JP2015051054A - Image processing device, image processing system and image processing method - Google Patents

Abstract

PROBLEM TO BE SOLVED: To simply and accurately distinguish a fundus image area and a mask area from fundus image data.SOLUTION: An ophthalmologic image processing device 110 extracts a mask area from fundus image data captured by an ophthalmologic photographing device 100 including an optical mask 101. Then, the ophthalmologic image processing device 110 determines the validity of the extracted mask area or validity of extracting the mask area from the fundus image data. Then, the ophthalmologic image processing device 110 executes image processing to the fundus image data on the basis of the mask area extracted from the fundus image data in the case of determining that the extracted mask area is valid or that it is valid to extract the mask area from the fundus image data.

Description

  The present invention relates to an image processing apparatus, an image processing system, and an image processing method for executing image processing on fundus image data.

  When performing white mask processing or panoramic synthesis processing on fundus image data obtained by photographing the fundus with an ophthalmologic imaging apparatus equipped with an optical mask, it is necessary to separate the fundus image area and the mask area from the fundus image data It becomes. At this time, a process of separating the fundus image area and the mask area by image processing using the difference in brightness can be considered. However, the periphery of the fundus image portion often becomes dark, and in this case, it is difficult to accurately separate the fundus image region and the mask region. Therefore, a technique for analyzing image data obtained by photographing a blank sheet with a mask set on the fundus camera and acquiring a fundus image area from the fundus image data based on the mask area obtained by the analysis is a patent. It is disclosed in Document 1.

JP 2003-38444 A

Here, in Patent Document 1, since it is necessary to separately photograph a blank sheet with a fundus camera at a timing different from the timing for photographing the fundus, it takes time and effort for the user.
In addition, when using filing software that handles a plurality of fundus image data obtained by fundus imaging devices of a plurality of manufacturers, a blank sheet can be obtained if the optical mask standard corresponding to the fundus imaging device of each manufacturer can be obtained. This saves you the trouble of shooting. However, it is not always possible to obtain an optical mask standard.
It is also conceivable to extract a mask area from the fundus image data based on the brightness of the fundus image data. However, when the fundus image data becomes dark as a whole, the boundary between the mask area and the black color becomes ambiguous, and extraction The accuracy becomes worse.

  Accordingly, an object of the present invention is to easily and accurately separate the fundus image area and the mask area from the fundus image data.

The image processing apparatus of the present invention includes an extraction unit that extracts a mask area from the fundus image data based on brightness in the fundus image data including the mask area, and the extraction based on the state of the extracted mask area. Determining means for determining the effectiveness of the extracted mask area, and if it is determined that the extracted mask area is valid, image processing is performed on the fundus image data based on the extracted mask area Image processing means.
Further, another image processing apparatus of the present invention includes a determination unit that determines the effectiveness of extracting a mask region from the fundus image data based on brightness of the fundus image data including the mask region, and the fundus image When it is determined that extracting the mask area from the data is effective, the extraction means for extracting the mask area from the fundus image data based on the brightness of the fundus image data, and the extracted mask area And image processing means for executing image processing on the fundus image data.
The image processing method of the present invention includes a step of extracting a mask area from the fundus image data based on brightness in the fundus image data including the mask area, and based on the state of the extracted mask area, A step of determining the validity of the extracted mask region, and if it is determined that the extracted mask region is valid, image processing is performed on the fundus image data based on the extracted mask region And a process.
Another image processing method of the present invention includes a step of determining the effectiveness of extracting a mask region from the fundus image data based on the brightness of the fundus image data including the mask region, and the fundus image data Extracting the mask area from the fundus image data based on the brightness of the fundus image data, and based on the extracted mask area And executing image processing on the fundus image data.

  According to the present invention, the fundus image area and the mask area can be easily and accurately separated from the fundus image data.

