JP2863945B2 - Visual field measuring device - Google Patents

Description

Description: BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a visual field measuring device for measuring a range of a visual field of a human eye, and in particular, to a visual field abnormal pattern estimating unit using a multilayer neural network. And an inference unit that infers a comprehensive visual field abnormal pattern from test data such as abnormal visual field patterns, intraocular pressure, fundus findings, eye refractive index, medical history, etc. Field of the Invention The present invention relates to a perimeter measuring device that can perform measurement. Further, the present invention relates to a visual field measuring device capable of automatically determining an additional target.

"Prior art" Perimetry is considered to be extremely important in ophthalmic clinical examinations, and is used for diagnosis of glaucoma, retinal detachment, brain disorder, hysteresis, and the like.

The field of view is "the area where you can look at one point and see with one eye"
However, since the sensitivity of the retina is not constant even within the range of the visual field, the visual field is accurately referred to as “visual sensitivity distribution”. The perimeter used for this clinical examination includes a dynamic quantitative perimeter and a static quantitative perimeter.

A line connecting the points of equal sensitivity in each part of the retina is called an isosensitivity line isopter, and optotypes of various luminances and sizes are moved from the periphery to the center, and the first time the optotype is confirmed (or disappeared) The isopter can be obtained by obtaining a figure in which the points of (h) are connected. By appropriately selecting this isopter, what obtains a visual field table is a dynamic quantitative visual field.For example, a target is presented at various brightness on a semi-circular screen, and the subject is displayed at each position. The Goldman perimeter shows the brightness (threshold) that starts to be felt and displays this in a diagram or the like. By using this figure, the measurer judged an abnormality in the visual field of the subject (a site with low sensitivity).

Static quantitative perimetry measures the sensitivity of the retina as the reciprocal of the luminance when the target is recognized for the first time after fixing the position of the visual field and increasing the luminance.

These perimeters include two types: manual and automatic.
There was kind.

However, in both the manual-type perimeter and the automatic perimeter, in order to accurately judge anomalies in the visual field, it is necessary for the measurer to sufficiently grasp various patterns of visual field abnormalities. Experience and attention are required, and there is a problem that the burden on the measurer is extremely large.

In view of this problem, the present applicant has proposed a visual field measuring apparatus that employs a multilayer neural network and includes an analogy section that analogizes a pattern of abnormal visual field of a subject from an output of the multilayer neural network. This visual field measuring device can reduce the burden on the measurer and the subject by supporting the measurer's diagnosis.

[Problem to be Solved by the Invention] However, since the above-mentioned visual field measuring device is configured to set an abnormal pattern of a specific visual field and to recognize the abnormal pattern and the measurement result of the subject, Exceptional diseases that do not depend on abnormal patterns, initial diseases that show only weak feature patterns, diseases that cannot be determined without combining with other data, and cannot be determined without comparing the visual field patterns of the left and right eyes There was a problem that it could not cope with various diseases.

Therefore, the emergence of a visual field measurement device that can reduce the burden on the subject and the subject by supporting the diagnosis of the subject by comprehensively inferring the left and right visual field abnormal patterns of the subject and other data. Was desired.

“Means for Solving the Problems” The present invention has been devised in view of the above problems, and has an index presenting unit that presents a measurement index, and a response that responds as to whether or not the subject has recognized the presented index. And a neural network having an input layer, a hidden layer, and an output layer, and having a neural weight previously determined based on a typical response when the subject's visual field is abnormal and a normal response. And an analogy unit for inputting a response from the response unit to the input layer of the multilayer neural network, and analogizing an abnormal pattern of the visual field of the subject from an output of the output layer at that time, and examination data other than the visual field measurement data. An inference unit that infers a comprehensive visual field abnormal pattern using the left and right visual field abnormal patterns analogized by the analog inference unit and the inspection data, and a visual field abnormality inferred by the inference unit. Additional indices depending on the pattern And determine
An additional target unit to be presented to the target presenting unit is provided.

In the present invention, the test data may be any one of intraocular pressure, fundus findings, and medical history.

[Operation] In the present invention configured as described above, the index presenting unit presents the measurement target, and the responding unit responds as to whether or not the subject has recognized the measurement index. A multilayer neural network comprising an input layer, a hidden layer and an output layer, is adapted to guide a nerve weight determined based on a response between a normal visual field and an abnormal visual field,
By inputting a response from the response unit to the input layer and sending an output from the output layer to the analogization unit, the analogization unit analogizes an abnormal pattern in the visual field of the subject. Further, the knowledge base stores inspection data other than the perimetry data. The inference unit can infer a comprehensive visual field abnormal pattern from the left and right visual field abnormal patterns analogized by the analog inference unit and the inspection data. Further, the additional optotype unit can determine an additional optotype in accordance with the abnormal visual field pattern inferred by the inference unit, and present the additional optotype to the optotype presenting unit.

Further, any one of the intraocular pressure, the fundus findings, and the medical history can be adopted as the inspection data other than the visual field measurement data, and a comprehensive visual field abnormal pattern can be inferred.

"Example" An example of the present invention will be described with reference to the drawings. 1 and 2 are views for explaining the mechanical configuration of the visual field measuring device 1, and the visual field measuring device 1 includes a visual field measuring device main body 100 and a gantry 200. The visual field measuring device main body 100 includes a housing 110, and the housing 110 is provided with a substantially hemispherical dome 120, and the inner surface of the dome 120 is a projection screen 130. A panel 140 is provided on the front part of the dome 120, and the panel 140 has a face receiving hole.
The face receiving hole 150 is provided with a face receiving member 160 for fixing the face. The forehead rest 170 and the chin rest 180 are attached to the face receiving member 160. The eye to be measured is a projection screen 130.
Is located in the vicinity of a substantially spherical center including the center of gravity O.

As shown in FIG. 2, the housing 110 is provided with a projection optical system 300 on the rear side of the dome 120. The projection optical system 300 includes an illumination light source 310, a condenser lens 320, and an index 330.
, A collimator lens 340, a projection lens 350, and reflection mirrors 360, 360. Where the illumination light source
The 310, the condenser lens 320, the target 330, and the collimator lens 340 constitute a first optical system for emitting the target light as a parallel light beam. The projection lens 350 and the reflection mirror 360
Together with the rotating mirror 400 described later, a second optical system is configured to guide the target projection light to the index presenting point I of the projection screen 130 through the vicinity of the sphere center excluding the sphere O by entering a parallel light beam. The dome 120 has a guide hole 121 formed therein. The target projection light reflected by the reflecting mirror 360 is guided to the rotating mirror 400 through the guide hole 121.

The rotating mirror 400 is provided in the vicinity of the spherical center excluding the spherical center O. When the rotating mirror 400 is rotated, the optotype presenting location I is changed.

Next, an electrical configuration of the visual field measuring device 1 of the present embodiment will be described with reference to FIG. The electric configuration of the visual field measuring device 1 includes a visual field projection control unit 2, a response switch 3, a BP (back propagation) execution unit 4, an optotype projection program storage unit 5, a response storage unit 6, It comprises a unit 7, a display unit 8, a CPU 9, and external data input means 10. The field-of-view projection control unit 2 is a mirror drive motor for projecting a target.
The control unit 21 controls the visual field focusing drive motor 22 and the index projecting light source 23, and corresponds to a target presenting unit. The target mirror rotating mirror drive motor 21 is a rotating mirror
The optotype presenting point I can be changed by rotating the rotating mirror 400. The optotype focusing drive motor 22 is for moving the imaging lens 350, and can change the distance L from the rotation center of the rotating mirror 400 to the optotype presenting position I. That is, when the rotating mirror 400 is rotated by driving the target mirror rotating mirror drive motor 21, the distance L from the rotation center of the rotating mirror 400 to the target presenting position I changes. In order to correct the change in the distance L, it is necessary to drive the optotype focusing drive motor 22 and move the imaging lens 350 in the optical axis direction. As a result, regardless of the change of the target presenting position I, an image of the target whose size and luminance hardly change can be displayed on the projection screen 130. The optotype projection light source 23 controls the lighting of the illumination light source 310, and can change the brightness (intensity) of the light source by adjusting the light source voltage as well as switching between lighting and extinguishing. And by adjusting the intensity of the illumination light source 310,
The luminance of the target on the projection screen 130 can be changed.

The response switch 3 corresponds to a response unit, and inputs whether or not the subject has recognized the target. It is desirable that the response switch 3 be operated by the person to be measured. However, when the person to be measured is a child or an elderly person, the measurer receives recognition from the person to be measured and is operated by the person to be measured. Good.

The BP execution unit 4 is for executing a determination by back propagation using a predetermined nerve weight based on a typical response when the visual field is abnormal and a normal response. Therefore, a typical response when the visual field is abnormal and the response of the subject are matched by the neural network, and an abnormal pattern of the visual field of the subject can be inferred.

The nerve weight used by the BP execution unit 4 is determined in advance based on a typical response and a normal response when the back propagation executes learning and the visual field is abnormal, as described below.

The optotype projection program storage section 5 stores a program for determining optotype presenting conditions for visual field measurement, and controls the luminance of the optotype, the position of the index, the lighting time, and the like to desired values. be able to. As the target projection program, for example, a screening measurement program, a meridional program, a glaucoma program, or the like can be adopted.

The response storage unit 6 is for storing whether or not the subject has recognized the optotype. That is, this is for storing whether or not the response switch 3 has been activated for the presented target. The operation unit 7 is for performing the entire operation of the visual field measurement device 1, and includes various control switches, a light pen, and the like. The display unit 8 includes a TV monitor, a printer, and the like.
It is possible to display the type and index distribution of the target projected on 0, a command input from a control switch or the like, and further, it is possible to display the result of the analogy of the abnormal pattern of the visual field of the measured person. .

The CPU 9 controls various arithmetic operations of the visual field measuring device 1. The CPU 9 also has a storage function, and also has a function of configuring a knowledge base from data input from the external data input unit 10.

The external data input means 10 is for inputting inspection data other than the visual field measurement data. The external data input means 10 may be a reading means such as an electronic medical record constituted by an IC card, a magnetic card, or the like, and a means manually input by a measurer such as a keyboard, a mouse, and a light pen. There may be. The external data input means 10 of this embodiment may be an interface for directly connecting to a tonometer or the like to transfer data. From the external data input means 10, data such as intraocular pressure, fundus findings, medical history and the like are input.

In this embodiment configured as described above, when a measurement start command is input through the operation unit 7, the CPU 9 reads the control program from the visual field projection program storage unit 5 and executes it. CPU9
Controls the target projection control unit 2 according to the control program to drive the index projection light source 23. Further, the position of the index is determined by controlling the drive motor 21 of the target target rotating mirror and rotating the rotating mirror 400. Further, the CPU 9 drives the optotype focusing motor 22 in accordance with the rotation of the rotating mirror 400, and adjusts the luminance and size of the optotype so as not to change. The response storage unit 6 stores the response of the subject. And CPU9
Performs matching with a typical abnormal pattern and a normal pattern in the visual field, and infers an abnormal pattern in the visual field. Then, the display unit 8 displays the inferred abnormal pattern of the visual field and the like.

Next, the configuration of the multilayer neural network constituting the neural network will be described in detail with reference to FIG.

A neural network is composed of a plurality of nerve cells (neurons). One neuron consists of a cell body, dendrites (signal input part), and axons (signal output part).
It is composed of The axon (signal output part) is synapse-coupled with dendrites of other neurons, forming a network.

The learning method applied to this neural network is called a back propagation method. The structure of the neural network is composed of an input layer A, an intermediate layer B, and an output layer C as shown in FIG. It has a multilayer structure. Although there is a connection between layers, there is no connection between units in the layer.

Since a neuron can be regarded as a multi-input / single-output nonlinear element, in other words, it can be regarded as an element having a “threshold action”. That is, the output pulse is turned on when the total amount of input signals is higher than the threshold, and the output is turned off when the total amount is less than the threshold.

Thus, the input signal _{S 1, S 2, S 3} , the output signal net against · · · S _n, the weighted sum of products It is described as follows. That is, the structure of the network can be changed by changing the weight (W).
The weight (W) takes positive, negative, and zero values, where zero indicates that there is no connection. The input / output characteristic function is sigmoi
d function is applied. This sigmoid function is a differentiable pseudo-linear function, for example, Can be adopted. The value range of this function is 0 to 1, becoming 1 as the input value increases, and becoming 0 as the input value decreases. And when the input value is 0, it is 0.
It is set to 5.

Next, the algorithm of the back propagation learning rule will be described. The intermediate layer B may be any number of layers, and assumes a network without feedback coupling (interlayer coupling). Here, the intermediate layer B may be called a (hidden layer), that is, a hidden layer.

(A) First, an input signal such as an image pattern is input to an input layer.

(B) Next, from the input layer A to the output layer C, the state change of each neuron accompanying the signal transmission process is sequentially calculated.

(C) The output of the j-th neuron of the output layer C obtained in (b) is _{defined as Opj} , the desired output (teacher signal) of the neuron with respect to the input signal is _{defined as Tpj,} and the square error of the following equation is evaluated. Define and operate as a function. The given image pattern is defined as p.

(D) changing the synaptic connections or weights of the network such that the cost function is at a local minimum (preferably a minimum) (ie, so that the actual output is as close as possible to the desired output).

That is, the strength of all the couplings may be changed so as to reduce the output error. Here, the change amount of the weight _Wji when the image pattern p is given is Is determined. If further _{modified, Δ p W ji = ηδ pj} O pi ... (5) In addition, O _pi is the input value from unit i to unit j, [delta] _pj the unit j is depends on whether the output unit or the intermediate unit , Δ _pj = (t _pj −op _p ) f ′ _j (net _pj ) (6) for the output unit, and Equation (7) is a recursive function.

The above is the basic algorithm of the back propagation method. Learning of each synaptic connection (correction of the weight) proceeds from the output layer to the input layer in the direction opposite to the signal propagation. This is why it is called back propagation. In this back propagation method, the calculation of ΔW is started from the output layer and proceeds to the unit of the intermediate layer. In the intermediate unit, the calculation cannot be performed unless the preceding stage ΔW is determined. Therefore, it is impossible to calculate without going back to the last input layer (because it is recursive). Therefore, in the back propagation method, learning data is input, and the result is output (forward). Next, the strength of the bond is changed (backward) to reduce the resulting error.
Then, the learning data is input again. By repeating these, ΔW is determined so as to minimize the error.

Here, if indicated general formula _{ΔW, ΔW ji (n + 1} ) = ηδ pj O pi + αΔW ji (n) ... (8) n is the number of times of learning, the first term is [Delta] W, the second term,
This is an additional term for preventing error oscillation and accelerating convergence.

Next, a back propagation method employed for learning a multilayer neural network will be described with reference to FIG.

FIG. 5 illustrates a subroutine (SUBROUTINE BP) for executing backpropagation learning.
First, in S51, an initial value of the nerve weight is set by a random number. Then, in S52, the calculation is repeatedly performed for the number of learning data. Next, the output of each cell is calculated in S53. In this embodiment, the above equation (2) is used for calculating the output. Then, in S54, an evaluation function is calculated by the above equation (3). Next, in order to minimize this evaluation function value
In S55, the nerve weight correction amount is calculated by the above equation (8). Note that the learning constant η and the stability constant α are empirically determined and, for example, η = 0.4 and α = 0.6. And S56
Then, the nerve weight is corrected based on the nerve weight correction amount, and the process returns to S52 to repeatedly calculate. Therefore, in this embodiment, the nerve weight is corrected for each learning data. Further, in the present embodiment, the sum of the evaluation functions of each data is calculated in S57, and S
At 58, it is determined whether the sum of the evaluation functions is smaller than a predetermined threshold value. That is, in S58, it is determined whether or not the sum of the errors is equal to or less than a predetermined value. If the sum of the evaluation functions is not equal to or less than the threshold value, the calculation is performed again using the nerve weight at this time. If the sum of the evaluation functions is equal to or less than the predetermined value, the process proceeds to S59
Output the final nerve weight. As a result,
(SUBROUTINE BP) ends.

Next, the analogy of the abnormal pattern of the visual field using the above-described multilayer neural network and learning by the back propagation method will be described in detail.

First, a typical pattern when the visual field is abnormal will be described with reference to FIG. FIG. 6 shows the dynamic amount visual field of the right eye. In addition, since it is a right eye, the right outside is wide.

FIG. 6A shows a typical visual field pattern in the case of a central dark spot. This is the case where there is a scotoma in the center of the field of view, in the case of disorders of the macular retina, for example in the case of macular degeneration or central retinitis, and diseases of the papillary macular fibril bundle, for example in the case of acute bulbar optic neuritis Is to be seen. FIG. 6 (b) shows a typical visual field pattern in the case of an annular dark spot. This is the case where the scotoma surrounds the center and assumes a ring shape, and is also seen in glaucoma where Seidel-Bjerrum scotoma (a phenomenon in which the Marriott scotoma extends and expands vertically) and retinitis pigmentosa is there. FIG. 6 (c) shows a typical visual field pattern in the case of visual field narrowing. In the case of afferent stenosis,
The visual field in each direction is narrowed to the same extent from the periphery toward the center. For example, it is found at the end of glaucoma, retinitis pigmentosa and the like. In some cases, stenosis is partially observed (subsidence), and in retinal detachment, stenosis in a portion corresponding to the detached portion is recognized. FIG. 6D shows a typical visual field pattern in the case of semi-blindness. The semi-blindness is a state in which the visual field on the half side is lost from a vertical line passing through the fixation point due to an obstacle in a visual conduction path. FIG. 6E shows a typical visual field pattern in the case of a Bierm scotoma. The Bierm scotoma is a scotoma that is found in a region (Bierm region) in the middle from the top and bottom of the Marriott blind spot and is characteristic of the glaucoma visual field. It is caused by damage to nerve fibers in the vertical direction of the optic disc. FIG. 6 (f) is an arcuate scotoma. Bierm scotoma usually appears in one of the up and down directions, and an extreme case of this is an arcuate scotoma. It occurs in the case of glaucoma. FIG. 6 (g) is an intensity dark spot. The intensity scotoma is a shape in which the arcuate scotoma extends in either of the upper and lower directions to form a donut horizontally divided into two parts, and reaches the horizontal meridian opposite to the macula. The field of view at this time is also called the Renne stairs. FIG. 6 (h) shows the visual field in the case of normal. There is an oblong dark spot, which is a Marriott blind spot. Marriott blind spots occur because there is no photoreceptor cell in the optic disc and the corresponding field of vision becomes a scotoma.

Therefore, learning can be performed by using the above-described typical abnormal pattern of the visual field and the teacher signal. Here, the teacher signal is composed of bits corresponding to the number of abnormal patterns in the visual field. , 0, 0 ".

Next, an example in the case where an actual measurement is performed will be described with reference to FIG. First, FIG. 7 (a) shows the average value and the standard deviation of the subject having normal vision. Based on this, 4
Set two levels. The level 5 dB brighter than the normal average is set to LEVEL 0 (normal), the level 3 dB brighter than this is LEVEL 1, and the level 3 dB brighter is LEVE.
L2, 3 dB brighter is LEVEL3, and the maximum brightness is LEVEL4. First, the target is presented at the luminance of LEVEL0,
If you do not see this, increase the brightness, LEVEL1, LEVEL2. Then, the mark of the level at which the subject is seen is plotted, and this plotting is performed for each target. Seventh
FIG. 2B shows an example in which semi-blindness and visual field stenosis appear.

When using actual measurement results instead of typical abnormal patterns, the teacher signal may be, for example, "0.1, 0.0,
0.4, 0.5, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0 ".

Next, the operation of the visual field measuring device 1 of the present embodiment will be described with reference to the flowcharts shown in FIGS. In this embodiment, several subroutines are set, and each subroutine will be described.

(SUBROUTINE Judgment BP) First, the SUBROUTINE judgment BP will be described in detail with reference to FIG. This subroutine corresponds to the analogy part. First, in step S1, the visual field measurement value is assigned to the expanded input cell group corresponding to the position. This extended input cell group
Unlike the configuration of the conventional back propagation, a radial network configuration is locally (in a small area around the measurement point of the basic measurement) in the input layer. Therefore, cells other than the cells corresponding to the basic measurement will be referred to as expanded input cell groups.

Next, in S2, the weight of the horizontal network is determined. Further, in S3, the output of the input cell corresponding to the additional input index is received, and the basic measurement cell input value is reset. Next, in S4, cells are prepared for the number of input cells, the number of intermediate cells, and the number of output cells used during learning. Then, in step S5, the neural weights connecting the cells, which are calculated in advance by the learning back propagation system, are read from the file, and the neural network is set. Further, in S6, each cell of the neural network configured in S5 outputs a response according to the input / output characteristic function. In S7, the output value of each cell in S6 and the corresponding abnormal pattern name in the visual field (judgment)
And exit.

(SUBROUTINE Site BP) Next, the SUBROUTINE site BP will be described with reference to FIG. This subroutine predicts an additional measurement site to be measured using a learning method based on back propagation. Therefore, it has the same configuration as the determination of the abnormal pattern of the visual field shown in FIG. That is, from S1
The process up to S6 is the same as the subroutine decision BP in FIG.
Then, in S7, the output value of each cell in S6 and the designated value of an additional measurement site to be measured thereafter corresponding thereto are returned as a return value, and the process ends.

(SUBROUTINE Inference) Next, SUBROUTINE inference will be described with reference to FIG. The SUBROUTINE inference corresponds to the inference unit, and is for inferring a comprehensive abnormal pattern of the visual field by using the data of the visual field measurement and the inspection data other than the visual field measurement. The inspection data other than the visual field measurement is stored (stored) as a knowledge base. In this embodiment, a case where an intraocular pressure value, a medical history, and a fundus finding are employed as data other than the visual field measurement will be described. Note that these inspection data are input from the external data input means 10.

First, in S1, if the measurement has already been performed, it is determined whether or not the other visual field data is semi-blind as a result of the one-eye measurement. If the other visual field data is semi-blind, the process proceeds to S2, in which the half-blind reaction rate is increased so that the possibility of semi-blindness is determined to be high. This is because the half-blindness includes the same-named half-blindness in which the left and right sides are missing, and the pseudonymous blindness in which the left and right sides are missing, and it is highly possible that both eyes are half-blind.

Next, the process proceeds to S3, where it is determined whether the intraocular pressure value is abnormally high. The eyeball is configured to fill the vitreous and aqueous humor in the eyeball, and maintains a normal shape by applying pressure from the inside. This pressure is called intraocular pressure. If the aqueous humor flows out of the anterior chamber corner, the aqueous humor must pass through the tissue at the corner, causing considerable resistance, and high resistance increases intraocular pressure. That is, a state in which visual flow impairment occurs due to an increase in outflow resistance at this corner is called glaucoma. Therefore, if it is determined that the intraocular pressure is abnormally high in S3 and there is a slight glaucomatous reaction, the process proceeds to S4, and the reaction rate of ocular hypertension glaucoma is increased.

Further, in S5, it is determined whether or not there is medical history data. If there is medical history data, the process proceeds to S6, and the response rate of the corresponding determination is increased. For example, if the diagnosis at the time of the previous consultation was glaucoma, all points mistakes can be the effect of severe glaucoma.

Then, in S7, it is determined whether there is a corresponding fundus finding, and if there is a fundus finding, the process proceeds to S8. For example, if there is evidence of depression near the fundus papilla and there is a glaucomatous reaction, the glaucoma response rate is increased. This is because, if the state of high intraocular pressure is continued, compression atrophy occurs in the optic nerve, causing visual field abnormality (glaucoma).

