CN110335253B - Eye image processing method, device, equipment and computer readable storage medium - Google Patents
Eye image processing method, device, equipment and computer readable storage medium Download PDFInfo
- Publication number
- CN110335253B CN110335253B CN201910494821.8A CN201910494821A CN110335253B CN 110335253 B CN110335253 B CN 110335253B CN 201910494821 A CN201910494821 A CN 201910494821A CN 110335253 B CN110335253 B CN 110335253B
- Authority
- CN
- China
- Prior art keywords
- eye image
- instruction
- detection result
- image processing
- type
- 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.)
- Active
Links
- 238000003672 processing method Methods 0.000 title claims abstract description 29
- 238000001514 detection method Methods 0.000 claims abstract description 217
- 230000002159 abnormal effect Effects 0.000 claims abstract description 142
- 230000008859 change Effects 0.000 claims abstract description 79
- 238000012545 processing Methods 0.000 claims abstract description 60
- 206010025421 Macule Diseases 0.000 claims abstract description 59
- 238000012986 modification Methods 0.000 claims description 51
- 230000004048 modification Effects 0.000 claims description 51
- 238000000034 method Methods 0.000 claims description 23
- 239000000049 pigment Substances 0.000 claims description 23
- 230000005856 abnormality Effects 0.000 claims description 21
- 230000002708 enhancing effect Effects 0.000 claims description 15
- 238000004891 communication Methods 0.000 claims description 13
- 239000003086 colorant Substances 0.000 claims description 3
- 238000005516 engineering process Methods 0.000 abstract description 2
- 238000012937 correction Methods 0.000 description 10
- 230000008569 process Effects 0.000 description 10
- 230000006870 function Effects 0.000 description 6
- 230000007246 mechanism Effects 0.000 description 6
- 208000030533 eye disease Diseases 0.000 description 4
- 210000002189 macula lutea Anatomy 0.000 description 4
- 206010064930 age-related macular degeneration Diseases 0.000 description 3
- 208000002780 macular degeneration Diseases 0.000 description 3
- 238000007639 printing Methods 0.000 description 3
- 230000001960 triggered effect Effects 0.000 description 3
- 238000010586 diagram Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000012552 review Methods 0.000 description 2
- 238000012512 characterization method Methods 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- ZZUFCTLCJUWOSV-UHFFFAOYSA-N furosemide Chemical group C1=C(Cl)C(S(=O)(=O)N)=CC(C(O)=O)=C1NCC1=CC=CO1 ZZUFCTLCJUWOSV-UHFFFAOYSA-N 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000002372 labelling Methods 0.000 description 1
- 230000003014 reinforcing effect Effects 0.000 description 1
- 210000001525 retina Anatomy 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 230000002123 temporal effect Effects 0.000 description 1
- 238000013519 translation Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
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
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H15/00—ICT specially adapted for medical reports, e.g. generation or transmission thereof
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/30—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for calculating health indices; for individual health risk assessment
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Medical Informatics (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Public Health (AREA)
- Primary Health Care (AREA)
- Epidemiology (AREA)
- Radiology & Medical Imaging (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Data Mining & Analysis (AREA)
- Biomedical Technology (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Pathology (AREA)
- Quality & Reliability (AREA)
- Databases & Information Systems (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Measuring And Recording Apparatus For Diagnosis (AREA)
- Image Processing (AREA)
- Eye Examination Apparatus (AREA)
Abstract
The invention discloses an eye image processing method, an eye image processing device, eye image processing equipment and a computer readable storage medium, wherein the eye image processing method comprises the following steps: when a detection instruction for an eye image is detected, a preset algorithm is called for detection, and a detection result comprising the eye type, the macula position, the optic disc position and the abnormal position is generated; when a prediction instruction for the abnormal change trend is detected, judging whether a risk correlation factor exists in the detection result, and if so, predicting the abnormal change probability corresponding to the risk correlation factor according to the corresponding relation between the number of the preset risk correlation factors and the probability; when the trigger instruction for generating the detection report is detected, the detection result, the risk related factors and the abnormal change probability are generated into a reference detection report of the eye image. According to the scheme, an image detection technology is adopted to carry out image processing on an eye image, and a reference detection report for medical staff to serve as a reference is generated; the medical staff can conveniently and rapidly judge the abnormal information in the eye images.
Description
Technical Field
The present invention relates generally to the field of image processing technology, and in particular, to an eye image processing method, apparatus, device, and computer readable storage medium.
Background
At present, in the process of eye disease inspection, an eye image is generally obtained through a fundus color illumination mode, then a medical staff manually determines a optic disc area and a macula area in the eye image, and further judges whether the macula area is diseased or not, whether abnormal information exists or not, and the like. The mode of judging the abnormal information in the eye image by the medical staff only can lead the workload of the medical staff to be very large; especially for medical staff lacking working experience, more time is spent, resulting in low working efficiency of the medical staff.
Disclosure of Invention
The invention mainly aims to provide an eye image processing method, an eye image processing device, eye image processing equipment and a computer readable storage medium, and aims to solve the problem that in the prior art, only medical staff manually judge abnormal information in an eye image, so that the working efficiency of the medical staff is low.
In order to achieve the above object, the present invention provides an eye image processing method, which includes the steps of:
When a detection instruction for an eye image is detected, a preset algorithm is called to detect the eye image, and a detection result is generated, wherein the detection result comprises an eye type, a macula position, a video disc position and an abnormal position in the eye image;
when a prediction instruction for the abnormal change trend is detected, judging whether a risk correlation factor exists in the detection result, and if so, predicting the abnormal change probability corresponding to the risk correlation factor according to the corresponding relation between the number of preset risk correlation factors and the probability;
when a trigger instruction for generating a detection report is detected, generating a reference detection report of the eye image by the detection result, the risk related factors and the abnormal change probability, and completing the processing of the eye image.
Preferably, the step of calling a preset algorithm to detect the eye image and generating a detection result includes:
invoking a first preset algorithm, positioning the center of a macula in the eye image, and determining the coordinates of the center point of the macula;
calling a second preset algorithm, dividing the optic disc area in the eye image, and determining the optic disc position, the optic disc center point coordinates and the optic disc diameter;
Determining an eye type according to the disc center point coordinates, and determining a macula position according to the macula center point coordinates and the disc diameter;
judging whether abnormal information exists in the eye image according to the second preset algorithm, if so, detecting the position of the abnormal information, determining an abnormal position, and generating the eye type, the macula position, the optic disc position and the abnormal position into the detection result.
Preferably, the step of generating the detection result includes:
when a modification instruction of the detection result is detected, determining the modification type of the modification instruction according to the type identifier in the modification instruction;
when the modification type is a modification type, correcting the eye type, the macula position, the optic disc position and the abnormal position in the detection result according to the modification instruction;
and when the modification type is a new addition type, determining pigment abnormality information in the eye image according to the modification instruction, and adding the pigment abnormality information into the detection result so as to update the detection result.
Preferably, the step of predicting the abnormal change probability corresponding to the risk related factor includes:
When an adjustment instruction for the risk correlation factor is detected, adjusting the risk correlation factor according to adjustment information in the adjustment instruction, and generating an adjusted risk correlation factor;
and updating the abnormal change probability according to the adjusted risk related factors.
Preferably, the step when detecting the detection instruction for the eye image includes, before:
when an opening instruction for an eye image is detected, opening and displaying the eye image in a preset terminal interface, and detecting whether a patient information input instruction corresponding to the eye image is received or not;
if a patient information input instruction corresponding to the eye image is received, displaying an information input box in the preset terminal interface, and detecting whether patient information input based on the information input box meets a preset rule or not;
and if the patient information input based on the information input box meets the preset rule, displaying the patient information in the eye image, and if the patient information input based on the information input box does not meet the preset rule, outputting the re-input prompt information.
Preferably, the step of displaying the patient information in the eye image comprises, after:
When an enhancement instruction for enhancing the image is detected, determining the enhancement type of the image enhancement according to the type code in the enhancement instruction;
when the enhancement type is a first preset type, color information in the enhancement instruction is read, and colors corresponding to the color information in the eye image are enhanced;
and when the enhancement type is a second preset type, enhancing the image in the frame selection area or the preset default area in the eye image based on the enhancement instruction.
Preferably, the eye image processing method further comprises the steps of:
when a parameter configuration instruction is received, judging whether the eye image exists in the preset terminal interface, and if so, outputting prompt information for closing the eye image;
and if the eye image does not exist, displaying a configuration input box in the preset terminal interface, and performing parameter configuration according to configuration information input based on the configuration input box.
In addition, to achieve the above object, the present invention also proposes an eye image processing apparatus including:
the detection module is used for calling a preset algorithm to detect the eye image when a detection instruction of the eye image is detected, and generating a detection result, wherein the detection result comprises the eye type, the macula position, the optic disc position and the abnormal position in the eye image;
The prediction module is used for judging whether a risk correlation factor exists in the detection result when a prediction instruction of the abnormal change trend is detected, and predicting the abnormal change probability corresponding to the risk correlation factor according to the corresponding relation between the number of the preset risk correlation factors and the probability if the risk correlation factor exists;
and the generation module is used for generating a reference detection report of the eye image according to the detection result, the risk related factors and the abnormal change probability when a trigger instruction for generating the detection report is detected, so as to finish the processing of the eye image.
In addition, to achieve the above object, the present invention also proposes an eye image processing apparatus including: a memory, a processor, a communication bus, and an eye image processing program stored on the memory;
the communication bus is used for realizing connection communication between the processor and the memory;
the processor is used for executing the eye image processing program to realize the following steps:
when a detection instruction for an eye image is detected, a preset algorithm is called to detect the eye image, and a detection result is generated, wherein the detection result comprises an eye type, a macula position, a video disc position and an abnormal position in the eye image;
When a prediction instruction for the abnormal change trend is detected, judging whether a risk correlation factor exists in the detection result, and if so, predicting the abnormal change probability corresponding to the risk correlation factor according to the corresponding relation between the number of preset risk correlation factors and the probability;
when a trigger instruction for generating a detection report is detected, generating a reference detection report of the eye image by the detection result, the risk related factors and the abnormal change probability, and completing the processing of the eye image.
In addition, to achieve the above object, the present invention also provides a computer-readable storage medium storing one or more programs executable by one or more processors for:
when a detection instruction for an eye image is detected, a preset algorithm is called to detect the eye image, and a detection result is generated, wherein the detection result comprises an eye type, a macula position, a video disc position and an abnormal position in the eye image;
when a prediction instruction for the abnormal change trend is detected, judging whether a risk correlation factor exists in the detection result, and if so, predicting the abnormal change probability corresponding to the risk correlation factor according to the corresponding relation between the number of preset risk correlation factors and the probability;
When a trigger instruction for generating a detection report is detected, generating a reference detection report of the eye image by the detection result, the risk related factors and the abnormal change probability, and completing the processing of the eye image.
According to the eye image processing method, when a detection instruction for an eye image is detected, a preset algorithm is called to detect the eye image, and a detection result comprising an eye type, a macula position, a video disc position and an abnormal position is generated; when a prediction instruction for the abnormal change trend is detected, judging whether a risk correlation factor exists in the detection result, and if the risk correlation factor exists, predicting the abnormal change probability corresponding to the risk correlation factor according to the corresponding relation between the number of the preset risk correlation factors and the probability; and finally, when a trigger instruction for generating a detection report is detected, generating a reference detection report related to the eye image by using a detection result, a risk related factor and abnormal change probability, thereby completing the processing of the eye image. According to the scheme, through image processing of an eye image, various detection results including eye type, macula position, optic disc position, abnormal position and the like in the eye image are obtained; meanwhile, predicting the abnormal change probability of the abnormal change trend according to the risk related factors in the detection result; generating a reference detection report for medical staff to use as a reference by using the detection result, the risk related factors and the abnormal change probability; the method is convenient for medical staff to rapidly judge the abnormal information in the eye image according to the reference detection report, avoids the situation that the medical staff only judges the abnormal information in the eye image manually, and improves the working efficiency of the medical staff.
Drawings
FIG. 1 is a flow chart of a first embodiment of an eye image processing method of the present invention;
FIG. 2 is a functional block diagram of a first embodiment of an ophthalmic image processing apparatus of the present invention;
FIG. 3 is a schematic diagram of a device architecture of a hardware operating environment involved in a method according to an embodiment of the present invention.
The achievement of the objects, functional features and advantages of the present invention will be further described with reference to the accompanying drawings, in conjunction with the embodiments.
Detailed Description
It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention.
The invention provides an eye image processing method.
Referring to fig. 1, fig. 1 is a flowchart illustrating a first embodiment of an eye image processing method according to the present invention. In this embodiment, the eye image processing method includes:
step S10, when a detection instruction for an eye image is detected, a preset algorithm is called to detect the eye image, and a detection result is generated, wherein the detection result comprises an eye type, a macula position, a video disc position and an abnormal position in the eye image;
the eye image processing method is suitable for processing the eye image through the server so as to assist medical staff in judging abnormal information in the eye image. Specifically, the server is in communication connection with a preset terminal with a display device, wherein the preset terminal can be a terminal such as a tablet computer, a desktop computer, a smart phone and the like; and taking the display interface of the display device as a preset terminal interface, and setting a tool window, a main image display area, a thumbnail display area and a functional area in the preset terminal interface. Wherein the tool window has various types of tools for editing the eye image; the main image display area is used for displaying the eye images which are currently processed, and the thumbnail is used for displaying the thumbnail of the eye images which are to be processed; the function area is provided with a plurality of function virtual keys for sending various types of trigger instructions to the server to process the eye images.
The functional area is provided with a virtual key for triggering the detection of the eye image, and the triggering operation of the virtual key is used as a detection instruction of the eye image; when the detection instruction is detected, the requirement of detecting the eye image is indicated, and the detected content comprises the eye type, the macula position, the optic disc position and the abnormal position in the eye image. Wherein the eye types include two types, left eye and right eye; the macula is a projection point which is 0.35cm below the temporal side of the fundus optic disc and is positioned in the optical central area of the human eye and is the visual axis; the retina has a pale red discoid structure with a diameter of about 1.5mm from the macula to the nasal side and clear boundaries; abnormal information such as drusen which is not possessed by the eye image of the normal eye is abnormal; the position of the macula lutea in the eye image is the macula lutea position, the position of the optic disc in the eye image is the optic disc position, and the position of the abnormal information in the eye image is the abnormal position. Preset algorithms for detecting the eye type, the macula position, the optic disc position and the abnormal position in the eye image are preset, the preset algorithms are called, the eye image is detected by the preset algorithms, and detection results representing the eye type, the macula position, the optic disc position and the abnormal position of the eye image displayed in the preset terminal interface are generated.
