Intraocular lens loading assembly system

Abstract

A method for providing automatic placement of a lens (110) in a cartridge (116). The method includes grasping, by a nozzle head (108) of a lift tool (105), a lens (110) from a pick-up position (113) of a platform (114) based on an airflow (109) through the nozzle head (108); and depositing the lens (110) by the lift tool (105) at a delivery point (115) in the cartridge (116) by varying the airflow (109) through the nozzle head (108). The method includes determining, by a processor coupled to the lifting tool (105), a position of a haptic (111) of the lens (110) relative to a feature (117) of the cartridge (116). The method includes adjusting, by the lifting tool (105), the haptic (111) from a position of the haptic (111) to a target orientation on the cartridge (116) when the position of the haptic (111) is determined to be misaligned with the feature (117). The method may be implemented as a device, a system, and / or a computer program product.

Description

[0001] Cross-references to related patent applications

[0002] This application claims priority to U.S. Provisional Application No. 63 / 375,513, filed on September 13, 2022, which is hereby incorporated by reference in its entirety. Technical Field

[0003] The present disclosure relates to an automated system and method for loading an intraocular lens (IOL) into a cassette. More specifically, the loading assembly system utilizes vacuum and clamping technology to provide automated placement of the IOL into the cassette. Background Art

[0004] Generally speaking, in ophthalmology, surgeons performing IOL implantation as part of a surgical procedure require the IOL to be placed in the box portion of an insertion system prior to insertion. The box is typically designed to hold the lens and facilitate its folding as the lens is advanced into the eye through the insertion system.

[0005] There are two major categories of insertion systems. In traditional IOL packaging, a nurse or assistant in the surgical operating room manually loads the IOL into a box prior to surgery. Recently, pre-loaded systems have become available in which the lens is provided in a pre-loaded configuration, so manual loading in the surgical operating room is not required. However, as part of the manufacturing process, such pre-loaded systems are still manually loaded. Although people can be trained in appropriate loading techniques, this process should not be rushed. There is also the possibility of human error during transfer. An automated system configured to load the IOL into a box can eliminate human error and provide manufacturing speed. Summary of the invention

[0006] According to one embodiment, a method is provided. The method provides automatic placement of a lens in a box. The method includes: based on the airflow through the nozzle head, the lens is grabbed from the pick-up position of the platform by the nozzle head of the lifting tool; and by changing the airflow through the nozzle head, the lens is stored at the delivery point in the box by the lifting tool. The method includes: determining the position of the tactile portion of the lens relative to the characteristic structure of the box by at least one processor connected to the lifting tool; and when the position of the tactile portion is determined to be misaligned with the characteristic structure, the lifting tool adjusts the tactile portion from the position to the target orientation on the box. According to one or more embodiments, the above method embodiments may be implemented as devices, systems and / or computer program products.

[0007] According to one embodiment, a system is provided. The system provides automatic placement of a lens in a box. The system includes a lifting tool having a nozzle head. The lifting tool is configured to grab a lens from a pick-up position of a platform based on an airflow through the nozzle head, deposit the lens at a delivery point in the box by changing the airflow through the nozzle head, and adjust the tactile portion of the lens from the position of the tactile portion to a target orientation on the box when the position of the tactile portion is determined to be misaligned with a feature structure of the box. The system includes at least one processor connected to the lifting tool. The at least one processor is configured to determine the position of the tactile portion relative to the feature structure of the box. According to one or more embodiments, the above-mentioned system embodiments can be implemented as devices, methods and / or computer program products. BRIEF DESCRIPTION OF THE DRAWINGS

[0008] A more detailed understanding may be obtained from the following detailed description provided by way of example in conjunction with the accompanying drawings, in which like reference numerals indicate like elements, and in which:

[0009] Figure 1 A system according to one or more embodiments is shown;

[0010] Figure 2 A method according to one or more embodiments is shown;

[0011] Figure 3 A system according to one or more embodiments is shown;

[0012] Figure 4 An artificial intelligence (AI) diagram illustrating a determination engine according to one or more embodiments;

[0013] Figure 5 A neural network and methods performed in the neural network according to one or more embodiments are shown;

[0014] Figure 6 A method according to one or more embodiments is shown;

[0015] Figure 7 A lifting tool according to one or more embodiments is shown;

[0016] Fig. 8A and Figure 8B According to one or more embodiments, Figure 7 A perspective view of a portion of a lifting tool;

[0017] Fig.9A and Fig. 9B shows a top view and a bottom view of an IOL in contact with a lifting tool according to one or more embodiments; and

[0018] Fig.10 Images detailing changes in position of an IOL based on operation of a system according to one or more embodiments are shown. DETAILED DESCRIPTION

[0019] Generally speaking, systems and methods for IOL packaging are disclosed herein. More specifically, the systems and methods herein provide for loading an IOL into a cassette using a loading assembly system that utilizes vacuum and clamping technology to provide automated placement of the IOL into the cassette.

[0020] Figure 1 A system 100 (e.g., a loading component system) according to one or more embodiments is shown. In general, the system 100 can be viewed as a combination of components, sensors, processing, diagnosis, and user devices. It should be noted that the items and elements of the system 100, although shown in the singular, represent one or more items or elements in the item or element. In order to achieve automatic placement, the system 100 implements one or more instances of the determination engine 101. According to one or more embodiments, the determination engine 101 can be configured in hardware, software, or a hybrid implementation. For example, the determination engine 101 can be stored as a software component, module, engine, instruction, etc. for execution by a processor (as described herein) to enable the system 100 to operate. It should be noted that the determination engine 101 can be viewed as a combination of instructions / software across the system 100, including a client instance (e.g., determination engine 101.A) that communicates with other elements of the system 100 (e.g., determination engine 101.B can be a server instance). For example, the determination engine 101 can have a specific software instance that implements a specific operation of the system 100 itself. The system also includes a device 102 (eg, including at least one processor and memory) and a camera 104, as further described herein.

[0021] The system 100 includes a lifting tool 105. The lifting tool 105 may include a frame 106, one or more clamps 107 and a nozzle head 108, as well as any motors, compressors, airways, gears, bearings, lubricants, sensors, circuits, wiring, lighting, etc., to achieve the grasping, movement and storage of the IOL 110 based on the communication to / from the determination engine 101. The frame 106 includes one or more components, each of which can be hinged and moved relative to the xyz direction with each other, such as by a motor. The one or more components can be made of any material, such as metal, plastic, rubber, wood, etc. Each of the one or more clamps 107 can be a bar or rod member extending from the frame 106. Each of the one or more clamps 107 can be moved relative to the zyz direction, such as by a motor.

[0022] The nozzle tip 108 can provide an airflow 109 over the IOL 110. The IOL 110 is an artificial implant used to replace the natural lens in the eye as part of a cataract or myopia treatment (e.g., typically implanted during cataract surgery after the cloudy natural lens of the eye has been removed). The IOL 110 can include a lens body 112 and one or more haptics 111. The lens body 112 (e.g., a small plastic lens) provides the same light focusing function as a natural lens. One or more haptics 111 (e.g., plastic side stays) hold the IOL 110 in place in the capsular bag inside the eye.

[0023] According to the Bernoulli principle, the airflow 109 can be in an inward direction to produce direct suction on the IOL 110, or in an outward direction to produce a suction effect. According to one or more embodiments, the nozzle head 108 contacts the outer periphery of the lens body 111 of the IOL 110 while the airflow 109 is enabled. By way of example, the nozzle head 108 can be configured to utilize the Bernoulli principle to provide a suction effect for lifting the IOL 110 while applying limited pressure thereto. Based on the configuration of the nozzle head 108 and the use of the Bernoulli principle, the lifting tool 105 only contacts the non-optical portion of the IOL 110 (e.g., minimally contacts the outer periphery of the lens body 111) during the grasping of the IOL 110.

[0024] According to one or more embodiments, one or more grippers 107 may be associated in pairs and match or correspond to the haptic 111 of the IOL 110. Generally speaking, one or more grippers 107 do not engage or contact the IOL 110 during the pick-up / grasping / depositing of the automated placement operation. Instead, one or more grippers 107 engage the IOL 110 after placement / depositing to achieve a smart loading operation. In this regard, for example, a pair of first grippers 107 may adjust the haptic 111.A relative to a first feature 117.A. Then, a pair of second grippers 107 may adjust the haptic 111.B relative to a second feature 117.B. Examples of one or more grippers 107 include, but are not limited to, electric grippers, grippers based on piezoelectric actuators, large displacement micro grippers, haptic grippers, and robotic grippers. As used herein, the term feature is used to refer to a location in a box designed for haptic placement. By way of example and not limitation, the feature may be a standoff, ledge, ramp, detent, protrusion, gap, or any other feature upon which, adjacent to, abutting, or beneath which the tactile portion may be placed.

[0025] The IOL 110 may be initially positioned at a pick-up location 113 of the platform 114. The lifting tool 110 may secure the IOL 110 and move it from the pick-up location 113 to a delivery point 115 of a box 116 (e.g., a lens module), such as onto one or more feature structures 117. The pick-up location 113 of the platform 114 may correspond to how the IOL 110 is delivered after manufacturing (e.g., via a production line or in a shipping container). The delivery point 115 of the box 116 may correspond to the packaging of the IOL 110 (e.g., at a box line). It is noted that the IOL 110 is loaded into the box 116 so that the IOL 110 can be appropriately folded without being damaged. Once the IOL 110 has been folded and during a surgical procedure, the IOL can be provided into the eye through a small incision (e.g., smaller than the unfolded size of the IOL 110) and unfolded when in the eye. It is essential that the IOL 110 be properly positioned within the cartridge 116 and upon the one or more features 117 so that the IOL 110 remains intact throughout the surgical procedure.

[0026] The system 100 also includes a cloud environment 129. The cloud environment 129 can be a wired network, a wireless network, and / or include one or more wired and wireless networks, such as an intranet, a local area network (LAN), a wide area network (WAN), a metropolitan area network (MAN), a short-range network, a direct connection or a series of connections, a cellular telephone network, or a network capable of facilitating communication using any of a variety of communication standards / protocols (e.g., Bluetooth, Wi-Fi, Zigbee, Z-Wave, near field communication (NFC), Zigbee, infrared (IR), Ethernet, universal serial bus (USB), or any other communication standard / protocol). Figure 1 Any other network or medium for communication between the various items. In addition, several networks can work alone or communicate with each other to facilitate communication in the cloud environment 129.

[0027] The cloud environment 129 includes a device 130 (e.g., a remote computing system) and a data / network service 140, each of which may include at least one processor and memory, as further described herein. In some instances, the device 130 and / or the data / network service 140 may be implemented as a single physical server on the cloud environment 129. In other instances, the device 130 and / or the data / network service 140 may be implemented as a virtual server of a public cloud computing provider of the cloud environment 129. The data / network service 140 may be a database (e.g., a SQL database) and / or another storage mechanism. Thus, the data / network service 125 may be used as a repository for storage on the entire system 100. According to one or more embodiments, the data / network service 140 may store data as well as machine learning (ML) models, determination models, driver components, native APIs, etc. for use by the determination engine 101. According to one or more embodiments, the data is any form of quantity, statistics, measurements, visual information, device speed, airflow information, date, identifier, etc. from any source, and predictors associated therewith. By way of example, device 102 can generate measurements based on visual information of one or more images. The measurements can include, but are not limited to, the location of the haptic, the distance between the haptic 111 and the wall of the feature 117.

