R0), where R0 is a preset user health score.
4. The system for capturing and analyzing image data of a target of claim 3, wherein the user health score, R, is calculated using the formula:
R＝(Q/25)/(W×0.43+P)；
wherein Q is the age of the user, W is the tobacco age of the user, and P is the number of diabetes stages of the user.
5. The system for capturing and analyzing image data of a subject according to claim 4, wherein when the image analyzing unit determines that the blood vessel edge definition corresponding to the actual blood vessel edge position coordinates does not meet the criterion and a region of interest exists, the image analyzing unit calculates an actual blood vessel edge definition difference Δ D, set as D-D2, and when the calculation is completed, the image analyzing unit compares Δ D with a preset blood vessel edge definition difference to classify the region of interest;
the preset blood vessel edge definition difference comprises a first preset blood vessel edge definition difference delta D1, a second preset blood vessel edge definition difference delta D2 and a third preset blood vessel edge definition difference delta D3, wherein delta D1 is smaller than delta D2 is smaller than delta D3;
when Δ D < Δd1, the image analysis unit determines that the region of interest is a primary region of interest;
when Δ D1 ≦ Δ D <. Δ D2, the image analysis unit determines the region of interest as a secondary region of interest;
when Δ D2 ≦ Δ D <. Δ D3, the image analysis unit determines that the region of interest is a tertiary region of interest;
when Δ D ≧ Δ D3, the image analysis unit determines that the region of interest is a four-level region of interest;
when the focus scanning unit scans the interested region, the interested region is scanned according to a priority order, wherein the priority order is that the fourth-level interested region is larger than the third-level interested region, and the second-level interested region is larger than the first-level interested region.
6. The system for capturing and analyzing image data of a target according to claim 1, wherein when the image analyzing unit determines that the blood vessel edge definition corresponding to the actual blood vessel edge position coordinates meets the criterion and no region of interest exists, the image analyzing unit calculates a blood vessel width a according to the blood vessel edge coordinates, compares a with a preset blood vessel width a0 to determine whether the blood vessel width meets the criterion;
when A is larger than A0, the image analysis unit judges that the width of the blood vessel does not meet the standard, and acquires the coordinate mark of the position as a region of interest;
when A is less than or equal to A0, the image analysis unit judges that the width of the blood vessel meets the standard and no region of interest exists.
7. The system of claim 6, wherein when the image processing unit calculates the vessel width, the image processing unit obtains a user's myopia degree F, compares F to a preset myopia degree F0 to determine whether to correct the vessel width a;
when F is less than or equal to F0, the image processing unit judges that the blood vessel width A does not need to be corrected;
when F > F0, the image processing unit determines that the blood vessel width a needs to be corrected, and sets the corrected blood vessel width as Aa, which is a × (1+ (F/F0) × 0.015).
8. The system for capturing and analyzing image data of a subject according to claim 7, wherein when the image analyzing unit determines that the blood vessel width does not meet the criterion and acquires the coordinate mark as the region of interest, the image analyzing unit calculates a blood vessel width difference Δ a, sets Δ a-a0, and when the calculation is completed, the image analyzing unit compares Δ a with a preset blood vessel width difference to classify the region of interest;
the preset blood vessel width difference values comprise a first preset blood vessel width difference value delta A1, a second preset blood vessel width difference value delta A2 and a third preset blood vessel width difference value delta A3, wherein delta A1 is less than delta A2 is less than delta A3;
when Δ a < Δa1, the image analysis unit determines that the region of interest is a primary region of interest;
when the area of interest is more than or equal to delta A1 and less than delta A2, the image analysis unit judges the area of interest as a secondary area of interest;
when the area of interest is more than or equal to delta A2 and less than delta A3, the image analysis unit judges the area of interest to be a three-level area of interest;
when the delta A is not less than the delta A3, the image analysis unit judges that the region of interest is a four-level region of interest;
when the focus scanning unit scans the interested region, the interested region is scanned according to a priority order, wherein the priority order is that the fourth-level interested region is larger than the third-level interested region, and the second-level interested region is larger than the first-level interested region.
9. The system for capturing and analyzing image data of a target according to claim 1, wherein the image processing unit acquires brightness S of each coordinate point in fundus oculi color photograph, compares S with preset brightness S0 to determine whether there is a region of interest;
when S is larger than or equal to S0, the image processing unit judges that an area of interest exists and sends the coordinates of the area of interest to the focus scanning unit;
when S < S0, the image processing unit determines that there is no region of interest.
10. The system for capturing and analyzing image data of a target of claim 1, wherein the lesion scanning unit is an OCT scanning device.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111284291.8A CN113947592A (en) | 2021-11-01 | 2021-11-01 | System for capturing and analyzing image data of target |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111284291.8A CN113947592A (en) | 2021-11-01 | 2021-11-01 | System for capturing and analyzing image data of target |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113947592A true CN113947592A (en) | 2022-01-18 |
Family
ID=79337429
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111284291.8A Pending CN113947592A (en) | 2021-11-01 | 2021-11-01 | System for capturing and analyzing image data of target |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113947592A (en) |
-
2021
- 2021-11-01 CN CN202111284291.8A patent/CN113947592A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US9905008B2 (en) | Automated fundus image field detection and quality assessment | |
| JP6025311B2 (en) | Ophthalmic diagnosis support apparatus and method | |
| JP6907563B2 (en) | Image processing device and image processing program | |
| EP2888718B1 (en) | Methods and systems for automatic location of optic structures in an image of an eye, and for automatic retina cup-to-disc ratio computation | |
| US7524061B2 (en) | System and method for robust optic disk detection in retinal images using vessel structure and radon transform | |
| US9619874B2 (en) | Image processing apparatus and image processing method | |
| CN109697719B (en) | Image quality evaluation method and device and computer readable storage medium | |
| US20110137157A1 (en) | Image processing apparatus and image processing method | |
| JP6878923B2 (en) | Image processing equipment, image processing system, and image processing program | |
| JP6230262B2 (en) | Image processing apparatus and image processing method | |
| CN112837805B (en) | Eyelid topological morphology feature extraction method based on deep learning | |
| CN110766656B (en) | Method, device, equipment and storage medium for screening fundus macular region abnormality | |
| Hunter et al. | Automated diagnosis of referable maculopathy in diabetic retinopathy screening | |
| Hernandez et al. | Early detection of Alzheimer's using digital image processing through iridology, an alternative method | |
| WO2019183092A1 (en) | Pupil edge detection in digital imaging | |
| EP1427338A2 (en) | System and method for screening patients for diabetic retinopathy | |
| CN113947592A (en) | System for capturing and analyzing image data of target | |
| Perez-Rovira et al. | Robust optic disc location via combination of weak detectors | |
| WO2000051080A9 (en) | Computer system for analyzing images and detecting early signs of abnormalities | |
| CN116030042A (en) | Diagnostic device, method, equipment and storage medium for doctor's diagnosis | |
| CN114119491B (en) | Data processing system based on medical image analysis | |
| CN112991289B (en) | Processing method and device for standard section of image | |
| CN116138729A (en) | Parameter determining method and system based on fundus camera and intelligent terminal | |
| CN113611403A (en) | Real-time remote eye ground camera inspection system | |
| CN113724214A (en) | Image processing method and device based on neural network |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |