Lesion detection system, lesion detection method, and program

Abstract

The invention according to the present disclosure provides a lesion detection system, and the like for suitably detecting lesions appearing within an iris region. The lesion detection system according to the present disclosure includes an acquisition unit, a calculation unit, and an evaluation unit. The acquisition unit acquires an image of a user including the iris that is compatible with biometric authentication. The calculation unit calculates a feature amount related to iris lesions from the image. The evaluation unit evaluates a degree of lesion progression, which indicates the extent of lesion appearance, on the basis of the feature amount of the iris. The lesion refers to a change in a body caused by disease and is a state in which tissue appears different from normal.

Description

Lesion Detection System, Lesion Detection Method, and Program

[0001] The present disclosure relates to a lesion detection system, a lesion detection method, and a program.

[0002] As represented by preventive medicine, early detection and prediction of diseases are critical social issues that affect improving the cure rate of diseases and reducing medical expenses. Regular hospital visits or frequent health check-ups are effective for early detection and prediction of diseases, but they are difficult to sustain in terms of effort, time, and cost. Here, biometric authentication enables the acquired information to be used for health examinations, and opportunities for using biometric authentication have increased in recent years. Patent Document 1 describes acquiring a first image suitable for authentication processing using an iris, identifying an iris image corresponding to an iris region and a skin image corresponding to a skin region from the first image, performing authentication processing for a subject based on the iris image, and generating health-related information based on the skin image.

[0003] Japanese Unexamined Patent Publication No. 2024-179083

[0004] However, Patent Document 1 does not describe detecting lesions based on information of an iris image. Therefore, the information processing apparatus described in Patent Document 1 cannot detect lesions appearing in an iris region, and cannot suitably achieve early detection and prediction of diseases.

[0005] An object of the present disclosure, in view of the above-described problems, is to provide a lesion detection system or the like that suitably examines lesions appearing in an iris region.

[0006] A lesion detection system according to the present disclosure includes an acquisition unit, a calculation unit, and an evaluation unit. The acquisition unit acquires a user's image including an iris suitable for biometric authentication. The calculation unit calculates a feature amount related to an iris lesion from the image. The evaluation unit evaluates a lesion progression degree indicating the degree of occurrence of a lesion based on the feature amount of the iris.

[0007] The lesion detection system described herein includes an iris authentication terminal and a detection terminal connected to the iris authentication terminal. The iris authentication terminal comprises an imaging unit, a storage unit, and an authentication unit. The imaging unit captures an iris image of a user that conforms to biometric authentication. The storage unit stores user information and registered iris information in association. The authentication unit extracts the user's iris information from the iris image, authenticates the user by comparing the extracted iris information with the registered iris information, and identifies the user information. The detection terminal comprises an acquisition unit, a calculation unit, and an evaluation unit. The acquisition unit connects to the iris authentication terminal and acquires an iris image. The calculation unit calculates feature quantities related to lesions in the iris from the iris image. The evaluation unit evaluates the degree of lesion progression, which indicates the degree of lesion appearance, based on the iris feature quantities.

[0008] The lesion detection method described herein involves a computer performing the following processes: In the acquisition process, the computer acquires an image of the user, including the iris, that conforms to biometric authentication. In the calculation process, the computer calculates feature quantities related to lesions in the iris from the image. In the evaluation process, the computer evaluates the degree of lesion progression, which indicates the degree of lesion appearance, based on the iris feature quantities.

[0009] The program relating to this disclosure causes a computer to perform the following processes: In the acquisition process, the computer acquires an image of the user, including the iris, that conforms to biometric authentication. In the calculation process, the computer calculates feature quantities related to lesions in the iris from the image. In the evaluation process, the computer evaluates the degree of lesion progression, which indicates the degree of lesion appearance, based on the iris feature quantities.

[0010] This disclosure provides a lesion detection system, a lesion detection method, and a program for suitably detecting lesions appearing within the iris region.

[0011] This is a first block diagram of the lesion detection system according to this disclosure. This is an image of an eye including the iris. This is a first flowchart of the lesion detection method according to this disclosure. This is a second block diagram of the lesion detection system according to this disclosure. This is a second flowchart of the lesion detection method according to this disclosure. This is a system configuration diagram of the lesion detection system according to this disclosure. This is a block diagram illustrating the hardware configuration of a computer.

[0012] The present disclosure will be described below through embodiments, but the invention claimed is not limited to the following embodiments. Furthermore, not all of the configurations described in the embodiments are necessarily essential for solving the problem. For clarity of explanation, the following descriptions and drawings have been omitted and simplified as appropriate. In each drawing, the same elements are denoted by the same reference numerals, and redundant explanations have been omitted where necessary.

[0013] Embodiment 1 Hereinafter, an example of the configuration of the lesion detection system 10 will be described with reference to Figure 1. Figure 1 is a first block diagram of the lesion detection system 10 according to this disclosure. The lesion detection system 10 acquires an image of a user that conforms to biometric authentication and evaluates the progression of the lesion. Here, biometric authentication can be any method that extracts biometric information using an image of the user's iris taken with sufficient resolution and authenticates based on the extracted biometric information. Note that the image is not limited to a still image, but may also be a video or a frame image contained in a video. Examples of biometric authentication include iris authentication, retinal authentication, facial authentication, or motion authentication. Furthermore, the progression of the lesion is an index that indicates the degree of appearance of the lesion. Here, a lesion refers to a change in the body caused by a disease, and is a state in which the tissue looks different from normal.

[0014] The lesion detection system comprises an acquisition unit 101, a calculation unit 102, and an evaluation unit 103. The acquisition unit 101 is connected to the calculation unit 102. The calculation unit 102 is connected to both the acquisition unit 101 and the evaluation unit 103. The evaluation unit 103 is connected to the calculation unit 102.

[0015] The acquisition unit 101 acquires an image of the user, including the iris, that is suitable for biometric authentication. The acquisition unit 101 may, for example, be connected to a biometric authentication device that performs biometric authentication and acquire an image from the biometric authentication device. Alternatively, the acquisition unit 101 may be connected to an imaging device or communication device that provides an image to the biometric authentication device that performs biometric authentication and acquire an image.

[0016] The calculation unit 102 calculates feature quantities related to iris lesions from the image acquired by the acquisition unit 101. First, the calculation unit 102 identifies the iris region from the image and extracts the image of the iris portion. Next, the calculation unit 102 extracts feature quantities related to lesions from the image of the iris portion. The feature quantities related to lesions include information such as the number, location, or shape of abnormally colored areas in the iris region, or the ratio of abnormally colored areas to the iris region. Abnormally colored areas are areas where the color has changed due to, for example, blood vessels in the iris, congestion in the iris, pigment deposition in the iris, or corneal opacity.

[0017] Here, the iris will be described in detail with reference to Figure 2. Figure 2 is an illustrative image of an eye 20 including the iris 21. The iris 21 is the area indicated by the diagonal lines within the pupil of the eye 20 in Figure 2, and is located between the white of the eye and the pupil 22. The pattern of the iris 21 differs from person to person. Generally, the pattern of the iris 21 is formed in early childhood and does not change throughout life after its formation. Therefore, the pattern of the iris 21 can be used for biometric authentication. Biometric authentication based on the pattern of the iris 21 is called iris authentication. Iris authentication terminals generally divide the area of ​​the iris 21 on the image into multiple regions according to the angle and distance from the center of the pupil 22, identify the color of each of the multiple regions, and perform iris authentication by authenticating based on the color pattern within the identified area of ​​the iris 21.

[0018] Although it has been explained that the pattern of the iris 21 generally does not change, it is known that symptoms can be observed in the iris 21 region in some diseases. Examples of symptoms observed in the iris 21 region include iris rubeosis and iritis. In addition, surgery on the iris 21 may be performed as a treatment for glaucoma. The calculation unit 102 calculates the changes in the iris 21 related to the above-mentioned lesions and postoperative course as characteristic quantities of the iris 21.

[0019] The evaluation unit 103 evaluates the progression of the lesion based on the iris feature quantities calculated by the calculation unit 102. The evaluation unit 103 may, for example, evaluate the progression of the lesion as a binary value of presence or absence of a lesion. Alternatively, the evaluation unit 103 may evaluate the progression of the lesion using a continuous numerical index. The evaluation unit 103 may also evaluate the progression of the lesion in a checklist format or using a multi-dimensional index. Furthermore, the evaluation unit 103 may comprehensively evaluate the progression of the lesion based on the iris feature quantities. The evaluation unit 103 may evaluate the progression of the lesion only for specific lesions. Alternatively, the evaluation unit 103 may evaluate the progression of the lesion for multiple lesions. The evaluation unit 103 may output the evaluated progression of the lesion to a recording unit (not shown) or a communication unit connected to an external device.

[0020] Next, the flow of the lesion detection method in the lesion detection system 10 will be explained using Figure 3. Figure 3 is a first flowchart of the lesion detection method according to this disclosure. The lesion detection method in the lesion detection system 10 includes steps S11 to S13.

[0021] Step S11 is an acquisition process. In step S11, the acquisition unit 101 of the lesion detection system 10 acquires an image of the user, including the iris, that is compatible with biometric authentication. The acquisition unit 101 connects, for example, to a biometric authentication device that performs biometric authentication and acquires an image from the biometric authentication device.

[0022] Step S12 is a calculation process. In step S12, the calculation unit 102 of the lesion detection system 10 calculates iris feature quantities from the image acquired by the acquisition unit 101. First, the calculation unit 102 identifies the iris region from the image and extracts the image of the iris portion. Next, the calculation unit 102 extracts feature quantities related to the lesion from the image of the iris portion. The feature quantities related to the lesion include information such as the number, location, or shape of abnormal color regions in the iris region, or the ratio of abnormal color regions to the iris region.

[0023] Step S13 is an evaluation process. In step S13, the evaluation unit 103 of the lesion detection system 10 evaluates the progression of the lesion based on the iris feature quantities calculated by the calculation unit 102. For example, the evaluation unit 103 comprehensively evaluates the progression of the lesion based on the iris feature quantities. The evaluation unit 103 may evaluate the progression of the lesion only for a specific lesion. Alternatively, the evaluation unit 103 may evaluate the progression of the lesion for multiple lesions, one for each.

[0024] As described above, the lesion detection system 10 acquires an image of a user that matches the biometric authentication criteria and evaluates the progression of the lesion by calculating characteristic quantities related to the iris lesion from the image. This allows the lesion detection system 10 to perform a health check of the iris at the same time as acquiring an image of the user including the iris for the purpose of biometric authentication. Therefore, the lesion detection system 10 can suitably perform a health check of lesions that appear within the iris region.

[0025] The lesion detection system 10 may also have a processor and a memory device, although these are not shown in the diagram. The memory device of the lesion detection system 10 may include, for example, a memory device that includes non-volatile memory such as flash memory or an SSD (Solid State Drive). In this case, the memory device stores a computer program (hereinafter also simply referred to as a program) for executing the above-described method. The processor loads the computer program from the memory device into a buffer memory such as DRAM (Dynamic Random Access Memory) and executes the program.

[0026] Each component of the lesion detection system 10 may be implemented with dedicated hardware. Furthermore, some or all of each component may be implemented by general-purpose or dedicated circuits, processors, etc., or combinations thereof. These may be implemented by a single chip or by multiple chips connected via a bus. Some or all of each component of each device may be implemented by a combination of the aforementioned circuits, etc., and programs. Processors include CPUs (Central Processing Units), GPUs (Graphics Processing Units), FPGAs (Field-Programmable Gate Arrays), etc. Also, at least a portion of the processing performed by the lesion detection system 10 may be provided as SaaS (Software as a Service). The descriptions of the configurations described herein may also apply to other systems described below in this disclosure.

[0027] Embodiment 2 Hereinafter, an example of the configuration of the lesion detection system 11 will be described with reference to Figure 4. Figure 4 is a second block diagram of the lesion detection system 11 according to this disclosure. Figure 4 shows the configuration of the lesion detection system 11. The lesion detection system 11 has some of the same configuration as the lesion detection system 10 described with reference to Figure 1. Therefore, the configuration that performs processing that overlaps with the lesion detection system 10 will not be described. The lesion detection system 11 includes a storage unit 111, an acquisition unit 112, a calculation unit 113, an evaluation unit 114, and a notification unit 115. The lesion detection system 11 communicates with the result provision device 30 via the network 40. The lesion detection system 11 acquires biometric authentication results from the result provision device 30 and evaluates the progression of the lesion from the iris image based on the user information indicated by the biometric authentication results.

[0028] The storage unit 111 stores the user's user information 1111. Here, user information 1111 is information used to identify the user in the system. User information 1111 may include, for example, an identification number, identification code, or the user's registered name. User information 1111 may also include information related to the evaluation of lesion detection. Information related to the evaluation of lesion detection may include, for example, medical history information showing the patient's medical history, medication information showing medications currently being taken, diagnostic information showing the results of a health checkup, or registration information showing the registration status in the health checkup application.

[0029] Furthermore, the memory unit 111 stores the progression of the lesion or characteristic quantities related to the lesion of the iris as state time-series information 1112, linked to the user information 1111. The state time-series information 1112 includes information on the progression of the lesion or characteristic quantities from at least one past time when the user underwent a health checkup for the iris. Here, the information on the progression of the lesion or characteristic quantities from the past may be calculated or evaluated by the lesion detection system 11, or it may be the result of a health checkup using another health checkup method. If the user has never undergone a health checkup for the iris, the state time-series information 1112 is empty data. The state time-series information 1112 may also include health checkup date and time information indicating the date and time of the health checkup in which the information on the progression of the lesion or characteristic quantities was generated. That is, the health checkup date and time information indicates the date and time of a past health checkup that the user underwent. With this, the lesion detection system 11 can determine the frequency and criteria for detecting lesions of the iris according to the user's health checkup status.

[0030] The storage unit 111 is a storage device that includes non-volatile memory such as flash memory or an SSD. The storage unit 111 may also be a storage device on a network, such as a server. Alternatively, the storage unit 111 may be a storage device implemented using multiple devices on a network with a distributed management method such as a cloud.

[0031] The acquisition unit 112 further acquires the user's biometric authentication result based on the image. Here, the acquisition unit 112 communicates with the result provision device 30 via the network 40 and acquires the user's biometric authentication result from the result provision device 30. As a result, the lesion detection system 11 can verify the user from the biometric authentication result and perform a health checkup tailored to the user. The acquisition unit 112 may further acquire an image of the user, including the iris, that matches the biometric authentication from the result provision device 30.

[0032] The result providing device 30 is a device that provides biometric authentication results. The result providing device 30 is, for example, a biometric authentication device that performs biometric authentication. The result providing device 30 may also be an external storage device such as a server that records biometric authentication results. In this case, the acquisition unit 112 acquires the user's location information and time information indicating the time when the user's biometric authentication was performed, and identifies and acquires the user's biometric authentication result from the external storage device. Here, the acquisition unit 112 may use the location and time information of the biometric authentication device and the current time as the user's location information and time information. Alternatively, the acquisition unit 112 may communicate with the user's terminal and acquire the user's location information and time information.

[0033] Here, biometric authentication is, for example, iris recognition. The lesion detection system 11 can use the iris recognition result to directly utilize the image of the user's iris used for iris recognition. Therefore, the lesion detection system 11 can reduce the computational load required for preprocessing the acquired image.

[0034] Furthermore, the network 40 connects the lesion detection system 11 and the result provisioning device 30. The network 40 is either a wired or wireless network. If the network 40 is a wireless network, it is configured using, for example, Bluetooth® or Wi-Fi®.

[0035] The calculation unit 113 calculates characteristic values ​​for blood vessels included in the iris region. Here, the blood vessels are neovascularizations. Normally, there are no clearly visible blood vessels in the iris, but it is known that neovascularization can be seen on the surface of the iris as a symptom of some diseases. The condition in which neovascularization is seen on the surface of the iris is called iris rubeosis. Iris rubeosis can be caused by diabetes, for example. Iris rubeosis can lead to the rapid progression of glaucoma, and early detection is important for this lesion.

[0036] The calculation unit 113 calculates characteristic values ​​for blood vessels based, for example, on the red intensity in the iris. Red intensity indicates how strong the red color is. Specifically, the calculation unit 113 uses the R (Red) value when the iris color is represented by an RGB color code as the red intensity. The calculation unit 113 may also use the ratio of the R value to the sum of the values ​​of each color in the RGB color code as the red intensity. With this, the calculation unit 113 can detect neovascularization that can be seen as a strong red color in an image captured with a normal camera sensor. Therefore, the lesion detection system can detect neovascularization caused by lesions at a lower cost and with less invasiveness than when using iris images taken with a near-infrared light camera.

[0037] Furthermore, the calculation unit 113 may calculate characteristic quantities for blood vessels when the proportion of the iris region where the red intensity exceeds a predetermined color threshold exceeds a predetermined proportion. This allows the lesion detection system 11 to perform a health check when there is a possibility of iris rubeosis. Therefore, the lesion detection system 11 can reduce its computational load.

[0038] The evaluation unit 114 determines the number of neovascularizations based on feature quantities and evaluates the progression of iris rubeosis as the progression of the lesion based on the number of neovascularizations. In this way, the lesion detection system 11 can quantitatively evaluate the progression of iris rubeosis. The evaluation unit 114 may also determine the location, distribution, or length of neovascularizations from feature quantities related to the iris lesion and use this to evaluate the progression of the lesion.

[0039] Furthermore, the evaluation unit 114 determines evaluation settings for at least one of the evaluation criteria and evaluation frequency based on the user information of the user corresponding to the biometric authentication result, and evaluates the progression of the lesion based on the evaluation settings.