By executing the above subroutine, it is possible to infer a comprehensive visual field abnormal pattern. Note that the SUBROUTINE inference is not limited to the findings such as the inspection data.

For example: (1) If it is determined that there is an abnormality in the brain or that there is a possibility of abnormality and that there is a slight reaction of half-blindness, the possibility of half-blindness can be increased.

(2) When it is determined that both eyes are reactive despite their low half blindness, the possibility of half blindness can be slightly increased.

(3) If it is determined that the one-eye pattern has a high ear-half blindness response, while it is determined that there is a slight ear-half blindness reaction, the possibility of bilateral half-blindness can be increased.

(4) When it is determined that the one-eye pattern has a high response to the ear half-blindness and a slight reaction to the nasal half-blindness, the possibility of the same name half-blindness can be increased.

(5) When the medical history data is high myopia (ref), the scotoma around the visual field can be ignored. This is because there is a case where it cannot be visually recognized due to the influence of the correction lens frame.

(SUBROUTINE data) Next, SUBROUTINE data will be described with reference to FIG.
The SUBROUTINE data is for inputting inspection data other than the visual field measurement data from the external data input means 10.

In S1, it is determined whether or not there is intraocular pressure data. If there is intraocular pressure data, the process proceeds to S2, where the intraocular pressure data is input from the external data input means 10 and the intraocular pressure is stored. The intraocular pressure data is
Although the data measured by the tonometer may be transferred via an electronic medical record constituted by an IC card or the like, the data may be transferred directly. Furthermore, the data of the tonometer can be stored in the history database of the perimeter, and this can be searched and used. Next, it is determined in S3 whether there is medical history data. If there is medical history data, the process proceeds to S4, where the medical history data is input from the external data input means 10 and the medical history is stored. The medical history data may be directly input by the measurer using a keyboard, a mouse, a light pen, or the like, or the medical history data input in the past may be searched from the history database of the perimeter. Further, in S5, it is determined whether or not there is a fundus finding. If there is a fundus finding, the process proceeds to S6, where the finding data is input from the external data input means 10 and the finding is stored. This fundus finding input method can use a keyboard or the like.

(Main Routine) [First Embodiment] Next, a main routine will be described with reference to FIG.

First, one of the eyes to be examined is placed at the spherical center of the projection screen 130 to start the measurement, and the process proceeds to S1. In S1, a basic measurement program stored in advance is read in order to perform basic measurement (generally, for example, one-point quick screening at the minimum basic measurement point required for visual field measurement).

Next, in S2, visual targets are sequentially presented at the basic measurement points according to the basic measurement program, and a visual field measurement is executed to store the response results. When the measurement at all the basic measurement points is completed, the process proceeds to S3.

At S3, SUBROUTINE data is called and executed. Then, in S4, the subroutine conclusion is called and executed. As a result, a comprehensive visual field abnormal pattern is inferred from the visual field abnormal pattern stored in S2 and the data other than the visual field measurement.

Next, in S5, it is determined whether or not the determination certainty in the determination in S4 exceeds a predetermined value. In this embodiment, it is set to 50%.
If the determination certainty is 50% or more, the process proceeds to S6. In S6, it is determined whether the determination name of the visual field abnormality is determined. If this judgment name is acceptable, the process proceeds to S7, where the judgment name of the abnormality of the visual field is determined, and the process ends. If it is determined in S6 that the visual field abnormality is undetermined, the process proceeds to S8. In S8, the subroutine BP is read. Then, the subroutine portion BP is executed in S9.
By executing the SUBROUTINE site BP, additional measurement sites to be added later are predicted. That is, a portion to be additionally measured is predicted based on the abnormal pattern of the visual field determined in S4. For example, when the abnormal pattern of the visual field determined in S4 is determined to be a central dark spot shown in FIG. 6 (a), an additional measurement site to be added is densely located near the boundary area of the central dark spot. To place. Further, when the abnormal pattern of the visual field determined in S4 is like an annular dark spot shown in FIG. Similarly, if it is determined that the visual field seems to be narrowed as shown in FIG. 6 (c), it is arranged at high density near the boundary area of the surrounding dark spots. When it is determined that the scotoma (because of glaucoma) as shown in FIG. 6 (e) is likely, the vicinity of the Marriott blind spot and the vicinity of the Bierm area (annular area near 10 degrees)
High density. If it is determined that the arc-shaped scotoma (probably due to glaucoma) shown in FIG. 6 (f) is likely, the dots are arranged at high density around the Bierm area. Further, if it is determined that the intensity scotoma (probably caused by glaucoma) shown in FIG. 6 (g) is likely, the scotoma is arranged more densely around the arcuate scotoma. Then, in the case of the normal visual field shown in FIG. 6 (h), it is presented according to the basic program.

