Intraocular lens loading assembly system

Abstract

A method for providing automated placement of a lens (110) in a cartridge (116) is provided. The method includes: a nozzle head (108) of a lift tool (105) capturing a lens (110) from a pick position (113) on a platform (114) based on an airflow (109) through the nozzle head (108); and the lift tool (105) placing the lens (110) at a delivery point (115) in the cartridge (116) by varying the airflow (109) through the nozzle head (108). The method includes a processor coupled to the lift tool (105) determining a position of a haptic (111) of the lens (110) relative to a feature (117) of the cartridge (116). The method includes, if the position of the haptic 111 is determined to be misaligned with respect to the feature 117, the lift tool 105 adjusts the haptic 111 from the position to a target orientation in the cartridge 116. The method can be implemented as an apparatus, a system, and / or a computer program product.

Description

[Technical Field]

[0001] (CROSS-REFERENCE TO RELATED APPLICATIONS) This application claims priority to U.S. Provisional Patent Application No. 63 / 375,513, filed September 13, 2022, which is incorporated herein by reference in its entirety.

[0002] FIELD OF THE INVENTION The present disclosure relates to an automated system and method for loading an intraocular lens (IOL) into a cartridge. In particular, the loading assembly system utilizes vacuum and gripper technology to provide automated placement of the IOL into the cartridge. [Background technology]

[0003] Generally, in ophthalmology, surgeons who implant IOLs as part of a surgical procedure require the IOL to be placed within the cartridge portion of an injection system prior to insertion. This cartridge is typically designed to hold the lens and facilitate folding of the lens as it is advanced through the injection system and into the eye.

[0004] There are two broad categories of insertion systems. In traditional IOL packaging, a nurse or assistant in the operating room manually loads the IOL into a cartridge prior to surgery. More recently, preloaded systems have become available in which the lenses are provided in a preloaded configuration, eliminating the need for manual loading in the operating room. However, such preloaded systems are still manually loaded as part of the manufacturing process. While personnel can be trained in proper loading techniques, it is not a process that should be performed in a rushed situation. Additionally, there is the potential for human error during transfer. An automated system configured to load IOLs into cartridges could eliminate human error and increase manufacturing speeds. Summary of the Invention [Means for solving the problem]

[0005] According to one embodiment, a method is provided for automatically positioning a lens in a cartridge. The method includes: a nozzle head of a lift tool capturing a lens from a pick position on a platform based on airflow through the nozzle head; and the lift tool placing the lens at a delivery point in the cartridge by varying the airflow through the nozzle head. The method includes at least one processor coupled to the lift tool determining a position of a haptic on the lens relative to a feature on the cartridge; and if the position of the haptic is determined to be misaligned relative to the feature, the lift tool adjusting the haptic from the position to a target orientation in the cartridge. According to one or more embodiments, the above-described method embodiments can be implemented as an apparatus, a system, and / or a computer program product.

[0006] According to one embodiment, a system is provided. The system provides automated placement of a lens in a cartridge. The system includes a lift tool including a nozzle head. The lift tool is configured to: capture a lens from a pick position on a platform based on airflow through the nozzle head; place the lens at a delivery point in the cartridge by varying the airflow through the nozzle head; and, if a position of a haptic on the lens is determined to be misaligned relative to a feature on the cartridge, adjust the haptic from its position to a target orientation in the cartridge. The system includes at least one processor coupled to the lift tool. The at least one processor is configured to determine the position of the haptic relative to the feature on the cartridge. According to one or more embodiments, the above-described system embodiments can be implemented as an apparatus, a method, and / or a computer program product. [Brief explanation of the drawings]

[0007] A more detailed understanding may be had from the following description, given by way of example in conjunction with the accompanying drawings, in which like reference numerals indicate similar elements and in which: [Figure 1] 1 illustrates a system according to one or more embodiments. [Figure 2] 1 illustrates a method according to one or more embodiments. [Figure 3] 1 illustrates a system according to one or more embodiments. [Figure 4] 1 illustrates an artificial intelligence (AI) diagram of a decision engine according to one or more embodiments. [Figure 5] 1 illustrates a neural network and a method implemented in the neural network, according to one or more embodiments. [Figure 6] 1 illustrates a method according to one or more embodiments. [Figure 7] 1 illustrates a lift tool according to one or more embodiments. [Figure 8A] 8 illustrates a perspective view of a portion of the lift tool of FIG. 7 according to one or more embodiments. [Figure 8B] 8 illustrates a perspective view of a portion of the lift tool of FIG. 7 according to one or more embodiments. [Figure 9A] 1 illustrates a top view of an IOL in contact with a lift tool, according to one or more embodiments. [Figure 9B] 1 illustrates a bottom view of an IOL in contact with a lift tool, according to one or more embodiments. [Figure 10] 10 shows images detailing the change in position of the IOL based on operation of the system in accordance with one or more embodiments. DETAILED DESCRIPTION OF THE INVENTION

[0008] Generally, systems and methods for IOL packaging are disclosed herein. In particular, the systems and methods provide for loading of an IOL into a cartridge by a loading assembly system that uses vacuum and gripper technology to provide automated placement of the IOL into the cartridge.

[0009] FIG. 1 illustrates a system 100 (e.g., a loading assembly system) according to one or more embodiments. The system 100 can be generally considered a combination of assemblies, sensors, processes, diagnostics, and user equipment. Note that items and elements of the system 100 are shown singularly, but represent one or more of the items or elements. To implement automated placement, the system 100 implements one or more instances of a decision engine 101. According to one or more embodiments, the decision engine 101 can be configured in hardware, software, or a hybrid implementation. For example, the decision engine 101 can be stored as a software component, module, engine, or instructions executed by a processor (as described herein) to operate the system 100. Note that the decision engine 101 can be considered a system-wide instruction / software combination, including a client instance (e.g., decision engine 101.A) that communicates with other elements of the system 100 (e.g., decision engine 101.B can be a server instance). For example, the decision engine 101 may comprise a particular software instance that implements the particular operation of the system 100 itself. The system also includes a device 102 (e.g., including at least one processor and memory) and a camera 104, as further described herein.

