Patent Application
20220079484
The present disclosure relates to an evaluation device, an evaluation method, and a medium.
In recent years, cognitive dysfunction and brain dysfunction are considered to be on the rise and it is required to find such cognitive dysfunction and brain dysfunction at early stages and quantitatively evaluate severity of symptoms. A method of, when making an evaluation on, for example, dementia with Lewy bodies among such cognitive dysfunction and brain dysfunction, asking a subject whether the subject has visual hallucinations and calling on the subject to answer has been disclosed (for example, refer to Japanese Laid-open Patent Publication No. 2017-217051).
The method described in Japanese Laid-open Patent Publication No. 2017-217051, however, depends on a subjective view of a subject and thus is with low objectivity and it is difficult to obtain accurate evaluation.
An evaluation device according to the present disclosure comprising: a display unit; a point-of-gaze detector configured to detect a position of a point of gaze of a subject on the display unit; a display controller configured to display, on the display unit, an image containing a target area serving as a target that a subject is caused to gaze at and containing, in a position different from that of the target area, an induction area for inducing a visual hallucination in the subject; an area setting unit configured to set a specific area corresponding to the induction area in the display unit; a determination unit configured to, based on position data on the point of gaze, determine whether the point of gaze is present in the specific area; a computing unit configured to, based on a determination result of the determination unit, calculate point-of-gaze data; and an evaluation unit configured to, based on the point-of-gaze data, calculate evaluation data on the subject.
An evaluation method according to the present disclosure comprising: detecting a position of a point of gaze of a subject on a display unit; displaying, on the display unit, an image containing a target area serving as a target that a subject is caused to gaze at and containing, in a position different from that of the target area, an induction area for inducing a visual hallucination in the subject; setting a specific area corresponding to the induction area in the display unit; based on position data on the point of gaze, determining whether the point of gaze is present in the specific area; based on a determination result, calculating point-of-gaze data; and based on the point-of-gaze data, calculating evaluation data on the subject.
A non-transitory computer readable recording medium storing therein an evaluation program according to the present disclosure for causing a computer to execute processes of detecting a position of a point of gaze of a subject on a display unit; displaying, on the display unit, an image containing a target area serving as a target that a subject is caused to gaze at and containing, in a position different from that of the target area, an induction area for inducing a visual hallucination in the subject; setting a specific area corresponding to the induction area in the display unit; based on position data on the point of gaze, determining whether the point of gaze is present in the specific area; based on a determination result, calculating point-of-gaze data; and based on the point-of-gaze data, calculating evaluation data on the subject.
According to the disclosure, it is possible to provide an evaluation device, an evaluation method, and an evaluation program that make it possible to make an evaluation on cognitive dysfunction and brain dysfunction accurately.
An embodiment of an evaluation device, an evaluation method, and an evaluation program according to the disclosure will be described below based on the drawings. The embodiment does not limit the invention. The components in the embodiment described below include those easily replaceable by those skilled in the art or those substantially the same.
In following description below, description will be given on a positional relationship among components, setting a three-dimensional global coordinate system. A direction parallel to a first axis on a given plane is set for an X-direction, a direction parallel to a second axis on a given plane orthogonal to the first axis is set for a Y-axis, and a direction parallel to a third axis orthogonal to each of the first axis and the second axis is set for a Z-axis direction. The given planes include an XY-plane.
Evaluation Device
As illustrated in
The display device 10 includes a flat panel display, such as a liquid crystal display (LCD) or an organic electroluminescence display (OLED). In the embodiment, the display device 10 includes a display unit 11. The display unit 11 displays information, such as an image. The display unit 11 is substantially parallel to the XY-plane. The X-axis direction is a left-right direction of the display unit 11, the Y-axis direction is an up-down direction of the display unit 11, and the Z-axis direction is a depth direction orthogonal to the display unit 11. The display device 10 may be a head mounted display. In the case of a head-mounted display, such a configuration as that of the image acquisition device 20 is arranged in a head mounted module.
The image acquisition device 20 acquires image data of left and right eye balls EB of the subject and transmits the acquired image data to the computer system 30. The image acquisition device 20 includes an imaging device 21.
The imaging device 21 acquires image data by capturing images of the left and right eyeballs EB of the subject. The imaging device 21 includes various cameras corresponding to a method of detecting a line of sight of the subject. For example, in the case of a system that detects a line of sight based on a position of a pupil of a subject and a position of a corneal reflex image, the imaging device 21 includes an infrared camera and includes an optical system that can transmit near-infrared light of a wavelength of 850 [nm] and an imaging element capable of receiving the near-infrared light. In the case of a system that detects a line of sight based on a position of an inner corner of an eye of a subject and a position of an iris, the imaging device 21 includes a visible light camera. The imaging device 21 outputs a frame synchronization signal. The period of the frame synchronization signal can be set at, for example, 20 [msec]; however, the period is not limited to this. The imaging device 21 can have a configuration of a stereo camera including a first camera 21A and a second camera 21B; however, the configuration is not limited to this.