It is a figure which shows the structure of the ophthalmic image processing system which concerns on embodiment of this invention. It is a figure which shows the example of the fundus image data image | photographed with an ophthalmologic imaging device. It is a figure for demonstrating the difference in the property of the pixel value of each area | region in the fundus image data for every imaging | photography format. It is a flowchart which shows the process of the ophthalmic image processing apparatus in the 1st Embodiment of this invention. It is a flowchart which shows the detail of the mask area | region extraction process in step S102 of FIG. 5 is a flowchart showing details of a mask area validity determination process in step S103 of FIG. It is a flowchart which shows the process of the ophthalmic image processing apparatus in the 2nd Embodiment of this invention. It is a flowchart which shows the detail of the effectiveness determination process of the mask area extraction in step S201 of FIG. It is a flowchart which shows the process of the ophthalmic image processing apparatus in the 3rd Embodiment of this invention. It is a flowchart which shows the process of the ophthalmic image processing apparatus in the 4th Embodiment of this invention. It is a flowchart which shows the detail of the mask area | region extraction process in step S401 of FIG.

  DESCRIPTION OF EXEMPLARY EMBODIMENTS Hereinafter, preferred embodiments to which the invention is applied will be described in detail with reference to the accompanying drawings.

<First Embodiment: Determination of Effectiveness of Mask Area Extracted from Fundus Image Data>
(Configuration of ophthalmic image processing system)
First, a first embodiment of the present invention will be described. FIG. 1 is a diagram showing a configuration of an ophthalmic image processing system according to the first embodiment of the present invention. As shown in FIG. 1, the ophthalmic image processing system according to the first embodiment includes an ophthalmologic photographing apparatus 100, an ophthalmic image processing apparatus 110, a display apparatus 120, and a printing apparatus 130. The ophthalmic image processing apparatus 110 is communicably connected to the ophthalmic imaging apparatus 100, the display apparatus 120, and the printing apparatus 130. The ophthalmic image processing apparatus 110 can be configured by a computer such as a general PC. In addition, the ophthalmologic photographing apparatus 100 includes an optical mask 101 for creating a mask area on photographed fundus image data.

  The ophthalmologic photographing apparatus 100 generates fundus image data by photographing the fundus of the subject. The generated fundus image data is transmitted from the ophthalmologic photographing apparatus 100 to the ophthalmic image processing apparatus 110. The ophthalmic image processing apparatus 110 displays fundus image data on the display device 120 or prints it on the printing device 130 in response to reception of fundus image data from the ophthalmologic photographing apparatus 100 or an instruction input from an operator.

(Fundus image data)
FIG. 2 is a diagram illustrating an example of fundus image data photographed by the ophthalmologic photographing apparatus 100. In FIG. 2, reference numeral 200 denotes fundus image data obtained by photographing processing of the ophthalmic photographing apparatus 100. The fundus image data 200 includes two regions: a fundus image region 202 in which a subject imaged by the ophthalmologic photographing apparatus 100 is shown, and a mask region 201 that is a region other than the fundus image region 202. The position, size, and shape of the fundus image area 202 are determined according to the optical mask 101 provided in the ophthalmologic photographing apparatus 100.

  Next, the difference in the property of the pixel value of each region in the fundus image data for each photographing format will be described with reference to FIG. In FIG. 3, fundus image data 300 is color fundus image data, and a graph 310 indicates lightness at a certain height 303 of the fundus image data 300. A range M delimited by a broken line on the graph 310 indicates the mask region 301 of the fundus image data 300. Similarly, a range R delimited by a broken line on the graph 310 indicates the fundus image region 302 of the fundus image data 300. As apparent from the graph 310, the brightness differs greatly between the mask area 301 and the fundus image area 302, and the mask area 301 is obtained by using the lightness step at the boundary between the mask area 301 and the fundus image area 302. Can be extracted.

  The fundus image data 320 is fundus image data obtained by imaging immediately after injection of a contrast medium by fluorescence contrast, and a graph 330 indicates the brightness at a certain height 323 of the fundus image data 320. Immediately after the injection of the contrast agent, since the portion other than the blood vessel portion through which the contrast agent has passed is dark, there is no difference in brightness between the range M and the range R. Therefore, if mask area extraction using the lightness level difference that is possible with the fundus image data 300 is performed with the fundus image data 320, the fundus image area 322 is also extracted as a mask area.

(Processing of ophthalmic image processing device)
Hereinafter, the processing of the ophthalmic image processing apparatus 110 according to the first embodiment will be described with reference to FIG. The process shown in FIG. 4 is a process realized by the CPU reading and executing necessary data and programs from a recording medium such as a ROM or HDD in the ophthalmic image processing apparatus 110.

  In step S <b> 101, the input unit (acquisition unit) in the ophthalmic image processing apparatus 110 inputs (acquires) fundus image data selected according to the operation of the operator among the fundus image data captured by the ophthalmic imaging apparatus 100. To do. In step S102, the extraction unit in the ophthalmologic image processing apparatus 110 extracts a mask region from the fundus image data. In step S103, the determination unit in the ophthalmic image processing apparatus 110 determines whether or not the extracted mask area 201 is valid. If the mask area 201 is valid, the process proceeds to step S105. On the other hand, if the mask area 201 is not valid (invalid), the process proceeds to step S104. Step S102 is a processing example of the first extraction unit.

  In step S104, the ophthalmic image processing apparatus 110 refers to a mask area designated in advance. When the process proceeds from step S104 to step S105, in step S105, the image processing unit in the ophthalmic image processing apparatus 110 converts the mask area referred to in step S104 in the fundus image data 200 to white. On the other hand, when the process directly proceeds from step S103 to step S105, in step S105, the ophthalmologic image processing apparatus 110 converts the mask area extracted in step S102 from the fundus image data to white.

  In addition, it is preferable to prepare in advance a mask area that does not overlap with an assumed fundus image area as the mask area referred to in step S104. Thereby, it is possible to prevent the fundus image region from being converted to white in the white mask processing in step S105. In the white mask process, the control unit in the ophthalmic image processing apparatus 110 controls the printing apparatus 130 to obtain an effect of reducing the ink amount when printing the fundus image data subjected to the image process on a print medium such as paper. It is done. In addition, when image processing is performed only on the fundus image area using the extracted mask area instead of white mask processing, there is no need to change the pixel value of the mask area, and the image processing time can be reduced. It becomes. Further, when a character string is overlaid on the mask area, the character string does not cover the fundus image area, so that a large font can be displayed.

(Mask area extraction processing)
Next, the mask area extraction process in step S102 of FIG. 4 will be described in detail with reference to FIG. In step S1021, the ophthalmologic image processing apparatus 110 calculates the brightness of each pixel of the entire fundus image data input in step S101. In step S1022, the ophthalmologic image processing apparatus 110 detects fundus image data as a mask region by detecting a portion where the difference in brightness between adjacent pixels is equal to or greater than a predetermined value based on the brightness calculated in step S1021. Divide into fundus image areas. At this time, the ophthalmologic image processing apparatus 110 sets a region located on the outermost side among the divided regions as a mask region. That is, the extraction unit in the ophthalmic image processing apparatus 110 extracts a mask area from the fundus image data based on the brightness in the fundus image data. Note that a median filter may be applied to the fundus image data before the mask area extraction process in step S102. Thereby, it is possible to reduce the noise of the fundus image data and reduce the failure of extracting the mask area.

(Masking area validity judgment processing)
Next, the mask area validity determination process in step S103 of FIG. 4 will be described in detail with reference to FIG. In step S1031, the ophthalmologic image processing apparatus 110 extracts the contour of the fundus image area, which is an example of the state of the mask area, from the mask area extracted in step S102. In step S1032, the ophthalmologic image processing apparatus 110 calculates the size and position, which are examples of the state of the fundus image area, based on the outline of the fundus image area, and determines whether or not they are valid. If both the size and position of the fundus image area are valid, the process proceeds to step S1033. On the other hand, if at least one of the size and position of the fundus image area is invalid, the process proceeds to step S1035. The validity of the size or position of the fundus image area may be determined using a threshold value. The threshold value at this time may be set using the maximum and minimum values of the proportion of the fundus image area in the assumed fundus image data and the maximum and minimum values of the shift of the center position of the fundus image area.