Next, in S10, a measurement point is set at an additional measurement site at random. Then, the measurement is executed in S11. Next, in S12,
The data measured in S11 is added to the result of the previous visual field measurement and used as input data. Further, the subroutine determination BP is called again in S13 and executed in S14 to determine the abnormality of the visual field. Further, in S15, SUBROUTINE data is called and executed. Then, in S16, SUBROUTINE inference is called and executed. As a result, a comprehensive visual field abnormal pattern is inferred from the visual field abnormal pattern determined in S14 and the data other than the visual field measurement.

Then, in S17, the judgment certainty of the judgment in S16 and the judgment in S4 are compared. If the judgment certainty in S16 is low, the process proceeds to S18. In S18, whether or not to continue the measurement is further prompted by the measurer.If not to continue, it is determined in S19 whether or not the binocular measurement has been completed. And return to S1, and perform the visual field measurement of the other eye. If the measurement of both eyes has been completed, the process proceeds to S20, ends the measurement using the current judgment name as the judgment name of visual field abnormality, and displays the judgment name and the like on the display unit 8. If the measurement is to be continued, the process returns to S8 and executes the SUBROUTINE site BP.

In S17, if the determination certainty in S16 is high, the process proceeds to S21, and it is determined whether the determination certainty exceeds a predetermined value. If the determination certainty exceeds the predetermined value, the process proceeds to S20 to end the measurement. If the diagnostic certainty does not exceed the predetermined value in S21, the process returns to S8 and executes the SUBROUTINE part BP.

Here, the handling of the response of the additional measurement point described in the main routine will be described in detail with reference to FIG. It is necessary to devise the response of the additional measurement point so as to give it to the response of the basic measurement target (measurement index before addition) near the additional measurement point. Therefore, an additional measurement target No. 1 as shown in FIG. 13 (a) can be set. Basic Measurement optotypes NO.10 around this additional measurement optotype NO.1 in the radius r _m, NO.11, are set so that there is NO.12. Then, the distances from the additional measurement index No. 1 to the basic measurement targets No. 10, NO.
If r ₁ , r ₂ , and r ₃ , r ₁ ≦ r ₂ and r ₁ ≦ r ₃ .

Then, the response of the additional measurement target and the response and the response of the basic measurement target are connected by a radial network. The weight of the network is determined according to the distance. As an example, a method of determining the weight in inverse proportion to the distance will be described. That is,
With the shortest distance as the minimum unit, the weight is determined according to the inverse ratio of the distance.

For example, in the case where the response of the basic measurement target No. 10 is 2, the response of NO.11 is 2, the response of NO.12 is 3, and the response of the additional measurement target No. 1 is 4, .10 input data, And the input data of NO.11 is And the input data of NO.12 is Can be determined.

That is, if the input data is represented by a general formula, However, the response of r ₁ ≤r ₂ r ₁ ≤r ₃ · the additional measurement target _No. (k) · is A (k).

· R ₁ ≦ r _{n n:} additional measurement visual target number r _1: the minimum distance in the r ₁ ~r _n.

Note that, as shown in FIG. 13 (b), areas centered on the basic measurement indices are provided slightly overlapping. The response of the additional measurement index is devised so as to affect the response of the basic measurement target in the area including the additional measurement index. That is, when a plurality of additional measurement targets exist in the area of a certain basic measurement target,
The response of the basic measurement target is corrected according to the inverse ratio of the distance with the shortest distance as the unit distance. The basic general formula is the same as the ninth formula.

The area is not limited to a circle, but may be a rectangle or the like. Although the size of the area can be determined as appropriate, the area near the center needs to be inspected precisely, so it is desirable to reduce the area.

As described above, the present embodiment in which an additional measurement target is set has an effect that even if data is insufficient, a measurer can add a measurement target which is deemed necessary.

Therefore, there is an excellent effect that the measurer can judge an appropriate visual field abnormal pattern.

Second Embodiment Next, a second embodiment of the visual field measuring device 1 will be described with reference to FIG. In the second embodiment, an abnormal pattern of a visual field is analogized while presenting a basic measurement target, and a basic measurement target to be presented is determined.

First, in S1, a measurement program instructed by the measurer is read from the optotype projection program storage unit 5, and several measurement points are executed. For example, perform the first 5 points of a 71-point quick screen. Next, in S2, the current data is added to the result of the previous visual field measurement to be used as input data. If the data is new, the data is used as it is. Then, in S3, the subroutine judgment BP is called, and in S4, the SUBROUTI
Execute the NE judgment BP to judge the abnormal pattern of the visual field based on the output cell value response value. Then, in S5, the subroutine data is called and executed. Then, in S6, SUBROUTINE inference is called and executed. As a result, a comprehensive visual field abnormal pattern is inferred from the visual field abnormal pattern determined in S4 and the inspection data other than the visual field measurement.

Further, in S7, the judgment certainty is compared with the previous judgment certainty,
If it is smaller than the previous determination certainty, the process proceeds to S8, and the examiner is prompted to determine whether to continue the measurement. If the measurer does not want to continue the measurement in S8, the process ends in S9 with the current decision name as the final decision.