Furthermore, for example, in the case of a system that detects a line of sight based on a position of a pupil of a subject and the position of a corneal reflex image, the image acquisition device 20 includes an illuminating device 22 that illuminates the eyeballs EB of the subject. The illuminating device 22 includes an LED (light emitting diode) light source and is capable of emitting near-infrared light of, for example, a wavelength of 850 [nm]. Note that, for example, in the case of a system that detects a line-of-sight vector based on a position of an inner corner of an eye of a subject and a position of an iris, the illuminating device 22 need not be arranged. The illuminating device 22 emits detection light such that the detection light is synchronized with a frame synchronization signal of the imaging device 21. The illuminating device 22 can be configured to include, for example, a first light source 22A and a second light source 22B; however, the configuration is not limited to this.
The computer system 30 controls operations of the evaluation device 100 overall. The computer system 30 includes an arithmetic processing unit 30A and a storage device 30B. The arithmetic processing unit 30A includes a microprocessor, such as a CPU (central processing unit). The storage device 30B includes a memory or a storage, such as a ROM (read only memory) or a RAM (random access memory). The arithmetic processing unit 30A performs arithmetic processing according to a computer program 30C that is stored in the storage device 30B.
The output device 40 includes a display device, such as a flat panel display. Note that the output device 40 may include a printing device. The input device 50 is operated and thus generates input data. The input device 50 includes a keyboard or a mouse for computer systems. Note that the input device 50 may include a touch sensor that is arranged in the display unit of the output device 40 serving as a display device.
The evaluation device 100 according to the embodiment is a device in which the display device 10 and the computer system 30 are independent from each other. Note that the display device 10 and the computer system 30 may be integrated. For example, the evaluation device 100 may include a tablet personal computer. In this case, a display device, an image acquisition device, a computer system, an input device, an output device, etc., may be installed in the tablet personal computer.
The display controller 31 displays, on the display unit, an evaluation image (image) containing a target area serving as a target that the subject is caused to gaze at and containing, in a position different from that of the target area, an induction area for inducing visual hallucinations in a subject suffering from dementia with Lewy bodies among subjects. In the evaluation image, the value of at least any one of sharpness, luminance, contrast and chroma of the induction area is lower than that of the target area. In the evaluation image, the value of at least any one of sharpness, luminance, contrast and chroma of the target area is higher than that of the surroundings.
The evaluation image is a photographic image obtained by capturing an image of a scenery where a subject in the target area is present on a front side in the depth direction and an inducing area and a subject in the inducing area is present on a back side in the depth direction, with the subject in the target area serving as a position of a focal point. A mode of display of the evaluation image may be any one of a still image and a moving image.
The point-of-gaze detector 32 detects position data on a point of gaze of the subject. In the embodiment, based on the image data on the left and right eyeballs EB of the subject that is acquired by the image acquisition device 20, the point-of-gaze detector 32 detects a line-of-sight vector of the subject that is set by the three-dimensional global coordinate system. The point-of-gaze detector 32 detects, as the position data on the point of gaze of the subject, position data on an intersection between the detected line-of-sight vector of the subject and the display unit 11 of the display device 10. In other words, in the embodiment, the position data on the point of gaze is position data on the intersection between the line-of-sight vector of the subject that is set by the three-dimensional global coordinate system and the display unit 11 of the display device 10. In the embodiment, the point of gaze is a specified point on the display unit 11 that is gazed at by the subject and thus is specified. The point-of-gaze detector 32 detects the position data on the point of gaze of the subject at intervals of a sampling period that is set. For the sampling period, it is possible to set, for example, a period (for example, every 20 [msec]) of the frame synchronization signal that is output from the imaging device 21.
In the display unit 11, the area setting unit 33 sets a specific area corresponding to the induction area and a comparison area corresponding to the target area on the display unit 11. In the embodiment, the positions of the induction area and the target area differ from each other. Thus, the area setting unit 33 sets the specific area and the comparison area independently.
During the period in which the area setting unit 33 sets the specific area and the comparison area, the determination unit 34 determines whether the point of gaze is present in the specific area and the comparison area based on the position data on the point of gaze and outputs determination data. The determination unit 34 determines whether the point of gaze is present in the specific area and the comparison area at intervals of the set determination period. The determination period can be, for example, the same period as the period (for example, every 20 [msec]) of the frame synchronization signal that is output from the imaging device 21. In this case, the period of determining by the determination unit 34 is the same as the period of sampling by the point-of-gaze detector 32.