[0040] Here, the evaluation criteria are the criteria and method for evaluating the progression of the lesion, which are set for each user. The evaluation criteria are, for example, the threshold values ​​set for each user when evaluating the progression of the lesion as a binary value. Based on the evaluation criteria, the evaluation unit 114 may determine the method for evaluating the progression of the lesion as a binary value or a continuous numerical index for each user. The evaluation frequency is the frequency of iris examinations set for each user. In other words, the evaluation frequency indicates how often the evaluation unit 114 evaluates the progression of the lesion in the iris. The evaluation frequency may be, for example, once a day, once a week, once a month, etc. With this, the lesion detection system 11 can evaluate the progression of the lesion with settings that are appropriate for each individual user.

[0041] Furthermore, the evaluation unit 114 may acquire state time-series information linked to user information and compare the latest lesion progression or characteristic quantity with past state time-series information. The evaluation unit 114 may also refer to the health check date and time information included in the state time-series information and extract the most recent state time-series information. This allows the evaluation unit 114 to evaluate the changes in the lesion over time. The evaluation unit 114 may also extract information from multiple previous health checks from the state time-series information and evaluate the changes in the lesion over time in more detail.

[0042] The notification unit 115 notifies the user based on the progression of the disease. The notification unit 115 is equipped with communication means or presentation means (not shown). The communication means connects to the user terminal or external presentation device via wired communication or wireless communication, etc. The communication means may also connect to the user terminal or external presentation device via the network 40. Here, the user terminal is, for example, a smartphone, tablet, or PC (Personal Computer) owned by the user. The external presentation device is, for example, a monitor or speaker. The external presentation device may be a communication terminal that sends a message or email based on the progression of the disease to the user terminal. The presentation means presents information based on the progression of the disease to the user through visual, auditory, or tactile stimuli. The presentation means is, for example, a monitor, printer, speaker, or vibrator.

[0043] The notification unit 115 may notify the user of a first warning indicating a high probability of a lesion when the progression of the lesion exceeds a first threshold determined in advance. The first threshold is a threshold for the progression of the lesion evaluated by the evaluation unit 114. The first warning is information that informs the user of the high probability of a lesion. The first warning is notified to the user using, for example, a message, light emission, sound, or vibration. In this way, the lesion detection system 11 can notify the user of information regarding the detected lesion. Therefore, the lesion detection system 11 can support the user in the early detection and treatment of diseases.

[0044] The notification unit 115 may notify the user of a second warning indicating a sudden change in a lesion when the difference between the lesion progression degree based on the feature amount calculated from an image and the lesion progression degree included in the state time-series information associated with the user information corresponding to the biometric authentication result is higher than a predetermined second threshold. The second threshold is a threshold for the difference between the lesion progression degree evaluated by the evaluation unit 114 and the past lesion progression degree included in the state time-series information. The second warning is information that notifies the user that the lesion has changed suddenly. The second warning is notified to the user by using, for example, a message, light emission, sound, or vibration. According to this configuration, the lesion detection system 11 can notify the user when the state of a lesion has changed abruptly. Therefore, the lesion detection system 11 can appropriately assist the user in early detection and early treatment of a disease.

[0045] In addition, the notification unit 115 may determine at least one of the first threshold and the second threshold based on the user information. The notification unit 115 can determine notification criteria based on, for example, the user's degree of interest in health or the presence or absence of a relevant medical history. According to this configuration, the lesion detection system 11 can provide the user with information related to the lesion according to the user's situation. Furthermore, the notification unit 115 may determine at least one of the first threshold and the second threshold based on the state time-series information. For example, when the user's previous medical examination result was poor, the notification unit 115 lowers the first threshold and the second threshold to determine whether to issue a notification. According to this configuration, the lesion detection system 11 can appropriately present information to a user who requires follow-up observation.

[0046] Next, the flow of a lesion detection method in the lesion detection system 11 will be described with reference to FIG. 5. FIG. 5 is a second flowchart of the lesion detection method according to the present disclosure. The lesion detection method in the lesion detection system 11 includes steps S21 to S28.

[0047] Step S21 is a storage process. In step S21, the storage unit 111 of the lesion detection system 11 stores user information of a user. The user information is information for identifying the user in the system. Further, the storage unit 111 stores the lesion progression level or feature amounts related to iris lesions in association with the user information as state time-series information. The state time-series information includes information on at least one past lesion progression level or feature amount obtained when the user underwent a health check-up for the iris.

[0048] Step S22 is an acquisition process. In step S22, the acquisition unit 112 of the lesion detection system 11 acquires a user's image including an iris adapted for biometric authentication and a user's biometric authentication result based on the image. The acquisition unit 112 acquires the user's image and the biometric authentication result from a result providing device via a network. The result providing device is, for example, a biometric authentication device that executes biometric authentication.

[0049] Step S23 is a calculation process. In step S23, the calculation unit 113 of the lesion detection system 11 calculates a feature amount for blood vessels included in the iris region based on red intensity. Here, the blood vessels are neovascular vessels. The red intensity indicates the degree of intensity of red in a color. For example, when the color of the iris is represented by an RGB color code, the calculation unit 113 uses the numerical value of R (Red) as the red intensity.

[0050] Step S24 is part of an evaluation process. In step S24, the evaluation unit 114 of the lesion detection system 11 determines an evaluation setting related to at least one of an evaluation criterion and an evaluation frequency based on the user information of the user corresponding to the biometric authentication result. Here, the evaluation criteria are the criteria and methods for evaluating the lesion progression level set for each user. The evaluation criterion is, for example, a threshold set for each user when the lesion progression level is evaluated in binary. Further, the evaluation frequency is the health check-up frequency for the iris set for each user. That is, the evaluation frequency indicates the frequency at which the evaluation unit 114 evaluates the lesion progression level of the iris. The evaluation frequency is, for example, once a day, once a week, once a month, or the like.

[0051] Step S25 is part of the evaluation process. In step S25, the evaluation unit 114 determines the number of neovascularizations based on feature quantities. The evaluation unit 114 may also determine the location, distribution, or length of neovascularizations from feature quantities relating to lesions in the iris.

[0052] Step S26 is part of the evaluation process. In step S26, the evaluation unit 114 evaluates the progression of the lesion based on the evaluation settings and the number of neovascularizations. Here, the evaluation unit 114 evaluates the progression of iris rubeosis as the progression of the lesion. Iris rubeosis can lead to the rapid progression of glaucoma, and early detection is important for this lesion.