[0028] Any of the memories of device 102, device 130, and data / network service 140 may include an instance of determination engine 101 (e.g., determination engine 101.A resides on device 102, and determination engine 101.B resides on device 130). Generally speaking, determination engine 101 is executed by at least one processor within system 100 (whether automatically or as directed by technician 150) to implement automatic placement operations. According to one or more embodiments, determination engine 101 can be fully autonomous, such as driven by machine learning and / or artificial intelligence (ML / AI) and programming as described herein. Technician 150 can be any one or more people who provide medical treatment and / or care. Examples of technicians 150 include, but are not limited to, engineers, programmers, assemblers, factory workers, surgeons, doctors, clinicians, medical staff, nurses, and medical assistants.

[0029] Go to Figure 2 , showing a method 200 according to one or more embodiments. For simplicity, the same reference numerals in the figures indicate the same elements, and similar objects, elements, items and reference numerals from previous figures are reused. Figure 2 .

[0030] Method 200 depicts an automated placement operation of IOL 110 in cartridge 116 of system 100. Generally, the automated placement operation includes when IOL 110 is positioned from pick-up location 113 to delivery point 115 by nozzle tip 108 of lift tool 105. Method 200 may be implemented by determination engine 101.

[0031] The method 200 begins at block 210 when the nozzle tip 108 of the lifting tool 105 grabs the IOL 110 from the pick-up location 113 of the platform 114 based on the airflow 109 through the nozzle tip 108. At block 230, the lifting tool 105 deposits the IOL 110 at the delivery point 115 in the box 116 by changing (e.g., stopping or reducing) the airflow 109 through the nozzle tip 108. Note that according to one or more embodiments, the box 116 can be "open" so that the IOL 110 is delivered into the box (e.g., the cover of the lens module can be in an open position and the delivery point 115 and the feature 117 are exposed and visible).

[0032] At block 250, at least one processor (e.g., of device 102 communicatively and operatively coupled to lifting tool 105) determines a position of at least one of the one or more haptics 111 of IOL 110 relative to a matching feature of one or more features 117 of cartridge 116 (e.g., determines first haptic 111.A relative to first feature 117.A). At block 270, when misalignment exists (e.g., the position of first haptic 111.A is determined to be misaligned with first feature 117.A), lifting tool 105 adjusts at least one of the one or more haptics 111 from that position to a target orientation on / in cartridge 116 or on a matching feature of one or more features 117 of cartridge 116. Note that, according to one or more embodiments, cartridge 116 may be "closed" such that IOL 110 is contained within the cartridge (e.g., a cover of a lens module may be automatically moved into a closed position by a rotation device).

[0033] Go to Figure 1 , devices 102 and 130 and data / network services 140 can be any computing device including software and / or hardware, such as a general-purpose computer, in structure, with appropriate interface circuitry for transmitting and receiving signals to and from other items of system 100. By way of example, devices 102 and 130 and data / network services 140 can be a single computing device. By way of example, devices 130 and data / network services 140 are shown as virtual and / or distributed devices in cloud environment 129.

[0034] As a representative example of system 100, Figure 3 A system 300 is shown according to one or more embodiments. For simplicity, like reference numerals in the figures indicate like elements, and similar objects, elements, items, and reference numerals from previous figures are reused. Figure 3 .

[0035] System 300 may represent any computing device and / or computing environment including hardware, software, or a combination thereof. In addition, embodiments of the disclosed system 300 may include devices, systems, methods, and / or computer program products at any possible level of technical detail integration.

[0036] System 300 shows device 102 having one or more central processing units (CPUs), collectively referred to as processor 310. Processor 310 (also referred to as processing circuitry) is coupled to system memory 320 and various other components via system bus 315. Device 102 (as well as device 130 and data / network services 140) may be adapted or configured to perform as an online platform, server, embedded computing system, personal computer, console, personal digital assistant (PDA), mobile phone, tablet computing device, quantum computing device, cloud computing device, mobile device, smart phone, fixed mobile device, smart display, wearable computer, etc.

[0037] Processor 310 may be any type of general or special purpose processor, including a central processing unit (CPU), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA), a graphics processing unit (GPU), a controller, a multi-core processing unit, a three-dimensional processor, a quantum computing device, or any combination thereof. Processor 310 may also have multiple processing cores, and at least some of these cores may be configured to perform specific functions. Multiple parallel processing may also be configured. In addition, at least processor 310 may be a neuromorphic circuit including a processing element that simulates a biological neuron. When executing determination engine 101, processor 131 may be configured to receive, process, and manage information of data / network service 140. Processor 131 may also represent cloud processing on the entire system 100.

[0038] The system bus 315 (or other communication mechanism) is configured to communicate signals (and data) to / from the processor 310, the system memory 320, and various other components (such as the adapter 325). The system memory 320 is an example of a (non-transitory) computer-readable storage medium in which the determination engine 101 may be stored as a software component, module, engine, instruction, etc. for execution by the processor 310, thereby causing the device 102 to operate, such as described herein with reference to the figures. The system memory 320 may include any combination of the following: read-only memory (ROM), random access memory (RAM), internal or external flash memory, embedded static RAM (SRAM), solid-state memory, cache memory, static storage device (such as a magnetic disk or optical disk), or any other type of volatile or non-volatile memory. The non-transitory computer-readable storage medium may be any medium that can be accessed by the processor 310, and may include volatile media, non-volatile media, etc. For example, ROM is coupled to the system bus 315 and may include a basic input / output system (BIOS) that controls certain basic functions of the device 102, and RAM is a read-write memory coupled to the system bus 315 for use by the processor 310. Non-transitory computer-readable storage media may include any media that is removable, non-removable, etc. The memory 132 may also be virtualized and distributed across the cloud environment 115.