Based on the determination data of the determination unit 34, the computing unit 35 calculates point-of-gaze data presenting the course of shift of the point of gaze during the period in which the specific area and the comparison area described above are set. The computing unit 35 calculates, as the point-of-gaze data, for example, at last any one of reach time data, shifting number-of-times data and presence time data and last area data. The reach time data represents a time to a reach time at which the point of gaze reaches the specific area for the first time. The shifting number-of-times data represents the number of times for which the position of the point of gaze shifts between the specific area and the comparison area until the point of gaze reaches the specific area for the first time. The presence time data represents a presence time during which the point of gaze is present in the specific area during a period of display of the reference images. The last area data represents an area in which the point of gaze is present lastly during the time of display among the specific area and the comparison area. The computing unit 35 includes a timer that detects a time elapsing from display of the evaluation image on the display unit 11 and a counter that counts the number of times for which the determination unit 34 determines that the point of gaze is present in the specific area and the comparison area.
Based on the point-of-gaze data, the evaluation unit 36 calculates evaluation data on the subject. The evaluation data contains data for making an evaluation on whether the subject is being capable of gazing at a specific subject and a comparison subject that are displayed on the display unit 11.
The input/output controller 37 acquires data from at least one of the image acquisition device 20 and the input device 50 (such as the image data on the eyeballs EB and input data). The input/output controller 37 outputs data to at least one of the display device 10 and the output device 40.
The storage 38 stores the determination data, the point-of-gaze data (presence time data) and the evaluation data described above. The storage 38 stores an evaluation program for causing a computer to execute processes of detecting a position of a point of gaze of a subject on the display unit 11; displaying, on the display unit 11, an evaluation image IM1 containing a target area M1 serving as a target that a subject is caused to gaze at and containing, in a position different from that of the target area M1, induction areas C1 and C2 for inducing visual hallucinations in a subject suffering from dementia with Lewy bodies among subjects; setting, in the display unit 11, specific areas A1 and A2 corresponding to the induction areas C1 and C2 and a comparison area B corresponding to the target area M1; based on position data on the point of gaze, determining whether the point of gaze is present in the specific areas A1 and A2 and the comparison area B; based on a determination result, calculating point-of-gaze data; and, based on the point-of-gaze data, calculating evaluation data on the subject.
Evaluation Method
The evaluation method according to the embodiment will be described next. In the evaluation method according to the embodiment, by using the evaluation device 100 described above, an evaluation on cognitive dysfunction and brain dysfunction of the subject is made. In the embodiment, for example, the case where an evaluation is made on dementia with Lewy bodies serving as cognitive dysfunction and brain dysfunction is described.
A symptom that visual hallucinations are induced is known as one of symptoms of dementia with Lewy bodies. In the case where a visual hallucination is induced in a subject suffering from dementia with Lewy bodies when the subject gazes at an image, the subject tends to gaze at an area serving as a subject of the visual hallucination. When an evaluation on such dementia with Lewy bodies is made, an image containing an area that induces visual hallucinations is shown to a subject.
In the evaluation image IM1 of the embodiment, the area of the trees on the back side is different from the target area M1 in the following aspects.
1. The focus is on the flowers and the trees are out of focus. In other words, the area of the trees has a lower sharpness than that of the target area M1.
2. The area of the trees has a lower luminance than that of (is darker than) the target area M1.
3. The area of the trees has a lower contrast than that of the target area M1.
In the case where the evaluation image IM1 is a color image, an image in which the area of the trees has a lower chroma than that of the target area M1 is used.
As a result, in the evaluation image IM1, the area of the trees contains areas that tend to induce visual hallucinations in a subject suffering from dementia with Lewy bodies. For example, an area C1 that is part of the area of the trees serves as an area that induces visual hallucinations of the figure of a person, and the like, in a subject suffering from dementia with Lewy bodies. The area C1 is referred to as an induction area C1 below. For example, an area C2 that is part of the area of the trees serves as an area that induces visual hallucinations of the face of a person, and the like, in a subject suffering from dementia with Lewy bodies. The area C2 is referred to as an induction area C2 below.
On the other hand, the induction areas C1 and C2 are areas that are merely part of the area of the trees whose sharpness, luminance and contrast (or chroma) are low to a subject not suffering from dementia with Lewy bodies and are areas that tend not to induce visual hallucinations of the figure of a person, the face of a person, etc. Thus, in the case where the subject is not suffering from dementia with Lewy bodies, when the evaluation image IM1 is displayed on the display unit 11, the subject is highly likely to gaze at the target area M1 whose sharpness, luminance and contrast are high.