Specifically, the step of calling a preset algorithm to detect the eye image and generating a detection result comprises the following steps:
s11, calling a first preset algorithm, positioning the center of a macula in the eye image, and determining the coordinates of the center point of the macula;
step S12, calling a second preset algorithm, dividing the video disc area in the eye image, and determining the video disc position, the video disc center point coordinates and the video disc diameter;
further, the preset algorithm comprises a first preset algorithm and a second preset algorithm, wherein the first preset algorithm can be a yolo algorithm, and the second preset algorithm can be a v-net algorithm; the yolo (You Only Look Once) algorithm is a target detection algorithm, the V-Net algorithm is a 3D version of U-Net [1], and the U-Net algorithm is an algorithm for classifying and dividing pictures by taking the pictures as a whole to reduce the calculated amount. In the process of detecting the eye image, a first preset algorithm is firstly called, and the center of the macula in the eye image is positioned through the first preset algorithm to obtain the coordinates of the center point of the macula. Then, a second preset algorithm is called, the optic disc area in the eye image is segmented through the second preset algorithm, the optic disc position is obtained through segmentation, the center of the optic disc position is positioned, and the center point coordinate of the optic disc is obtained; and detecting the length of the video disc in the vertical direction, and taking the length as the diameter of the video disc.
It should be noted that, in order to facilitate positioning to obtain the center point coordinates, a virtual coordinate system may be established in the eye image; if the starting position of the left lower corner of the eye image is used as a coordinate dot, or the central position of the eye image on the length dimension and the width dimension is used as a coordinate dot, a virtual coordinate system is established, and then the coordinate of the central point of the video disc is determined according to the position point of the center of the video disc in the virtual coordinate system.
Step S13, determining the type of eyes according to the coordinate of the center point of the optic disc, and determining the position of the macula lutea according to the coordinate of the center point of the macula lutea and the diameter of the optic disc;
further, according to the coordinate of the center point of the optic disc, the eye type represented by the eye image is identified, and the eye type is determined; meanwhile, the center coordinate of the macula is used as the center of a circle, the diameter of the optic disc is doubled as the radius to make a circle, and the obtained center area is the macula position.
Step S14, judging whether the eye image has abnormal information according to the second preset algorithm, if so, detecting the position of the abnormal information, determining an abnormal position, and generating the eye type, the macula position, the optic disc position and the abnormal position as the detection result.
In consideration of the fact that the abnormal information in the eye image mainly aims at the abnormal in the macular area, after the macular position is determined, in order to judge whether the abnormal exists in the eye image, the image of the macular position can be optimized, and the style of the image can be unified. And then judging whether abnormal information exists in the eye image according to a second preset algorithm aiming at the optimized macular position, if so, identifying and detecting the position of the abnormal information, and determining the abnormal position.
After detecting an eye image by utilizing a first preset algorithm and a second preset algorithm to obtain detection results comprising an eye type, a macula position, a video disc position and an abnormal position, displaying the detection results in corresponding detection items in a preset terminal interface function area, and if the detected abnormal information is drusen, displaying the detected drusen area in the detection items of drusen in the function area; meanwhile, the detection result is directly displayed in the eye image, so that the position and the area size of each detection item in the eye image are intuitively reflected. When the detection result is displayed in the eye image, in order to facilitate medical staff to check different types of information in the detection result, selecting and marking the same type of information in the eye image by lines with the same color; selecting a red line at the boundary of the macula position, selecting a blue line at the boundary of the position of an abnormality A, and the like; the types of abnormalities in the eye images are characterized by lines of different colors, and the positions of the abnormalities are represented.
Understandably, the detection result obtained by the server detecting the eye image has inaccuracy, and in order to improve the accuracy of the detection result, a modification mechanism for modifying the detection result is provided; specifically, the step of generating the detection result includes:
step a, when detecting a modification instruction of the detection result, determining a modification type of the modification instruction according to a type identifier in the modification instruction;
after a detection result is generated aiming at the eye image, medical staff checks the eye image and the corresponding detection result, and judges whether the eye type, the macula position, the optic disc position and the abnormal position determined in the detection result are accurate or not based on experience; if any one of the items is inaccurate, the change can be performed through various editing tools in a tool window of a preset terminal interface. The modified content comprises various types of selection frames such as drawing rectangular frames, circles, unsealed curves, polygons and the like so as to modify inaccurate detection results; if the determined boundary of the macula position in the detection result is inaccurate, so that the area of the macula position is larger, the macula position can be selectively adjusted through a round tool, and the determined macula position is more accurate. Meanwhile, a measuring tool, a dragging tool, a modifying tool, a translation tool, an eraser tool and the like are also arranged in the tool window; the method comprises the steps that various selection frames for changing drawing can be measured through a measuring tool, the area of each selection frame is determined, and the area of each position after adjustment is updated; and simultaneously, labels can be added to the drawn selection boxes to perform operations such as naming, modifying the line width of the selection boxes, translating the selection boxes, modifying the outlines of the selection boxes and the like.
In addition, a new mechanism is arranged on the detection result, and the server does not detect abnormal information in the eye image, such as pigment abnormal information in the eye image, through the experience of medical staff; the anomaly information can be newly added to the detection result through a new adding mechanism. The same new addition is also performed by various editing tools in the tool window, such as drawing and measuring tools; when the modification instruction is detected, the operation type aimed at by the modification instruction needs to be determined because the processing modes aiming at the modification operation and the new operation are different. Specifically, the modifying instruction carries a type identifier representing the operation type in the sending process, and when the modifying instruction is detected, the type identifier is read, and the modifying type of the modifying instruction is determined according to the read type identifier.
B, when the modification type is a modification type, correcting the eye type, the macula position, the optic disc position and the abnormal position in the detection result according to the modification instruction;
further, the modification type comprises two aspects of a modification type and a new addition type, wherein the modification type is used for changing the detection result, and the new addition type is used for adding the detection result. When the modification type of the modification instruction is determined to be the modification type through the type identifier, the eye type, the macula position, the optic disc position and the abnormal position in the detection result are modified according to the modification instruction. Specifically, the correction instruction carries information representing the change required for the detection result; if the area occupied by the macula position determined in the detection result is a, the changing information is to adjust the boundary of the macula position, so that the boundary is enlarged, and the area occupied by the macula position after being changed by the changing information is a+x; the size of the macula area displayed in the functional area and the eye image is corrected according to the correction, and the value of the macula area is corrected from a to a+x.
And c, when the modification type is a new addition type, determining pigment abnormality information in the eye image according to the modification instruction, and adding the pigment abnormality information into the detection result so as to update the detection result.