[0053] Step S27 is part of the evaluation process. In step S27, the evaluation unit 114 acquires state time-series information linked to user information and compares the latest lesion progression or feature quantity with past state time-series information. The evaluation unit 114 may also extract information from multiple previous health checkups from the state time-series information to evaluate the changes in the lesion over time in more detail. This allows the evaluation unit 114 to evaluate the changes in the lesion over time. The evaluation process that started from step S24 ends upon completion of step S27.

[0054] Step S28 is a notification process. In step S28, the notification unit 115 of the lesion detection system 11 notifies the user based on the lesion progression. The notification unit 115 includes in the notification content the result of comparing the latest lesion progression or feature quantity performed in step S27 with past state time series information.

[0055] Here, the notification unit 115 includes communication means or presentation means (not shown). The communication means connects to a user terminal or external presentation device via wired communication or wireless communication, etc. The external presentation device is, for example, a monitor or speaker. The external presentation device may also be a communication terminal that sends messages or emails based on the information progress to the user terminal. The presentation means presents information based on the information progress to the user through visual, auditory, or tactile stimuli. The presentation means is, for example, a monitor, printer, speaker, or vibrator. The processing of the series of lesion detection methods is completed upon completion of step S28.

[0056] As described above, the lesion detection system 11 evaluates the progression of neovascularization in the iris region from an image of a user that matches the biometric authentication. This allows the lesion detection system 11 to perform a health check for iris rubeosis simultaneously with acquiring an image of the user including the iris for the purpose of biometric authentication. Therefore, the lesion detection system 11 can more effectively check for lesions appearing in the iris region. Furthermore, the lesion detection system 11 acquires the user's biometric authentication result and determines evaluation settings based on user information corresponding to the user. This allows the lesion detection system 11 to effectively check for lesions appearing in the iris region with settings appropriate for the user.

[0057] In the above-described embodiment, the case of detecting neovascularization within the iris region using red intensity was explained, but the invention is not limited to this. For example, the method of this disclosure can also be applied to images acquired using a near-infrared light camera. In detail, hemoglobin contained in blood has a high absorption rate of near-infrared light. Therefore, in an iris image taken with a near-infrared light camera, blood vessels carrying blood are represented by a strong black color. In other words, the calculation unit can detect neovascularization based on the low brightness of the iris image taken with a near-infrared light camera. As a result, the lesion detection system can clearly detect neovascularization caused by lesions.

[0058] Furthermore, the acquisition unit may communicate with the iris authentication terminal and acquire the noise rate in the image during iris authentication from the iris authentication terminal. Here, the noise rate is the percentage of the iris image in the region that the iris authentication terminal judged to be noise during iris authentication. Neovascularization forms on the iris and is treated as noise in iris authentication. Therefore, a high noise rate during iris authentication indicates that iris rubeosis is progressing and that there may be many neovascularizations within the iris region.

[0059] In this case, the calculation unit calculates iris features based on the noise rate. For example, the calculation unit starts calculating iris features when the noise rate exceeds a predetermined threshold. The calculation unit may, for example, determine a threshold for red intensity during feature calculation according to the noise rate. This allows the lesion detection system to effectively support the early detection and treatment of diseases in the user.

[0060] Embodiment 3 Hereinafter, an example of the configuration of the lesion detection system 12 will be described with reference to Figure 6. Figure 6 is a system configuration diagram of the lesion detection system 12 according to this disclosure. The lesion detection system 11 includes an iris authentication terminal 121 and a detection terminal 122. The iris authentication terminal 121 and the detection terminal 122 communicate via a network 41. The lesion detection system 12 has some of the same configuration as the lesion detection system 11 described with reference to Figure 4. Therefore, the configuration that performs processing that overlaps with the lesion detection system 11 will not be described.

[0061] The iris authentication terminal 121 is a device that captures an image of the user's iris and performs user authentication using iris authentication based on the captured iris image. The iris authentication terminal 121 is installed, for example, near the entrance of a facility to manage entry and exit. The iris authentication terminal 121 includes an imaging unit 1211, a storage unit 1212, an authentication unit 1213, and a communication means 1214.

[0062] The imaging unit 1211 captures an iris image of the user that conforms to biometric authentication. The imaging unit 1211 is, for example, a camera. The imaging unit 1211 may be a near-infrared camera, or an imaging device equipped with a visible light camera and a near-infrared camera. The imaging unit may be equipped with a presentation means to present to the user an explanation of the imaging status and instructions for re-imaging. The presentation means may be, for example, a monitor, a projection device, or a speaker. The presentation means presents information about imaging to the user, for example, by displaying it on a monitor, projecting an image onto a wall or glass, or outputting audio from a speaker.

[0063] The storage unit 1212 stores user information and registered iris information in association. For example, the storage unit 1212 receives input from the interface (not shown) of the iris authentication terminal and the imaging unit 1211 in advance, and records the user information and registered iris information in association. The storage unit 1212 may also be connected to an external network such as the Internet, and acquire and record user information and registered iris information from the external network.

[0064] The authentication unit 1213 extracts the user's iris information from the iris image, authenticates the user by comparing the extracted iris information with registered iris information, and identifies the user information. The authentication unit 1213 may perform a general iris authentication method. Therefore, a detailed explanation of the iris authentication method performed by the authentication unit 1213 is omitted.

[0065] The communication means 1214 communicates with the detection terminal 122 via the network 41. The iris authentication terminal 121 connects to the detection terminal 122 via the communication means 1214 and transmits the user's iris image to the detection terminal 122. For example, the iris authentication terminal 121 transmits the captured iris image to the detection terminal 122 via the communication means 1214 each time iris authentication is performed. The iris authentication terminal 121 may also transmit the captured iris image to the detection terminal 122 via the communication means 1214 based on the user's authentication result.