In the embodiment, for example, it is possible to use an image with which a significant difference is shown between a subject not suffering from dementia with Lewy bodies and a subject suffering from dementia with Lewy bodies after evaluations are made on multiple subjects. In other words, it is possible to use an image containing a target area that a subject not suffering from dementia with Lewy bodies more tends to gaze at and an induction area that a subject not suffering from dementia with Lewy bodies more tends not to gaze at and a subject suffering from dementia with Lewy bodies more tends to gaze at.
Furthermore, using the above-described photographic image as the evaluation image IM1 more assuredly enables a subject not suffering from dementia with Lewy bodies to gaze at the subject in the target area M1 on the front side. Furthermore, the induction areas C1 and C2 that cause a less sense of discomfort and that is natural to a subject not suffering from dementia with Lewy bodies are contained in the evaluation image IM1. Accordingly, a subject not suffering from dementia with Lewy bodies is inhibited from gazing at the induction areas C1 and C2.
During the period in which the evaluation image IM1 is displayed as described above, the area setting unit 33 sets each of the specific areas A1 and A2 corresponding to the induction areas C1 and C2. The area setting unit 33 sets the comparison area B corresponding to the target area M1. The area setting area 33 is able to set each of the specific areas A1 and A2 in an area containing at least part of the induction areas C1 and C2. The area setting unit 33 is able to set the comparison area B in an area containing at least part of the target area M1. In the embodiment, the area setting unit 33 sets the specific area A1 in a rectangular area containing the induction are C1 and sets a specific area A2 in a circular area containing the induction area C2. The area setting unit 33 sets the comparison area B in a rectangular area containing the target area M1.
During the period in which the evaluation image IM1 is displayed, the point-of-gaze detector 32 detects position data on the point of gaze P of the subject at intervals of the set sampling period (for example, 20 [msec]). When the position data on the point of gaze P of the subject is detected, the determination unit 34 determines whether the point of gaze of the subject is present in the specific areas A1 and A2 and the comparison area B and outputs determination data. Thus, the determination unit 34 outputs determination data at intervals of the same determination period as the above-described sampling period.
Based on the determination data, the computing unit 35 calculates point-of-gaze data representing the course of shift of the point of gaze P during the period of display. The computing unit 35 calculates, as the point-of-gaze data, for example, presence time data, shifting number-of-times data, last area data, and reach time data.
The presence time data represents a presence time during which the point of gaze P is present in the specific areas A1 and A2. In the embodiment, the larger the number of times for which the determination unit 34 determines that the point of gaze is present in the specific areas A1 and A2 is, the more it can be estimated that the presence time in which the point of gaze P is present in the specific areas A1 and A2 is long. Thus, the presence time data can be the number of times for which the determination unit 34 determines that the point of gaze is present in the specific areas A1 and A2 or the comparison area B. In other words, the computing unit 35 can set count values CNTA1, CNTA2 and CNTB of the counter for the presence time data. The count value CNTA1 is the number of times for which it is determined that the point of gaze is present in the specific area A1. The count value CNTA2 is the number of times for which it is determined that the point of gaze is present in the specific area A2. The count value CNTB is the number of times for which it is determined that the point of gaze is present in the comparison area B.
The shifting number-of-times data represents the number of times for which the position of the point of gaze P shifts between the specific areas and the comparison area B until the point of gaze P reaches the specific area A1 or the specific area A2. Thus, the computing unit 35 is able to count how many times the point of gaze P shifts between the specific areas A1l and A2 and the comparison area B and set, for the shifting number-of-times data, the result of counting until the point of gaze P reaches the specific area A1 or A2.
The last area data represents an area in which the point of gaze P is present lastly among the specific areas A1 and A2 and the comparison area B, that is, the area at which the subject gazes lastly as an answer. By updating area in which the point of gaze P is present on every detection of the point of gaze P, the computing unit 35 is able to set, for the last area data, the detection result at the time when displaying the evaluation image IM1 ends.
The reach time data represents the time from the time at which displaying the evaluation image IM1 is started until the time at which the point of gaze P reaches the specific area A1 or A2 for the first time. Thus, by measuring the elapse of time from the start of display with a timer T1 and, at the time when the point of gaze reaches the specific area A1 or the specific area A2 for the first time, detecting a measured value of the timer T1 as a flag value FA1 or a flag value FA2, the computing unit 35 is able to set a detection result of the timer T1 for the reach time data.