Furthermore, when the modification type of the modification instruction is determined to be a new type according to the type identifier, pigment abnormality information is indicated to exist in the eye image, wherein the pigment abnormality information comprises pigment enhancement and pigment shedding, and is determined by medical staff in particular. Medical staff marks the position of the pigment abnormal information through an editing tool in a tool window, and the marking operation is a modification instruction with a modification type of a new addition type; the labeling operation used as the modification instruction is received, the modification instruction carries type information representing the type of pigment abnormality information and position information of the pigment abnormality information, pigment abnormality information in an eye image can be determined according to the modification instruction, the pigment abnormality information is added into a detection result, and the detection result is updated to represent pigment abnormality information and positions existing in the eye image.
Step S20, judging whether a risk related factor exists in the detection result when a prediction instruction of an abnormal change trend is detected, and predicting the abnormal change probability corresponding to the risk related factor according to the corresponding relation between the number of preset risk related factors and the probability if the risk related factor exists;
Understandably, the abnormal information in the detection result indicates that there is an abnormality in the eye image, that is, the patient from which the eye image is derived suffers from a certain type of eye disease, and the eye disease may change with time. The embodiment is provided with a mechanism for predicting the abnormal change trend according to the detection result, wherein the predicted content comprises information for judging whether the eye image has the risk of representing the patient suffering from advanced AMD (age-related macular degeneration) in the next five years or not and the change possibility of the information quantity; and taking the predicted result as a reference basis for medical staff to judge the change trend of the eye diseases. Specifically, a virtual key for predicting an abnormal change trend of the eye image is arranged in the functional area, and a click operation of the virtual key is used as a prediction instruction for predicting the abnormal change trend.
When the prediction instruction is detected, judging whether a risk related factor exists in a detection result; because the abnormal information in the detection result comprises two types of drusen and pigment abnormality, the risk related factors are used for representing abnormal matters such as that the maximum drusen diameter is more than 125 mu m, pigment abnormality exists due to pigment loss or pigment enhancement, and the like. When the prediction instruction is detected, judging the detection result, determining whether any one of two risk related factors is carried in the detection result, and if any one risk related factor exists, judging that the risk related factor exists in the detection result, namely, indicating that information representing the risk of the patient for developing AMD exists in the eye image in the next five years. The risk related factors existing in the detection result are the risk information in the eye image, the number of the risk related factors in the detection result is different, the possibility of information quantity change is different, and the possibility is taken as the abnormal change probability; the corresponding relation between the number and the probability of the characterization risk related factors is preset, for example, the probability that any risk factor does not exist is set to be 0.5%, the probability that any risk factor exists is set to be 10%, the probability that two risk factors exist is set to be 25%, and the like. After judging that the risk related factors exist in the detection result, calling the preset corresponding relation, comparing the number of the risk related factors in the detection result with the corresponding relation, and determining the probability corresponding to the number of the risk related factors, wherein the corresponding probability is the predicted abnormal change probability corresponding to the risk related factors. The abnormal change probability output is displayed as reference information to the medical staff.
Understandably, the server has inaccuracy in predicting risk information existing in the eye image and the variation possibility of the information quantity, namely, the risk related factors in the judged detection result and the predicted abnormal variation probability are inaccurate; in order to improve the accuracy of the risk correlation factor and the risk correlation factor, an adjusting mechanism for adjusting the risk correlation factor is arranged; specifically, the step of predicting the abnormal change probability corresponding to the risk correlation factor includes:
step d, when an adjustment instruction for the risk correlation factor is detected, adjusting the risk correlation factor according to adjustment information in the adjustment instruction, and generating an adjusted risk correlation factor;
and e, updating the abnormal change probability according to the adjusted risk related factors.
After generating abnormal change probability aiming at the detection result of the eye image, medical staff checks the eye image, the detection result, the risk related factors and the abnormal change summary, and judges whether the risk related factors determined in the detection result are accurate or not based on experience; if the risk related factor determined by the detection result is not accurate, the risk related factor can be adjusted through various editing tools in a tool window of a preset terminal interface. If a tool for modifying the outline of the selection frame is selected, the area of the drusen is modified, so that the area of the drusen is enlarged or reduced; the enlarged or reduced area is the adjustment information for adjusting the risk related factors, and the change operation of drusen is an adjustment instruction for adjusting the risk related factors; and adding the adjustment information into an adjustment instruction and sending the adjustment instruction to the server so as to adjust the risk related factors. When the server detects the adjustment instruction, the server reads the adjustment information carried by the adjustment instruction and adjusts the risk related factors according to the adjustment information; the detection items which are originally risk related factors in the detection results after the adjustment operation may be changed into non-risk related factors, while the detection items which are not originally risk related factors may be changed into risk related factors. And sending a change by adjusting the number of items of the risk correlation factors in the operation detection result, wherein the changed risk correlation factor number is the generated adjusted risk correlation factor. The change of the abnormal change probability is caused by the change of the number of the risk related factors, the adjusted risk related factors are compared with the corresponding relation between the preset risk factors and the probability, the probability corresponding to the adjusted risk related factors is determined, and the probability is the new abnormal change probability, so that the abnormal change probability is updated.
And step S30, when a trigger instruction for generating a detection report is detected, generating a reference detection report of the eye image by the detection result, the risk related factors and the abnormal change probability, and completing the processing of the eye image.
Further, in order to make the detection result, the risk related factor and the abnormal change probability better provide references for medical staff, a virtual key for generating a detection report for the eye image is arranged in the functional area. When the need for generating the detection report exists, the virtual key is triggered, and the triggering operation is used as a triggering instruction for generating the detection report to detect. When the trigger instruction is detected, the requirement for generating a detection report is indicated, so that information such as the eye type, the macula position, the optic disc position, the abnormal position and the like in the detection result and risk related factors are used, the abnormal change probability generates a reference detection report of the eye image, and the eye image is processed. The generated reference detection report is thereafter provided as reference information to medical personnel for review reference.
Considering that the detection result, the risk correlation factor in the judgment detection result and the correction of the abnormal change probability are involved in the process of generating the detection result and judging the risk correlation factor in the detection result and predicting the abnormal change probability, if the correction operation is after the step of generating the reference detection report; that is, after the reference detection report of the eye image is generated for the detection result, the risk related factor and the abnormal change probability, any one of the detection result, the risk related factor or the abnormal change probability is corrected, so that the generated reference detection report is inaccurate, and at this time, the reference detection report needs to be updated according to the correction term. If the disc position in the detection result is corrected after the reference detection report is generated, the disc position in the detection result of the reference detection report needs to be corrected correspondingly to update the reference detection report. And when the correction operation is performed after the step of generating the reference detection report, and there is a case of correcting any one of the detection result, the risk correlation factor, or the abnormal change probability, the corrected detection result, the risk correlation factor, and the abnormal change probability are directly used to generate the reference detection report of the eye image.
In addition, a virtual key for saving and printing the reference detection report is further arranged in the functional area, and when the reference detection report is generated, the virtual key is triggered to save the reference detection report in a PDF format in a preset path. If a save operation is performed before, the reference detection report generated for the same eye image will cover the content saved before. Meanwhile, by triggering the printing virtual key, the printing operation can be performed on the latest stored reference detection report. By this save and print operation, the reference detection report is facilitated to be provided to medical personnel for review and reference.
