Ultrasonic ocular surgery warning device using ultrasonic sensor and method thereof

The ultrasonic eye surgery alarm device addresses the challenge of depth perception during eye surgeries by using an ultrasonic sensor and processor to output notifications based on distance, enhancing surgical safety and success rates by preventing instrument contact with sensitive areas.

WO2024237558A1PCT designated stage expired Publication Date: 2024-11-21THE CATHOLIC UNIV OF KOREA IND ACADEMIC COOP FOUND
View PDF 5 Cites 0 Cited by

Patent Information

Application Number
PCT/KR2024/006237
Authority / Receiving Office
WO · WO
Patent Type
Applications
Current Assignee / Owner
Priority Date
2023-05-18
Filing Date
2024-05-09
Publication Date
2024-11-21

AI Technical Summary

Technical Problem

During eye surgeries like cataract procedures, the small size and obstructed vision of the eye pose challenges in determining the depth of surgical instrument insertion, risking damage to the surgical site due to the inability to directly visualize the insertion depth.

Method used

An ultrasonic eye surgery alarm device equipped with an ultrasonic sensor on an eye surgery device measures the distance from a critical point within the eye and uses a processor to output notifications, such as sound, vibration, or messages, based on predefined standards to alert the surgeon of proximity to sensitive areas, thereby preventing damage.

Benefits of technology

The device enhances surgical safety by providing real-time distance feedback, reducing the risk of surgical site damage and improving the success rate of eye surgeries by allowing surgeons to maintain awareness of instrument proximity to critical areas.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure KR2024006237_21112024_PF_FP_ABST
    Figure KR2024006237_21112024_PF_FP_ABST
Patent Text Reader

Abstract

Disclosed are an ultrasonic ocular surgery warning device using an ultrasonic sensor and a method thereof. The ultrasonic ocular surgery alarm device according to an embodiment of the present invention includes: an ultrasonic sensor, provided at one end of an ocular surgery device, for measuring the distance from a first point on an eyeball; and a processor that outputs a notification on the basis of the distance, from the first point to the ultrasonic sensor, transmitted from the ultrasonic sensor. The processor compares the distance, from the first point to the ultrasonic sensor, transmitted from the ultrasonic sensor with a notification reference, and outputs a distance-dependent notification according to the comparison result, differentially outputting the notification according to the identified distance from the first point to the ultrasonic sensor.
Need to check novelty before this filing date? Find Prior Art

Description

Ultrasonic ocular surgery alarm device using an ultrasonic sensor and method thereof

[0001] The present disclosure relates to an ultrasonic ocular surgery warning device. More specifically, the present disclosure relates to an ultrasonic ocular surgery warning device using an ultrasonic sensor and a method thereof.

[0002] With the aging population and increased use of electronic devices like computers, demand for ophthalmic surgeries, including cataract surgery, is increasing. Consequently, the industry is focusing its attention on safe and efficient ophthalmic surgical techniques.

[0003] Typically, intraocular surgery is performed by making a hole in the eyeball and inserting surgical instruments. However, because the eyeball is small and the surgery is performed in an environment where the field of vision is obstructed by cataracts, there is a problem in that it is impossible to directly see the surgical site, such as the lens capsule, or to know the depth to which the surgical instrument is inserted.

[0004] Accordingly, there is a risk of damage to the surgical site during ophthalmic surgery, including cataract surgery.

[0005] The purpose of the embodiment disclosed in the present disclosure is to provide an ultrasonic eye surgery alarm device and method using an ultrasonic sensor for detecting a distance from a surgical site during eye surgery and generating an alarm.

[0006] The problems to be solved by the present disclosure are not limited to the problems mentioned above, and other problems not mentioned will be clearly understood by those skilled in the art from the description below.

[0007] In order to achieve the above-described technical problem, an ultrasonic eye surgery alarm device according to one aspect of the present disclosure includes: an ultrasonic sensor formed at one end of an eye surgery device for measuring a distance from a first point of an eye; and a processor for outputting a notification based on a distance from the first point to the ultrasonic sensor transmitted from the ultrasonic sensor; wherein the processor compares the distance from the first point to the ultrasonic sensor transmitted from the ultrasonic sensor with a notification standard, and outputs a notification according to the distance based on the comparison result, and can output a notification differently depending on the distance from the first point to the ultrasonic sensor that has been identified.

[0008] The processor, when outputting the notification in a differentiated manner, outputs one of a sound, a message, a vibration, and a combination thereof according to the distance from the first point to the ultrasonic sensor through an output unit, and the output unit may include a speaker or a display.

[0009] The processor can output a sound having a pitch of 1000 Hz and a volume of 10 dB when the distance from the first point to the ultrasonic sensor is 5 mm, output a sound having a pitch of 2000 Hz and a volume of 20 dB when the distance from the first point to the ultrasonic sensor is 4 mm, output a sound having a pitch of 4000 Hz and a volume of 30 dB when the distance from the first point to the ultrasonic sensor is 3 mm, output a sound having a pitch of 8000 Hz and a volume of 40 dB when the distance from the first point to the ultrasonic sensor is 2 mm, and output a sound having a pitch of 16000 Hz and a volume of 50 dB when the distance from the first point to the ultrasonic sensor is 1 mm.

[0010] The above ultrasonic sensor may include at least one of an ultrasonic rangefinder, an ultrasonic micrometer, an ultrasonic strain gauge, an ultrasonic proximity sensor, an ultrasonic rangefinder, an ultrasonic proximity sensor, an ultrasonic level sensor, an ultrasonic water level gauge, an ultrasonic locator, and an ultrasonic wave gauge.