The evaluation unit 36 calculates an evaluation value based on the presence time data, the shifting number-of-times data, the last area data, and the reach time data and calculates evaluation data based on the evaluation value. For example, the data value of the last area data is D1, the data values of the presence time data are D2 to D4, the data value of the reach time data is D5, and the data value of the shifting number-of-times data is D6. Note that the data value D1 of the last area data is set at 1 when the last point of gaze P of the subject is present in the specific area A1, is set at 0.8 when the last point of gaze P is present in the specific area A2, and is set at 0 when the last point of gaze P is present in the comparison area B. For each of the data values D2 to D4 of the presence time data, seconds during which the point of gaze P is present in each of the specific areas A1 and A2 and the comparison area B are set. For the data values D2 to D4, an upper limit that is seconds shorter than the period during which the evaluation image IM1 is displayed may be set. For the data value D5 of the reach time data, an inverse of the reach time (for example, 1/(reach time)÷10) (10: a coefficient for keeping the minimum value of the reach time at 0.1 second and keeping the reach time evaluation value at 1 or smaller). As for the data value D6 of the shifting number-of-times data, the count value is used directly. Note that an upper limit may be set for the data value D6 as appropriate.
In this case, an evaluation value ANS is represented by, for example, as follows.
ANS=D1·K1+D2·K2+D3·K3−D4·K4+D5·K5−D6·K6
K1 to K6 are constants for weighting. The constants K1 to K6 can be set as appropriate. K4=0 may be met. In other words, the data value D4 of the presence time data on the comparison area B need not be contained in the evaluation.
The value of the evaluation value ANS represented by the equation above increases when the data value D1 of the last area data is 1 or 0.8, when the data values D2 and D3 of the presence time data are large, when the data value D4 of the presence time data is small, when the data value D5 of the reach time data is large, or when the data value D6 of the shifting number-of-times data is small. In other words, the evaluation value ANS increases as the last point of gaze P is present in the specific area A1 or A2, the time during which the point of gaze P is present in the specific areas A1 and A2 is long, the time during which the point of gaze P is present in the comparison area B is short, the reach time taken by the point of gaze P to reach the specific area A1 or A2 from the time at which the period of display starts is short, or the number of times for which the point of gaze P shifts between areas is small.
Furthermore, the evaluation value ANS decreases when the data value D1 of the last area data is 0, when the data values D2 and D3 of the presence time data are small, when the data value D4 of the presence time data is large, when the data value D5 of the reach time data is small, or when the value of the data value D6 of the shifting number-of-times data is large. In other words, the evaluation value ANS decreases as the last point of gaze P is present in the comparison area B, the time during which the point of gaze P is present in the specific areas A1 and A2 is short, the time during which the point of gaze P is present in the comparison area B is long, the reach time taken by the point of gaze P to reach the specific area A1 or A2 from the time at which the period of display starts is long or the point of gaze P does not reach the specific area A1 or A2, or the number of times for which the point of gaze P shifts between areas is large.
Accordingly, by determining whether the evaluation value ANS is equal to or larger than a given value, the evaluation unit 36 is able to calculate evaluation data. For example, when the evaluation value ANS is smaller than the given value, it is possible to evaluate that the subject is less likely to be suffering from dementia with Lewy bodies. When the evaluation value ANS is equal to or larger than the given value, it is possible to evaluate that the subject is highly likely to be suffering from dementia with Lewy bodies.
The evaluation unit 36 is able to store the value of the evaluation value ANS in the storage 38. For example, the evaluation values ANS on the same subject may be stored cumulatively and an evaluation may be made in comparison with an evaluation value in the past. For example, when the evaluation value ANS is lower than the evaluation value in the past, it is possible to evaluate that the brain function has improved compared to the previous evaluation. When the cumulative value of evaluation values ANS is gradually decreasing, it is possible to evaluate that the brain function is gradually improving.
The evaluation unit 36 may make an evaluation using the presence time data, the shifting number-of-times data, the last area data, and the reach-time data independently or in combination. For example, when the point of gaze P reaches the comparison area B incidentally during seeing of many objects, the data value D6 of the shifting number-of-times data increases. In this case, it is possible to make an evaluation in combination with the data value D4 of the presence time data described above. For example, in the case where the presence time is long even when the number of times of shifting is small, it is possible to evaluate that the comparison area B can be gazed at. Furthermore, when the number of times of shifting is small and the time of presence is short, it is possible to evaluate that the point of gaze P incidentally passes through the comparison area B.
In the case where the number of times of shifting is small, when the last area is the compassion area B, for example, it is possible to evaluate that the compassion area B is reached in few shifts of the point of gaze. On the other hand, in the aforementioned case where the number of times of shifting is small, when the last area is not the comparison area B, for example, it is possible to evaluate that the point of gaze P incidentally passes though the comparison area B. Thus, it is possible to calculate evaluation data based on the course of shift of the point of gaze by making an evaluation using the point-of-gaze data and thus it is possible to reduce the effect of contingency.
