JP2008237839A - Image analysis system and image analysis program - Google Patents

Abstract

Image analysis capable of accurately calculating the depth in the optic disc region and the optic disc depression region of a fundus image that can be expressed three-dimensionally without being blocked by a plurality of blood vessels running on the fundus The issue is to provide a system.
An image analysis system 1 targets a fundus including an optic disc area and an optic disc depression area, and uses a depth information 11 included in the acquired fundus image data 6 to obtain a depth profile curve. By calculating and assuming that the optic papilla region exhibits a smooth curved surface, the optic papilla depression region is accurately determined, and an accurate value of the C / D ratio is provided to an ophthalmologist, etc. Mainly constituted by an image analysis computer 2 capable of providing useful information for diagnosis of system diseases.
[Selection] Figure 1

Description

  The present invention relates to an image analysis system and an image analysis program, and more particularly to an image analysis system and an image analysis program that can provide doctors with information useful for diagnosis of ophthalmic diseases such as glaucoma. .

  Conventionally, the eyeball is irradiated with light from the outside, and the state of the fundus is observed through the eyeball. In addition, a fundus photograph obtained by imaging the state of the fundus using an optical device such as a camera is left as a medical record. By examining this fundus photograph in detail, a doctor can make a diagnosis of various diseases. Here, observation of the fundus is not generally imposed on a subject (patient) and can be obtained by a device with a relatively simple configuration, and thus is generally performed in a medical institution. It is one of the inspection methods.

  In addition, blood vessels taken by fundus photography are a part of the cerebral blood vessels in the brain located in the back of the eyeball, and are the only method that can directly observe the inside of the brain from outside the body. Therefore, very useful information can be provided to doctors and the like. In addition, this fundus photograph is used not only for diagnosis of ophthalmic diseases such as glaucoma but also for diagnosis of lifestyle-related diseases such as diabetes.

  Here, in the fundus photograph of a healthy subject, the entire fundus is yellowish reddish brown, and is a circle or oval of 1.2 mm to 1.7 mm at a position about 15 degrees outward (ear side direction) of the subject's line of sight. An optic nerve head is observed. This optic nerve head is anatomically called an optic disc, and the boundary between the fundus portion and the optic nerve head is more clearly observed on the ear side than on the nose side. Is. In the vicinity of the center of the optic nerve head, an area called a optic nerve crevice or a physiologic cup having a circular shape is observed.

  When diagnosing glaucoma using fundus photographs, as one of the criteria for diagnosis, the ratio of the diameters of the optic nerve head and the optic nerve crevice (depression) described above, that is, the substantially circular optic nerve. The value of the diameter ratio (hereinafter referred to as “C / D ratio”) of the optic disc depression (C: Cup) to the nipple (D: Disc) is obtained. Among the C / D ratios, the C / D ratio in the vertical direction (vertical C / D ratio) is particularly useful for determining the presence or absence of glaucomatous changes. As one criterion, the vertical C / D ratio is 0.7. Glaucoma is suspected in the above cases or when the difference in the vertical C / D ratio between the right and left fundus is 0.2 or more. Diagnosis of glaucoma is not made only by the value of the C / D ratio, but is made in combination by other examinations, doctor's findings, etc. The value of the C / D ratio is determined by the diagnosis. This value is not one of the most useful information for glaucoma.

  Here, the structure of the fundus will be described in more detail. The fundus, which is a part of the eyeball, is three-dimensionally configured with a three-dimensional curved surface (spherical surface). However, the above-described fundus photograph is actually configured by converting it into a two-dimensional (planar) form even if it has a three-dimensional structure. Therefore, when diagnosing various diseases using the fundus photograph, the two-dimensional fundus photograph is imaged as a three-dimensional image in the head, and based on that, the optic disc depression is identified. There was a case to judge expansion. Therefore, there is a possibility that an ophthalmologist who has little diagnostic experience cannot make an accurate diagnosis. Therefore, attempts have been made to add three-dimensional information and increase the accuracy of the C / D ratio to enable accurate diagnosis.