  By the way, when the shape of the mask area is a perfect circle, it is based on the maximum value and minimum value of the diameter of the fundus image area, and the maximum value and minimum value of the deviation between the center position of the diameter and the center position of the fundus image area. Thus, it is possible to generate a mapping diagram in which a region that is necessarily a mask region and a region that is necessarily a fundus image region are mapped. Then, the ophthalmic image processing apparatus 110 compares the contour of the fundus image area extracted in step S1031 with the mapping diagram, and if there is a contour line in the area that is always the mask area or the area that is always the fundus image area, It is determined that the mask area is invalid. On the other hand, even when the shape of the mask region is not a perfect circle, the effectiveness of the mask region can be determined by a similar method by using information indicating the shape of the mask region. In addition to the method for generating the mapping diagram, the numerical range of the proportion of the fundus image area in the fundus image data is calculated based on the information indicating the shape of the fundus image area. The ophthalmologic image processing apparatus 110 may determine that the fundus image area in the fundus image data obtained from the mask area extracted in step S102 is invalid if the ratio is outside the above numerical range. .

  In step S1033, the ophthalmologic image processing apparatus 110 determines whether the contour shape of the fundus image area is valid. If the contour shape of the fundus image area is valid, the process proceeds to step S1034. On the other hand, if the contour shape of the fundus image area is invalid, the process proceeds to step S1035. The shape of the mask area of the fundus image data is determined according to the ophthalmologic photographing apparatus 100 and the photographing format. Therefore, it is possible to determine whether the contour shape of the fundus image region is effective by determining the similarity between the contour shape of the fundus image region and the shape of the mask region. In step S1034, the ophthalmic image processing apparatus 110 determines that the mask region extracted in step S102 is valid. In step S1035, the ophthalmologic image processing apparatus 110 determines that the mask area extracted in step S102 is invalid.

  A specific example of the similarity measurement method will be described. The ophthalmologic image processing apparatus 110 includes the center of gravity of the contour of the standard fundus image area obtained from the ophthalmologic imaging apparatus 100 and the imaging format, and the center of gravity of the outline extracted in step S1031. Ask for. Then, the ophthalmologic image processing apparatus 110 has a distance from the center of gravity of the contour of the standard fundus image region to the contour, and a distance from the center of gravity of the contour of the fundus image region extracted in step S1031 to the contour. Ask for. As the distance from the center of gravity to the contour, 12 numerical values in 12 directions are calculated for each contour at an angular interval of 30 degrees from the directly above direction. Then, the ophthalmologic image processing apparatus 110 crosses the contour from the center of gravity of the contour of the fundus image region extracted in step S1031 to the contour from the center of gravity of the contour of the standard fundus image region for each direction. Find the value divided by the distance to and the standard deviation of them. Then, the ophthalmic image processing apparatus 110 determines that the similarity is high when the standard deviation is 0.1 or less. The determination accuracy may be increased by reducing the angle interval, or the determination criterion may be tightened by decreasing the threshold value of the standard deviation that is the determination value of the similarity.

As described above, in the present embodiment, the validity of the extracted mask area is determined, and then the white mask process for the mask area is performed. Therefore, according to the present embodiment, it is possible to perform white mask processing by simply and accurately separating the fundus image region and the mask region regardless of the positional relationship between the camera that captures the fundus image data and the base. The burden on the operator can be reduced. In addition, as described with reference to FIG. 3, even if the fundus image data obtained by imaging immediately after the contrast agent injection is performed by fluorescence contrast, the effectiveness of the mask region extracted from the fundus image data is determined. Then, white mask processing is performed. Therefore, according to the present embodiment, it is possible to perform the white mask process by simply and accurately dividing the fundus image area and the mask area.
In the conventional fundus photographing apparatus, since it is necessary to separately photograph a blank sheet with a fundus camera at a timing different from the timing for photographing the fundus, it takes time and effort for the user. Here, some fundus photographing apparatuses are equipped with a camera for photographing fundus image data and a base for adjusting the position of the eye to be examined and the camera. In the case of such a fundus imaging apparatus, in the prior art, the positional relationship between the camera and the base changes each time the camera is attached, and the positional relationship between the mask region and the eye to be examined also changes. In this case, in the above-described technique, a method of acquiring the mask area every time the image is attached can be considered. Such a trouble can be eliminated by the present embodiment.