[0066] Next, the detection terminal 122 is a device that acquires the user's iris image and detects lesions occurring in the iris region. The detection terminal 122 is, for example, a server device connected to an iris authentication terminal. The detection terminal 122 may be manufactured together with the iris authentication terminal and contained in the same housing. The detection terminal 122 includes an acquisition unit 1221, a calculation unit 1222, and an evaluation unit 1223.

[0067] The acquisition unit 1221 communicates with the iris authentication terminal 121 via the network 41. The detection terminal 122 connects to the iris authentication terminal 121 via the acquisition unit 1221 and acquires the iris image used by the iris authentication terminal 121 for iris authentication. In Figure 6, the detection terminal 122 is connected to one iris authentication terminal 121, but it is not limited to this and may be connected to multiple iris authentication terminals 121 to acquire iris images. With this configuration, the lesion detection system 12 can suitably collect iris images from multiple iris authentication terminals and detect lesions in the irises of a wide range of users.

[0068] The calculation unit 1222 calculates feature quantities related to iris lesions from the iris image acquired via the acquisition unit 1221. The method for calculating the feature quantities in the calculation unit 1222 is omitted here as it overlaps with the explanation of the calculation unit described with reference to Figures 1 and 4.

[0069] The evaluation unit 1223 evaluates the degree of lesion progression, which indicates the extent of lesion appearance, based on the characteristic quantities of the iris. The evaluation method of the evaluation unit 1223 for the degree of lesion progression is omitted here as it overlaps with the explanation of the evaluation unit described with reference to Figures 1 and 4. The evaluation unit 1223 may be equipped with a presentation means to present information about the evaluated degree of lesion progression to the user. The presentation means may be, for example, a monitor, a projection device, or a speaker. The presentation means may present information about the degree of lesion progression by, for example, displaying it on a monitor, projecting an image onto a wall or glass, or outputting sound from a speaker.

[0070] The evaluation unit 1223 may output information to the display means provided by the imaging unit 1211 to display information about the progression of the lesion. Furthermore, the evaluation unit 1223 may be equipped with means for communication with an external network such as the Internet, and may send a message or email based on the progression of the lesion to the user's terminal.

[0071] Network 41 connects the iris authentication terminal 121 and the detection terminal 122. Network 41 is either a wired or wireless network. If network 41 is a wireless network, it is configured using, for example, Bluetooth® or Wi-Fi®.

[0072] As described above, the lesion detection system 12 includes an iris authentication terminal 121 and a detection terminal 122. Based on the user's iris image captured by the iris authentication terminal 121 for iris authentication, the detection terminal 122 can evaluate the progression of iris lesions. Therefore, the lesion detection system 12 can suitably detect lesions that appear in the iris region when iris authentication is performed.

[0073] <Examples of Hardware Configurations> The following describes examples of how each functional configuration of the lesion detection system described herein can be realized through a combination of hardware and software.

[0074] Figure 7 is a block diagram illustrating the hardware configuration of a computer. The lesion detection system according to this disclosure can realize the above-described functions using a computer 500 including the hardware configuration shown in the figure. The computer 500 may be a portable computer such as a smartphone or tablet terminal, or a stationary computer such as a PC. The computer 500 may be a dedicated computer designed to realize each device, or it may be a general-purpose computer. The computer 500 can realize the desired functions by installing a predetermined application.

[0075] The computer 500 includes a bus 502, a processor 504, a memory 506, a storage device 508, an input / output interface (I / F) 510, and a network interface (I / F) 512. The bus 502 is a data transmission path for the processor 504, memory 506, storage device 508, input / output interface 510, and network interface 512 to send and receive data to and from each other. However, the method of connecting the processor 504 and the other components to each other is not limited to bus connection.

[0076] The processor 504 is a variety of processor such as a CPU, GPU, or FPGA. The memory 506 is a main memory implemented using RAM (Random Access Memory) or the like.

[0077] The storage device 508 is an auxiliary storage device implemented using a hard disk, SSD, memory card, or ROM (Read Only Memory). The storage device 508 stores a program for realizing a desired function. The processor 504 reads this program into memory 506 and executes it to realize each functional component of each device.

[0078] The input / output interface 510 is an interface for connecting the computer 500 with input / output devices. For example, input devices such as keyboards and output devices such as display devices are connected to the input / output interface 510. The network interface 512 is an interface for connecting the computer 500 to a network.

[0079] In the embodiments described above, the disclosure was explained as a hardware configuration, but the disclosure is not limited thereto. The disclosure can also be implemented by having a CPU (Central Processing Unit) execute a computer program to perform the processing steps described in the flowchart of Figure 3.

[0080] Programs can be stored and supplied to a computer using various types of non-transitory computer-readable medium. Non-transitory computer-readable mediums include various types of tangible storage mediums. Examples of non-transitory computer-readable mediums include magnetic storage media (e.g., flexible disks, magnetic tapes, hard disk drives), magneto-optical storage media (e.g., magneto-optical disks), CD-ROMs, CD-Rs, CD-R / Ws, and semiconductor memory (e.g., mask ROMs, PROMs (Programmable ROMs), EPROMs (Erasable PROMs), flash ROMs, RAMs). Programs may also be supplied to a computer using various types of transient computer-readable mediums. Examples of transient computer-readable mediums include electrical signals, optical signals, and electromagnetic waves. Transitory computer-readable mediums can be supplied to a computer via wired communication channels such as electric wires and optical fibers, or via wireless communication channels.

[0081] While this disclosure has been described with reference to embodiments, it is not limited to the embodiments described above. Various modifications to the structure and details of this disclosure are possible, as can be understood by those skilled in the art within the scope of this disclosure. Furthermore, each embodiment can be combined with other embodiments as appropriate.

[0082] Each drawing is merely illustrative to illustrate one or more embodiments. Each drawing may be associated with one or more other embodiments, rather than being associated with only one specific embodiment. As those skilled in the art will understand, various features or steps described with reference to any one drawing can be combined with features or steps shown in one or more other drawings to create embodiments that are not explicitly illustrated or described. Not all features or steps shown in any one drawing to illustrate an exemplary embodiment are necessarily required, and some features or steps may be omitted. The order of steps shown in any of the drawings may be changed as appropriate.