[0011] The processor may further include performing learning to identify the boundary of the membrane within the eye based on a plurality of distances from the first point to the ultrasonic sensor obtained from the ultrasonic sensor and an eye image matching each of the plurality of distances.

[0012] The processor may further include performing the learning to determine whether there is hemorrhage from a real-time eye image by labeling multiple hemorrhage-inducing eye images and multiple non-hemorrhage-inducing eye images, respectively.

[0013] The processor may further include labeling a distance at which bleeding will occur and a distance at which bleeding will not occur based on a plurality of hemorrhage-inducing eye images and a plurality of non-hemorrhage-inducing eye images, respectively, and performing learning to predict a distance at which bleeding will occur and a distance at which bleeding will not occur from a real-time eye image using the labeling.

[0014] The processor may further include performing learning to predict a distance from a first point within the eye to the ultrasonic sensor from a real-time eye image based on a plurality of distances from the first point to the ultrasonic sensor obtained from the ultrasonic sensor and an image matching each of the plurality of distances.

[0015] The first point may be any one of the posterior lens capsule, the retina, the anterior lens capsule, the cornea, the iris, and a designated point within the eye.

[0016] The above ultrasonic sensor can be formed to have an overall size smaller than the size of the lens area.

[0017] In addition, an ultrasonic eye surgery warning method according to another aspect of the present disclosure may include a step of measuring a distance from a first point of an eyeball through an ultrasonic sensor formed at one end of an eye surgery device by the ultrasonic eye surgery warning device; a step of comparing a distance from the first point to the ultrasonic sensor transmitted from the ultrasonic sensor with a notification standard; and a step of outputting a notification according to a distance based on the comparison result, and outputting a notification differently according to the distance from the identified first point to the ultrasonic sensor.

[0018] The above ultrasonic eye surgery alarm method can, in the step of differentially outputting the notification, differentially output any one of sound, message, vibration, and a combination thereof according to the distance from the first point to the ultrasonic sensor through the output unit.

[0019] The above ultrasonic eye surgery alarm method can output a sound having a pitch of 1000 Hz and a volume of 10 dB in the step of differentially outputting the notification, when the distance from the first point to the ultrasonic sensor is 5 mm, output a sound having a pitch of 1000 Hz and a volume of 10 dB, when the distance from the first point to the ultrasonic sensor is 4 mm, output a sound having a pitch of 2000 Hz and a volume of 20 dB, when the distance from the first point to the ultrasonic sensor is 3 mm, output a sound having a pitch of 4000 Hz and a volume of 30 dB, when the distance from the first point to the ultrasonic sensor is 2 mm, output a sound having a pitch of 8000 Hz and a volume of 40 dB, and when the distance from the first point to the ultrasonic sensor is 1 mm, output a sound having a pitch of 16000 Hz and a volume of 50 dB.

[0020] The above ultrasonic eye surgery warning method may further include a step of performing learning to identify the boundary of the intraocular membrane based on a plurality of distances from the first point to the ultrasonic sensor obtained from the ultrasonic sensor and an eye image matching each of the plurality of distances.

[0021] The above ultrasound eye surgery warning method may further include a step of performing the learning to determine whether there is bleeding from a real-time eye image by labeling multiple eye images with bleeding and multiple non-bleeding eye images, respectively.

[0022] The above ultrasound eye surgery warning method may further include a step of labeling the distance at which bleeding will occur and the distance at which bleeding will not occur based on multiple images of an eye with bleeding and multiple images of an eye without bleeding, and performing the learning to predict the distance at which bleeding will occur and the distance at which bleeding will not occur from a real-time eye image using the label.

[0023] The above ultrasonic eye surgery warning method may further include a step of performing learning to predict a distance from a first point in the eye to the ultrasonic sensor from a real-time eye image based on a plurality of distances from the first point to the ultrasonic sensor obtained from the ultrasonic sensor and an image matching each of the plurality of distances.

[0024] The first point may be any one of the posterior lens capsule, the retina, the anterior lens capsule, the cornea, the iris, and a designated point within the eye.

[0025] In addition, a computer program stored in a computer-readable recording medium for executing the present disclosure may be further provided.

[0026] In addition, a computer-readable recording medium recording a computer program for executing a method for implementing the present disclosure may be further provided.

[0027] According to the aforementioned problem solving means of the present disclosure, when performing eye surgery such as cataract surgery and retinal surgery, the surgical device can be prevented from coming into contact with the surgical site, thereby enabling the surgery to be performed in a safe environment, thereby reducing the burden on medical staff and increasing the success rate of the surgery.

[0028] In addition, according to the aforementioned problem solving means of the present disclosure, the surgeon can hear the height and volume of the sound and know that the ocular surgical instrument is approaching a dangerous area, and thus can be careful not to cause rupture or damage to the surgical area, thereby providing an effect of performing a safer surgery.

[0029] The effects of the present disclosure are not limited to the effects mentioned above, and other effects not mentioned will be clearly understood by those skilled in the art from the description below.

[0030] Figure 1 is a block diagram of the ultrasonic eye surgery warning device of the present disclosure.

[0031] Figure 2 is an example diagram for explaining the distance-based differential warning method of the present disclosure.

[0032] Figures 3 to 6 are exemplary diagrams for explaining the ultrasonic eye surgery warning method of the present disclosure.