In the embodiment, when the evaluation unit 36 outputs evaluation data, the input/output controller 37 is able to cause the output device 40 to output, for example, character data of “The subject seems to be less likely to be suffering from dementia with Lewy bodies.”, character data “The subject seems to be highly likely to be suffering from dementia with Lewy bodies.”, or the like. When the evaluation value ANS on the same subject is lower than the evaluation value ANS in the past, the input/output controller 37 is able to cause the output device 40 to output character data of “The brain function has improved”, or the like.
On the other hand, in the evaluation image IM2, the area of the trees on the back side is different from the target area M2 in the following aspects.
4. The focus is on the bicycle and the trees are out of focus. In other words, the area of the trees has a lower sharpness than that of the target area M2.
5. The area of the trees has a lower luminance than that of (is darker) the target area M2.
6. The area of the trees has a lower contrast than that of the target area M2.
In the case where the evaluation image IM2 is a color image, an image in which the area of the trees has a lower chroma than that of the target area M2 is used.
As a result, an area that tends to induce visual hallucinations in a subject suffering from dementia with Lewy bodies is present in the evaluation image IM2. For example, an area C3 that is part of the area of the trees serves as an area that induces a visual hallucination of the figure of a person, or the like, in a subject suffering from dementia with Lewy bodies. The area C3 is referred to as an induction area C3 below. An area C4 that is part of the area of the trees serves as an area that induces a visual hallucination of the face of a person in a subject suffering from dementia with Lewy bodies. The area C4 is referred to as an induction area C4 below.
During the period in which the evaluation image IM2 is displayed, the area setting unit 33 sets each of the specific areas A1 and A2 corresponding to the induction areas C3 and C4. The area setting unit 33 sets a comparison area B corresponding to the target area M2. The area setting unit 33 is able to set the specific areas A1 and A2 in areas containing at least part of the induction areas C3 and C4, respectively. The area setting unit 33 is able to set the comparison area B in an area containing at least part of the target area M2. In the embodiment, the area setting unit 33 sets the specific area A1 in a rectangular area containing the induction area C3 and sets the specific area A2 in a circular area containing the induction area C4. The area setting unit 33 sets the comparison area B in a rectangular area containing the target area M2.
The display controller 31 is able to display the evaluation image IM2 illustrated in
An example of the evaluation method according to the embodiment will be described with reference to
As illustrated in
When it is determined that the point of gaze P is in the specific area A1 (YES at step S108), the computing unit 35 determines whether the flag value FA1 is 1, that is, whether the point of gaze P reaches the specific area A1 for the first time (1: reached, 0: not reached) (step S109). When the flag value FA1 is 1 (YES at step S109), the computing unit 35 skips steps S110 to S112 below and performs the process of step S113 to be described below.
When the flag value FA1 is not 1, that is, when the point of gaze P reaches the specific area A1 for the first time (NO at step S109), the computing unit 35 extracts a measurement result of the timer T1 as reach time data (step S110) and saves a cumulative number representing how many times the point of gaze P shifts among areas until the point of gaze P reaches the specific area A1 (step S111). Thereafter, the computing unit 35 changes the flag value to 1 (step S112).
The computing unit 35 determines whether the area in which the point of gaze P is present in the last detection, that is, the last area is the specific area A1 (step S113). When it is determined that the last area is the specific area A1 (YES at step S113), the computing unit 35 skips step S114 and step S115 below and performs the process of step S116 to be described below. When it is determined that the last area is not the specific area A1 (NO at step S113), the computing unit 35 incrementally increases by 1 the cumulative number representing how many times the point of gaze P shifts among areas (step S114), sets the specific area A1 for the last area (step S115), and incrementally increases by 1 the count value CNTA1 representing the data on the time of presence in the specific area A1 (step S116). Thereafter, the computing unit 35 performs the process at and after step S131 to be described below.
When it is determined that the point of gaze P is not present in the specific area A1 (NO at step S108), the computing unit 35 determines whether the point of gaze P is present in the specific area A2 (step S117). When it is determined that the point of gaze P is present in the specific area A2 (YES at step S117), the computing unit 35 determines whether the flag value FA2 is 1, that is, whether the point of gaze P reaches the specific area A2 for the first time (1: reached, 0: not reached) (step S118). When the flag value FA2 is 1 (YES at step S118), the computing unit 35 skips steps S119 to S121 below and performs the process of step S122 to be described below.
When the flag value FA2 is not 1, that is, when the point of gaze P reaches the specific area A2 for the first time (NO at step S118), the computing unit 35 extracts a measurement result of the timer T1 as reach time data (step S119) and saves a cumulative number representing how many times the point of gaze P shifts among areas until the point of gaze P reaches the specific area A2 (step S120). Thereafter, the computing unit 35 changes the flag value to 1 (step S121).