[0010] The system 100 includes a lift tool 105. The lift tool 105 can include a frame 106, one or more grippers 107, and a nozzle head 108, as well as optional motors, compressors, air passages, gears, bearings, lubricants, sensors, circuitry, wiring, lighting, and the like, to capture, move, and place the IOL 110 based on communication to / from the decision engine 101. The frame 106 includes one or more members, each of which can be articulated and moved in the x, y, and z directions and relative to each other, such as by an electric motor. The one or more members can be made of any material, such as metal, plastic, rubber, wood, and the like. Each of the one or more grippers 107 can be a bar or rod member extending from the frame 106. Each of the one or more grippers 107 can be movable in the y, z directions, such as by an electric motor.

[0011] Nozzle head 108 can provide airflow 109 to IOL 110. IOL 110 is an artificial implant used to replace the natural lens in the eye as part of the treatment of cataracts or myopia (e.g., typically implanted after the eye's cloudy natural lens is removed during cataract surgery). IOL 110 can include a lens body 112 and one or more haptics 111. Lens body 112 (e.g., a small plastic lens) provides the same light-gathering function as the natural lens. One or more haptics 111 (e.g., plastic side struts) hold IOL 110 in place within the capsular bag inside the eye.

[0012] The air flow 109 can be along an inward direction to create direct suction on the IOL 110, or along an outward direction to create a suction effect according to Bernoulli's principle. According to one or more embodiments, the nozzle head 108 contacts the periphery of the lens body 111 of the IOL 110 while the air flow 109 is active. By way of example, the nozzle head 108 can be configured to utilize Bernoulli's principle to provide a suction effect that is used to lift the IOL 110 while limiting pressure on the IOL 110. Due to the configuration of the nozzle head 108 and the use of Bernoulli's principle, the lift tool 105 only contacts the non-optical portion of the IOL 110 (e.g., minimal contact with the periphery of the lens body 111) during capture of the IOL 110.

[0013] According to one or more embodiments, the one or more grippers 107 may be matingly associated and may conform or correspond to the haptics 111 of the IOL 110. The one or more grippers 107 generally do not engage or contact the IOL 110 during the picking / capturing / placing of the automated placement operation. Rather, the one or more grippers 107 engage the IOL 110 after placement / placing to enable a smart loading operation. In this regard, for example, a first gripper 107 of the pair can align the haptic 111.A with respect to the first feature 117.A. Then, a second gripper 107 of the pair can align the haptic 111.B with respect to the second feature 117.B. Examples of the one or more grippers 107 include, but are not limited to, an electric gripper, a gripper using a piezoelectric actuator, a large-displacement microgripper, a haptic gripper, and a robotic gripper. As used herein, the term feature is used to refer to a location within the cartridge designed for placement of a haptic. By way of example and not limitation, a feature may be a seat, ledge, ramp, detent, protrusion, gap, or any other feature upon, adjacent to, against, or beneath which a haptic may be placed.

[0014] Initially, the IOL 110 may be positioned at a pick position 113 on a platform 114. The lift tool 110 may secure and move the IOL 110 from the pick position 113 to a delivery point 115 of a cartridge 116 (e.g., a lens module), e.g., onto one or more features 117. The pick position 113 on the platform 114 may correspond to how the IOL 110 is being delivered after manufacture (e.g., via a product manufacturing line or in a shipping container). The delivery point 115 of the cartridge 116 may correspond to the packaging of the IOL 110 (e.g., in a cartridge line). Note that the IOL 110 is loaded into the cartridge 116 so that it can be properly folded without being damaged. After folding, the IOL 110 can be presented into the eye through a small incision (e.g., smaller than the size of the unfolded IOL 110) and an unfolder during surgery while in the eye. Proper placement of the IOL 110 within the cartridge 116 and on one or more features 117 is essential to prevent the IOL 110 from being damaged throughout the surgery.

[0015] System 100 also includes a cloud environment 129. Cloud environment 129 may be a wired network, a wireless network, and / or may 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 series of connections, a cellular network, or any other network or medium capable of facilitating communication between the items of FIG. 1 , and may use any one of a variety of communication standards / protocols (e.g., Bluetooth, Wi-Fi, Zigbee, Z-Wave, near field communications (NFC), Zigbee, infrared (IR), Ethernet, Universal Serial Bus (USB), or any other communication standard / protocol). Furthermore, several networks may operate alone or in communication with each other to facilitate communication within cloud environment 129.

[0016] Cloud environment 129 includes devices 130 (e.g., remote computing systems) and data / web services 140, each of which may include at least one processor and memory, as described further herein. In some examples, devices 130 and / or data / web services 140 may be implemented as a single physical server on cloud environment 129. In other examples, devices 130 and / or data / web services 140 may be implemented as virtual servers on a public cloud computing provider of cloud environment 129. Data / web services 140 may be a database (e.g., an SQL database) and / or another storage mechanism. Thus, data / web services 125 may be used as a repository for storage across system 100. According to one or more embodiments, data / web services 140 may store data, machine learning (ML) models, decision models, driver components, native APIs, and the like, used by decision engine 101. According to one or more embodiments, the data may be in the form of any quantity, statistics, measurements, visual information, device speed, airflow information, dates, identification information, etc. from any source, as well as associated predictors. As an example, device 102 may generate measurements from visual information of one or more images. Measurements may include, but are not limited to, the location of a haptic, the distance between haptic 111 and the wall of feature 117, etc.