[0033] Figure 7 is a flow chart for explaining the ultrasonic eye surgery alarm method of the present disclosure.

[0034] Throughout this disclosure, the same reference numerals denote the same components. This disclosure does not describe all elements of the embodiments, and any content that is general in the technical field to which this disclosure belongs or that overlaps between embodiments is omitted. The terms "part, module, element, block" used in the specification may be implemented by software or hardware, and depending on the embodiments, a plurality of "parts, modules, elements, blocks" may be implemented as a single component, or a single "part, module, element, block" may include a plurality of components. Throughout the specification, when a part is said to be "connected" to another part, this includes not only cases where it is directly connected, but also cases where it is indirectly connected, and an indirect connection includes a connection via a wireless communication network.

[0035] Additionally, when a part is said to "include" a component, this does not mean that it excludes other components, but rather that it may include other components, unless otherwise specifically stated.

[0036] Throughout the specification, when we say that an element is "on" another element, this includes not only cases where the element is in contact with the other element, but also cases where another element exists between the two elements.

[0037] The terms first, second, etc. are used to distinguish one component from another, and the components are not limited by the aforementioned terms.

[0038] Singular expressions include plural expressions unless the context clearly indicates otherwise.

[0039] The identification codes for each step are used for convenience of explanation and do not describe the order of each step. Each step may be performed in a different order than specified unless the context clearly indicates a specific order.

[0040] The operating principle and embodiments of the present disclosure are described below with reference to the attached drawings.

[0041] In this specification, the term "ultrasonic ocular surgery warning device according to the present disclosure" encompasses various devices capable of performing computational processing and providing results to the user. For example, the ultrasonic ocular surgery warning device according to the present disclosure may include a computer, a server device, and a portable terminal, or may be any one of them.

[0042] Here, the computer may include, for example, a notebook, desktop, laptop, tablet PC, slate PC, etc. equipped with a web browser.

[0043] The above server device is a server that processes information by communicating with an external device, and may include an application server, a computing server, a database server, a file server, a game server, a mail server, a proxy server, and a web server.

[0044] The above portable terminal may include, for example, a wireless communication device that ensures portability and mobility, and may include all kinds of handheld-based wireless communication devices such as a PCS (Personal Communication System), GSM (Global System for Mobile communications), PDC (Personal Digital Cellular), PHS (Personal Handyphone System), PDA (Personal Digital Assistant), IMT (International Mobile Telecommunication)-2000, CDMA (Code Division Multiple Access)-2000, W-CDMA (W-Code Division Multiple Access), WiBro (Wireless Broadband Internet) terminal, a smart phone, and a wearable device such as a watch, ring, bracelet, anklet, necklace, glasses, contact lens, or head-mounted-device (HMD).

[0045] Figure 1 is a block diagram of the ultrasonic ocular surgery warning device of the present disclosure.

[0046] Hereinafter, the present disclosure will be described with reference to FIG. 2, which is an exemplary diagram for explaining the distance-based differentiation warning method, and FIGS. 3 to 6, which are exemplary diagrams for explaining the ultrasonic eye surgery warning method of the present disclosure.

[0047] Referring to FIG. 1, the ultrasonic eye surgery warning device (100) includes an ultrasonic sensor (110), a processor (120), an output unit (130), a memory (140), and a communication unit (150). The components illustrated in FIG. 1 are not essential for implementing the ultrasonic eye surgery warning device (100) according to the present disclosure, and thus the ultrasonic eye surgery warning device (100) described in this specification may have more or fewer components than the components listed above.

[0048] Referring to FIG. 2, an ultrasonic sensor (110) may be formed at one end of an ocular surgical device (10) and configured to measure a distance (D) from a first point (P1) of the eye. The ultrasonic sensor (110) is configured to be installed in the ocular surgical device (10) and may be implemented separately from the processor (120), but is not limited thereto. It is also possible for the ultrasonic ocular surgical warning device (100) to be implemented as an integral part of the ocular surgical device (10) and implemented entirely in a single configuration.

[0049] In the present disclosure, the first point may refer to a point that the ocular surgical device (10) should not contact during ocular surgery. Specifically, the first point may be any one of the posterior lens capsule, the retina, the anterior lens capsule, the cornea, the iris, and a designated point within the eye. In this case, the designated point within the eye may refer to a specific point within the eye where the operator wishes to detect a separation distance.

[0050] The ultrasonic sensor (110) may include at least one of an ultrasonic rangefinder, an ultrasonic micrometer, an ultrasonic strain gauge, an ultrasonic proximity sensor, an ultrasonic rangefinder, an ultrasonic proximity sensor, an ultrasonic level sensor, an ultrasonic water level gauge, an ultrasonic locator, and an ultrasonic wave gauge, but is not limited thereto, and it may also be possible to include other types of ultrasonic sensors.

[0051] Specifically, the ultrasonic distance sensor is a sensor for measuring distance, and measures the distance to an object using an ultrasonic signal, and can measure up to a distance of several millimeters; the ultrasonic micrometer is a sensor used when high-precision measurement is required, and calculates distance by measuring vibration, and can measure vibration of several millimeters or less; and the ultrasonic strain gauge is a sensor that detects and measures deformation of an object, and can detect deformation of an object and measure displacement using an ultrasonic signal.