[0039] According to one or more embodiments, the determination engine 101 may be configured in hardware, software or a hybrid implementation. The determination engine 101 may be composed of modules that communicate with each other and transmit information or instructions. According to one or more embodiments, the determination engine 101 may provide one or more UIs, such as representing an operating system or other application and / or directly providing as needed. UIs include, but are not limited to, graphical UIs (GUIs), window interfaces and / or other visual interfaces for applications, operating systems, folders, etc. Therefore, user activities may include any interaction or manipulation of the UI provided by the determination engine 101. The determination engine 101 may also include a customization module to perform application-specific processes or derivatives thereof, so that the computing system 200 may include additional functionality.

[0040] For example, according to one or more embodiments, the determination engine 101 may be configured to store logic to be executed or processed by the processor 310 to implement Figure 2 Method 200 (as represented by blocks 210, 230, 250, and 270 within determination engine 101) and Figure 6 The method 600 may include information, instructions, commands or data. For example, the determination engine 101 is communicatively and operably coupled to the lifting tool 105 to send commands thereto and cause operation thereof. Figure 1 and Figure 3The determination engine 101 may also represent an operating system, a mobile application, a client application instance, a server application instance, etc. According to one or more embodiments, the functionality of the device 102 with respect to the determination engine 101 may also be implemented on the device 130 and data / network services, as represented by separate instances of the determination engine 101.

[0041] In addition, it is determined that the module of engine 101 can be implemented as a hardware circuit in a programmable hardware device (e.g., field programmable gate array, programmable array logic, programmable logic device), a graphics processing unit, etc., which includes a customized very large scale integration (VLSI) circuit or gate array, a ready-made semiconductor such as a logic chip, a transistor or other discrete components. The module of engine 101 can be at least partially implemented in software for being executed by various types of processors. According to one or more embodiments, the identified unit of executable code may include one or more physical or logical blocks of computer instructions, which may be organized in the form of an object, a program, a routine, a subroutine or a function, for example. The executable files of the identified modules are co-located or stored in different locations so that when logically joined together, the module is included. The module of executable code can be a single instruction, one or more data structures, one or more data sets, multiple instructions, etc. distributed on several different code segments, between different programs, across several storage devices, etc. Operational data or functional data can be identified and shown in the module of engine 101 herein, and can be implemented in a suitable form and organized in a data structure of any suitable type.

[0042] In addition, the modules of the determination engine 101 may also include, but are not limited to, a position module, an augmented reality module, and an ML / AI algorithm module. The position module may be configured to create, build, store, and provide algorithms and models that determine the position of the lifting tool 105 and determine the relative distance between the tactile portion 111 and the characteristic structure 117. According to one or more embodiments, the positioning module may implement positioning, spatial navigation, surveying, distance, direction, and / or time software. The augmented reality module may be configured to create, build, store, and provide algorithms and models that provide an interactive experience with the automatic placement operation of the system 100, wherein objects (e.g., the tactile portion 111 and the characteristic structure 117) residing in the real world are enhanced by computer-generated perceptual information, sometimes across multiple sensory modalities. The ML / AI algorithm module may be configured to create, build, store, and provide algorithms and models that are automatically improved through experience, as well as to mimic the "natural" cognitive abilities of humans. In one example, ML software uses training data to build a specific model and improve the model, while AI software perceives the environment (e.g., receives activity data) and takes actions (e.g., applies the model) to solve problems and / or produce outputs. AI software can use models built by humans and / or ML software. AI software can also provide feedback to ML software to improve any of its models. ML / AI can exist independently and / or coexist.

[0043] Adapter 325 may represent an input / output (I / O) adapter, a communications adapter, and a device adapter.

[0044] According to one or more embodiments, frequency division multiple access (FDMA), single carrier FDMA (SC-FDMA), time division multiple access (TDMA), code division multiple access (CDMA), orthogonal frequency division multiplexing (OFDM), orthogonal frequency division multiple access (OFDMA), global system for mobile communications (GSM), general packet radio service (GPRS), universal mobile telecommunications system (UMTS), cdma2000, wideband CDMA (W-CDMA), high speed downlink packet access (HSDPA), high speed uplink packet access (HSUPA) are considered , High Speed ​​Packet Access (HSPA), Long Term Evolution (LTE), LTE-Advanced (LTE-A), 802.11x, Wi-Fi, Zigbee, Ultra-Wideband (UWB), 802.16x, 802.15, Home Node B (HNb), Bluetooth, Radio Frequency Identification (RFID), Infrared Data Association (IrDA), Near Field Communication (NFC), Fifth Generation (5G), New Radio (NR), or any other wireless or wired device / transceiver for communication, the I / O adapter can be configured as a Small Computer System Interface (SCSI).

[0045] The communication adapter interconnects the system bus 315 with the cloud environment 129 (which may be an external network), thereby enabling the device 102 to communicate signals (and data) with other such devices (e.g., such as remote computing systems). In one embodiment, the adapter 325 may be connected to one or more I / O buses that are connected to the system bus 315 via an intermediate bus bridge. Suitable I / O buses for connecting peripheral devices such as hard disk controllers, network adapters, and graphics adapters typically include a common protocol, such as the Peripheral Component Interconnect (PCI).

[0046] Device adapters interconnect input / output devices to the system bus 315, such as the display 341, control devices 342, camera 104, lift tool 105, etc. (eg, speakers).