If the diagnosis certainty is larger than the previous time in S7, the process proceeds to S10. In S10, it is determined whether or not the determination certainty exceeds a predetermined value, and if it exceeds, the process proceeds to S9 to end the measurement. If the determination certainty does not exceed the predetermined value in S10, the process proceeds to S11. In S11, call the SUBROUTINE site BP,
In S12, a SUBROUTINE site BP is executed, an additional measurement site to be measured is predicted, and a new measurement point is set. Then, returning to S2, the measurement is continued.

Note that the second embodiment has a simpler configuration than the first embodiment and has an effect that the measurement time can be shortened because automatic measurement is performed from the beginning.

In the present embodiment configured as described above, the labor, time, and the like of the measurer are also reduced, and thus there is an effect that the burden on the measurer and the subject can be significantly reduced.

In this embodiment, an example in which the present invention is applied to a static perimeter is described. However, it is needless to say that the present invention is also applicable to a dynamic perimeter.

Further, the visual field measuring device 1 of the above-described embodiment is
The optotype presenting position I is moved by rotating 0, but a light source such as an LED can be embedded as an optotype on the screen.

"Effect" The present invention configured as described above, an index presenting unit that presents a measurement index, a response unit that responds whether or not the subject has recognized the presented index, an input layer, a hidden layer, A multi-layer neural network having an output layer and having a nerve weight determined based on a typical response and a normal response when the visual field of the subject is abnormal in advance, and a response from the response unit. An analogization unit that inputs to the input layer of the multilayer neural network and infers an abnormal pattern in the visual field of the subject from an output of the output layer at that time; a knowledge base storing inspection data other than the visual field measurement data; An inference unit that infers a comprehensive visual field abnormal pattern using the left and right visual field abnormal patterns and the test data inferred by the unit, and an additional visual target according to the visual field abnormal pattern inferred by the inference unit. Determined and presented to the optotype presenting section It is possible to estimate the abnormal pattern of the visual field of the person to be measured, and not only to assist the determination of the abnormal pattern of the visual field of the person to be measured, There is an outstanding effect that a comprehensive judgment using inspection data other than the above can be made.

Further, since it is possible to cope with exceptional diseases and initial diseases that do not depend on the abnormal pattern of a specific visual field, there is an excellent effect that prediction accuracy is dramatically improved.

Further, since the present invention includes the additional target unit, the additional measurement target is automatically presented to the target presenting unit in accordance with the inferred abnormal pattern of the visual field, so that a highly reliable determination can be made. In addition, since the measurement time is shortened, there is an excellent effect that the pain of the subject is reduced.

[Brief description of the drawings]

FIG. 1 shows a visual field measuring apparatus according to one embodiment of the present invention. FIG. 1 is a diagram showing an external configuration of the present embodiment. FIG. 3 is a diagram for explaining an electrical configuration of the present embodiment, FIG. 4 is a diagram for explaining a multilayer neural network, FIG. 5 is a diagram for explaining a back propagation method, and FIG. FIG. 7 shows a typical example, FIG. 7 illustrates a specific measurement result, and FIG.
9 illustrates the subroutine section
FIG. 10 illustrates BP, FIG. 10 illustrates SUBROUTINE inference, FIG. 11 illustrates SUBROUTINE data, FIG. 12 illustrates a main routine (first embodiment), and FIG. FIG. 14 is a view for explaining a measurement target, and FIG. 14 is a view for explaining a second embodiment. DESCRIPTION OF SYMBOLS 1 ... Visual field measuring device 2 ... Target projection control part 3 ... Response switch 4 ... BP execution part 5 ... Target target projection program storage part 6 ... Response storage part 7 ... Operation part 8 ... Display part 9 CPU 10 External data input means 130 Imaging screen 300 Imaging optical system 330 Target 400 Rotating mirror

Claims (2)

(57) [Claims] 1. An index presenting section for presenting a measurement index, a responding section for responding whether or not the subject has recognized the presented index, an input layer, a hidden layer, and an output layer. A multilayer neural network having a neural weight determined based on a typical response and a normal response when the visual field is abnormal;
A response from the response unit is input to the input layer of the multilayer neural network, and an analogy unit for analogizing an abnormal pattern of the visual field of the subject from an output of the output layer at that time, and storing inspection data other than the visual field measurement data. Knowledge base to perform, an inference unit that infers a comprehensive visual field abnormality pattern using the left and right visual field abnormal pattern and the inspection data analogized by the analog inference unit, and a visual field abnormal pattern inferred by the inference unit. A visual field measuring device, comprising: an additional visual target that is determined in accordance with the additional visual target and presented to the visual target presenting unit. 2. The visual field measuring apparatus according to claim 1, wherein the examination data is any one of an intraocular pressure, a fundus finding, and a medical history.