[0052] In addition, the ultrasonic rangefinder may refer to a sensor that measures distance by emitting an ultrasonic pulse toward a measured object and measuring the time until receiving a reflected wave reflected from the object, and the ultrasonic level sensor may refer to a sensor that uses ultrasonic waves for level detection in a level measurement method that continuously measures the liquid surface and a level measurement method that detects that the liquid surface has reached a certain level.

[0053] The ultrasonic sensor (110) may be formed to have an overall size smaller than the size of the lens area. In this case, the size smaller than the lens area means that the overall size of the ultrasonic sensor (110) may be smaller than the size of the area inserted into the eye, taking into account the situation in which the ultrasonic sensor (110) is inserted into the eye to measure the distance.

[0054] For example, the ultrasonic sensor (110) may be a sensor having signal characteristics capable of measuring a displacement of 1 mm.

[0055] As another example, the ultrasonic sensor (110) may have an overall size of 1 mm or more and 18 mm or less, but is not limited thereto, and any size that allows distance measurement with a specific displacement (2 mm) of movement within the lens space (5 mm) is possible.

[0056] The processor (120) may output a notification based on the distance from the first point transmitted from the ultrasonic sensor (110) to the ultrasonic sensor. At this time, the distance from the first point to the ultrasonic sensor may mean a case where the ultrasonic sensor (110) is formed at the end of the ocular surgical device (10). If the ultrasonic sensor (110) is not formed at the end of the ocular surgical device (10), the distance from the first point of the present disclosure to the ultrasonic sensor may mean a distance that considers the distance from the first point to the end of the ocular surgical device (10) as a correction value. That is, the distance from the first point of the present disclosure to the ultrasonic sensor or the distance (D) from the first point (P1) of the eye may mean a distance D from the end of the ocular surgical device (10) to a point where the ocular surgical device (10) should not come into contact, as shown in FIG. 2.

[0057] The processor (120) may compare the distance from the first point transmitted from the ultrasonic sensor (110) to the ultrasonic sensor (110) with a notification criterion. The notification criterion may refer to a criterion for differentially outputting a notification according to the distance from the first point to the ultrasonic sensor (110). For example, the processor (120) may perform the following actions: gradually increasing the notification sound as the ultrasonic sensor (110) approaches the first point, emphasizing and displaying a text notification multiple times, or transmitting a danger notification to a terminal (not shown) of a user other than the surgical surgeon, according to the notification criterion.

[0058] The processor (120) outputs a distance-based notification based on the comparison result, but can output the notification differently based on the distance from the identified first point to the ultrasonic sensor (110).

[0059] When the processor (120) outputs a notification in a differentiated manner, it can output any one of sound, message, vibration, and a combination thereof depending on the distance from the first point to the ultrasonic sensor (110) through the output unit (130).

[0060] Distance (mm) 5 mm 4 mm 3 mm 2 mm 1 mm Frequency (Hz) 1000 Hz 2000 Hz 4000 Hz 8000 Hz 16000 Hz Magnitude (dB) 10 dB 20 dB 30 dB 40 dB 50 dB

[0061] Specifically, referring to Table 1, the processor (120) can output a sound having a frequency (pitch) of 1000 Hz and a sound volume of 10 dB when the distance from the first point to the ultrasonic sensor (110) is 5 mm. The processor (120) can output a sound having a pitch of 2000 Hz and a sound volume of 20 dB when the distance from the first point to the ultrasonic sensor (110) is 4 mm.

[0062] The processor (120) can output a sound with a pitch of 4000 Hz and a loudness of 30 dB when the distance from the first point to the ultrasonic sensor (110) is 3 mm.

[0063] The processor (120) can output a sound having a pitch of 8000 Hz and a loudness of 40 dB when the distance from the first point to the ultrasonic sensor (110) is 2 mm.

[0064] The processor (120) can output a sound having a pitch of 16000 Hz and a loudness of 50 dB when the distance from the first point to the ultrasonic sensor (110) is 1 mm.

[0065] The pitch and sound volume according to Table 1 described above are examples and can be changed according to the operator's needs.

[0066] An ultrasonic sensor (110) can be mounted on an ocular surgical device (10) (e.g., a cataract surgical device (ultrasonic emulsifier), a retinal surgical device (vitrectomizer), etc.) and detect ultrasonic waves reflected from a first point (e.g., a posterior capsule of the lens (200 of FIGS. 4 and 5), a retina (300 of FIG. 6), etc.). The ultrasonic emulsifier is an ocular surgical device that crushes and suctions a cataract, and the vitrectomizer may be an ocular surgical device that includes a configuration such as an electric saw and is inserted into the eye to eliminate bleeding when performing retinal surgery.

[0067] Referring to FIGS. 3 and 4, cataract surgery is a surgery that requires removing a cataract, and only the internal cataract must be removed while leaving the posterior capsule surrounding the lens intact. If the posterior capsule of the lens is ruptured during cataract surgery, the posterior capsule may rupture and cause lens fragments to fall deep into the eye, which may cause inflammation or loss of vision. Accordingly, the processor (120) outputs differentiated notifications according to the distance between the eye surgery device (10) and the first point (posterior capsule (200) or retina (300)).

[0068] Meanwhile, as the time for which the ultrasound is detected becomes shorter, the ultrasound sensor (110) is judged to be closer to the first point (posterior lens capsule (200), retina (300)), and thus outputs a higher frequency sound (e.g., high-pitched sound) and simultaneously outputs a relatively high dB sound (e.g., relatively louder sound). Accordingly, the user (e.g., surgical surgeon) can hear the height and volume of the sound and know that the ocular surgical device (10) is closer to the first point (posterior lens capsule (200), retina (300)), and can be more careful not to cause rupture of the first point (posterior lens capsule (200), retina (300)). As a result, the user can perform the surgery in a safer environment.