[0047] The display 341 is configured to provide one or more UIs or graphical UIs (GUIs) that can be captured and analyzed by the determination engine 101 when a user interacts with the device 102. Examples of the display 341 may include, but are not limited to, plasma, liquid crystal display (LCD), light emitting diode (LED), field emission display (FED), organic light emitting diode (OLED) display, flexible OLED display, flexible substrate display, projection display, 4K display, high definition (HD) display, Display, in-plane switching (IPS) display, etc. Display 341 can be configured as a touch-type three-dimensional (3D) touch, multi-input touch or multi-touch display using resistive, capacitive, surface acoustic wave (SAW) capacitive, infrared, optical imaging, dispersive signal technology, acoustic pulse recognition, frustrated total internal reflection, etc., as understood by ordinary technicians in this field for input / output (I / O).

[0048] A control device 342 (such as a keyboard, computer mouse, trackpad, touch screen, keypad, etc.) may be further coupled to the system bus 315 for input to the device 102. Additionally, one or more inputs may be provided to the computing system 300 remotely via another computing system in communication therewith (e.g., remote computing system 355), or the device 102 may operate autonomously.

[0049] The camera 104 may be any light-sensitive device for capturing one or more images (e.g., still and / or video) of the IOL 110 and the lifting tool 105 relative to the platform 114 and the box 116. The one or more images may have any resolution suitable for providing (or determining thereby) visual information about the position of the IOL 110 and the lifting tool 105 relative to the platform 114 and the box 116. It is noted that the one or more images of the camera 104 may be stored in a common repository (such as the data / network service 140) and may be downloaded (as needed) to and / or from each of the device 102, the device 130, and / or the data / network service 140. The camera 104 may be positioned above the lifting tool 105 to capture a topographical view of the IOL 110. The camera 104 may be fixed (e.g., positioned above the delivery point 115). The camera 104 may move as the lifting tool moves 105. Camera 104 may represent a plurality of cameras, with a first camera being over pick-up location 113 , a second camera being over delivery point 115 , and / or a third camera moving with lifting tool 105 .

[0050] Generally, the determination engine 101 utilizes one or more images to guide the automatic placement operation of the lifting tool 105. The determination engine 101 can utilize modules and / or ML / AI algorithms to automatically receive, process, and interpret one or more images and other data from a public repository. Figure 4 , illustrates an AI graph 400 of a determination engine 101 according to one or more embodiments. The AI ​​graph 400 includes data 410, machines 420, models 430, results 440, and (below) hardware 450.

[0051] For ease of understanding where appropriate, refer to Figures 1 to 3 conduct Figure 4 For example, machine 420, model 430, and hardware 450 may represent Figure 1 The hardware 450 may also represent aspects of the determination engine 101 (e.g., the ML / AL algorithms therein). Figure 1 Devices 102 and 130 and / or data / network services 140. In general, the AI ​​system 400 (e.g., Figure 1 The ML / AI algorithm implemented by the determination engine 101 uses data 410 to operate relative to hardware 450 to train the machine 420, build a model 430, and predict an outcome 440.

[0052] Data 410 may be any data as described herein. For example, data may include IOL information and measurements, such as IOL master data, image data, video data, precision measurement data, three-dimensional data, and box data. Data 410 may be data being generated, or output data associated with hardware 450. Data 410 may also include currently collected data, historical data, or other data from hardware 450. Data 410 may be divided into one or more subsets by machine 420.

[0053] The machine 420 operates and / or is associated with the hardware 450 as a controller or data collection device. The machine 420 is trained, such as with respect to the hardware 450. The training may also include parsing, analyzing, combining, and correlating the collected data 410. According to one or more embodiments, training the machine 420 may include self-training by the determination engine 101 using the one or more subsets.

[0054] Model 430 may be an unsupervised learning model, such as a self-discovery algorithm, or a supervised learning model, such as a support vector machine (SVM), that analyzes data 410. For example, SVM provides a prediction method using a statistical learning framework for classification and regression analysis of data 410. Model 430 may employ any combination of classification, clustering, regression, anomaly detection, data cleaning, reinforcement learning, structured prediction, feature engineering or learning, semi-supervised learning, decision trees, linear regression, neural or artificial neural networks, logistic regression, recursive selection, relevance vectors, and support vector operations, among others.

[0055] The model 430 (e.g., an ML / AI model and / or a resulting deterministic model) is built based on the data 410 associated with the hardware 450. Building the model 430 may include physical hardware or software modeling, algorithmic modeling, etc. that attempts to represent the data 410 (or a subset thereof) that has been collected and trained. In some aspects, the building of the model 430 is part of a self-training operation performed by the machine 420.

[0056] The model 430 may be configured to model the operation of the hardware 450 and the data 410 collected from the hardware 450 to predict the results 440 achieved by the hardware 450 (e.g., achieving automatic placement of the IOL 110 on / in the box 116 or on the feature 117 of the box 116 in a target orientation). Predicting the results 440 (of the model 430 associated with the hardware 450) may utilize the trained model 430. Thus, using the predicted results 440, the machine 420, the model 430, and the hardware 450 may be further configured or refined accordingly.

[0057] Thus, for AI diagram 400 to operate with respect to hardware 450 using data 410 to train machine 420, build model 430 and predict outcome 440, the ML / AI algorithm may include a neural network. A neural network is a network or circuit of neurons, or in the modern sense, an artificial neural network (ANN) composed of artificial neurons or nodes or cells. For example, an ANN involves a network of simple processing elements (artificial neurons) that can exhibit complex global behaviors determined by the connections between the processing elements and element parameters. These connections of the network or circuit of neurons are modeled as weights. Positive weights reflect excitatory connections, while negative values ​​represent inhibitory connections. The inputs are modified by weights and summed using linear combinations. An activation function may control the amplitude of the output. For example, the acceptable output range is typically between 0 and 1, or the range may be between -1 and 1. In most cases, an ANN is an adaptive system that changes its structure based on external or internal information flowing through the network.