The computing unit 35 determines whether the area in which the point of gaze P is present in the last detection, that is, the last area is the specific area A2 (step S122). When it is determined that the last area is the specific area A2 (YES at step S122), the computing unit 35 skips steps S123 and step S124 below and performs the process of step S125 to be described below. When it is determined that the last area is not the specific area A2 (NO at step S122), the computing unit 35 incrementally increases by 1 the cumulative number representing how many times the point of gaze P shifts among areas (step S123), sets the specific area A2 for the last area (step S124), and incrementally increases by 1 the count value CNTA2 representing the data on the time of presence in the specific area A2 (step S125). Thereafter, the computing unit 35 performs the process at and after step S131 to be described below.
When it is determined that the point of gaze P is not present in the specific area A2 (NO at step S117), the computing unit 35 determines whether the point of gaze P is present in the comparison area B (step S126). When it is determined that the point of gaze P is present in the comparison area B (YES at step S126), the computing unit 35 determines whether the area in which the point of gaze P is present in the last detection, that is, the last area is the comparison area B (step S127). When it is determined that the last area is the comparison area B (YES at step S127), the computing unit 35 skips step S128 and step S129 below and performs the process of step S130. When it is determined that the last area is not the comparison area B (NO at step S127), the computing unit 35 incrementally increases by 1 the cumulative number representing how many times the point of gaze P shifts among areas (step S128), sets the comparison area B for the last area (step S129), and incrementally increases by 1 the count value CNTB representing the data on the time of presence in the comparison area B (step S130). After step S130, when it is determined that the point of gaze P is not present in the comparison area B at step S126 (NO at step S126), the computing unit 35 performs the process at and after step S131 to be described below.
Thereafter, based on a detection result of the detection timer T1, the computing unit 35 determines whether the time at which reproduction of the evaluation image completes is reached (step S131). When it is determined that the time at which reproduction of the evaluation image completes is not reached (NO at step S131), the computing unit 35 performs the process at and after step S105 repeatedly.
When the computing unit 35 determines that the time at which reproduction of the evaluation image completes is reached (YES at step S131), as illustrated in
The evaluation device 100 according to the embodiment includes the display unit 11; the point-of-gaze detector 32 that detects a position of a point of gaze of a subject on the display unit 11; the display controller 31 that displays, on the display unit 11, the evaluation image IM1 containing the target area M1 serving as a target that the subject is caused to gaze at and containing, in a position different from that of the target area M1, the induction areas C1 and C2 for inducing a hallucination in a subject; the area setting unit 33 that sets, in the display unit 11, the specific areas A1 and A2 corresponding to the induction areas C1 and C2; the determination unit 34 that, based on position data on the point of gaze, determines whether the 1point of gaze is present in the specific area A1 or A2; the computing unit 35 that calculates point-of-gaze data based on a determination result of the determination unit 34, and the evaluation unit 36 that calculates evaluation data on the subject based on the point-of-gaze data.
The evaluation method according to the embodiment includes detecting a position of a point of gaze of a subject on the display unit 11; displaying, on the display unit 11, the evaluation image IM1 containing the target area M1 serving as a target that a subject is caused to gaze at and containing, in a position different from that of the target area M1, the induction areas C1 and C2 for inducing visual hallucinations in a subject; setting, in the display unit 11, the specific areas A1 and A2 corresponding to the induction areas C1 and C2; based on position data on the point of gaze, determining whether the point of gaze is present in the specific area A1 or A2; based on a determination result, calculating point-of-gaze data; and, based on the point-of-gaze data, calculating evaluation data on the subject.
The evaluation program according to the embodiment causes a computer to execute processes of detecting a position of a point of gaze of a subject on the display unit 11; displaying, on the display unit 11, the evaluation image IM1 containing the target area M1 serving as a target that a subject is caused to gaze at and containing, in a position different from that of the target area M1, the induction areas C1 and C2 for inducing visual hallucinations in a subject; setting, in the display unit 11, the specific areas A1 and A2 corresponding to the induction areas C1 and C2; based on position data on the point of gaze, determining whether the point of gaze is present in the specific area A1 or A2; based on a determination result, calculating point-of-gaze data; and, based on the point-of-gaze data, calculating evaluation data on the subject.
In the case where the subject is not suffering from dementia with Lewy bodies, when the evaluation image IM1 is displayed on the display unit 11, the subject is highly likely to gaze at the target area M1 whose sharpness, luminance, and contrast are high. In the case where the subject is suffering from dementia with Lewy bodies, when the evaluation image IM1 is displayed on the display unit 11, the subject is highly likely to gaze at the induction area C1 or C2 that induces visual hallucinations. According to the above-described configuration, because a subject is caused to gaze at the evaluation image IM1 in which the area that tends to induce visual hallucinations in a subject suffering from dementia with Lewy bodies is present, it is possible to make an evaluation not depending on the subjective view of the subject. It is also possible to reduce the effect of contingency because it is possible to calculate evaluation data based on the point-of-gaze data on the subject.