[0069] For example, since the thickness of the cataract is 5 mm, the relationship between the distance and frequency (pitch) and sound volume (dB) of the present disclosure (frequency and volume of the alarm sound according to distance) may be as shown in Table 1.

[0070] That is, the present disclosure attaches an ultrasonic sensor (110) to an ocular surgical device (such as a phacoemulsifier or vitrectomy device) (10) during ocular surgery such as cataract surgery or retinal surgery, and calculates the distance to the posterior capsule of the lens or the retina based on the time detected by the ultrasonic sensor (110), and accordingly changes the pitch of the warning sound based on the difference in sound frequency.

[0071] As another example, when the processor (120) outputs a notification differently, it may also be possible to output characters and sounds together, such as “The distance to the first point is a danger zone,” “The distance to the first point is a safety zone,” “Danger zone,” “Safe zone,” “0.5 mm away from the first point,” “Level 1 warning,” etc., depending on the distance (D) from the first point to the ultrasonic sensor (Fig. 2). At this time, as the distance (D) between the first point and the ocular surgical device (10) (or the ultrasonic sensor (110)) gets closer, the characters may be displayed relatively multiple times additionally, the size of the characters may be increased, or an image emphasizing the characters may be added and displayed. In addition, as the distance (D) between the first point and the ocular surgical device (10) (or the ultrasonic sensor (110)) gets closer, the sound guiding the corresponding phrase may be output relatively louder, or it may also be output repeatedly.

[0072] At this time, the output unit (130) may be implemented as a display or a speaker. If the ultrasonic eye surgery alarm device (100) is implemented separately from the eye surgery device (10), the output unit (130) may additionally implement vibration when outputting a notification, so that a user other than the surgeon holding the eye surgery device (10) can quickly recognize a dangerous situation and convey it to the surgeon. For example, when the processor (120) outputs a notification differently, the closer the distance (D) of the ultrasonic sensor (110) from the first point is, the more repeatedly the vibration may be output, or the stronger the vibration intensity may be output. For this purpose, it will be appreciated that the output unit (130) may additionally be equipped with a vibration output function.

[0073] In the present disclosure, when the aforementioned sounds, messages, and vibrations are output simultaneously, the output cycles can be synchronized to enable the sounds, messages, and vibrations to be output simultaneously. This is not limited to this, and it is also possible for the sounds, messages, and vibrations to be output at different cycles, depending on the operator's needs.

[0074] Meanwhile, in the present disclosure, when outputting the above-described notification, the processor (120) can differentiate the notification method depending on whether the ultrasonic ocular surgery alarm device (100) and the ocular surgery device (10) are implemented together or separately. This is to prevent a user holding the ocular surgery device (120) (e.g., a surgical surgeon) from being startled by a sudden notification or from interrupting the concentration of the surgery in advance.

[0075] The processor (120) can perform learning to identify the boundary of the membrane within the eye based on a plurality of distances from a first point acquired from the ultrasonic sensor (110) to the ultrasonic sensor (110) and an eye image matching each of the plurality of distances.

[0076] The processor (120) can perform the above learning to determine whether there is hemorrhage from a real-time eye image by labeling multiple hemorrhage-inducing eye images and multiple non-hemorrhage-inducing eye images, respectively.

[0077] The processor (120) performs labeling by distinguishing the distance at which bleeding will occur and the distance at which bleeding will not occur based on multiple ocular images with bleeding and multiple ocular images without bleeding, and can perform the above learning to predict the distance at which bleeding will occur and the distance at which bleeding will not occur from real-time ocular images using this.

[0078] The processor (120) can perform learning to predict the distance from a first point in the eye to the ultrasonic sensor from a real-time eye image based on a plurality of distances from a first point to the ultrasonic sensor (110) obtained from the ultrasonic sensor (110) and an image matching each of the plurality of distances.

[0079] The processor (120) of the present disclosure can perform a role such as guiding the path of the ocular surgical device (10) to the user from a real-time ocular image by using the learning results described above.

[0080] The processor (120) of the present disclosure may be composed of one or more cores, and may include a processor for data analysis and deep learning, such as a central processing unit, a general purpose graphics processing unit, and a tensor processing unit of a computing device. The processor (120) may read a computer program stored in a memory (150) and perform data processing for machine learning according to the present disclosure. According to the present disclosure, the processor (120) may perform operations for learning a neural network. The processor (120) may perform calculations for learning a neural network, such as processing input data for learning in deep learning, extracting features from input data, calculating errors, and updating weights of a neural network using backpropagation.

[0081] The above neural network model may be a deep neural network. In the present disclosure, neural network, network function, and neural network may be used interchangeably. A deep neural network (DNN) may refer to a neural network that includes multiple hidden layers in addition to an input layer and an output layer. Using a deep neural network, it is possible to identify latent structures of data. That is, it is possible to identify latent structures of photos, text, videos, voices, and music (e.g., what objects are in the photo, what the content and emotion of the text are, what the content and emotion of the voice are, etc.). A deep neural network may include a convolutional neural network (CNN), a recurrent neural network (RNN), a restricted Boltzmann machine (RBM), a deep belief network (DBN), a Q network, a U network, a Siamese network, etc.