  For example, three-dimensional data can be obtained by performing a stereo matching process by calculating and analyzing a pair of left and right stereo image data photographed by a stereo fundus camera and correcting by distortion such as parallax, imaging magnification, and aberration. Then, based on the obtained three-dimensional data, a fundus stereoscopic image analysis method and apparatus for designating a region of the optic nerve head are proposed. Here, each photographed fundus image includes a plurality of blood vessels that travel along a curved surface of the fundus and are partially crossed. Therefore, it is known that the presence of this blood vessel becomes a factor that hinders accuracy in constructing a fundus stereoscopic image by performing the above stereo matching processing or the like. That is, it is known that this blood vessel may blur the boundary between the optic disc area and the optic disc depression area, and the accuracy of calculating the C / D ratio used for glaucoma diagnosis may be significantly reduced.

  In view of this, a technique has been developed that removes the blood vessel portion included in the fundus image by image processing, interpolates the missing portion after removal based on the surrounding data, and thereby obtains three-dimensional information of the fundus. (For example, refer to Patent Document 1).

JP-A-4-276232

  However, in the above-described fundus image, a plurality of blood vessels (blood vessel portions) travels in a complicated manner, and it is relatively difficult to recognize and remove the blood vessel portions. Furthermore, the fact that the blood vessel part is agglomerated may cause the accuracy of the three-dimensional information of the fundus obtained by the interpolation to be significantly reduced because the distance from the surrounding data used for the interpolation is too far. there were.

  Therefore, in view of the above circumstances, the present invention particularly calculates the depth in the optic disc recessed region of the fundus image that can be expressed in three dimensions without being blocked by a plurality of blood vessels running on the fundus. It is an object of the present invention to provide an image analysis system and an image analysis program that can be used.

  In order to solve the above-described problems, the image analysis system of the present invention uses an image analysis computer to obtain depth information calculated from image data obtained by photographing a subject having a concave or convex shape that changes in a curve. An image analysis system for correcting, wherein the image analysis computer primarily calculates the depth of the imaging target based on information data acquisition means for acquiring the depth information from the image data and the acquired depth information. A profile curve calculating means for calculating a depth profile curve expressed by an original distribution, and a peculiarity in which a change rate of the depth profile curve is predicted to be large by using a difference in pixel value from the acquired image data A specific region specifying means for specifying a region, and a change in the depth profile curve surrounding the depth profile curve corresponding to the specified specific region And the curve correction means for correcting, based on the basis of the corrected said depth profile curve is composed mainly comprises a "and depth information correcting means for correcting the depth information of the imaging target.

  Here, the image data is a concave or convex imaging object that changes in a curved shape, for example, a part of the eyeball that has a substantially spherical shape, and a fundus image obtained by imaging a fundus curved in a concave shape is used as electronic data. The acquired depth information is information that can display the curved state of the fundus as a numerical value. Three-dimensional position information is given to the depth information acquired from the image data. Based on this depth information, a three-dimensional fundus image that displays the fundus in three dimensions can be constructed.

  In addition, as what acquires depth information from image data, such as a fundus image, it is possible to use a well-known technique, for example, using an imaging device such as a stereo fundus camera capable of stereoscopic shooting, Based on this, parallax is obtained from image data including depth information, or from two two-dimensionally displayed fundus images obtained by shifting the photographing position for photographing the fundus. In this example, the three-dimensional structure of the eyeball is constructed and acquired as a three-dimensional fundus image.

  The information data acquisition means refers to a means for reading the image data stored in advance in a storage means (hard disk drive or the like) built in the image analysis computer as appropriate by operating a keyboard or the like, or a storage medium such as a CD-R. And the like that read the image data stored in the network or those that acquire the image data via a communication network. That is, any data can be used as long as data stored in a format that can be analyzed by the image analysis computer can be read as appropriate. Furthermore, it is also possible to combine the above-described stereo fundus camera and the image analysis system of the present invention, and use the image data including the captured depth information as it is for the analysis processing.

  Further, the profile curve calculation means calculates a depth profile curve that can display the depth of the imaging target in a one-dimensional distribution based on depth information included in the acquired image data. For example, when the imaging target is the fundus, assume a virtual component (approximately equivalent to the diameter of the optic disc region) that passes through the approximate center of the fundus (corresponding to the optic disc region) and place this on the horizontal axis. The value corresponding to the depth of the fundus is sequentially plotted on the vertical axis. As a result, a curvilinear change with respect to the depth direction of the fundus can be indicated by the depth profile curve.

  On the other hand, the singular region specifying means specifies a region that is empirically predicted from the image data including depth information that the rate of change of the depth profile curve is significant, and includes, for example, a fundus image. This is for specifying a blood vessel region or the like that is darker than the surroundings as a specific region. That is, when the imaging target is the fundus, the above depth profile curve theoretically changes smoothly from the periphery of the fundus to the central optic disc depression area, and the gradient change with respect to the depth direction changes significantly. There is no. However, as described above, it is empirically known that when the image data includes a blood vessel region, imaging noise, and the like, the rate of change of the gradient changes rapidly before and after that. Therefore, it becomes easy to correct the depth information by specifying a portion having a possibility that the change of the change rate becomes large as the singular region.

  Therefore, according to the image analysis system of the present invention, the depth profile curve of the imaging target is obtained based on the depth information, and the depth profile curve corresponding to the specific region identified from the calculated depth profile curve is obtained. Correction is performed based on the change in the surrounding depth profile curve, and depth information can be corrected by the corrected depth profile curve. As a result, it is possible to virtually remove a fundus having a smooth curve change by removing a part that becomes an obstacle in constructing a three-dimensional image such as a blood vessel region in the fundus image. As a result, the depth information is corrected, and it is possible to obtain highly accurate three-dimensional image information using the depth information. This makes it possible to provide a diagnostic technique that is particularly useful for diagnosing glaucoma. Here, the curve includes a linear curve, that is, a “straight line”.

  Further, the image analysis system according to the present invention may include, in addition to the above configuration, “the image analysis computer deletes the specific region profile curve corresponding to the specified specific region from the calculated depth profile curve. Further comprising an erasing unit, wherein the curve correcting unit calculates a correction profile curve that substantially matches a rate of change of the depth profile curve remaining after the singular region profile curve is erased, and the depth information correcting unit May correct the depth information of the object to be imaged based on the calculated correction profile curve.

  Here, the singular region erasing means is the position of the depth profile curve corresponding to the end of the specified singular region, that is, the range indicated by the singular region on the imaginary line segment on the horizontal axis (singular region profile Curve) is specified and the curve is deleted. As a result, since the singular region profile curve is removed from the depth profile curve that is one-dimensionally represented by one curve, the remaining depth profile curve is divided into a plurality of lines in such a state. Will be displayed. Correction of the correction profile curve by the curve correction means may be performed by correcting the correction profile curve of the singular region portion, or by correcting the correction profile curve of the singular region portion and interpolating between them. Any method may be used.

  Furthermore, the curve correction means in the present invention calculates a correction profile curve that corrects the deleted specific region profile curve based on the remaining depth profile curve that is divided into a plurality of lines. The calculation of the curve is, for example, to calculate a curve that connects the ends of the divided depth profile curves adjacent to each other. At this time, the correction profile curve is calculated such that the ends are connected with a smooth curve based on the change rate of the two depth profile curves to be connected. As a result, the depth profile curve divided by the correction profile curve is again one-dimensionally expressed by a smooth curve. Based on the result, the depth information of the imaging target is corrected.

  Furthermore, in addition to the above configuration, the image analysis system of the present invention may include “the curve correction unit includes a spline curve calculation unit that calculates a spline curve as the correction profile curve”.

  Therefore, according to the image analysis system of the present invention, the correction profile curve is calculated as a spline curve. Here, the spline curve changes in a curve connecting two points (corresponding to the end of the depth profile curve), and a method for obtaining the spline curve is already well known. Therefore, the spline curve formed as the correction profile curve can be approximately approximated to the curve change rate of the depth profile curve before and after the correction profile curve. As a result, for example, when the fundus is the imaging target, it is possible to perform correction with a correction profile curve that substantially matches the curve change rate of the fundus, and the accuracy of the obtained depth information is improved.

  Furthermore, the image analysis system of the present invention has the above-described configuration, in which “the image data is a fundus image capturing device, and a fundus image acquired using the optic disc depression region as the imaging target is used. The specifying means may specify a plurality of blood vessel regions that run in the optic disc recessed region of the fundus image as the specific regions.

  Therefore, according to the image analysis system of the present invention, it is possible to select an optic disc recessed region that is a part of the fundus as a photographing target, correct depth information for the region of the fundus image, and increase its accuracy. It becomes. As a result, there is no error in depth information due to multiple blood vessels running in the optic disc concavity region of the fundus, and by using the corrected depth information, the three-dimensional of the optic disc concavity region of the fundus It is possible to construct an image with high accuracy. Thereby, the calculation accuracy of the C / D ratio that can be used for diagnosis of glaucoma and the like is improved, and it is possible to provide useful information for diagnosis by a doctor or the like.

  On the other hand, according to the image analysis program of the present invention, “information data acquisition means for acquiring depth information from image data obtained by photographing a concave or convex imaging object that changes in a curve, the acquired depth information Based on the profile curve calculating means for calculating a depth profile curve expressing the depth of the object to be photographed in a one-dimensional distribution, using the difference in pixel value from the acquired image data, the depth profile curve Specific region specifying means for specifying a specific region that is predicted to have a large rate of change, and curve correction for correcting the depth profile curve corresponding to the specified specific region based on a change in the surrounding depth profile curve Image analysis as depth information correction means for correcting the depth information of the object to be imaged based on the corrected depth profile curve A singular region erasing means for erasing a singular region profile curve corresponding to the specified singular region from the calculated depth profile curve, and the singular region profile curve. The correction information curve that substantially matches the rate of change of the depth profile curve that remains after being erased, and the depth information of the object to be imaged based on the calculated correction profile curve The image analysis computer may further function as the depth information correction means for correcting the image.

  Therefore, by executing the image analysis program of the present invention, it is possible to cause the image analysis computer to exhibit the above-described excellent operational effects.

  As an effect of the present invention, a one-dimensional depth profile curve is calculated from image data including depth information, and the profile curve corresponding to a specific region such as a blood vessel region is removed using the depth profile curve. The depth profile curve can be corrected according to the surrounding situation. Thereby, it is possible to obtain an image with high accuracy in the depth direction by constructing a three-dimensional image using image data including corrected depth information.

  In particular, by selecting the imaging target as the optic disc concavity region of the fundus, a correction profile curve that approximates the actual fundus curve change rate can be calculated, and the accuracy is improved.

  Hereinafter, an image analysis system 1 and an image analysis program according to an embodiment of the present invention will be described with reference to FIGS. Here, FIG. 1 is a block diagram showing a functional configuration of the image analysis computer 2 in the image analysis system 1 of the present embodiment, and FIG. 2 images the fundus 5 including the optic disc area 3 and the optic disc depression area 4. 3 is a fundus photograph showing an example of the fundus image data 6, and FIG. 3A is a schematic diagram showing a cross section of the extraction region 24 including the optic disc region 3 and the optic disc depression region 4, and FIG. 3B is the extraction region. FIG. 4 is a curve diagram showing an example of 24 depth profile curves 7a. FIG. 4A is a schematic diagram showing a cross section of the extraction region 24 including the optic disc region 3 and the optic disc depression region 4, and FIG. FIG. 5 is a curve diagram showing an example of the singular region profile curve 9 corresponding to the region 8, FIG. 5 is a curve diagram showing (a) a depth profile curve 7b from which the singular region profile curve 9 is removed, and (b) a correction profile. FIG. 6 is a flowchart showing the depth profile curve 7c connected by the il curve 10, and FIG. 6 is a flowchart showing the processing flow of the image analysis computer 2 that performs the correction processing of the depth information 11. FIG. FIG. 6 is a curve diagram showing another example of correction of the depth profile curve 7a, and FIG. 5B is a curve diagram showing a corrected depth profile curve 7d. Here, in the following specification, the depth profile curves 7a, 7b, 7c, 7d are “depth curves 7a, 7b, 7c, 7d”, the specific region profile curve 9 is “singular curve 9”, and The correction profile curve 10 is referred to as “correction curve 10”.

  As shown in FIGS. 1 to 6, the image analysis system 1 according to the present embodiment targets the fundus 5 including the imaged optic papilla region 3 and the optic papular depression region 4 and is imaged. By correcting the depth information 11 included in the fundus image data 6 of the fundus photograph assuming that the fundus 5 has a smooth concave curved surface, a cupline indicating the outline of the optic disc recessed region 4 is obtained. It is possible to determine accurately and provide an ophthalmologist with an accurate value of the ratio (C / D ratio) of the optic disc depression region 4 / optic disc region 3 to support diagnosis of ophthalmic diseases such as glaucoma. Mainly constituted by a simple image analysis computer 2.

  Note that the image analysis computer 2 can use a general-purpose personal computer, and can acquire the fundus image data 6 having depth information 11 for photographing the fundus and displaying it in three dimensions. A camera 12, a liquid crystal display 13 for displaying the results of various processes and analysis results based on the acquired fundus image data 6, a keyboard and a mouse for receiving input of various commands and data to the image analysis computer 2, and the like ( And an operation input device 14 (not shown). Various data and information acquired or created by the stereo fundus camera 12 or the like are stored in the data storage unit 15 built in the image analysis computer 2. The data stored in an external storage device (for example, HDD or the like: not shown) connected to the image analysis computer 2 is read at any time, or is read into a data server (not shown) connected to the network. You may accumulate | store and acquire this by reading through the internet.

  Here, the functional configuration of the image analysis computer 2 will be described. As mainly shown in FIG. 1, the data storage means 15 that is photographed by the stereo fundus camera 12 and stores the fundus image data 6 including the depth information 11 is stored. Information data acquisition means 16 that reads the stored fundus image data 6 from the data storage means 15 and acquires depth information 11 relating to the depth direction of the fundus image 5 that is the photographing target of the fundus image data 6 and the fundus image data 6; Based on the acquired depth information 11, the profile curve calculation means 17 for calculating the depth curve 7 a expressing the depth of the fundus 5 in a one-dimensional distribution, and the difference in pixel value from the acquired fundus image data 6 Is used to identify the singular region 8 for identifying the singular region 8 where the rate of change of the depth curve 7a is predicted to be large, and from the calculated depth curve 7a The singular region erasing means 19 for erasing the portion of the singular curve 9 corresponding to the singular region 8 and the spline curve that substantially matches the rate of change of the depth curve 7b remaining after the singular curve 9 is erased. The curve correction unit 20 having the spline curve calculation unit 23 for calculating the correction curve 10 and the depth curve 7b are corrected based on the calculated correction curve 10, and based on the depth curve 7c acquired as a result of the correction. It mainly comprises a depth information correction means 21 for correcting the depth information 11 of the fundus image data 6. Here, the specific region 8 of the fundus image data 6 mainly corresponds to a blood vessel region that travels along the fundus 5, and the fundus image data 6 of the present embodiment corresponds to the image data of the present invention.

  Further, as another configuration of the image analysis computer 2, signal control for displaying the acquired fundus image data 6 and the calculated depth curve 7a on the display means such as the liquid crystal display 13 so as to be recognized through vision is performed. The operation control means 26 accepts a signal sent from the operation input device 14 which is operated to input data or the like to the display control means 25 and the image analysis computer 2 or to input an instruction relating to the analysis processing. It has a configuration. In addition, the extraction area data 32 related to the extraction area 24 extracted including the optic disc recessed area 4 and the specific area data 27 related to the specified specific area 8 are stored in the data storage means 15. Further, the depth curve data 29 related to the depth curve 7a and the like calculated by the profile curve calculating means 17, the singular curve data 30 related to the singular curve 9 of the singular area 8 specified by the singular area specifying means 18, and the curve correction The correction curve data 31 of the correction curve 10 calculated by the means 20 is stored and stored together in the profile data 28 in the data storage means 15. Note that the data 32 and the like are appropriately stored in each step of the flowchart of FIG. 6 shown below, and the description regarding the storage / save processing is omitted unless otherwise specified. Further, the progress in each process shown in FIGS. 3 to 5 can be appropriately displayed through the display control means 25 or the like.

  Next, the details of the image analysis system 1 of the present embodiment will be described with reference to the flowchart of FIG. It is assumed that the image analysis computer 2 has already acquired fundus image data 6 to be analyzed including depth information 11 related to the fundus 5 and has stored it in the data storage unit 15. Here, Steps S1 to S9 in FIG. 6 correspond to the image analysis program of the present invention.

  First, fundus image data 6 to be analyzed is read from the data storage means 15 and acquired (see step S1, FIG. 2). Corresponding to the optic papilla region 3 corresponding to the optic papilla from the surrounding fundus region 22 and the optic papilla recess located inside thereof using the difference in pixel value of each pixel constituting the image from the read fundus image data 6 The optic disc recessed area 4 to be extracted is extracted (step S2). Here, the extraction process of the extraction area 24 including the optic disc area 3 and the optic disc depression area 4 is performed by using a well-known image processing technique. It is assumed that the information data acquisition means 20 includes the extraction function. Thereafter, the depth curve 7a in the extraction region 24 including the extracted optic disc region 3 and the optic disc depression region 4 is calculated based on the depth information 11 included in the fundus image data 6 (step S3).

  More specifically, a virtual line segment L (see FIG. 2) corresponding to the diameter of the substantially circular optic nerve head region 3 is arranged on the horizontal axis, and the depth value of each point on the virtual line segment L is expressed as follows. Plot on the vertical axis based on the depth information 11. Then, by connecting the plotted points, a depth curve 7a expressing the depth of the extraction region 24 in a one-dimensional manner is calculated (see FIG. 3B). Here, FIG. 3A is a schematic cross-sectional view of the extraction region 24 viewed from the side. In this case, as shown in FIGS. 3A and 3B, a blood vessel region as the specific region 8 is confirmed so as to overlap the optic disc region 3 and the optic disc depression region 4. is there. Therefore, the calculated depth curve 7a has a portion where the gradient change of the curve changes remarkably (see FIG. 3B). Here, the above-described extraction region 24 including the optic disc region 3 and the optic disc recess region 4 of the fundus 5 is configured to be curved in a smooth concave shape. Therefore, the depth curve 7a calculated as a one-dimensional distribution should theoretically be expressed as a smooth concave curve. That is, a part where the gradient change as described above changes remarkably or the slope of the gradient changes in the reverse direction (for example, the direction in which the concave part protrudes) is a specific part.

  Therefore, the position of the singular region 8 in the fundus image data 6 is specified (step S4: FIG. 4A). Specifically, the singular region 8 such as a blood vessel region is generally shown in a darker color than the surrounding optic papilla region 3 and optic papilla depression region 4 in general. Therefore, the specific region 8 is specified using the difference in pixel value from each region 22 or the like.

  Thereafter, the singular curve 9 on the depth curve 7a corresponding to the identified singular region 8 is deleted (step S5). Here, the singular curve 9 corresponds to the range of the depth curve 7a corresponding between the left end LP and the right end RP of the specified singular region 8, as shown in FIGS. 4 (a) and 4 (b). . Therefore, the range of the singular curve 9 is determined as indicated by the broken line between FIGS. 4 (a) and 4 (b). Thereby, the depth curve 7b is divided into at least two or more curves (see FIG. 4B and FIG. 5A). Next, a correction curve 10 is obtained which connects the respective end portions P1 and P2 of the divided depth curve 7b and substantially matches the curve change of the depth curve 7b remaining on the fundus 5 (step S6). Here, the correction curve 10 is a curve (spline curve) passing through two points, one end P1 of one depth curve 7b and the other end P2 of the other depth curve 7b, and a known spline curve technique is obtained. Is calculated by Thereby, the divided depth curve 7b is connected to each other, and a smooth correction curve 10 that changes in accordance with the curve change rate of the depth curve 7b is obtained.

  Then, using the obtained correction curve 10, the divided depth curve 7b is connected, and the depth curve 7c showing a smooth gradient change indicated by a single curve is reconstructed (step S7). ). Then, the depth information 11 included in the fundus image data 6 is corrected according to the value of “depth” on the vertical axis indicated by the constructed depth curve 7c. As a result, by using the depth information 11 of the fundus image data 6 and the singular region 8 specified by the difference in pixel value, the depth approximated to the shape of the actual fundus 5 curved in a theoretically smooth concave shape. Information (corrected depth information 33) is obtained. In FIG. 1, for simplicity of description, the original depth information 11 and the corrected depth information 33 are illustrated so as to coexist. The contents are overwritten and saved in new corrected depth information 33 after correction, and are completely replaced. Therefore, the fundus image data 6 is processed so that there is always only one depth information 11.

  Then, based on the obtained depth information 11, the optic disc recessed region 4 is specified, and using this, the ratio of the optic disc recessed region 4 (Cup) / optic disc region 3 (Disc) (C / D Ratio) is calculated (step S9). The diameter length of the optic nerve head region 3 can be calculated using a known technique and using a difference in pixel value, and thus a detailed description thereof is omitted here.

  Thereby, useful information for diagnosing diseases such as glaucoma can be provided to doctors and the like. In particular, since the above-mentioned C / D ratio can be obtained by deleting the specific region 8 such as a blood vessel region existing so as to overlap the optic disc region 3 and the optic disc depression region 4, the calculation accuracy is remarkably improved. . As a result, the accuracy of diagnosis by a doctor or the like is also improved. Further, by using the corrected depth information 11 (corrected depth information 33), even when the fundus image data 6 is displayed in a three-dimensional manner, the difference between the actual fundus 5 and the obtained stereoscopic image is displayed. Increases accuracy.

  The present invention has been described with reference to preferred embodiments. However, the present invention is not limited to these embodiments, and various modifications can be made without departing from the spirit of the present invention as described below. And design changes are possible.

  That is, in the image analysis system 1 of the present embodiment, the vascular region is mainly assumed as the singular region 8, but the present invention is not limited to this, and shadows at the time of photographing included in the fundus image data 6 are not limited thereto. A thing that reduces the accuracy of C / D ratio calculation such as noise may be recognized as the singular region 8. In addition, although one virtual line segment L set on the horizontal axis has been described, of course, the present invention is not limited to this. For example, the position of the approximate center of the optic disc recessed region 4 is used as a reference position. The virtual line segment L may be changed by a predetermined angle (for example, by 1 degree) and the depth curve 7a at each angle may be corrected. Thereby, it becomes possible to correct the depth information 11 for the entire region of the fundus image data 6 obtained by photographing the fundus to be photographed, and the accuracy of calculating the C / D ratio can be further increased.

  Further, as an example of the curve correction means 20 for correcting the depth curve 7a, a conventionally known spline curve is used. However, the present invention is not limited to this, and other techniques for correcting the depth curve 7a are available. It doesn't matter. For example, in the calculated depth curve 7a, when there is a portion where the gradient change changes significantly or the gradient gradient changes in the opposite direction (for example, the direction in which the concave part protrudes), As shown in FIG. 7A, a line segment is extended in a substantially horizontal direction from the starting point X of the gradient change on the depth curve 7a, and an end point Y of the gradient change that intersects the depth curve 7a is specified. And you may correct | amend the depth curve 7a with the line segment Q (namely, straight line) which consists of a linear curve connected with this start point X and the end point Y. FIG. That is, as shown in FIG. 7B, the corrected depth curve 7d may partially change in a step shape. Thereby, compared with what calculates a spline curve as mentioned above, the process which concerns on curve correction can be simplified.

  Further, as an example of the elimination of the singular curve 9 from the depth curve 7a (see FIG. 3B), the singular region 8 has been described as an example, but the present invention is not limited to this. 3 and the optic disc recessed area 4 may include a plurality of specific areas 9 that are deleted from the corresponding specific curve 9 from the depth curve 7a, and the correction curve 10 may be calculated. In this case, the single depth curve 7 a is divided into a plurality of lines according to the number of singular regions 8.

  Moreover, although the thing which mainly assumed the fundus 5 was shown as the object for correcting the depth information 11, it is not limited to this, and mountains and the like are three-dimensionally displayed based on aerial photographs taken from an airplane. It can also be used in accordance with various situations such as when creating a three-dimensional map.

It is a block diagram which shows the functional structure of the image analysis computer in the image analysis system of this embodiment shape object. It is a fundus photograph showing an example of fundus image data 6 obtained by photographing the fundus including the optic disc area and the optic disc depression area. (A) The schematic diagram which shows typically the cross section of the extraction area | region containing an optic disc area | region and an optic disc concavity area | region, (b) It is a curve figure which shows an example of the depth profile curve of the said extraction area | region. (A) The schematic diagram which shows typically the cross section of the extraction area | region containing an optic disc area | region and an optic disc concavity area | region, (b) It is a curve figure which shows an example of the specific area profile curve corresponding to a specific area. (A) Curve diagram showing depth profile curve from which singular region profile curve is removed, (b) Curve diagram showing depth profile curve connected by correction profile curve. It is a flowchart which shows the flow of a process of the image analysis computer 2 which performs the correction process of depth information. (A) Curve diagram showing another example of correction of depth profile curve, (b) Curve diagram showing corrected depth profile curve.

Explanation of symbols

DESCRIPTION OF SYMBOLS 1 Image analysis system 2 Image analysis computer 4 Optic disc dent area 5 Fundus (photographing object)
6 Fundus image data (image data)
7a, 7b, 7c, 7d Depth curve (depth profile curve)
8 Singular region 9 Singular curve (Singular region profile curve)
10 Correction curve (correction profile curve)
DESCRIPTION OF SYMBOLS 11 Depth information 16 Information data acquisition means 17 Profile curve calculation means 18 Singular area specification means 19 Singular area elimination means 20 Curve correction means 21 Depth information correction means 23 Spline curve calculation means

Claims (6)

An image analysis system that uses an image analysis computer to correct depth information calculated from image data obtained by imaging a concave or convex imaging object that changes in a curve,
The image analysis computer
Information data acquisition means for acquiring the depth information from the image data;
Profile curve calculation means for calculating a depth profile curve expressing the depth of the imaging target in a one-dimensional distribution based on the acquired depth information;
Using a difference in pixel value from the acquired image data, a specific region specifying means for specifying a specific region that is predicted to have a large rate of change in the depth profile curve,
Curve correcting means for correcting the depth profile curve corresponding to the specified singular region based on a change in the surrounding depth profile curve;
An image analysis system comprising: depth information correction means for correcting the depth information of the object to be imaged based on the corrected depth profile curve. The image analysis computer
A singular region erasing means for erasing a singular region profile curve corresponding to the identified singular region from the calculated depth profile curve;
The curve correcting means includes
Calculating a correction profile curve that substantially matches the rate of change of the depth profile curve remaining after the singular region profile curve is erased;
The depth information correcting means includes
The image analysis system according to claim 1, wherein the depth information of the imaging target is corrected based on the calculated correction profile curve. The curve correcting means includes
The image analysis system according to claim 2, further comprising spline curve calculation means for calculating a spline curve as the correction profile curve. The image data is
Using a fundus image capturing device, a fundus image acquired using the optic disc depression area as the imaging target is used,
The specific region specifying means includes
4. The image analysis system according to claim 1, wherein a plurality of blood vessel regions that run in the optic disc concavity region of the fundus image are specified as the specific regions. 5.   Information data acquisition means for acquiring depth information from the image data obtained by imaging a concave or convex imaging target that changes in a curve, and based on the acquired depth information, the depth of the imaging target is one-dimensional. A profile curve calculation means for calculating a depth profile curve expressed by a typical distribution, and using a difference in pixel value from the acquired image data, a singular region predicted to have a large rate of change of the depth profile curve Specific region specifying means for specifying, specific region deleting means for deleting a specific region profile curve corresponding to the specified specific region from the calculated depth profile curve, and the depth corresponding to the specified specific region Curve correction means for correcting a profile curve based on a change in the surrounding depth profile curve, and the corrected depth profile Based on the line, as the depth information correcting means for correcting the depth information of the photographed object, the image analysis program for causing to function image analysis computer.   Singular region erasing means for erasing the singular region profile curve corresponding to the specified singular region from the calculated depth profile curve, a change in the depth profile curve remaining after the singular region profile curve is erased The image analysis unit as the curve correction unit that calculates a correction profile curve that substantially matches a rate, and the depth information correction unit that corrects the depth information of the imaging target based on the calculated correction profile curve. The image analysis program according to claim 5, further causing a computer to function.

Images