In the evaluation device 100 according to the embodiment, the area setting unit 33 further sets the comparison area B corresponding to the target area M1 in the display unit 11 and the determination unit 34 determines whether the point of gaze is present in the specific areas A1 and A2 and the comparison area B. Accordingly, it is possible to evaluate the subject more accurately.
In the evaluation device 100 according to the embodiment, the values of at least one of sharpness, luminance, contrast and chroma of the induction areas C1 and C2 are lower than that of the target area M1.
Accordingly, the area that tends to cause visual hallucinations in a subject suffering from dementia with Lewy bodies can be contained efficiently.
In the evaluation device 100 according to the embodiment, the value of at least one of sharpness, luminance, contrast and chroma of the target area M1 is higher than that of the surroundings. Accordingly, a subject not suffering from dementia with Lewy bodies is to gaze at the target area M1 and thus it is possible to make an accurate evaluation.
In the evaluation device 100 according to the embodiment, the evaluation image IM1 is a photographic image in which the subject in the target area M1 is present on the front side in the depth direction and the subject in the induction areas C1 and C2 is present on the back side in the depth direction and that is captured with the subject in the target area M1 serving as a position of a focal point. This more assuredly enables a subject not suffering from dementia with Lewy bodies to gaze at the subject in the target area M1 on the front side. Furthermore, the induction areas C1 and C2 that are less artificial and natural can be contained in the evaluation image IM1. Thus, it is possible to inhibit a subject not suffering from dementia with Lewy bodies from gazing at the induction areas C1 and C2 and make an accurate evaluation.
In the evaluation device 100 according to the embodiment, the point-of-gaze data contains at least one of reach time data representing a time to a time at which the point of gaze reaches the specific area A1 or A2 for the first time, shifting number-of-times data representing the number of times for which the position of the point of gaze shifts between the specific area A1 or A2 and the multiple comparison areas B until the point of gaze reaches the specific area A1 or A2 for the first time, and presence time data representing presence time of presence in the specific areas A1 and A2 and last area data representing the area in which the point of gaze is present lastly during the time of display among the specific areas A1 and A2 and the comparison area B and the evaluation unit 36 weights the reach time data, shifting number-of-times data, the presence time data and the last area data differently and calculates evaluation data. Thus, it is possible to reduce the effect of contingency more assuredly.
In the evaluation device 100 according to the embodiment, images with which a significant difference is shown between a subject not suffering from dementia with Lewy bodies and a subject suffering from dementia with Lewy bodies as a result of evaluation by the evaluation unit 36 are used as the evaluation images IM1 and IM2. Accordingly, it is possible to accurately make an evaluation on the possibility that a subject would suffer from dementia with Lewy bodies.
The technical scope of the disclosure is not limited to the embodiment described above and changes can be added as appropriate without departing from the purpose of the disclosure. For example, the above-described embodiment has been described, exemplifying the case where the induction areas C1 to C4 that induce visual hallucinations of the figure of a person or the face of a person are contained in the evaluation images IM1 and IM2; however, embodiments are not limited thereto. For example, an induction area that induces a visual hallucination of an animal other than a person, such as a small animal or an insect, may be contained in the evaluation image.
In the above-described embodiment, the example where an evaluation value is calculated using point-of-gaze data on the specific areas A1 and A2 and the comparison area B; however, embodiments are not limited thereto. For example, an evaluation value may be calculated based on only the point-of-gaze data on the specific areas A1 and A2 without using point-of-gaze data on the comparison area B. In this case, for example, the area setting unit 33 is able to set only the specific areas A1 and A2 without setting the comparison area B.
In the above-described embodiment, the case where a photographic image is displayed as an evaluation image has been described; however, the evaluation image is not limited to a photographic image and a drawn or created image may be used.
The evaluation device, the evaluation method and the evaluation program are usable for, for example, a line-of-sight detection device.
| Number | Date | Country | Kind |
|---|---|---|---|
| 2019-114539 | Jun 2019 | JP | national |
This application is a Continuation of PCT international application Ser. No. PCT/JP2020/024264 filed on Jun. 19, 2020 which designates the United States, incorporated herein by reference, and which claims the benefit of priority from Japanese Patent Application No. 2019-114539, filed on Jun. 20, 2019, incorporated herein by reference.
| Number | Date | Country | |
|---|---|---|---|
| Parent | PCT/JP2020/024264 | Jun 2020 | US |
| Child | 17537556 | US |