[0082] Convolutional neural networks (CNNs) are a type of deep neural network that include neural networks containing convolutional layers. CNNs are a type of multilayer perceptron designed to use minimal preprocessing. CNNs can be composed of one or more convolutional layers and artificial neural network layers combined with them. CNNs can additionally utilize weight and pooling layers. This structure allows CNNs to fully utilize two-dimensional input data. CNNs can be used to recognize objects in images. CNNs can process image data by representing it as a matrix with dimensions. For example, in the case of image data encoded in RGB (red-green-blue), each of the R, G, and B colors can be represented as a two-dimensional (for example, in a two-dimensional image) matrix. That is, the color value of each pixel of the image data can be an element of a matrix, and the size of the matrix can be the same as the size of the image. Therefore, the image data can be represented as three two-dimensional matrices (a three-dimensional data array).

[0083] In a convolutional neural network, a convolutional process (input and output of a convolutional layer) can be performed by moving the convolutional filter and multiplying the matrix elements at each location of the image with the convolutional filter. The convolutional filter can be composed of an n*n matrix. The convolutional filter can generally be composed of a fixed-shape filter that is smaller than the total number of pixels in the image. That is, when an m*m image is input to a convolutional layer (for example, a convolutional layer whose convolutional filter has a size of n*n), a matrix representing n*n pixels containing each pixel of the image can be component-wise multiplied with the convolutional filter (i.e., each element of the matrix is ​​multiplied). By multiplying with the convolutional filter, a component matching the convolutional filter can be extracted from the image. For example, a 3*3 convolutional filter for extracting up and down straight line components from an image can be configured as [[0,1,0], [0,1,0], [0,1,0]]. When a 3*3 convolutional filter for extracting up and down straight line components from an image is applied to an input image, up and down straight line components matching the convolutional filter from the image can be extracted and output. A convolutional layer can apply a convolutional filter to each matrix for each channel representing an image (i.e., R, G, B colors in the case of an R, G, B coded image). A convolutional layer can extract features matching the convolutional filter from the input image by applying a convolutional filter to the input image. The filter value of the convolutional filter (i.e., the value of each element of the matrix) can be updated by backpropagation during the learning process of a convolutional neural network.

[0084] A subsampling layer can be connected to the output of a convolutional layer to simplify the output of the convolutional layer, thereby reducing memory usage and computational complexity. For example, when the output of a convolutional layer is input to a pooling layer having a 2*2 max pooling filter, the image can be compressed by outputting the maximum value included in each patch for each 2*2 patch from each pixel of the image. The above-described pooling may be a method of outputting the minimum value in a patch or the average value of a patch, and any pooling method may be included in the present disclosure.

[0085] A convolutional neural network may include one or more convolutional layers and subsampling layers. A convolutional neural network can extract features from an image by repeatedly performing convolutional and subsampling processes (e.g., the aforementioned max pooling). Through repeated convolutional and subsampling processes, the neural network can extract global features of the image.

[0086] The output of a convolutional layer or a subsampling layer can be input to a fully connected layer. A fully connected layer is a layer in which all neurons in one layer are connected to all neurons in the neighboring layer. A fully connected layer can refer to a structure in a neural network in which all nodes in each layer are connected to all nodes in other layers.

[0087] At least one of the CPU, GPGPU, and TPU of the processor (120) can process network function learning. For example, the CPU and GPGPU can jointly process network function learning and data classification using the network function. Furthermore, in one embodiment of the present disclosure, processors of multiple computing devices can be used together to process network function learning and data classification using the network function. Furthermore, a computer program executed in a computing device according to one embodiment of the present disclosure may be a CPU, GPGPU, or TPU executable program.

[0088] The output unit (130) may include a speaker or a display.

[0089] The output unit (130) can display a user interface (UI) for providing various types of information related to ultrasonic eye surgery alerts. The output unit can output any type of information generated or determined by the processor (120) and any type of information received by the communication unit (150).

[0090] The output unit (130) may include at least one of a liquid crystal display (LCD), a thin film transistor-liquid crystal display (TFT LCD), an organic light-emitting diode (OLED), a flexible display, and a three-dimensional display (3D display). Some of these display modules may be configured as transparent or light-transmitting so that the outside can be viewed through them. This may be referred to as a transparent display module, and a representative example of the transparent display module is TOLED (Transparent OLED).

[0091] The memory (140) can store a computer program for providing an ultrasonic eye surgery warning method, and the stored computer program can be read and operated by the processor (120). The memory (140) can store any form of information generated or determined by the processor (120) and any form of information received by the communication unit (150).

[0092] The memory (140) can store data supporting various functions of the ultrasonic eye surgery warning device (100), a program for the operation of the processor (120), can store input / output data, and can store a plurality of application programs (or applications) run by the ultrasonic eye surgery warning device (100), data for the operation of the ultrasonic eye surgery warning device (100), and commands. At least some of these application programs can be downloaded from an external server via wireless communication.

[0093] The memory (140) may include at least one type of storage medium among a flash memory type, a hard disk type, an SSD type, an SDD type, a multimedia card micro type, a card type memory (e.g., SD or XD memory, etc.), a random access memory (RAM), a static random access memory (SRAM), a read-only memory (ROM), an electrically erasable programmable read-only memory (EEPROM), a programmable read-only memory (PROM), a magnetic memory, a magnetic disk, and an optical disk. In addition, the memory may be a database that is separate from the device but is connected by wire or wirelessly.