According to the eye image processing method, when a detection instruction for an eye image is detected, a preset algorithm is called to detect the eye image, and a detection result comprising an eye type, a macula position, a video disc position and an abnormal position is generated; when a prediction instruction for the abnormal change trend is detected, judging whether a risk correlation factor exists in the detection result, and if the risk correlation factor exists, predicting the abnormal change probability corresponding to the risk correlation factor according to the corresponding relation between the number of the preset risk correlation factors and the probability; and finally, when a trigger instruction for generating a detection report is detected, generating a reference detection report related to the eye image by using a detection result, a risk related factor and abnormal change probability, thereby completing the processing of the eye image. According to the scheme, through image processing of an eye image, various detection results including eye type, macula position, optic disc position, abnormal position and the like in the eye image are obtained; meanwhile, predicting the abnormal change probability of the abnormal change trend according to the risk related factors in the detection result; generating a reference detection report for medical staff to use as a reference by using the detection result, the risk related factors and the abnormal change probability; the method is convenient for medical staff to rapidly judge the abnormal information in the eye image according to the reference detection report, avoids the situation that the medical staff only judges the abnormal information in the eye image manually, and improves the working efficiency of the medical staff.
In another embodiment of the method for processing an eye image of the present invention, the step when detecting the detection command for the eye image includes:
step S40, when an opening instruction of an eye image is detected, opening and displaying the eye image in a preset terminal interface, and detecting whether a patient information input instruction corresponding to the eye image is received or not;
understandably, before the eye image is detected, the eye image needs to be opened and displayed in a preset terminal interface; specifically, a tool for opening the eye image is arranged in the tool window, a dialog box for selecting a path of the eye image is popped up, and the path of the eye image is selected through the dialog box, so that an opening instruction for the eye image can be triggered. When the opening instruction is detected, opening the eye images in the selected path and displaying the eye images in a main image display area of a preset terminal interface so as to view and process the displayed eye images. Meanwhile, virtual keys for inputting patient information are arranged in the functional area, wherein the patient information is information of a patient corresponding to the eye image, and the patient information comprises a name, a gender, an age, an examination number, an examination date and the like. The virtual key is provided with a corresponding identifier, and whether a patient information input instruction corresponding to the eye image is received is determined by detecting whether a trigger instruction carrying the identifier is received.
Step S50, if a patient information input instruction corresponding to the eye image is received, an information input box is displayed in the preset terminal interface, and whether patient information input based on the information input box meets a preset rule is detected;
further, if it is determined that the patient information input instruction corresponding to the eye image is received through the identifier, it is indicated that patient information of a patient from which the eye image is to be input is required for the eye image, so that an information input box is displayed in a preset terminal interface, so that patient information is input through the information input box. After receiving the patient information input based on the information input box, detecting the received patient information and judging whether the received patient information meets the preset rule. The preset rules are rules preset for judging whether the patient information is reasonable or not, such as setting the name length of the patient to be not more than 6 words, setting the preset fields of the gender to be between 'men' and 'women', setting the age to be between 0 and 120 years old, setting the detection date to be within 30 years before the current date, and the like. And comparing the received patient information with preset rules to judge whether the patient information meets the preset rules or not so as to ensure the accuracy of the input patient information.
And step S60, if the patient information input based on the information input box meets the preset rule, displaying the patient information in the eye image, and if the patient information input based on the information input box does not meet the preset rule, outputting the re-input prompt information.
Further, if the comparison determines that each piece of input patient information meets the preset rule set in advance, storing each piece of patient information; while displaying the various patient information items at predetermined locations in the eye image, such as the upper left corner of the main image display area. If any one item of patient information which is input by comparison and determination does not meet the preset rule, distinguishing and displaying the item of patient information and other patient information which meets the preset rule, and outputting prompt information for re-inputting the item of patient information which does not meet the preset rule.
Understandably, after the eye image is displayed on the preset terminal interface, the eye image may have a problem of unclear display due to various factors in the shooting process, which affects the processing result of the eye image; in order to avoid the influence on the processing result, the present embodiment is provided with a mechanism of enhancing the color in the eye image. Specifically, the step of displaying patient information in the ocular image includes:
Step S70, when an enhancement instruction for enhancing the image is detected, determining the enhancement type of the image enhancement according to the type code in the enhancement instruction;
further, the image enhancement in the present embodiment includes three-color channel enhancement and preset algorithm enhancement, the functional area is provided with different virtual keys for the two enhancement types, and each virtual key carries different type codes. The triggering operation performed on any one of the two virtual keys is used as an enhancement instruction for enhancing the image to be detected; when the enhancement instruction is detected, the type code carried in the enhancement instruction is read first, so that the enhancement type for image enhancement of the eye image is determined according to the type code.
Step S80, when the enhancement type is a first preset type, reading color information in the enhancement instruction, and enhancing the color corresponding to the color information in the eye image;
furthermore, the three-color channel enhancement type in the image enhancement is used as a first preset type, wherein the three-color channel is a red, green and blue color channel, and the first preset type is the enhancement type through the red, green and blue color channels. The type of image enhancement aims at the whole image, when the type of enhancement of the image enhancement is determined to be a first preset type through type coding, color information representing the required enhancement color is carried in an enhancement instruction of the image enhancement, and the color information in the enhancement instruction is read firstly to determine a color channel required to be enhanced through the color information; and further enhancing the color corresponding to the color information in the eye image, namely enhancing the color channel represented by the color information in the eye image, so that the whole image of the eye image presents the color corresponding to the color information.
And step S90, when the enhancement type is a second preset type, enhancing the image in the frame selection area or the preset default area in the eye image based on the enhancement instruction.
Further, the preset algorithm enhancement in the image enhancement is used as a second preset type, wherein the preset algorithm can be an AREDS algorithm, and the second preset type is the type enhanced by the AREDS algorithm. The type of image enhancement aims at a frame selection area or a preset default area in the eye image, and when the type of enhancement of the image enhancement is determined to be a second preset type through type coding, the eye image is detected, and whether the frame selection area exists or not is judged; if yes, enhancing the image in the frame selection area and enhancing the instruction; if the image is not present, a preset default area in the eye image is determined, and the image in the preset default area is enhanced according to the enhancement instruction. The default area is determined by a preset rule, for example, a circular area with a center point of the eye image as a round point and a radius as a certain value is preset as the default area.
In addition, in order to be convenient for look over the original image of eye image, still be provided with the virtual button that cancels to the image enhancement in the functional area, when detecting the triggering command to this virtual button, cancel the image enhancement part in the eye image, the original image of displaying eye image to compare the eye image around the reinforcing.
Further, in another embodiment of the eye image processing method of the present invention, the eye image processing method further includes the steps of:
step q1, when a parameter configuration instruction is received, judging whether the eye image exists in the preset terminal interface, and if so, outputting prompt information for closing the eye image;
further, a virtual key for configuring the whole parameters of the eye image is also arranged in the tool window, when the requirement for configuring the parameters exists, the virtual key is clicked, and the clicking operation is used as a parameter configuration instruction to be received; wherein the parameters supporting the configuration include image size units, conversion between size units, and the like. When the parameter configuration instruction is received, detecting whether an eye image is displayed in a main image display area of a preset terminal interface, and outputting prompt information for closing the displayed eye image if the eye image is displayed; after the eye image is closed, the parameters are configured, so that the influence of the configured parameters on the displayed eye image is avoided.