[0017] Any of the memories of device 102, device 130, and data / web services 140 may include an instance of decision engine 101 (e.g., decision engine 101.A residing on device 102 and decision engine 101.B residing on device 130). Generally, decision engine 101 is executed by at least one processor in system 100 to perform automated deployment operations, whether automatically or at the direction of a technician 150. According to one or more embodiments, decision engine 101 may be fully autonomous as driven by machine learning and / or an artificial intelligence (ML / AI) and programming described herein. Technician 150 may be any one or more personnel providing medical treatment and / or care. Examples of technician 150 include, but are not limited to, engineers, programmers, assembly workers, factory workers, surgeons, doctors, clinicians, medical staff, nurses, and medical assistants.

[0018] Referring now to Figure 2, a method 200 according to one or more embodiments is shown. For purposes of brevity, like reference numbers in each figure indicate like elements, and Figure 2 uses like objects, elements, items, and reference numbers as in previous figures.

[0019] Method 200 illustrates an automatic placement operation of an IOL 110 within a cartridge 116 of system 100. Generally, the automatic placement operation includes when an IOL 110 is provided by a nozzle head 108 of a lift tool 105 from a pick position 113 to a delivery point 115. Method 200 can be performed by decision engine 101.

[0020] The method 200 begins at block 210 with the nozzle head 108 of the lift tool 105 capturing the IOL 110 from the pick position 113 of the platform 114 based on the airflow 109 through the nozzle head 108. At block 230, the lift tool 105 places the IOL 110 at the delivery point 115 within the cartridge 116 by altering (e.g., stopping or reducing) the airflow 109 through the nozzle head 108. It should be noted that, according to one or more embodiments, the cartridge 116 can be "opened" (e.g., the lid of the lens module can be in an open position, exposing and making the delivery point 115 as well as the feature 117 visible) so that the IOL 110 can be delivered into the cartridge 116.

[0021] In block 250, at least one processor (e.g., of device 102 communicatively and operably coupled to lift tool 105) determines the position of at least one of one or more haptics 111 of IOL 110 relative to a corresponding one of one or more features 117 of cartridge 116 (e.g., first haptic 111.A is determined relative to first feature 117.A). In block 270, if the position is misaligned (e.g., the position of first haptic 111.A is determined to be misaligned relative to first feature 117.A), lift tool 105 adjusts at least one of the one or more haptics 111 from its position to a target orientation on / in cartridge 116 or relative to a corresponding one of one or more features 117 of cartridge 116. It should be noted that, according to one or more embodiments, the cartridge 116 can be "closed" so that the IOL 110 is housed within the cartridge 116 (e.g., the lens module lid can be automatically moved to a closed position by a rotating device).

[0022] 1 , devices 102 and 130 and data / web services 140 may be structurally any computing device, such as a general-purpose computer, including software and / or hardware, with suitable interface circuitry for sending and receiving signals to and from other items in system 100. By way of example, devices 102 and 130 and data / web services 140 may be a single computing device. By way of example, device 130 and data / web services 140 are shown as virtual and / or distributed devices within cloud environment 129.

[0023] As a representative example of system 100, Figure 3 illustrates system 300 according to one or more embodiments. For purposes of brevity, like reference numerals in each figure indicate like elements, and Figure 3 uses like objects, elements, items, and reference numerals from previous figures.

[0024] System 300 may represent any computing device and / or computing environment, including hardware, software, or a combination thereof. Furthermore, embodiments of the disclosed system 300 may include devices, systems, methods, and / or computer program products at any possible level of technical detail integration.

[0025] System 300 illustrates device 102 having one or more central processing units (CPUs), collectively or generically referred to as processors 310. Processor 310, also referred to as processing circuitry, is coupled to system memory 320 and various other components via a system bus 315. Device 102 (as well as devices 130 and data / web services 140) may be adapted or configured to operate as an online platform, a server, an embedded computing system, a personal computer, a console, a personal digital assistant (PDA), a mobile phone, a tablet computing device, a quantum computing device, a cloud computing device, a mobile device, a smartphone, a fixed mobile device, a smart display, a wearable computer, or the like.

[0026] The processor 310 may be any type of general-purpose 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. The processor 310 may also have multiple processing cores, at least some of which may be configured to perform specific functions. It may also be configured for multiple parallel processes. Additionally, at least the processor 310 may be a neuromorphic circuit, including processing elements that mimic biological neurons. The processor 131 may be configured to receive, process, and manage information from the data / web services 140 when executing the decision engine 101. The processor 131 may also represent cloud processing across the system 100.

[0027] The system bus 315 (or other communication mechanism) is configured for communication of signals (and data) to / from various other components, such as the processor 310, the system memory 320, and the adapter 325. The system memory 320 is an example of a (non-transitory) computer-readable storage medium on which the decision engine 101 may be stored, such as software components, modules, engines, or instructions executed by the processor 310 to operate the device 102 as described herein with reference to the figures. The system memory 320 may include any combination of read-only memory (ROM), random access memory (RAM), internal or external flash memory, embedded static RAM (SRAM), solid-state memory, cache, static storage such as a magnetic or optical disk, or any other type of volatile or non-volatile memory. The non-transitory computer-readable storage medium may be any medium accessible by the processor 310 and may include volatile or non-volatile media, etc. For example, ROM may be 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 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, removable or non-removable. The memory 132 may also be virtualized and distributed across the cloud environment 115.

[0028] According to one or more embodiments, the decision engine 101 can be configured in hardware, software, or a hybrid implementation. The decision engine 101 can be configured with modules that operatively communicate with each other and pass information or instructions to each other. According to one or more embodiments, the decision engine 101 can provide one or more UIs, for example, instead of an operating system or other application and / or directly as needed. UIs include, but are not limited to, a graphic user interface (GUI), a windowing interface, an internet browser, and / or other visual interfaces for applications, operating systems, file folders, and the like. Thus, user activity can include any interaction or manipulation of a UI provided by the decision engine 101. The decision engine 101 can further include custom modules that perform application-specific processes or derivatives thereof, such that the computing system 200 can include additional functionality.