[0094] The communication unit (150) may include one or more components that enable communication with an external device, and may include, for example, at least one of a broadcast reception module, a wired communication module, a wireless communication module, a short-range communication module, and a location information module.

[0095] Although not shown, the ultrasonic ocular surgery alarm device (100) of the present disclosure may further include an input unit.

[0096] The input unit can receive information input by a user. The input unit can include keys and / or buttons on a user interface, or physical keys and / or buttons, for receiving information input by a user. A computer program for controlling a display according to embodiments of the present disclosure can be executed based on user input through the input unit.

[0097] Figure 7 is a flowchart for explaining the ultrasonic eye surgery alarm method of the present disclosure.

[0098] The ultrasonic eye surgery warning method disclosed in FIG. 7 can perform all operations implemented in the ultrasonic eye surgery warning device (100) disclosed through FIGS. 1 to 6 described above in the same manner, and for the convenience of explanation, redundant descriptions will be omitted.

[0099] The processor (120) of the ultrasonic eye surgery alarm device (100) can measure the distance from a first point of the eyeball through an ultrasonic sensor (110) formed at one end of the eye surgery device (10) (1100). The first point may be any one of the posterior lens capsule, the retina, the anterior lens capsule, the cornea, the iris, and a designated point within the eyeball.

[0100] Next, the processor (120) can compare the distance from the first point transmitted from the ultrasonic sensor (110) to the ultrasonic sensor (120) with a notification criterion (1200).

[0101] Next, the processor (120) outputs a distance-based notification based on the comparison result, but can output the notification differently based on the distance from the identified first point to the ultrasonic sensor (110) (1300).

[0102] At step 1300, the processor (120) can differentially output any one of sound, message, vibration, and a combination thereof according to the distance from the first point to the ultrasonic sensor (110) through the output unit (130).

[0103] For example, in step 1300, the processor (120) can output a sound having a pitch of 1000 Hz and a loudness of 10 dB through the output unit (130) when the distance from the first point to the ultrasonic sensor is 5 mm.

[0104] Additionally, the processor (120) can output a sound having a pitch of 2000 Hz and a loudness of 20 dB when the distance from the first point to the ultrasonic sensor is 4 mm through the output unit (130).

[0105] Additionally, the processor (120) can output a sound having a pitch of 4000 Hz and a volume of 30 dB when the distance from the first point to the ultrasonic sensor is 3 mm through the output unit (130).

[0106] Additionally, the processor (120) can output a sound having a pitch of 8000 Hz and a loudness of 40 dB when the distance from the first point to the ultrasonic sensor is 2 mm through the output unit (130).

[0107] Additionally, the processor (120) can output a sound having a pitch of 16000 Hz and a volume of 50 dB when the distance from the first point to the ultrasonic sensor is 1 mm through the output unit (130).

[0108] Meanwhile, the processor (120) can perform learning to identify the boundary of the membrane within the eye based on a plurality of distances from the first point acquired from the ultrasonic sensor (110) to the ultrasonic sensor and an eye image matching each of the plurality of distances.

[0109] As another example, the processor (120) can perform the above learning to determine whether there is hemorrhage from a real-time eye image by labeling multiple hemorrhagic eye images and multiple non-hemorrhagic eye images, respectively.

[0110] As another example, the processor (120) may label the distance at which bleeding will occur and the distance at which bleeding will not occur based on multiple ocular images with bleeding and multiple ocular images without bleeding, and may use this to perform learning to predict the distance at which bleeding will occur and the distance at which bleeding will not occur from real-time ocular images.

[0111] As another example, the processor (120) may perform learning to predict the distance from a first point in the eye to the ultrasonic sensor from a real-time eye image based on a plurality of distances from a first point to the ultrasonic sensor obtained from the ultrasonic sensor (110) and an image matching each of the plurality of distances.

[0112] Meanwhile, the method according to the present disclosure described above can be implemented as a program (or application) and stored in a medium to be executed in combination with a hardware server.

[0113] The disclosed embodiments may be implemented in the form of a recording medium storing computer-executable instructions. The instructions may be stored in the form of program code, and when executed by a processor, may generate program modules to perform the operations of the disclosed embodiments. The recording medium may be implemented as a computer-readable recording medium.

[0114] Computer-readable storage media include all types of storage media that store instructions that can be deciphered by a computer. Examples include read-only memory (ROM), random access memory (RAM), magnetic tape, magnetic disks, flash memory, and optical data storage devices.

[0115] The disclosed embodiments have been described with reference to the attached drawings as described above. Those skilled in the art will understand that the present disclosure can be implemented in forms other than the disclosed embodiments without altering the technical spirit or essential features of the present disclosure. The disclosed embodiments are illustrative and should not be construed as limiting.

Claims

1. An ultrasonic sensor formed at one end of an ocular surgical device for measuring the distance from a first point of the eye; and A processor that outputs a notification based on the distance from the first point transmitted from the ultrasonic sensor to the ultrasonic sensor; The above processor, Compare the distance from the first point transmitted from the ultrasonic sensor to the ultrasonic sensor with the notification standard, and An ultrasonic eye surgery alarm device that outputs a distance-based notification based on the comparison result, and outputs the notification differently based on the distance from the identified first point to the ultrasonic sensor.

2. In paragraph 1, The above processor, when outputting the notification differently, outputs one of sound, message, vibration, and a combination thereof differently depending on the distance from the first point to the ultrasonic sensor through the output unit, The above output unit is an ultrasonic eye surgery alarm device including a speaker or a display.