[0083] Some or all of the above embodiments may also be described as follows, but are not limited to the following: (Note 1) A lesion detection system comprising: an acquisition unit that acquires an image of a user including an iris that conforms to biometric authentication; a calculation unit that calculates feature quantities relating to lesions in the iris from the image; and an evaluation unit that evaluates the degree of lesion progression indicating the degree of appearance of the lesion based on the feature quantities of the iris. (Note 2) The lesion detection system according to Note 1, wherein the calculation unit calculates the feature quantities for blood vessels included in the region of the iris. (Note 3) The lesion detection system according to Note 2, wherein the blood vessels are neovascularization, and the evaluation unit determines the number of neovascularizations based on the feature quantities and evaluates the degree of progression of iris rubeosis as the degree of lesion progression based on the number of neovascularizations. (Note 4) The lesion detection system according to Note 2 or 3, wherein the calculation unit calculates the feature quantities for the blood vessels based on the red intensity in the iris. (Note 5) The lesion detection system according to any one of Notes 2 to 4, wherein the calculation unit calculates the feature quantity for the blood vessel when the proportion of the region of the iris in which the red intensity exceeds a predetermined color threshold exceeds a predetermined proportion. (Note 6) The lesion detection system according to any one of Notes 1 to 5, further comprising a storage unit for storing the user information of the user, the acquisition unit further acquiring the user's biometric authentication result based on the image, and the evaluation unit determining evaluation settings for at least one of evaluation criteria and evaluation frequency based on the user information of the user corresponding to the biometric authentication result, and evaluating the lesion progression based on the evaluation settings. (Note 7) The lesion detection system according to Note 6, wherein the storage unit stores the lesion progression or the feature quantity as state time-series information linked to the user information, and the evaluation unit acquires the state time-series information linked to the user information and compares the latest lesion progression or the feature quantity with past state time-series information.(Note 8) A lesion detection system according to any one of Notes 1 to 7, further comprising a notification unit that notifies the user based on the progression of the lesion, wherein the notification unit notifies the user of a first warning indicating a high probability of a lesion when the progression of the lesion exceeds a first threshold determined in advance. (Note 9) A lesion detection system according to Note 8, further comprising a storage unit that stores the progression of the lesion or the feature quantity as state time-series information linked to the user's user information, wherein the acquisition unit further acquires the user's biometric authentication result based on the image, wherein the notification unit notifies the user of a second warning indicating a sudden change in the lesion when the difference between the progression of the lesion based on the feature quantity calculated from the image and the progression of the lesion included in the state time-series information linked to the user information corresponding to the biometric authentication result is higher than a second threshold determined in advance. (Note 10) A lesion detection system according to Note 9, wherein the notification unit determines at least one of the first threshold and the second threshold based on the user information. (Note 11) The lesion detection system according to any one of Notes 1 to 10, wherein the biometric authentication is iris authentication. (Note 12) The lesion detection system according to Note 11, wherein the acquisition unit communicates with an iris authentication terminal and acquires the noise rate in the image at the time of iris authentication from the iris authentication terminal, and the calculation unit calculates the feature quantities of the iris based on the noise rate. (Note 13) A lesion detection system comprising an iris authentication terminal and a detection terminal connected to the iris authentication terminal, wherein the iris authentication terminal includes: an imaging unit for capturing an iris image of a user suitable for biometric authentication; a storage unit for storing user information and registered iris information in association; an authentication unit for extracting the user's iris information from the iris image, authenticating the user by comparing the extracted iris information and the registered iris information, and identifying the user information; and the detection terminal includes: an acquisition unit connected to the iris authentication terminal for acquiring the iris image; a calculation unit for calculating feature quantities relating to lesions in the iris from the iris image; and an evaluation unit for evaluating the degree of lesion progression indicating the degree of appearance of the lesion based on the feature quantities of the iris.(Note 14) A lesion detection method comprising: an acquisition process in which a computer acquires an image of a user including an iris that conforms to biometric authentication; a calculation process in which a feature quantity relating to a lesion in the iris is calculated from the image; and an evaluation process in which a lesion progression degree indicating the degree of appearance of the lesion is evaluated based on the feature quantity of the iris. (Note 15) The lesion detection method according to Note 14, wherein in the calculation process, the feature quantity is calculated for blood vessels included in the region of the iris. (Note 16) The lesion detection method according to Note 15, wherein the blood vessels are neovascularization, and in the evaluation process, the number of neovascularizations is determined based on the feature quantity, and the progression of iris rubeosis is evaluated as the lesion progression degree based on the number of neovascularizations. (Note 17) The lesion detection method according to Note 15 or 16, wherein in the calculation process, the feature quantity is calculated for the blood vessels based on the red intensity in the iris. (Note 18) A lesion detection method according to any one of Notes 15 to 17, wherein in the calculation process, the feature quantity is calculated for the blood vessel when the proportion of the region of the iris in which the red intensity exceeds a predetermined color threshold exceeds a predetermined proportion. (Note 19) A lesion detection method according to any one of Notes 14 to 18, further comprising a storage process for storing the user information of the user, wherein in the acquisition process, the biometric authentication result of the user based on the image is further acquired, and in the evaluation process, evaluation settings relating to evaluation criteria and evaluation frequency are determined based on the user information of the user corresponding to the biometric authentication result, and the degree of lesion progression is evaluated based on the evaluation settings. (Note 20) A program that causes a computer to execute: an acquisition process for acquiring an image of a user including an iris that conforms to biometric authentication; a calculation process for calculating a feature quantity relating to a lesion in the iris from the image; and an evaluation process for evaluating a degree of lesion progression indicating the degree of appearance of the lesion based on the feature quantity of the iris.

[0084] Some or all of the elements (e.g., configuration and function) described in Appendices 2 to 12 that are dependent on Appendice 1 may also be dependent on Appendices 13, 14, and 20 in the same way as those described in Appendices 2 to 12. Some or all of the elements described in any appendice may be applied to various hardware, software, recording means, systems, and methods for recording software.