And q2, if the eye image does not exist, displaying a configuration input box in the preset terminal interface, and performing parameter configuration according to configuration information input based on the configuration input box.
If the detected main image display area of the preset terminal interface does not have the displayed eye image, a configuration input box is popped up and displayed in the preset terminal interface so as to input various parameters through the configuration input box for configuration. After receiving the configuration information input based on the configuration input box, configuring each parameter according to the configuration information; if the original image size unit is mm and the size unit received by the input frame is mu m, the original image size unit mm is modified to mu m, so that the configuration of the image size unit is realized. Through the configuration of the parameters, the consistency of each parameter in the eye image is ensured, and different parameters can be configured according to different processing requirements, so that the processing precision is consistent with the processing requirements.
In addition, referring to fig. 2, the present invention provides an eye image processing apparatus, in a first embodiment of the present invention, the eye image processing apparatus includes:
the detection module 10 is configured to invoke a preset algorithm to detect an eye image when a detection instruction for the eye image is detected, and generate a detection result, where the detection result includes an eye type, a macula position, a optic disc position and an abnormal position in the eye image;
The prediction module 20 is configured to determine whether a risk correlation factor exists in the detection result when a prediction instruction for an abnormal variation trend is detected, and if the risk correlation factor exists, predict an abnormal variation probability corresponding to the risk correlation factor according to a corresponding relationship between a preset number of risk correlation factors and a probability;
and the generating module 30 is configured to generate a reference detection report of the eye image according to the detection result, the risk related factor and the abnormal change probability when the trigger instruction for generating the detection report is detected, so as to complete the processing of the eye image.
In the eye image processing apparatus of the present embodiment, when detecting a detection instruction for an eye image, the detection module 10 invokes a preset algorithm to detect the eye image, and generates a detection result including an eye type, a macula position, a disc position, and an abnormal position; when a prediction instruction for the abnormal change trend is detected, the prediction module 20 judges whether a risk correlation factor exists in the detection result, and if the risk correlation factor exists, the abnormal change probability corresponding to the risk correlation factor is predicted according to the corresponding relation between the number of preset risk correlation factors and the probability; finally, when the trigger instruction for generating the detection report is detected, the generating module 30 generates a reference detection report related to the eye image by using the detection result, the risk related factor and the abnormal change probability, and then the eye image is processed. According to the scheme, through image processing of an eye image, various detection results including eye type, macula position, optic disc position, abnormal position and the like in the eye image are obtained; meanwhile, predicting the abnormal change probability of the abnormal change trend according to the risk related factors in the detection result; generating a reference detection report for medical staff to use as a reference by using the detection result, the risk related factors and the abnormal change probability; the method is convenient for medical staff to rapidly judge the abnormal information in the eye image according to the reference detection report, avoids the situation that the medical staff only judges the abnormal information in the eye image manually, and improves the working efficiency of the medical staff.
Further, in another embodiment of the eye image processing apparatus of the present invention, the detection module further includes:
the positioning unit is used for calling a first preset algorithm, positioning the center of the macula in the eye image and determining the coordinates of the center point of the macula;
the calling unit is used for calling a second preset algorithm, dividing the video disc area in the eye image and determining the video disc position, the video disc center point coordinate and the video disc diameter;
a determining unit, configured to determine an eye type according to the optic disc center point coordinates, and determine a macula position according to the macula center point coordinates and the optic disc diameter;
the detection unit is used for judging whether abnormal information exists in the eye image according to the second preset algorithm, if so, detecting the position of the abnormal information, determining an abnormal position, and generating the eye type, the macula position, the video disc position and the abnormal position into the detection result.
Further, in another embodiment of the eye image processing apparatus of the present invention, the eye image processing apparatus further includes:
the first determining module is used for determining the modification type of the modification instruction according to the type identifier in the modification instruction when the modification instruction of the detection result is detected;
The correction module is used for correcting the eye type, the macula position, the optic disc position and the abnormal position in the detection result according to the correction instruction when the correction type is the correction type;
and the first updating module is used for determining pigment abnormality information in the eye image according to the modification instruction when the modification type is a new addition type, and adding the pigment abnormality information into the detection result so as to update the detection result.
Further, in another embodiment of the eye image processing apparatus of the present invention, the eye image processing apparatus further includes:
the adjusting module is used for adjusting the risk related factors according to the adjusting information in the adjusting instruction when an adjusting instruction for the risk related factors is detected, and generating adjusted risk related factors;
and the second updating module is used for updating the abnormal change probability according to the adjusted risk related factors.
Further, in another embodiment of the eye image processing apparatus of the present invention, the eye image processing apparatus further includes:
the display module is used for opening and displaying the eye image in a preset terminal interface when an opening instruction of the eye image is detected, and detecting whether a patient information input instruction corresponding to the eye image is received or not;
The receiving module is used for displaying an information input box in the preset terminal interface if receiving a patient information input instruction corresponding to the eye image, and detecting whether patient information input based on the information input box meets a preset rule or not;
and the output module is used for displaying the patient information in the eye image if the patient information input based on the information input box meets the preset rule, and outputting the re-input prompt information if the patient information input based on the information input box does not meet the preset rule.
Further, in another embodiment of the eye image processing apparatus of the present invention, the eye image processing apparatus further includes:
the second determining module is used for determining the enhancement type of the image enhancement according to the type code in the enhancement instruction when the enhancement instruction of the image enhancement is detected;
the reading module is used for reading the color information in the enhancement instruction when the enhancement type is a first preset type and enhancing the color corresponding to the color information in the eye image;
and the enhancement module is used for enhancing the image in the frame selection area or the preset default area in the eye image based on the enhancement instruction when the enhancement type is a second preset type.
Further, in another embodiment of the eye image processing apparatus of the present invention, the eye image processing apparatus further includes:
the judging module is used for judging whether the eye image exists in the preset terminal interface or not when a parameter configuration instruction is received, and outputting prompt information for closing the eye image if the eye image exists;
and the configuration module is used for displaying a configuration input box in the preset terminal interface if the eye image does not exist, and carrying out parameter configuration according to configuration information input based on the configuration input box.
The virtual function modules of the eye image processing apparatus are stored in the memory 1005 of the eye image processing device shown in fig. 3, and when the processor 1001 executes the eye image processing program, the functions of the modules in the embodiment shown in fig. 2 are implemented.
Referring to fig. 3, fig. 3 is a schematic device structure of a hardware running environment related to a method according to an embodiment of the present invention.
The eye image processing device of the embodiment of the invention can be a PC (personal computer ) or terminal devices such as a smart phone, a tablet personal computer, an electronic book reader, a portable computer and the like.