[0058] In more practical terms, a neural network is a nonlinear statistical data modeling or decision-making tool that can be used to model complex relationships between inputs and outputs or to find patterns in data. Therefore, ANNs can be used for predictive modeling and adaptive control applications while being trained via data sets. Self-learning resulting from experience can occur within the network, which can draw conclusions from complex and seemingly unrelated groups of information. The practicality of artificial neural network models lies in that they can be used to infer functions from observations and can also be used to use the functions. According to one or more embodiments, the neural network can implement a long short-term memory neural network architecture, a convolutional neural network architecture (CNN), or other similar architectures. The neural network may be configured with respect to the following items: multiple layers, multiple connections (e.g., encoder / decoder connections), regularization techniques (e.g., pressure difference); and optimization features.

[0059] Now go to Figure 5 , shows a neural network 500 and a method 501 performed in the neural network 500 according to one or more embodiments. The neural network 500 operates to support the methods described herein (e.g., as described by Figure 1 The neural network 500 may be implemented in hardware (such as Figure 4 As indicated herein, for ease of understanding where appropriate, reference is made to Figures 1 to 4 conduct Figure 5 Description.

[0060] In the example operation, Figure 1 The determination 101 includes collecting data 410 from hardware 450. In the neural network 500, the input layer 510 is composed of multiple inputs (e.g., Figure 5With respect to block 520 of method 501 , input layer 510 receives inputs 512 and 514 .

[0061] At block 525 of method 501, neural network 500 encodes inputs 512 and 514 using any portion of data 410 (e.g., data sets and predictions generated by AI system 400) to produce a latent representation or data encoding. The latent representation includes one or more intermediate data representations derived from multiple inputs. According to one or more embodiments, the latent representation is composed of Figure 2 The element-level activation function (e.g., sigmoid function or trimmed linear unit) of the determination engine 101 is generated. Figure 5 As shown, inputs 512 and 514 are provided to a hidden layer 530 depicted as including nodes 532, 534, 536, and 538. Neural network 500 performs processing via hidden layer 530 of nodes 532, 534, 536, and 538 to exhibit complex global behavior determined by the connections between processing elements and element parameters. Thus, the transition between layers 510 and 530 can be considered an encoder stage that takes inputs 512 and 514 and transmits them to the deep neural network (within layer 530) to learn some smaller representation of the inputs (e.g., a resulting latent representation).

[0062] The deep neural network can be a CNN, a long short-term memory neural network, a fully connected neural network, or a combination thereof. The encoding provides a dimensionality reduction of inputs 512 and 514. Dimensionality reduction is a process of reducing the number of random variables (of inputs 512 and 514) considered by obtaining a set of primary variables. For example, dimensionality reduction can be a feature extraction of data (e.g., inputs 512 and 514) from a high-dimensional space (e.g., more than 10 dimensions) to a low-dimensional space (e.g., 2 to 3 dimensions). The technical effects and benefits of reducing the dimensionality include reducing the time and storage space requirements of data 410, improving the visualization of data 410, and improving the parameter interpretation for ML. The data conversion can be linear or nonlinear. The operations of receiving (box 520) and encoding (box 525) can be considered as the data preparation part of the multi-step data manipulation performed by the determination engine 101.

[0063] At block 545 of method 510, neural network 500 decodes the latent representation. The decoding stage takes the encoder output (e.g., the resulting latent representation) and attempts to reconstruct some form of the inputs 512 and 514 using another deep neural network. In this regard, nodes 532, 534, 536, and 538 are combined to produce output 552 in output layer 550, as shown in block 560 of method 510. That is, output layer 550 reconstructs inputs 512 and 514 in a reduced dimension, but without signal interference, signal artifacts, and signal noise.

[0064] Go to Figure 6 , a method 600 is shown according to one or more embodiments. The method 600 depicts a general automated placement operation of the IOL 110 in the cartridge 116 of the system 100. Figure 6 The supplement provides Figures 7 to 10 . Figure 7 A lifting tool 700 is shown according to one or more embodiments. The lifting tool 700 is a schematic example of the lifting tool 105 of the system 100. Fig. 8A and Figure 8B According to one or more embodiments, Figure 7 801 and 802 of a portion 701 of a lifting tool 700. Figure 7 , Fig. 8A and Figure 8B As shown, the lifting tool 700 includes frame members 821 , 822 , 823 , and 824 , a center member 831 including a hole 832 , and clamps 841 , 842 , 843 , and 844 . Fig.9A and Fig. 9B According to one or more embodiments, Figure 7 A top view 901 and a bottom view 902 of the lifting tool 700 contacting the IOL 110 . Fig.10 According to one or more embodiments, the detailed description is based on Figure 7 1001 and 1002 show the change in position of the IOL 110 as a result of the operation of the lifting tool 700. For simplicity, like reference numerals in the figures indicate like elements, and similar objects, elements, items, and reference numerals from previous figures are reused. Figures 6 to 10 .

[0065] Method 600 begins at block 605, when camera 104 captures one or more images of lifting tool 700, IOL 110, and haptic 111 relative to platform 114. Note that camera 104 may capture one or more images intermittently or continuously, such that visual information is fed to device 102 throughout method 600. In method 600, oval A illustrates a non-limiting example of how camera 104 can capture one or more images and later provide visual information (e.g., camera 104 captures one or more images of IOL 110 and haptic 111 relative to box 116). Thus, system 100 provides guided vision for automated placement.

[0066] At block 610 (see, e.g., Figure 2210), the nozzle head 108 of the lifting tool 105 grabs the IOL 110 from the pick-up location 113 of the platform 114 based on the airflow 109 passing through the nozzle head 108. Using the sensors of the lifting tool 105, the determination engine 101 can adjust the airflow 109 so as not to bend or damage the IOL 110. It is noted that the determination engine 101 uses visual information to confirm that the lifting tool 105 is in the proper position above the pick-up location 113. Go to Fig.9A and Fig. 9B , top view 901 and bottom view 902 of IOL 101 grasped by central member 831. Note that first haptic 111.A is located between holders 841 and 842, and second haptic 111.B is located between holders 843 and 844.

[0067] At block 630 (see, e.g., Figure 2 210), the lifting tool 105 deposits the IOL 110 at the delivery point 115 in the cassette 116 by changing (e.g., reducing or stopping) the airflow 109 through the nozzle head 108. Note that the determination engine 101 utilizes visual information to confirm that the lifting tool 105 is in the proper position over the delivery point 115. Go to Fig.10 , image 1001 provides visual information of IOL 110 within box 116.

[0068] At block 650, determination engine 101 determines the position of at least one of the one or more haptics 111 of IOL 110 relative to a matching feature of one or more features 117 of cartridge 116 (e.g., determines first haptic 111.A relative to first feature 117.A). In general, determination engine 101 determines incremental position states of IOL 110 and haptics 111 relative to pick-up location 113, delivery point 115, and features 117 throughout method 600. Return Fig.10 Note that in image 1001, the first tactile portion 111.A is separated from the wall of the first feature structure 117.A by a distance X. The distance X is determined by the determination engine 101. According to one or more embodiments, Fig.10 Features 117.A and 117.B include a flat support or table-like surface with at least one wall extending perpendicularly from an edge of the surface.

[0069] At decision block 655, the determination engine 101 determines whether the target position is achieved. The target position may be a position when the haptic 111 is adjacent, proximate, or otherwise in contact with the wall of the feature 117. For example, the determination engine 101 determines whether the distance X is a value at which the IOL 110 is properly loaded into the box 116 and can be properly folded without being damaged. If the target position is achieved (e.g., aligned), the method 600 proceeds (e.g., as indicated by a "yes" arrow) to block 680. If the target position is not achieved (e.g., not aligned), the method 600 proceeds (e.g., as indicated by a "no" arrow) to block 270.

[0070] At block 670 (see, e.g., Figure 2 At block 270 of FIG. 1 , when there is a misalignment, the determination engine 101 causes the lifting tool 105 to adjust at least one of the tactile portions 111 from the current position to the target position. Sub-block 672 further describes the operation of block 670. At sub-block 672, one or more frame members 821, 822, 823, and 824 and / or one or more clamps 841, 842, 843, and 844 may be actuated to adjust the tactile portion 111 from the current position to a subsequent orientation (i.e., to achieve the ultimate goal of the target position). For example, the clamps 841 and 842 may be moved laterally with the frame member 822 to contact the first tactile portion 111.A and adjust its position. It is noted that, according to one or more embodiments, the clamps 841, 842, 843, and 844 may be moved independently from the nozzle head 106 and the one or more frame members 821, 822, 823, and 824. Then, the method 600 loops through the block 650 and the decision block 655 to determine whether further adjustments are needed. For example, the determination engine 101 determines whether the distance Y of the image 1002 is a value at which the IOL 110 is properly loaded into the box 116 and can be properly folded without being damaged. Since the distance Y is acceptable (zero or close to zero), the process proceeds to block 680.

[0071] At block 680, determination engine 101 determines the position of at least one of the one or more haptics 111 of IOL 110 relative to a matching feature of the one or more features 117 of box 116 (e.g., second haptic 111.B relative to second feature 117.B). Note that the visual information generated by camera 104 at block 610 may be continuously fed to determination engine 101, as demarcated by ellipse A.

[0072] At decision block 685, the determination engine 101 determines whether the target position is achieved. If the target position is achieved (e.g., aligned), the method 600 proceeds (e.g., as indicated by a "yes" arrow) to block 690 and ends. If the target position is not achieved (e.g., not aligned), the method 600 proceeds (e.g., as indicated by a "no" arrow) to block 695.

[0073] At block 695, when misalignment exists, determination engine 101 causes lifting tool 105 to adjust at least one of haptics 111 from the current position to the target position. Subblock 672 further describes the operation of block 670. By way of example, determination engine 101 causes lifting tool 700 to adjust second haptic 111.B from the second position to the target position on second feature 117.B of cartridge 116. Method 600 then loops through block 680 and decision block 685 to determine if further adjustment is needed. If IOL 110 is properly loaded, method 600 proceeds to block 690.

[0074] The flow charts and block diagrams in the accompanying drawings illustrate the possible specific implementation architecture, functions and operations of the system, method and computer program product according to various embodiments of the present invention. In this regard, each box in the flow chart or block diagram may represent a module, fragment or part of an instruction, which includes one or more executable instructions for implementing a specified logical function. In some alternative implementations, the function indicated in the box may not occur in the order indicated in the accompanying drawings. For example, depending on the function involved, the two boxes shown in succession may actually be executed substantially simultaneously, or the box may sometimes be executed in the opposite order. It should also be noted that each box in the block diagram and / or the flow chart diagram and the combination of the boxes in the block diagram and / or the flow chart diagram can be implemented by a system based on dedicated hardware that performs a specified function or action or by a combination of dedicated hardware and computer instructions.

[0075] Although features and elements are described above in detail, it will be appreciated by those skilled in the art that each feature or element may be used alone or in any combination with other features and elements. In addition, the methods described herein may be implemented in a computer program, software, or firmware incorporated in a computer-readable medium for execution by a computer or processor. As used herein, a computer-readable medium should not be understood as a transient signal per se, such as a radio wave or other freely propagating electromagnetic wave, an electromagnetic wave propagating through a waveguide or other transmission medium (e.g., a light pulse passing through a fiber optic cable), or an electrical signal transmitted by wire.

[0076] Examples of computer-readable media include electronic signals (transmitted via a wired or wireless connection) and computer-readable storage media. Examples of computer-readable storage media include, but are not limited to, registers, cache memories, semiconductor memory devices, magnetic media such as internal hard disks and removable disks, magneto-optical media, optical media such as compact disks (CDs) and digital versatile disks (DVDs), random access memories (RAMs), read-only memories (ROMs), erasable programmable read-only memories (EPROMs or flash memories), static random access memories (SRAMs), and memory sticks. A processor associated with software can be used to implement a radio frequency transceiver used in a terminal, a base station, or any host computer.

[0077] The terms used herein are only for the purpose of describing specific embodiments and are not intended to be limiting. As used herein, unless the context clearly indicates otherwise, the singular forms "a", "a", and "the / said" include plural references. It should also be understood that the terms "comprise" and / or "comprising" when used in this specification specify the presence of the features, integers, steps, operations, elements and / or parts, but do not exclude the presence or addition of one or more other features, integers, steps, operations, elements and / or groups thereof.

[0078] The description of various embodiments herein is presented for the purpose of illustration, but is not intended to be exhaustive or limited to the disclosed embodiments. Many modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope and essence of the described embodiments. The terminology used herein is selected to best explain the principles of the embodiments, practical applications or technical improvements over technologies available on the market, or to enable other persons of ordinary skill in the art to understand the embodiments disclosed herein.

Claims

1. A method for automatically placing a lens in a cassette, the method comprising: grabbing the lens from a pick-up position of the platform by the nozzle head of the lifting tool based on the air flow passing through the nozzle head; depositing the lens at a delivery point in the cartridge by the lifting tool by varying the air flow through the nozzle tip; determining, by at least one processor coupled to the lifting tool, a position of a haptic of the lens relative to a feature of the cartridge; as well as When the position of the tactile portion is determined to be misaligned with the feature structure, the tactile portion is adjusted by the lifting tool from the position to a target orientation on the box.

2. The method according to claim 1, further comprising: Incremental positional states of the lens and the haptics of the lens relative to the pick-up location, the delivery point, and the feature are determined by the at least one processor based on the one or more images.

3. The method according to claim 1, further comprising: One or more images of the lens and the haptics of the lens relative to the platform and the box are captured by a camera coupled to the at least one processor to provide guided vision to the at least one processor.

4. The method of claim 1 wherein during said grasping of said lens said lifting tool contacts only a non-optical portion of said lens.

5. The method according to claim 1, further comprising: Based on the signal from the one or more images from the at least one processor, a gripper of the lifting tool is actuated to adjust the haptic from the position to the target orientation.

6. The method according to claim 1, further comprising: determining, by the at least one processor, a second position of a second haptic of the lens relative to a second feature of the cartridge; as well as When the second position of the tactile portion is determined to be misaligned with the second feature, the second tactile portion is adjusted by the lifting tool from the second position to a target orientation on the cartridge.

7. The method of claim 1, wherein the lifting tool comprises a first clamp and a second clamp, each of the first clamp and the second clamp being configured to adjust one of the haptics of the lens.

8. The method of claim 1 wherein the nozzle tip contacts an outer periphery of a body of the lens.

9. The method of claim 1, wherein the feature of the box comprises a planar surface having at least one wall extending perpendicularly from an edge of the surface.

10. The method of claim 1, wherein the lifting tool comprises a frame, one or more holders, and the nozzle head, the frame comprising one or more components, each of the one or more components being configured to articulate and move relative to an xyz direction.

11. A system for automatically placing a lens in a cassette, the system comprising: A lifting tool having a nozzle tip, the lifting tool being configured to: grabbing the lens from a pick-up position of the platform based on an air flow through the nozzle head, depositing the lens at a delivery point in the cartridge by varying the air flow through the nozzle tip, and When the position of the haptic is determined to be misaligned with a feature of the cartridge, adjusting the haptic of the lens from the position of the haptic to a target orientation on the cartridge, and At least one processor coupled to the lifting tool is configured to determine the position of the tactile portion relative to the feature of the cartridge.

12. The system of claim 11, wherein the at least one processor is configured to determine, based on one or more images, an incremental position state of the lens and the haptic portion of the lens relative to the pick-up location, the delivery point, and the feature structure.

13. The system of claim 11, wherein the system comprises a camera coupled to the at least one processor, the camera configured to capture one or more images of the lens and the haptic portion of the lens relative to the platform and the box to provide guided vision to the at least one processor.

14. The system of claim 11, wherein during the grasping of the lens, the lifting tool contacts only a non-optical portion of the lens.

15. The system of claim 11, wherein the system comprises a gripper actuated by the lifting tool and configured to adjust the haptic from the position to the target orientation based on signals from the at least one processor from one or more images.

16. The system of claim 11, wherein the at least one processor is configured to determine a second position of a second haptic of the lens relative to a second feature of the cartridge, and The lifting tool is configured to adjust the second tactile portion from the second position to a target orientation on the cartridge when the second position of the tactile portion is determined to be misaligned with the second feature.

17. The system of claim 11, wherein the lifting tool comprises a first clamp and a second clamp, each of the first clamp and the second clamp being configured to adjust one of the haptics of the lens.

18. The system of claim 11 wherein the nozzle tip contacts an outer periphery of the body of the lens.

19. The system of claim 11, wherein the feature of the cartridge comprises a planar surface having at least one wall extending perpendicularly from an edge of the surface.

20. The system of claim 11, wherein the lifting tool comprises a frame, one or more grippers, and the nozzle head, the frame comprising one or more components, each of the one or more components being configured to articulate and move relative to an xyz direction.

Images