[0085] 10, 11, 12 Lesion detection system 20 Eye 21 Iris 22 Pupil 30 Result provision device 40, 41 Network 101, 112 Acquisition unit 102, 113 Calculation unit 103, 114 Evaluation unit 111 Storage unit 115 Notification unit 121 Iris authentication terminal 122 Detection terminal 500 Computer 502 Bus 504 Processor 506 Memory 508 Storage device 510 Input / Output interface 512 Network interface 1111 User information 1112 State time-series information 1211 Imaging unit 1212 Storage unit 1213 Authentication unit 1214 Communication means 1221 Acquisition unit 1222 Calculation unit 1223 Evaluation unit

Claims

1. A lesion detection system comprising: an acquisition unit that acquires an image of a user including the iris that conforms to biometric authentication; a calculation unit that calculates characteristic quantities relating to lesions in the iris from the image; and an evaluation unit that evaluates the degree of lesion progression indicating the degree of appearance of the lesion based on the characteristic quantities of the iris.

2. The lesion detection system according to claim 1, wherein the calculation unit calculates the characteristic quantity for blood vessels included in the iris region.

3. The lesion detection system according to claim 2, wherein the blood vessels are neovascularizations, the evaluation unit determines the number of neovascularizations based on the characteristic quantities, and evaluates the progression of iris rubeosis as the progression of the lesion based on the number of neovascularizations.

4. The lesion detection system according to claim 2 or 3, wherein the calculation unit calculates the characteristic quantity for the blood vessel based on the red intensity in the iris.

5. The lesion detection system according to any one of claims 2 to 4, wherein the calculation unit calculates the characteristic quantity for the blood vessel when the proportion of the region of the iris in which the red intensity exceeds a predetermined color threshold exceeds a predetermined proportion.

6. A lesion detection system according to any one of claims 1 to 5, further comprising a storage unit for storing user information of the user, the acquisition unit further acquiring a biometric authentication result of the user based on the image, and the evaluation unit determining an evaluation setting relating to at least one of an evaluation criterion and an evaluation frequency based on the user information of the user corresponding to the biometric authentication result, and evaluating the progression of the lesion based on the evaluation setting.

7. The lesion detection system according to claim 6, wherein the storage unit stores the lesion progression or the characteristic quantity as state time-series information linked to the user information, and the evaluation unit acquires the state time-series information linked to the user information and compares the latest lesion progression or the characteristic quantity with past state time-series information.

8. A lesion detection system according to any one of claims 1 to 7, further comprising a notification unit that notifies the user based on the progression of the lesion, wherein the notification unit notifies the user of a first warning indicating a high probability of a lesion when the progression of the lesion exceeds a first threshold determined in advance.

9. The lesion detection system according to claim 8, further comprising a storage unit that stores the lesion progression or the feature quantity as state time-series information linked to the user's user information, the acquisition unit further acquires the user's biometric authentication result based on the image, and the notification unit notifies the user of a second warning indicating a sudden change in the lesion when the difference between the lesion progression based on the feature quantity calculated from the image and the lesion progression included in the state time-series information linked to the user information corresponding to the biometric authentication result is higher than a predetermined second threshold.

10. The lesion detection system according to claim 9, wherein the notification unit determines at least one of the first threshold and the second threshold based on the user information.

11. The lesion detection system according to any one of claims 1 to 10, wherein the biometric authentication is iris recognition.

12. The lesion detection system according to claim 11, wherein the acquisition unit communicates with an iris authentication terminal and acquires the noise rate in the image at the time of iris authentication from the iris authentication terminal, and the calculation unit calculates the feature quantities of the iris based on the noise rate.

13. A lesion detection system comprising an iris authentication terminal and a detection terminal connected to the iris authentication terminal, wherein the iris authentication terminal includes: an imaging unit for capturing an iris image of a user suitable for biometric authentication; a storage unit for storing user information and registered iris information in association; an authentication unit for extracting the user's iris information from the iris image, authenticating the user by comparing the extracted iris information and the registered iris information, and identifying the user information; and the detection terminal includes: an acquisition unit connected to the iris authentication terminal for acquiring the iris image; a calculation unit for calculating feature quantities relating to lesions in the iris from the iris image; and an evaluation unit for evaluating the degree of lesion progression indicating the degree of appearance of the lesion based on the feature quantities of the iris.

14. A lesion detection method comprising: an acquisition process in which a computer acquires an image of a user including an iris that conforms to biometric authentication; a calculation process in which a feature quantity relating to a lesion in the iris is calculated from the image; and an evaluation process in which a lesion progression degree indicating the degree of appearance of the lesion is evaluated based on the feature quantity of the iris.

15. The lesion detection method according to claim 14, wherein the characteristic quantity is calculated for blood vessels included in the iris region in the calculation process.

16. The lesion detection method according to claim 15, wherein the blood vessels are neovascularizations, and in the evaluation process, the number of neovascularizations is determined based on the feature quantities, and the progression of iris rubeosis is evaluated as the progression of the lesion based on the number of neovascularizations.

17. The lesion detection method according to claim 15 or 16, wherein in the calculation process, the characteristic quantity is calculated for the blood vessel based on the red color intensity in the iris.

18. The lesion detection method according to any one of claims 15 to 17, wherein in the calculation process, the characteristic quantity is calculated for the blood vessel when the proportion of the region in the iris in which the red intensity exceeds a predetermined color threshold exceeds a predetermined proportion.

19. A lesion detection method according to any one of claims 14 to 18, further comprising a storage process for storing user information of the user, wherein in the acquisition process, a biometric authentication result of the user based on the image is further acquired, and in the evaluation process, evaluation settings relating to evaluation criteria and evaluation frequency are determined based on the user information of the user corresponding to the biometric authentication result, and the degree of lesion progression is evaluated based on the evaluation settings.

20. A program that causes a computer to perform the following: an acquisition process to acquire an image of a user including an iris that conforms to biometric authentication; a calculation process to calculate feature quantities relating to lesions in the iris from the image; and an evaluation process to evaluate the degree of lesion progression, which indicates the degree of appearance of the lesions, based on the feature quantities of the iris.

Images