[0029] For example, according to one or more embodiments, the decision engine 101 may be configured to store information, instructions, commands, or data that are executed or processed by the processor 310 to logically implement method 200 of FIG. 2 and method 600 of FIG. 6 (represented by blocks 210, 230, 250, and 270 within the decision engine 101). For example, the decision engine 101 is communicatively and operably coupled to the lift tool 105 to send commands to the lift tool 105 and cause it to operate. The decision engine 101 of FIGS. 1 and 3 may also represent an operating system, a mobile application, a client application instance, a server application instance, and / or the like. According to one or more embodiments, the functionality of the device 102 related to the decision engine 101 may also be implemented in the device 130 and data / web services, as represented by separate instances of the decision engine 101.

[0030] Furthermore, the modules of the decision engine 101 can be implemented as hardware circuits including custom very large scale integration (VLSI) circuits or gate arrays, off-the-shelf semiconductors such as logic chips, transistors, or other discrete components, in programmable hardware devices (e.g., field programmable gate arrays, programmable array logic, programmable logic devices), or graphics processing units, etc. The modules of the decision engine 101 can be implemented at least in part in software for execution by various processors. According to one or more embodiments, a particular unit of executable code may comprise one or more physical or logical blocks of computer instructions, which may be organized as, for example, an object, a procedure, a routine, a subroutine, or a function. The executables of a particular module may be co-located or stored in different locations such that when logically combined they constitute a module. A module of executable code may be a single instruction, one or more data structures, one or more data sets, or multiple instructions, which may be distributed across multiple different code segments, different programs, multiple memory devices, etc. As used herein, operational or functional data may be identified and instantiated within modules of the decision engine 101 and may be embodied in any suitable form and organized within any suitable type of data structure.

[0031] Additionally, modules of the decision engine 101 can also include, but are not limited to, a location determination module, an augmented reality module, and an ML / AI algorithm module. The location determination module can be configured to create, build, store, and provide algorithms and models that determine the position of the lift tool 105 and the relative distance between the haptics 111 and the features 117. According to more embodiments, the location determination module can implement location determination, spatial navigation, surveying, distance, direction, and / or time software. The augmented reality module can be configured to create, build, store, and provide algorithms and models that provide an interactive experience, along with the automated placement operations of the system 100, where objects present in the real world (e.g., the haptics 111 and the features 117) are augmented with computer-generated perceptual information, potentially across multiple sensory modalities. The ML / AI algorithm module can be configured to create, build, store, and provide algorithms and models that not only emulate “natural” human cognitive abilities but also automatically improve through experience. In one example, ML software builds a particular model and uses training data to improve the model, while AI software perceives the environment (e.g., receives active data) and takes action (e.g., applies the model) to solve problems and / or generate outputs. AI software can use models built by humans and / or ML software. AI software can also provide feedback to the ML software to improve any of its models. ML / AI can exist independently and / or coexist.

[0032] Adapters 325 may represent input / output (I / O) adapters, communication adapters, and device adapters.

[0033] In accordance with one or more embodiments, the I / O adapter may be configured as a small computer system interface (SCSI) and may support a variety of protocols, including 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 (GSM) communications, 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), 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 may be considered.

[0034] The communications adapter interconnects the system bus 315 with the cloud environment 129, which may be an external network, allowing the device 102 to communicate signals (and data) with other such devices (e.g., remote computing systems, etc.). In one embodiment, the adapter 325 may be connected to one or more I / O buses, which may be connected to the system bus 315 through 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 Peripheral Component Interconnect (PCI).

[0035] The device adapters interconnect input / output devices such as a display 341 , a manipulation device 342 , a camera 104 , a lift tool 105 , or other devices (eg, speakers) to the system bus 315 .

[0036] The display 341 is configured to provide one or more UIs or graphical UIs (GUIs) that can be captured and analyzed by the decision engine 101 as a user interacts with the device 102. Examples of the display 341 may include, but are not limited to, a 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, Retina (copyright) display, or in-plane switching (IPS) display. Display 341 may be configured as a touch, three dimensional (3D) touch, multi-input touch, or multi-touch display, using resistive, capacitive, surface-acoustic wave (SAW) capacitive, infrared, image recognition, vibration detection, acoustic pulse recognition, attenuated total reflection, or other methods of input / output (I / O) understood by those skilled in the art.

[0037] Further coupled to the system bus 315 may be a navigation device 342, such as a keyboard, computer mouse, touchpad, touchscreen, or keypad, for providing input to the device 102. Additionally, one or more inputs may be provided remotely to the computing system 300 via another computing system (e.g., a remote computing system 355) in communication with the computing system 300, or the device 102 may operate autonomously.

[0038] The camera 104 can be any light-sensitive device for taking one or more images (e.g., still and / or video) of the IOL 110 and lift tool 105 relative to the platform 114 and cartridge 116. The one or more images can be of any resolution suitable for providing (or determining from) visual information regarding the position of the IOL 110 and lift tool 105 relative to the platform 114 and cartridge 116. It should be noted that the one or more images from the camera 104 can be stored in a common repository, such as the data / web service 140, and can be downloaded (on demand) to and / or from each of the device 102, the device 130, and / or the data / web service 140. The camera 104 can be positioned above the lift tool 105 to take a topographic image of the IOL 110. The camera 104 can be fixed (e.g., positioned above the delivery point 115). The camera 104 can move with the movement of the lift tool 105. The camera 104 can also represent multiple cameras, where a first camera is above the pick position 113, a second camera is above the delivery point 115, and / or a third camera moves with the lift tool 105.

[0039] Generally, the decision engine 101 utilizes one or more images to guide the automated placement operation of the lift tool 105. The decision engine 101 may utilize modules and / or ML / AI algorithms to automatically receive, process, and interpret one or more images and other data from a common repository. Referring to FIG. 4, an AI diagram 400 of the decision engine 101 is shown in accordance with one or more embodiments. The AI ​​diagram 400 includes data 410, machine 420, model 430, outcome 440, and (underlying) hardware 450.

[0040] Where appropriate, for ease of understanding, the description of Figure 4 will be made with reference to Figures 1-3. For example, machine 420, model 430, and hardware 450 may represent aspects of decision engine 101 of Figure 1 (e.g., ML / AI algorithms therein), while hardware 450 may also represent devices 102 and 130 and / or data / web services 140 of Figure 1. Generally, the ML / AI algorithms of AI system 400 (e.g., as implemented by decision engine 101 of Figure 1) operate on hardware 450 using data 410 to train machine 420, build model 430, and predict outcome 440.

[0041] The data 410 can be any data described herein. For example, the data can include IOL information and measurements, such as IOL master data, image data, video data, precision measurement data, three-dimensional data, and cartridge data. The data 410 can be ongoing data or output data associated with the hardware 450. The data 410 can also include currently collected data, historical data, or other data from the hardware 450. The data 410 can be divided into one or more subsets by the machine 420.

[0042] The machine 420 acts as a controller or data collection associated with and / or is associated with the hardware 450. The machine 420 is trained, for example, against the hardware 450. This training may also include parsing, analyzing, merging, and correlating the collected data 410. According to one or more embodiments, training the machine 420 may include self-training by the decision engine 101 using one or more subsets.

[0043] The model 430 can 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 the data 410. For example, an SVM provides a predictive method that uses a statistical learning framework for classification and regression analysis of the data 410. The model 430 can use 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, etc.

[0044] A model 430 (e.g., an ML / AI model and / or a resulting decision model) is constructed for data 410 associated with hardware 450. Constructing model 430 may include physical hardware or software modeling, algorithmic modeling, and / or similar modeling intended to represent collected and trained data 410 (or a subset thereof). In some aspects, constructing model 430 is part of a self-training operation by machine 420.

[0045] The model 430 can be configured to model the operation of the hardware 450 and to model the data 410 collected from the hardware 450 to predict an outcome 440 to be achieved by the hardware 450 (e.g., to achieve automatic placement of the IOL 110 on / in the cartridge 116 or at a target orientation relative to the features 117 of the cartridge 116). The prediction of the outcome 440 (of the model 430 associated with the hardware 450) can use the trained model 430. The predicted outcome 440 can then be used to further configure and / or refine the machine 420, model 430, and hardware 450 accordingly.

[0046] Thus, the ML / AI algorithms therein may include neural networks, where AI diagrams 400 use data 410 to operate against hardware 450 to train machines 420, build models 430, and predict outcomes 440. Generally, neural networks are networks or circuits of neurons, or in the modern sense, artificial neural networks (ANNs) comprised of artificial neurons or nodes or cells. For example, ANNs include networks of processing elements (artificial neurons) that can exhibit complex global behavior determined by connections between the processing elements and element parameters. These connections in a neuronal network or circuit are modeled as weights. Positive weights reflect excitatory connections, while negative values ​​represent inhibitory connections. Inputs are modified by the weights and summed using linear combinations. An activation function can control the amplitude of the output. For example, the acceptable range of the output is typically between 0 and 1, but can also be between -1 and 1. ANNs are often adaptive systems that change their structure based on external or internal information flowing through the network.

[0047] In more practical terms, neural networks are nonlinear statistical data modeling or decision-making tools 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 through data sets. Note that self-learning arising from experience can occur within ANNs, allowing them to draw conclusions from complex and seemingly unrelated sets of information. The usefulness of artificial neural network models lies in the fact that they can be used to estimate and use functions from observations. According to one or more embodiments, neural networks may implement long-short-term memory neural network architectures, convolutional neural network (CNN) architectures, or other similar architectures. Neural networks may be configurable with multiple layers, multiple connections (e.g., encoder / decoder connections), regularization techniques (e.g., dropout), and optimization features.

[0048] Referring now to Figure 5, a neural network 500 and a method 501 performed by the neural network 500 are shown, in accordance with one or more embodiments. The neural network 500 operates to assist in the implementation of the ML / AI algorithms described herein (e.g., as implemented by decision 101 of Figure 1). The neural network 500 may be implemented in hardware, such as the machine 420 and / or hardware 450 of Figure 4. As provided herein, the description of Figure 5 will be made with reference to Figures 1-4, where appropriate, for ease of understanding.

[0049] 1 includes collecting data 410 from hardware 450. In neural network 500, input layer 510 is represented by multiple inputs (e.g., inputs 512 and 514 in FIG. 5). With respect to block 520 of method 501, input layer 510 receives input 512 and input 514.

[0050] In block 525 of method 501, neural network 500 encodes inputs 512 and 514 using any portion of data 410 (e.g., datasets and predictions generated by AI system 400) to generate latent representations or data encodings. The latent representations include one or more intermediate data representations derived from multiple inputs. According to one or more embodiments, the latent representations are generated by element-wise activation functions (e.g., sigmoid functions or rectified linear functions) of decision engine 101 of FIG. 2. As shown in FIG. 5, inputs 512 and 514 are provided to hidden layer 530, which is shown to include nodes 532, 534, 536, and 538. Neural network 500 executes processing through 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 layer 510 and layer 530 can be viewed as an encoder stage that takes input 512 and input 514 and forwards them to a deep neural network (in layer 530) to learn smaller representations of some of the inputs (e.g., resulting latent representations).

[0051] The deep neural network may be a CNN, a long-short-term memory neural network, a fully connected neural network, or a combination thereof. This encoding results in dimensionality reduction of the inputs 512 and 514. Dimensionality reduction is the process of reducing the number of random variables being considered (in the inputs 512 and 514) by obtaining a set of key variables. For example, dimensionality reduction may be feature extraction, which transforms the data (e.g., the inputs 512 and 514) from a high-dimensional space (e.g., greater than 10 dimensions) to a low-dimensional space (e.g., two to three dimensions). Technical effects and advantages of dimensionality reduction include reducing the time and storage space requirements of the data 410, improving the visualization of the data 410, and improving parameter interpretability for ML. This data transformation may be linear or nonlinear. The receiving (block 520) and encoding (block 525) operations may be considered the data preparation portion of the multi-stage data manipulation by the decision engine 101.

[0052] At block 545 of method 510, neural network 500 decodes the latent representations. The decoding stage receives the encoder output (e.g., the resulting latent representations) and attempts to reconstruct a particular form of input 512 and input 514 using another deep neural network. In this regard, nodes 532, 534, 536, and 538 are combined to generate output 552 at output layer 550, as shown at block 560 of method 510. That is, output layer 550 reconstructs input 512 and input 514 with reduced dimensionality but without signal interference, signal artifacts, and signal noise.

[0053] Referring now to FIG. 6 , a method 600 is shown in accordance with one or more embodiments. Method 600 outlines the automated placement of an IOL 110 into a cartridge 116 of system 100. FIGS. 7-10 are provided as supplements to FIG. 6 . FIG. 7 illustrates a lift tool 700 in accordance with one or more embodiments. Lift tool 700 is a schematic example of a lift tool 105 of system 100. FIGS. 8A and 8B illustrate perspective views 801 and 802 of a portion 701 of lift tool 700 of FIG. 7 in accordance with one or more embodiments. As shown in FIGS. 7 , 8A, and 8B, lift tool 700 includes frame members 821, 822, 823, and 824, a central member 831 including a bore 832, and grippers 841, 842, 843, and 844. 9A and 9B show top and bottom views 901 and 902 of the IOL 110 in contact with the lift tool 700 of FIG. 7, in accordance with one or more embodiments. FIG. 10 shows images 1001 and 1002 detailing the change in position of the IOL 110 based on the operation of the lift tool 700 of FIG. 7, in accordance with one or more embodiments. For purposes of brevity, like reference numbers in each figure indicate like elements, and like objects, elements, items, and reference numbers are used in FIGS. 6-10 as in previous figures.

[0054] Method 600 begins in block 605 with camera 104 capturing one or more images of lift tool 700, IOL 110, and haptics 111 relative to platform 114. Note that camera 104 can capture one or more images intermittently or continuously such that visual information is provided to device 102 throughout method 600. Ellipse A illustrates a non-limiting example of how camera 104 can capture one or more images and subsequently provide visual information in method 600 (e.g., camera 104 captures one or more images of IOL 110 and haptics 111 relative to cartridge 116). Thus, system 100 provides guided vision for automated placement.

[0055] In block 610 (see, e.g., block 210 of FIG. 2 ), the nozzle head 108 of the lift tool 105 captures the IOL 110 from the pick position 113 of the platform 114 based on the airflow 109 passing through the nozzle head 108. Using sensors in the lift tool 105, the decision engine 101 can adjust the airflow 109 so as not to bend or damage the IOL 110. Note that the decision engine 101 uses visual information to verify that the lift tool 105 is in a home position above the pick position 113. See FIGS. 9A and 9B, which are top and bottom views 901 and 902 of the IOL 101 captured by the central member 831. Note that the first haptic 111.A is between grippers 841 and 842, and the second haptic 111.B is between grippers 843 and 844.

[0056] In block 630 (see, e.g., block 210 of FIG. 2 ), the lift tool 105 places the IOL 110 at the delivery point 115 in the cartridge 116 by varying (e.g., reducing or stopping) the air flow 109 through the nozzle head 108. Note that the decision engine 101 uses visual information to verify that the lift tool 105 is in position above the delivery point 115. Referring to FIG. 10 , an image 1001 provides visual information of the IOL 110 in the cartridge 116.

[0057] In block 650, the decision engine 101 determines the position of at least one of the one or more haptics 111 of the IOL 110 relative to a corresponding one of the one or more features 117 of the cartridge 116 (e.g., the first haptic 111.A is determined relative to the first feature 117.A). Generally, the decision engine 101 determines the incremental positional status of the IOL 110 and haptics 111 relative to the pick position 113, delivery point 115, and features 117 throughout the method 600. Returning to FIG. 10 , note that in image 1001, the first haptic 111.A is a distance X away from the wall of the first feature 117.A. The distance X is determined by the decision engine 101. According to one or more embodiments, features 117.A and 117.B of FIG. 10 include a flat pedestal or tabletop-like surface with at least one wall extending perpendicularly from an edge of the surface.

[0058] At decision block 655, the decision engine 101 determines whether the target position has been achieved. The target position may be when the haptic 111 is adjacent to, near, or otherwise in contact with the wall of the feature 117. For example, the decision engine 101 determines whether the distance X is such that the IOL 110 is properly loaded into the cartridge 116 and can be properly folded without being damaged. If the target position has been achieved (e.g., aligned), the method 600 proceeds to block 680 (e.g., as indicated by a YES arrow). If the target position has not been achieved (e.g., misaligned), the method 600 proceeds to block 270 (e.g., as indicated by a NO arrow).

[0059] If the position is misaligned, in block 670 (see, for example, block 270 of FIG. 2 ), the decision engine 101 causes the lift tool 105 to adjust at least one of the haptics 111 from the current position to the target position. Sub-block 672 further describes the operation of block 670. In sub-block 672, one or more frame members 821, 822, 823, and 824 and / or one or more grippers 841, 842, 843, and 844 can be actuated to adjust the haptics 111 from the current position to a subsequent orientation (i.e., the final goal of achieving the target position). For example, the grippers 841 and 842 can be moved laterally together with the frame member 822 to contact the first haptic 111.A and adjust its position. It should be noted that, according to one or more embodiments, grippers 841, 842, 843, and 844 may be movable independently of nozzle head 106 and one or more frame members 821, 822, 823, and 824. Next, method 600 repeats block 650 and decision block 655 to determine whether further adjustments are needed. For example, decision engine 101 determines whether distance Y of image 1002 is such that IOL 110 can be properly loaded into cartridge 116 and properly folded without damage. Since distance Y is acceptable (0 or close to zero), the process proceeds to block 680.

[0060] In block 680, the decision engine 101 determines the position of at least one of the one or more haptics 111 of the IOL 110 relative to a corresponding one of the one or more features 117 of the cartridge 116 (e.g., the second haptic 111.B is determined relative to the second feature 117.B). Note that the visual information generated by the camera 104 in block 610 can be continuously provided to the decision engine 101, as bounded by ellipse A.

[0061] At decision block 685, the decision engine 101 determines whether the target position has been achieved. If the target position has been achieved (e.g., aligned), the method 600 proceeds to block 690 and ends (e.g., as indicated by a YES arrow). If the target position has not been achieved (e.g., misaligned), the method 600 proceeds to block 695 (e.g., as indicated by a NO arrow).

[0062] If misaligned, in block 695, the decision engine 101 causes the lift tool 105 to adjust at least one of the haptics 111 from its current position to its target position. Sub-block 672 further describes the operation of block 670. As an example, the decision engine 101 causes the lift tool 700 to adjust the second haptic 111.B from its second position to its target position on the second feature 117.B of the cartridge 116. Next, the method 600 repeats block 680 and decision block 685 to determine whether further adjustments are needed. If the IOL 110 is properly loaded, the method 600 proceeds to block 690.

[0063] The flowcharts and block diagrams in the figures illustrate the structure, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of the present invention. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of instructions, including one or more executable instructions for implementing the depicted logical function(s). In some alternative implementations, the functions depicted in the blocks may occur out of the order depicted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending on the functionality involved. It should also be noted that each block of the block diagrams and / or flowchart illustrations, and combinations of blocks in the block diagrams and / or flowchart illustrations, may be implemented by a dedicated hardware-based system that performs the specified functions or operations, or may operate or execute a combination of dedicated hardware and computer instructions.

[0064] Although features and elements have been described above in particular combinations, those skilled in the art will understand that each feature or element can be used alone or in combination with other features and elements. Additionally, the methods described herein can be implemented in a computer program, software, or firmware embodied in a computer-readable medium for execution on a computer or processor. Computer-readable medium, as used herein, should not be construed as being a transitory signal per se, such as an electric 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 through a conductor.

[0065] Examples of computer-readable media include electrical signals (transmitted via wired or wireless connections) and computer-readable storage media. Examples of computer-readable storage media include, but are not limited to, registers, cache memory, 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 memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), static random access memory (SRAM), and memory sticks. A processor together with software can be used to implement a radio frequency transceiver for use in a terminal, a base station, or any host computer.

[0066] The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting. As used herein, the singular forms "a," "an," and "the" are intended to include the plural forms unless the context clearly indicates otherwise. It is further understood that the terms "comprise" and / or "comprising," as used herein, indicate the presence of stated features, integers, steps, operations, elements, and / or components, but do not exclude the presence or addition of another other feature, integer, step, operation, element, component, and / or group thereof.

[0067] The description of various embodiments herein is provided for illustrative purposes and is not intended to be exhaustive or limited to the disclosed embodiments. Many modifications and variations will be apparent to those skilled in the art without departing from the scope and spirit of the described embodiments. The terms used herein have been selected to best explain the principles, practical applications, or technical improvements of the embodiments compared to technologies found in the market, or to enable those skilled in the art to understand the embodiments disclosed herein.

[0068] [Embodiment] (1) A method for automated placement of a lens in a cartridge, said method comprising: a nozzle head of a lift tool capturing the lens from a pick position on a platform based on airflow through the nozzle head; the lift tool depositing the lens at a delivery point within the cartridge by varying the air flow through the nozzle head; at least one processor coupled to the lift tool determining a position of the lens haptics relative to features of the cartridge; and if the position of the haptic is determined to be misaligned relative to the feature, the lift tool adjusts the haptic from the position to a target orientation on the cartridge. (2) The method of embodiment 1, further comprising the at least one processor determining from one or more images the pick position, the delivery point, and incremental positional states of the lens and the haptics of the lens relative to the feature. (3) The method of embodiment 1, further comprising a camera coupled to the at least one processor taking one or more images of the lens and the haptics of the lens relative to the platform and the cartridge to provide a guide image to the at least one processor. (4) The method of claim 1, wherein the lift tool contacts only a non-optical portion of the lens during the capture of the lens. (5) The method of embodiment 1, further comprising actuating a gripper of the lift tool 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.

[0069] (6) the at least one processor determining a second position of a second haptic of the lens relative to a second feature of the cartridge; and The method of embodiment 1, further comprising: if it is determined that the second position of the haptic is misaligned relative to the second feature, the lift tool adjusts the second haptic from the second position to a target orientation in the cartridge. (7) The method of embodiment 1, wherein the lift tool includes a first gripper and a second gripper, each of the first gripper and the second gripper configured to adjust one of the haptics of the lens. (8) The method of claim 1, wherein the nozzle head contacts the outer periphery of the body of the lens. (9) The method of embodiment 1, wherein the feature of the cartridge includes a flat surface and at least one wall extending perpendicularly from an edge of the surface. (10) The method of embodiment 1, wherein the lift tool includes a frame, one or more grippers, and the nozzle head, the frame including one or more members, each of the one or more members configured to articulate and move in x, y, and z directions.

[0070] (11) A system for automatic placement of a lens in a cartridge, said system comprising: 1. A lift tool including a nozzle head, the lift tool comprising: capturing the lens from a pick position on a platform based on an air flow through the nozzle head; placing the lens at a delivery point within the cartridge by varying the air flow through the nozzle head; a lift tool configured to adjust the lens haptics from their positions to a target orientation on the cartridge when the positions of the lens haptics are determined to be misaligned with respect to the features of the cartridge; and at least one processor coupled to the lift tool, the at least one processor configured to determine the position of the haptic relative to the feature of the cartridge. (12) The system of embodiment 11, wherein the at least one processor is configured to determine the pick position, the delivery point, and incremental positional states of the lens and the haptics of the lens relative to the feature from one or more images. (13) The system of embodiment 11, wherein the system includes a camera coupled to the at least one processor, the camera configured to capture one or more images of the lens and the haptics of the lens relative to the platform and the cartridge to provide a guide image to the at least one processor. (14) The system of claim 11, wherein the lift tool contacts only a non-optical portion of the lens during the capture of the lens. (15) The system of embodiment 11, wherein the system includes a gripper configured to be actuated by the lift tool and adjust the haptic from the position to the target orientation based on a signal from the at least one processor from one or more images.

[0071] (16) 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; The system of embodiment 11, wherein the lift tool is configured to adjust the second haptic from the second position to a target orientation in the cartridge when it is determined that the second position of the haptic is misaligned relative to the second feature. (17) The system of embodiment 11, wherein the lift tool includes a first gripper and a second gripper, each of the first gripper and the second gripper configured to adjust one of the haptics of the lens. (18) The system of embodiment 11, wherein the nozzle head contacts the outer periphery of the body of the lens. (19) The system of embodiment 11, wherein the feature of the cartridge includes a flat surface and at least one wall extends perpendicularly from an edge of the surface. (20) The system of embodiment 11, wherein the lift tool includes a frame, one or more grippers, and the nozzle head, the frame including one or more members, each of the one or more members configured to articulate and move in x, y, and z directions.

Claims

1. 1. A method for automated placement of a lens in a cartridge, the method comprising: a nozzle head of a lift tool capturing the lens from a pick position on a platform based on airflow through the nozzle head; the lift tool depositing the lens at a delivery point within the cartridge by varying the air flow through the nozzle head; at least one processor coupled to the lift tool determining a position of the lens haptics relative to features of the cartridge; and if the position of the haptic is determined to be misaligned relative to the feature, the lift tool adjusts the haptic from the position to a target orientation on the cartridge.

2. The method of claim 1 , further comprising the at least one processor determining incremental positional states of the lens and the haptics of the lens relative to the pick position, the delivery point, and the feature from one or more images.

3. The method of claim 1 , further comprising a camera coupled to the at least one processor taking one or more images of the lens and the haptics of the lens relative to the platform and the cartridge to provide a guide image to the at least one processor.

4. The method of claim 1 , wherein the lift tool contacts only a non-optical portion of the lens during the capture of the lens.

5. The method of claim 1 , further comprising actuating a gripper of the lift tool 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.

6. the at least one processor determining a second position of a second haptic of the lens relative to a second feature of the cartridge; The method of claim 1 , further comprising: if it is determined that the second position of the haptic is misaligned relative to the second feature, the lift tool adjusts the second haptic from the second position to a target orientation on the cartridge.

7. 2. The method of claim 1, wherein the lift tool includes a first gripper and a second gripper, each of the first gripper and the second gripper configured to adjust one of the haptics of the lens.

8. The method of claim 1 , wherein the nozzle head contacts the periphery of the body of the lens.

9. The method of claim 1 , wherein the feature of the cartridge includes a flat surface with at least one wall extending perpendicularly from an edge of the surface.

10. 2. The method of claim 1, wherein the lift tool includes a frame, one or more grippers, and the nozzle head, the frame including one or more members, each of the one or more members configured to articulate and move relative to x-y-z directions.

11. 1. A system for automated placement of a lens in a cartridge, the system comprising:

1. A lift tool including a nozzle head, the lift tool comprising: capturing the lens from a pick position on a platform based on an air flow through the nozzle head; placing the lens at a delivery point within the cartridge by varying the air flow through the nozzle head; a lift tool configured to adjust the lens haptics from their positions to a target orientation on the cartridge when the positions of the lens haptics are determined to be misaligned with respect to the features of the cartridge; and at least one processor coupled to the lift tool, the at least one processor configured to determine the position of the haptic relative to the feature of the cartridge.

12. The system of claim 11 , wherein the at least one processor is configured to determine incremental positional states of the lens and the haptics of the lens relative to the pick position, the delivery point, and the feature from one or more images.

13. 12. The system of claim 11, wherein the system includes a camera coupled to the at least one processor, the camera configured to capture one or more images of the lens and the haptics of the lens relative to the platform and the cartridge to provide a guide image to the at least one processor.

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

15. The system of claim 11 , wherein the system comprises a gripper actuated by the lift 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 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; The system of claim 11 , wherein the lift tool is configured to adjust the second haptic from the second position to a target orientation on the cartridge when it is determined that the second position of the haptic is misaligned relative to the second feature.

17. 12. The system of claim 11, wherein the lift tool includes a first gripper and a second gripper, each of the first gripper and the second gripper configured to adjust one of the haptics of the lens.

18. The system of claim 11 , wherein the nozzle head contacts the periphery of the body of the lens.

19. The system of claim 11 , wherein the feature of the cartridge includes a flat surface with at least one wall extending perpendicularly from an edge of the surface.

20. 12. The system of claim 11, wherein the lift tool includes a frame, one or more grippers, and the nozzle head, the frame including one or more members, each of the one or more members configured to articulate and move relative to x-y-z directions.

Images