As shown in fig. 3, the eye image processing apparatus may include: a processor 1001, such as a CPU (Central Processing Unit ), a memory 1005, and a communication bus 1002. Wherein a communication bus 1002 is used to enable connected communication between the processor 1001 and a memory 1005. The memory 1005 may be a high-speed RAM (random access memory ) or a stable memory (non-volatile memory), such as a disk memory. The memory 1005 may also optionally be a storage device separate from the processor 1001 described above.
Optionally, the eye image processing device may further include a user interface, a network interface, a camera, an RF (Radio Frequency) circuit, a sensor, an audio circuit, a WiFi (Wireless Fidelity, wireless broadband) module, and the like. The user interface may comprise a Display, an input unit such as a Keyboard (Keyboard), and the optional user interface may further comprise a standard wired interface, a wireless interface. The network interface may optionally include a standard wired interface, a wireless interface (e.g., WI-FI interface).
It will be appreciated by those skilled in the art that the ocular image processing device structure shown in fig. 3 does not constitute a limitation of the ocular image processing device, and may include more or fewer components than shown, or may combine certain components, or may be a different arrangement of components.
As shown in fig. 3, an operating system, a network communication module, and an eye image processing program may be included in a memory 1005 as one type of computer-readable storage medium. The operating system is a program that manages and controls the hardware and software resources of the eye image processing device, supporting the operation of the eye image processing program and other software and/or programs. The network communication module is used to enable communication between components within the memory 1005 and with other hardware and software in the eye image processing apparatus.
In the eye image processing apparatus shown in fig. 3, the processor 1001 is configured to execute an eye image processing program stored in the memory 1005, and implement the steps in the embodiments of the above-described eye image processing method.
The present invention provides a computer-readable storage medium storing one or more programs that are further executable by one or more processors for implementing the steps in the embodiments of the above-described eye image processing method.
It should also be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.
The foregoing embodiment numbers of the present invention are merely for the purpose of description, and do not represent the advantages or disadvantages of the embodiments.
From the above description of the embodiments, it will be clear to those skilled in the art that the above-described embodiment method may be implemented by means of software plus a necessary general hardware platform, but of course may also be implemented by means of hardware, but in many cases the former is a preferred embodiment. Based on such understanding, the technical solution of the present invention may be embodied essentially or in a part contributing to the prior art in the form of a software product stored in a computer readable storage medium (e.g. ROM/RAM, magnetic disk, optical disk) as described above, comprising instructions for causing a terminal device (which may be a mobile phone, a computer, a server, or a network device, etc.) to perform the method according to the embodiments of the present invention.
The foregoing description is only of the preferred embodiments of the present invention and is not intended to limit the scope of the invention, and all equivalent structural changes made by the specification and drawings of the present invention or direct/indirect application in other related technical fields are included in the scope of the present invention.
Claims (10)
1. An eye image processing method, characterized in that the eye image processing method comprises the following steps:
when a detection instruction for an eye image is detected, a preset algorithm is called to detect the eye image, and a detection result is generated, wherein the detection result comprises an eye type, a macula position, a video disc position and an abnormal position in the eye image;
when a prediction instruction for the abnormal change trend is detected, judging whether a risk correlation factor exists in the detection result, and if so, predicting the abnormal change probability corresponding to the risk correlation factor according to the corresponding relation between the number of preset risk correlation factors and the probability;
when a trigger instruction for generating a detection report is detected, generating a reference detection report of the eye image by the detection result, the risk related factors and the abnormal change probability, and completing the processing of the eye image.
2. The method for processing an eye image according to claim 1, wherein the step of calling a preset algorithm to detect the eye image and generating a detection result includes:
Invoking a first preset algorithm, positioning the center of a macula in the eye image, and determining the coordinates of the center point of the macula;
calling a second preset algorithm, dividing the optic disc area in the eye image, and determining the optic disc position, the optic disc center point coordinates and the optic disc diameter;
determining an eye type according to the disc center point coordinates, and determining a macula position according to the macula center point coordinates and the disc diameter;
judging whether abnormal information exists in the eye image according to the second preset algorithm, if so, detecting the position of the abnormal information, determining an abnormal position, and generating the eye type, the macula position, the optic disc position and the abnormal position into the detection result.
3. The eye image processing method according to claim 1, wherein the step of generating the detection result includes, after:
when a modification instruction of the detection result is detected, determining the modification type of the modification instruction according to the type identifier in the modification instruction;
when the modification type is a modification type, correcting the eye type, the macula position, the optic disc position and the abnormal position in the detection result according to the modification instruction;
And when the modification type is a new addition type, determining pigment abnormality information in the eye image according to the modification instruction, and adding the pigment abnormality information into the detection result so as to update the detection result.
4. The eye image processing method according to claim 1, wherein the step of predicting the abnormal change probability corresponding to the risk related factor includes, after:
when an adjustment instruction for the risk correlation factor is detected, adjusting the risk correlation factor according to adjustment information in the adjustment instruction, and generating an adjusted risk correlation factor;
and updating the abnormal change probability according to the adjusted risk related factors.
5. The eye image processing method according to any one of claims 1 to 4, wherein the step when detecting the detection instruction for the eye image is preceded by:
when an opening instruction for an eye image is detected, opening and displaying the eye image in a preset terminal interface, and detecting whether a patient information input instruction corresponding to the eye image is received or not;
if a patient information input instruction corresponding to the eye image is received, displaying an information input box in the preset terminal interface, and detecting whether patient information input based on the information input box meets a preset rule or not;
And if the patient information input based on the information input box meets the preset rule, displaying the patient information in the eye image, and if the patient information input based on the information input box does not meet the preset rule, outputting the re-input prompt information.
6. The eye image processing method according to claim 5, wherein the step of displaying the patient information in the eye image includes:
when an enhancement instruction for enhancing the image is detected, determining the enhancement type of the image enhancement according to the type code in the enhancement instruction;
when the enhancement type is a first preset type, color information in the enhancement instruction is read, and colors corresponding to the color information in the eye image are enhanced;
and when the enhancement type is a second preset type, enhancing the image in the frame selection area or the preset default area in the eye image based on the enhancement instruction.
7. The eye image processing method according to claim 6, wherein the eye image processing method further comprises the steps of:
when a parameter configuration instruction is received, judging whether the eye image exists in the preset terminal interface, and if so, outputting prompt information for closing the eye image;
And if the eye image does not exist, displaying a configuration input box in the preset terminal interface, and performing parameter configuration according to configuration information input based on the configuration input box.
8. An eye image processing apparatus, characterized in that the eye image processing apparatus comprises:
the detection module is used for calling a preset algorithm to detect the eye image when a detection instruction of the eye image is detected, and generating a detection result, wherein the detection result comprises the eye type, the macula position, the optic disc position and the abnormal position in the eye image;
the prediction module is used for judging whether a risk correlation factor exists in the detection result when a prediction instruction of the abnormal change trend is detected, and predicting the abnormal change probability corresponding to the risk correlation factor according to the corresponding relation between the number of the preset risk correlation factors and the probability if the risk correlation factor exists;
and the generation module is used for generating a reference detection report of the eye image according to the detection result, the risk related factors and the abnormal change probability when a trigger instruction for generating the detection report is detected, so as to finish the processing of the eye image.