3. In paragraph 2, The above processor, When the distance from the first point to the ultrasonic sensor is 5 mm, a sound with a pitch of 1000 Hz and a loudness of 10 dB is output, When the distance from the first point to the ultrasonic sensor is 4 mm, a sound with a pitch of 2000 Hz and a loudness of 20 dB is output. When the distance from the first point to the ultrasonic sensor is 3 mm, a sound with a pitch of 4000 Hz and a loudness of 30 dB is output, When the distance from the first point to the ultrasonic sensor is 2 mm, a sound with a pitch of 8000 Hz and a loudness of 40 dB is output, and An ultrasonic eye surgery alarm device that outputs a sound with a pitch of 16,000 Hz and a loudness of 50 dB when the distance from the first point to the ultrasonic sensor is 1 mm.

4. In paragraph 1, The above processor, An ultrasonic eye surgery warning device further comprising: performing learning to identify the boundary of the intraocular membrane based on a plurality of distances from the first point to the ultrasonic sensor obtained from the ultrasonic sensor and an eye image matching each of the plurality of distances.

5. In paragraph 1, The above processor, An ultrasonic eye surgery warning device further comprising performing the above learning to identify the presence of bleeding from a real-time eye image by labeling the eye images with multiple hemorrhages and the eye images without multiple hemorrhages, respectively.

6. In paragraph 1, The above processor, An ultrasonic eye surgery warning device further comprising labeling a distance at which bleeding will occur and a distance at which bleeding will not occur based on multiple images of an eye with bleeding and multiple images of an eye without bleeding, and performing learning to predict a distance at which bleeding will occur and a distance at which bleeding will not occur from a real-time eye image using the labeling performed above.

7. In paragraph 1, The above processor, An ultrasonic eye surgery warning device further comprising: performing learning to predict a distance from a first point in the eye to the ultrasonic sensor from a real-time eye image based on a plurality of distances from the first point to the ultrasonic sensor obtained from the ultrasonic sensor and an image matching each of the plurality of distances.

8. In a method performed by an ultrasonic eye surgery alarm device, A step of measuring the distance from a first point of the eyeball through an ultrasonic sensor formed at one end of an eye surgery device by an ultrasonic eye surgery alarm device; A step of comparing the distance from the first point transmitted from the ultrasonic sensor to the ultrasonic sensor with a notification standard; and An ultrasonic eye surgery alarm method, comprising: a step of outputting a distance-based notification according to a comparison result, and outputting the notification differently according to the distance from the identified first point to the ultrasonic sensor.

9. In paragraph 8, In the step of outputting the above notification differently, An ultrasonic eye surgery alarm method that differentially outputs one of a sound, a message, a vibration, and a combination thereof according to the distance from the first point to the ultrasonic sensor through an output unit.

10. In paragraph 9, In the step of outputting the above notification differently, When the distance from the first point to the ultrasonic sensor is 5 mm, a sound with a pitch of 1000 Hz and a loudness of 10 dB is output, When the distance from the first point to the ultrasonic sensor is 4 mm, a sound with a pitch of 2000 Hz and a loudness of 20 dB is output. When the distance from the first point to the ultrasonic sensor is 3 mm, a sound with a pitch of 4000 Hz and a loudness of 30 dB is output, When the distance from the first point to the ultrasonic sensor is 2 mm, a sound with a pitch of 8000 Hz and a loudness of 40 dB is output, and An ultrasonic eye surgery alarm method that outputs a sound having a pitch of 16,000 Hz and a loudness of 50 dB when the distance from the first point to the ultrasonic sensor is 1 mm.

11. In paragraph 8, An ultrasonic eye surgery warning method further comprising a step of performing learning to identify the boundary of the intraocular membrane based on a plurality of distances from the first point to the ultrasonic sensor obtained from the ultrasonic sensor and an eye image matching each of the plurality of distances.

12. In paragraph 8, An ultrasound eye surgery warning method further comprising a step of performing the above learning to identify the presence of bleeding from a real-time eye image by labeling the eye images with multiple hemorrhages and the eye images without multiple hemorrhages, respectively.

13. In paragraph 8, An ultrasound eye surgery warning method further comprising a step of labeling the distance at which bleeding will occur and the distance at which bleeding will not occur based on multiple hemorrhage-inducing eye images and multiple non-hemorrhage-inducing eye images, and performing the learning to predict the distance at which bleeding will occur and the distance at which bleeding will not occur from real-time eye images using the labeling.

14. In paragraph 8, An ultrasonic eye surgery warning method further comprising a step of performing learning to predict a distance from a first point in the eye to the ultrasonic sensor from a real-time eye image based on a plurality of distances from the first point to the ultrasonic sensor obtained from the ultrasonic sensor and an image matching each of the plurality of distances.

15. A computer-readable recording medium having recorded thereon a computer program for performing the ultrasonic eye surgery alarm method of Article 8.

Citation Information

Patent Citations

  • Method and apparatus for intraocular brachytherapy

    JP2009515655A

  • Method for facilitating dignosis of subject based on fovea image thereof and apparatus using the same

    KR101848321B1

  • Apparatus and method of determining an eye prescription

    KR1020160058748A

  • System for improving operational efficency of m-DRT vehicle based on predicted demand and method thereof

    KR1020240081676A

  • Method, system and use for therapeutic ultrasound

    US20180064962A1