<Second Embodiment: Determination of Effectiveness of Extracting Mask Area from Fundus Image Data>
Next, a second embodiment of the present invention will be described. As described above, in the first embodiment, the validity of the mask area extracted from the fundus image data is determined, and the mask area used for the white mask processing is switched depending on whether the mask area is valid. ing. On the other hand, in the second embodiment, not the effectiveness of the mask region but the effectiveness of extracting the mask region from the fundus image data is determined, and the mask used for the white mask processing is determined according to the determination result. The area is switched. The configuration of the ophthalmic image processing system according to the second embodiment is the same as the configuration of the ophthalmic image processing system according to the first embodiment shown in FIG. 1, and therefore, in the following description, FIG. The indicated symbols are used.

(Processing of ophthalmic image processing device)
Hereinafter, the processing of the ophthalmic image processing apparatus 110 according to the second embodiment will be described with reference to FIG. 7, processes similar to those in FIG. 4 are denoted by the same reference numerals as those in FIG. 4, and description thereof may be omitted. Further, the process shown in FIG. 7 is a process realized by the CPU reading and executing necessary data and programs from a recording medium such as a ROM or HDD in the ophthalmic image processing apparatus 110.

  In step S201, the ophthalmic image processing apparatus 110 determines whether it is effective to extract a mask region from the fundus image data input in step S101. If the extraction of the mask area is valid, the process proceeds to step S102. Thereby, a mask region is extracted from the fundus image data. On the other hand, if the extraction of the mask area is invalid, the process proceeds to step S104. Thereby, a mask area designated in advance is referred to.

  In this embodiment, it is determined whether it is effective or invalid to extract the mask area from the fundus image data before the mask area extraction process. If it is invalid, the mask area is extracted from the fundus image data. I try not to extract it. Therefore, according to the present embodiment, the processing time can be shortened as much as unnecessary mask region extraction processing is not performed.

(Masking area extraction validity judgment processing)
Next, the mask area extraction validity determination process in step S201 of FIG. 7 will be described in detail with reference to FIG. In step S2011, the ophthalmologic image processing apparatus 110 calculates the brightness of each pixel of the entire fundus image data input in step S101. In step S2012, the ophthalmic image processing apparatus 110 calculates an average value of the brightness of the entire fundus image data based on the calculated brightness, and determines whether the average value is higher than a predetermined threshold. That is, the determination unit in the ophthalmologic image processing apparatus 110 determines the effectiveness of extracting the mask region from the fundus image data based on the brightness in the fundus image data. If the average value is higher than the predetermined threshold, the process proceeds to step S2013. On the other hand, when the average value is equal to or less than the predetermined threshold, the process proceeds to step S2014. In step S2013, the ophthalmologic image processing apparatus 110 determines that the extraction of the mask area is effective. In step S2014, the ophthalmic image processing apparatus 110 determines that the extraction of the mask area is invalid. As the predetermined threshold value, an average value of brightness that is considered that a mask area can be accurately extracted from fundus image data is set. Note that the effectiveness of mask area extraction may be determined according to how much of the entire fundus image data is occupied by pixels with low brightness close to the brightness of the mask area. The determination may be made according to the format (color imaging / fluorescence contrast imaging).

  Note that after determining that the extraction of the mask area is effective in step S201 and extracting the mask area in step S102, the validity of the mask area may be determined in the same manner as in step S103 of FIG. In this case, when it is determined that the mask area is valid, the white mask processing of the fundus image data is performed based on the mask area. When the mask area is determined to be invalid, the mask area is based on the mask area designated in advance. Thus, white mask processing of the fundus image data is executed.

<Third Embodiment: When Mask Area Extracted from Fundus Image Data is Invalid>
Next, a third embodiment of the present invention will be described. In the first embodiment, the method of using a mask area designated in advance when the mask area extracted from the fundus image data is invalid has been described. On the other hand, in the third embodiment, when the mask area extracted from the fundus image data is invalid, a method of extracting the mask area from other fundus image data photographed within the same examination as the fundus image data. Will be described. The configuration of the ophthalmic image processing system according to the third embodiment is the same as the configuration of the ophthalmic image processing system according to the first embodiment shown in FIG. 1, and therefore, in the following description, FIG. The indicated symbols are used.

(Processing of ophthalmic image processing device)
Hereinafter, the processing of the ophthalmic image processing apparatus 110 according to the third embodiment will be described with reference to FIG. 9, processes similar to those in FIG. 4 are denoted by the same reference numerals as those in FIG. 4, and description thereof may be omitted. 9 is a process realized by the CPU reading and executing necessary data and programs from a recording medium such as a ROM or HDD in the ophthalmic image processing apparatus 110.

  When the mask area extracted from the fundus image data is invalid, in step S301, the ophthalmologic image processing apparatus 110 extracts a mask area from other fundus image data photographed within the same examination as the fundus image data. The mask area extraction process at this time is the same as the method in step S102. In step S302, the ophthalmic image processing apparatus 110 determines whether or not the mask area extracted in step S301 is valid. The mask area validity determination process in step S302 is the same as the method in step S103. If the mask area is valid, the process proceeds to step S105. On the other hand, if the mask area is invalid, the process proceeds to step S104. When the process proceeds from step S302 to S105, in step S105, the ophthalmic image processing apparatus 110 converts the mask area extracted in step S301 in the fundus image data 200 to white. Note that in step S301, not other fundus image data photographed in the same examination but other fundus image data whose photographing date and time (shooting time) is included in a predetermined range or selected according to the model. You may extract a mask area | region from the other fundus image data image | photographed with the other ophthalmologic imaging device (the ophthalmic imaging device of the same model as the ophthalmic imaging device 100, or a similar model). Step S301 is a processing example of the second extraction unit.

  In the present embodiment, when the mask area extracted from the target fundus image data is invalid, the mask area is extracted from other fundus image data that is assumed to match the subject, and the validity of the mask area is determined. Is determined, and the white mask processing of the mask area is performed. Therefore, according to this embodiment, even if the mask area extracted from the target fundus image data is invalid, the mask area is extracted from other fundus image data assumed to be the same subject, and the fundus image area and the mask area are extracted. And white mask processing can be performed.

<Fourth Embodiment: When Extracting Mask Area from Fundus Image Data is Invalid>
Next, a fourth embodiment of the present invention will be described. In the second embodiment, the method of using a mask area designated in advance when extracting a mask area from fundus image data is invalid has been described. On the other hand, in the fourth embodiment, when it is invalid to extract the mask area from the fundus image data, the mask area is extracted from other fundus image data photographed within the same examination as the fundus image data. A method will be described. The configuration of the image processing system according to the fourth embodiment is the same as the configuration of the fundus image processing system according to the first embodiment shown in FIG. Shall be used.

(Processing of ophthalmic image processing device)
Hereinafter, the processing of the ophthalmic image processing apparatus 110 according to the fourth embodiment will be described with reference to FIG. 10, the same processes as those in FIGS. 4, 7, and 9 are denoted by the same reference numerals. 10 is a process realized by the CPU reading and executing necessary data and programs from a recording medium such as a ROM or HDD in the ophthalmic image processing apparatus 110.

  If it is invalid to extract the mask area from the fundus image data, in step S401, the ophthalmologic image processing apparatus 110 extracts the mask area from other fundus image data photographed within the same examination as the fundus image data. . Processing other than step S401 is the same as in the third embodiment. In step S401, not other fundus image data photographed in the same examination, other fundus image data whose photographing date and time is included in a certain range, and other fundus image data photographed by a similar ophthalmologic photographing apparatus. A mask region may be extracted from the fundus image data.

(Mask area extraction processing)
Next, the mask area extraction process in step S401 of FIG. 10 will be described in detail with reference to FIG. In step S4021, the ophthalmologic image processing apparatus 110 has another fundus image data shot in the same examination as the fundus image data input in step S101 of FIG. 10 and shot in the same format as the fundus image data. It is determined whether or not to do. That is, in step S4021, whether or not the image was captured in the same format because it was captured with mydriatic imaging, or was captured with non-mydriatic imaging, and the shape of the mask area may vary depending on the imaging magnification. Is judged. If there is other fundus image data shot in the same examination and shot in the same format, the process proceeds to step S4022. On the other hand, if there is no other fundus image data shot in the same examination and shot in the same format, the process proceeds to step S4027.

  In step S4027, the ophthalmologic image processing apparatus 110 performs invalidity determination regarding extraction of a mask region from other fundus image data captured within the same examination. In step S4022, the ophthalmologic image processing apparatus 110 determines whether or not the fundus image data determined to exist in step S4021 includes fluorescence contrast image data having a high average brightness. If fluorescent contrast image data with a high average brightness is included, the process proceeds to step S102. On the other hand, when the fluorescence contrast image data having a high average brightness is not included, the process proceeds to step S4023. Note that the fluorescence contrast image data having a high average brightness has a high possibility that the entire fundus image area is bright evenly, and the possibility that the mask area can be extracted more accurately than the color fundus image data is high.

  When the process directly proceeds from step S4022 to S102, in step S102, the ophthalmic image processing apparatus 110 extracts a mask region from the fluorescence contrast image data. In step S4023, the ophthalmologic image processing apparatus 110 determines whether color fundus image data is included in the fundus image data determined to exist in step S4021. If color fundus image data is included, the process proceeds to step S102. On the other hand, when the color fundus image data is not included, the process proceeds to step S4024.

  When the process directly proceeds from step S4023 to S102, in step S102, the ophthalmic image processing apparatus 110 extracts a mask region from the color fundus image data. In step S4204, the ophthalmologic image processing apparatus 110 calculates fundus image data other than the fluorescence contrast image data and the color fundus image data from the other fundus image data captured in the same examination and in the same format determined to exist in step S4021. Select. When the process proceeds from step S4024 to S102, in step S102, the ophthalmologic image processing apparatus 110 extracts a mask region from the fundus image data selected in step S4024.

  In step S103, the ophthalmic image processing apparatus 110 determines the validity of the mask region extracted in step S102. If the mask area is valid, the process proceeds to step S4025. On the other hand, if the mask area is invalid, the process returns to step S4021. In step S4025, the ophthalmologic image processing apparatus 110 registers the mask area extracted in step S102 as a target for white mask processing. In step S4026, the ophthalmologic image processing apparatus 110 determines that the mask area extracted in step S102 is valid. In step S4027, the ophthalmologic image processing apparatus 110 determines that the mask area extracted in step S102 is invalid.

  As described above, in the present embodiment, it is determined whether the extraction of the mask area from the fundus image data is effective or invalid before the mask area extraction process. The mask area is not extracted. Therefore, according to the present embodiment, the processing time can be shortened as much as unnecessary mask region extraction processing is not performed. In the present embodiment, fundus image data to be extracted from the mask area is selected according to the type of fundus image data. This makes it possible to accurately extract the mask region from other fundus image data.

  In addition, this invention is not limited to the said embodiment, In the range which does not deviate from the main point of this invention, it can implement by performing a various deformation | transformation and change. For example, in the above embodiment, the white mask process is taken as an example. However, the present invention is not limited to this. For example, when the fundus image area and the mask area are separated into a digital conversion process, such as a panorama synthesis process. However, the present invention may be applied.

  The present invention can also be realized by executing the following processing. That is, software (program) that realizes the functions of the above-described embodiments is supplied to a system or apparatus via a network or various storage media, and a computer (or CPU, MPU, or the like) of the system or apparatus reads the program. It is a process to be executed.

Claims (18)

Extraction means for extracting a mask area from the fundus image data based on brightness in the fundus image data including the mask area;
Determination means for determining the effectiveness of the extracted mask region based on the state of the extracted mask region;
Image processing means for performing image processing on the fundus image data based on the extracted mask region when it is determined that the extracted mask region is valid;
An image processing apparatus comprising:   The determination means determines whether the extracted mask area is valid based on at least one of the size, position, and shape of a fundus image area that is an area other than the extracted mask area in the fundus image data. The image processing apparatus according to claim 1, wherein the image processing apparatus determines the property.   2. The image processing unit according to claim 1, wherein when it is determined that the extracted mask region is invalid, the image processing unit performs image processing on the fundus image data based on a mask region designated in advance. Or the image processing apparatus of 2. A second extracting means for extracting a mask region from other fundus image data;
When it is determined that the mask area extracted from the fundus image data is invalid, the image processing unit performs image processing on the fundus image data based on the mask area extracted from the other fundus image data. The image processing apparatus according to claim 1, wherein the image processing apparatus is executed. A second extracting means for extracting a mask region from other fundus image data;
The determination means determines the effectiveness of the mask area extracted from the other fundus image data,
The image processing means includes
If it is determined that the mask area extracted from the other fundus image data is valid, image processing is performed on the fundus image data based on the mask area extracted from the other fundus image data;
2. The image processing for the fundus image data is executed based on a mask area designated in advance when it is determined that a mask area extracted from the other fundus image data is invalid. Or the image processing apparatus of 2.   The second extraction unit selects the other fundus image data from which a mask region is to be extracted according to the type of the other fundus image data, and extracts a mask region from the selected other fundus image data. The image processing apparatus according to claim 4, wherein: Determination means for determining the effectiveness of extracting the mask area from the fundus image data based on the brightness of the fundus image data including the mask area;
An extraction means for extracting a mask area from the fundus image data based on the brightness of the fundus image data when it is determined that extracting the mask area from the fundus image data is effective;
Image processing means for performing image processing on the fundus image data based on the extracted mask region;
An image processing apparatus comprising:   The image processing apparatus according to claim 7, wherein the determination unit determines the effectiveness of extracting a mask region from the fundus image data based on brightness or an imaging format of the fundus image data.   The image processing unit performs image processing on the fundus image data based on a mask region designated in advance when it is determined that the determination unit is invalid to extract a mask region from the fundus image data. The image processing apparatus according to claim 7, wherein the image processing apparatus is an image processing apparatus. A second extracting means for extracting a mask region from other fundus image data;
When it is determined that extracting a mask area from the fundus image data is invalid, the image processing unit performs image processing on the fundus image data based on a mask area extracted from the other fundus image data. The image processing apparatus according to claim 7, wherein:   The other fundus image data is taken in the same examination and is taken in the same format, other fundus image data, other fundus image data whose shooting time is included in a predetermined range, or depending on the model The image processing apparatus according to claim 4, wherein the image processing apparatus is other fundus image data photographed by another selected ophthalmologic photographing apparatus. The image processing means converts the mask processing in the fundus image data into white by performing image processing on the fundus image data,
The image processing apparatus according to claim 1, wherein the image processing apparatus is communicably connected to a printing apparatus that prints fundus image data subjected to the image processing on a print medium.   13. The apparatus according to claim 1, further comprising an acquisition unit that is communicably connected to an ophthalmic imaging apparatus including an optical mask and acquires the fundus image data obtained by imaging by the ophthalmic imaging apparatus. The image processing apparatus according to any one of the above.   A program that causes a computer to function as each unit of the image processing apparatus according to any one of claims 1 to 13. An image processing apparatus according to any one of claims 1 to 12, an ophthalmologic photographing apparatus that is communicably connected to the image processing apparatus and includes an optical mask,
An image processing system comprising: Extracting a mask region from the fundus image data based on brightness in the fundus image data including the mask region;
Determining the effectiveness of the extracted mask region based on the state of the extracted mask region;
Executing the image processing on the fundus image data based on the extracted mask area when it is determined that the extracted mask area is valid;
An image processing method comprising: Determining the effectiveness of extracting the mask region from the fundus image data based on the brightness of the fundus image data including the mask region;
If it is determined that extracting a mask area from the fundus image data is effective, extracting a mask area from the fundus image data based on brightness of the fundus image data;
Performing image processing on the fundus image data based on the extracted mask region;
An image processing method comprising:   A program for causing a computer to execute each step of the image processing method according to claim 16 or 17.

Images