9. An eye image processing apparatus, characterized in that the eye image processing apparatus comprises: a memory, a processor, a communication bus, and an eye image processing program stored on the memory;
the communication bus is used for realizing connection communication between the processor and the memory;
the processor is configured to execute the eye image processing program to implement the steps of the eye image processing method according to any one of claims 1-7.
10. A computer-readable storage medium, wherein an eye image processing program is stored on the computer-readable storage medium, which when executed by a processor, implements the steps of the eye image processing method according to any one of claims 1-7.
Priority Applications (3)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910494821.8A CN110335253B (en) | 2019-06-05 | 2019-06-05 | Eye image processing method, device, equipment and computer readable storage medium |
| SG11202008484YA SG11202008484YA (en) | 2019-06-05 | 2019-11-14 | Eye image processing method, apparatus and device, and computer readable storage medium |
| PCT/CN2019/118548 WO2020215701A1 (en) | 2019-06-05 | 2019-11-14 | Eye image processing method, apparatus and device, and computer readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910494821.8A CN110335253B (en) | 2019-06-05 | 2019-06-05 | Eye image processing method, device, equipment and computer readable storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110335253A CN110335253A (en) | 2019-10-15 |
| CN110335253B true CN110335253B (en) | 2023-12-15 |
Family
ID=68140861
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910494821.8A Active CN110335253B (en) | 2019-06-05 | 2019-06-05 | Eye image processing method, device, equipment and computer readable storage medium |
Country Status (3)
| Country | Link |
|---|---|
| CN (1) | CN110335253B (en) |
| SG (1) | SG11202008484YA (en) |
| WO (1) | WO2020215701A1 (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110335253B (en) * | 2019-06-05 | 2023-12-15 | 平安科技（深圳）有限公司 | Eye image processing method, device, equipment and computer readable storage medium |
| CN111192679B (en) * | 2019-12-25 | 2024-04-19 | 上海联影智能医疗科技有限公司 | Method, device and storage medium for processing image data abnormality |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2010071898A2 (en) * | 2008-12-19 | 2010-06-24 | The Johns Hopkins Univeristy | A system and method for automated detection of age related macular degeneration and other retinal abnormalities |
| CN105513077A (en) * | 2015-12-11 | 2016-04-20 | 北京大恒图像视觉有限公司 | System for screening diabetic retinopathy |
| CN107169257A (en) * | 2016-03-07 | 2017-09-15 | 刘江 | Many eye illnesses " intelligent to look into " screening method and system of view-based access control model image |
| CN109191451A (en) * | 2018-09-11 | 2019-01-11 | 百度在线网络技术（北京）有限公司 | Method for detecting abnormality, device, equipment and medium |
| CN109584152A (en) * | 2018-11-30 | 2019-04-05 | 深圳市脸萌科技有限公司 | Image processing method, device, electronic equipment and computer readable storage medium |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105786385B (en) * | 2016-02-29 | 2019-06-07 | 康桥(深圳)科技股份有限公司 | Device based on human body image detection disease symptoms |
| US20180060535A1 (en) * | 2016-08-31 | 2018-03-01 | International Business Machines Corporation | Updating probabilities of conditions based on annotations on medical images |
| US10489932B2 (en) * | 2017-11-27 | 2019-11-26 | Huntercraft Limited | Intelligent shooting training management system |
| CN108803994B (en) * | 2018-06-14 | 2022-10-14 | 四川和生视界医药技术开发有限公司 | Retinal blood vessel management method and retinal blood vessel management device |
| CN110335253B (en) * | 2019-06-05 | 2023-12-15 | 平安科技（深圳）有限公司 | Eye image processing method, device, equipment and computer readable storage medium |
-
2019
- 2019-06-05 CN CN201910494821.8A patent/CN110335253B/en active Active
- 2019-11-14 SG SG11202008484YA patent/SG11202008484YA/en unknown
- 2019-11-14 WO PCT/CN2019/118548 patent/WO2020215701A1/en active Application Filing
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2010071898A2 (en) * | 2008-12-19 | 2010-06-24 | The Johns Hopkins Univeristy | A system and method for automated detection of age related macular degeneration and other retinal abnormalities |
| CN105513077A (en) * | 2015-12-11 | 2016-04-20 | 北京大恒图像视觉有限公司 | System for screening diabetic retinopathy |
| CN107169257A (en) * | 2016-03-07 | 2017-09-15 | 刘江 | Many eye illnesses " intelligent to look into " screening method and system of view-based access control model image |
| CN109191451A (en) * | 2018-09-11 | 2019-01-11 | 百度在线网络技术（北京）有限公司 | Method for detecting abnormality, device, equipment and medium |
| CN109584152A (en) * | 2018-11-30 | 2019-04-05 | 深圳市脸萌科技有限公司 | Image processing method, device, electronic equipment and computer readable storage medium |
Non-Patent Citations (1)
| Title |
|---|
| SD-OCT参数预测青光眼视野进展;裘凯凯 等;昆明医科大学学报;第39卷(第10期);第90-96页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110335253A (en) | 2019-10-15 |
| SG11202008484YA (en) | 2020-11-27 |
| WO2020215701A1 (en) | 2020-10-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20220344044A1 (en) | User-customized skin diagnosis system and method | |
| CN109658999B (en) | Chronic disease inspection report generation method, device, equipment and storage medium | |
| US20160328873A1 (en) | Image compositing device and image compositing method | |
| US9734591B2 (en) | Image data processing method and electronic device supporting the same | |
| US11900594B2 (en) | Methods and systems for displaying a region of interest of a medical image | |
| CN109191410A (en) | A kind of facial image fusion method, device and storage medium | |
| EP3979194A1 (en) | Image state determination method and device, apparatus, system, and computer storage medium | |
| US10521965B2 (en) | Information processing apparatus, method and non-transitory computer-readable storage medium | |
| CN110335253B (en) | Eye image processing method, device, equipment and computer readable storage medium | |
| KR102500715B1 (en) | Electronic apparatus and controlling method thereof | |
| US9691156B2 (en) | Object image labeling apparatus, method and program | |
| US10852939B2 (en) | Medical image display apparatus and recording medium | |
| CN110390260A (en) | Picture scanning part processing method, device, computer equipment and storage medium | |
| CN112135041B (en) | Method and device for processing special effect of human face and storage medium | |
| CN113780201B (en) | Hand image processing method and device, equipment and medium | |
| KR20180109217A (en) | Method for enhancing face image and electronic device for the same | |
| CN108229545B (en) | Glaucoma diagnosis method and device and electronic equipment | |
| CN106406693B (en) | Image chooses method and device | |
| WO2018233117A1 (en) | Method and device for evaluating correction risk factors of business data tables, and storage medium | |
| CN109147911A (en) | Illness information display method and device, computer readable storage medium | |
| CN111104085B (en) | Display screen adaptation method, device, computer equipment and storage medium | |
| CN111540060B (en) | Display calibration method and device of augmented reality equipment and electronic equipment | |
| KR20220058865A (en) | fabric measuring device that determines the color information of the fabric | |
| CN114626950A (en) | Insurance claim settlement information input method and device, computer equipment and storage medium | |
| CN108874333A (en) | Input interface display system and method for portable equipment |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |