Verification of solid dissolution in robotic drug preparation

Abstract

Image-based verification of progress and / or results, and / or detection of adverse conditions, for automated operations for preparing pharmaceuticals, particularly relating to the dissolution of pharmaceutical materials contained in vials. In some embodiments, imaging and image processing are used to track the progress of a process that converts solid and / or concentrated materials (e.g., crystallized and / or lyophilized) into fluid solutions and / or suspensions. As conditions change, the dilution time may vary, and detection of adverse conditions can reduce risk and / or waste. In some embodiments, the amount of fluid used for dissolution / dilution is monitored in itself at one or more stages. A method for evaluating the fluid contents of vials, including vials distributed for use in manual operations, which may contain visual obstructions such as labels.

Description

Technical Field

[0001] Related applications This application claims the benefit of priority of U.S. Provisional Patent Application No. 63 / 455,117, filed Mar. 28, 2023, the content of which is hereby incorporated by reference in its entirety.

[0002] Technical field In some embodiments, the present invention relates to the field of devices for the robotic preparation of pharmaceuticals, and more specifically, although not exclusively, to the mixing of substances by such devices.

Background Art

[0003] Problems in implementing the automation of pharmaceutical preparation have been recognized in the prior art, and various techniques have been developed to provide solutions.

Summary of the Invention

[0004] According to aspects of some embodiments of the present disclosure, a method for evaluating the contents of a vial, the contents including pharmaceutical components, the method comprising: manipulating the vial to vary the tilt angle of the vial with respect to the boundary region of the contents of the vial; acquiring at least one image of the vial during the period in which the tilt angle is varied; calculating, by image processing using a processing circuit, the position of the boundary region in the at least one image; comparing the position of the boundary region with a target criterion, the target criterion taking into account the shift in the position of the boundary region due to the tilt angle; and automatically determining, according to the result of the comparison, the use or rejection of the contents of the vial in the automated preparation of pharmaceutical preparation.

[0005] According to some embodiments of the present disclosure, manipulating varies the tilt angle such that the boundary region in at least one image of the vial extends along the bottom surface of the vial.

[0006] According to some embodiments of this disclosure, the target criterion includes a target position extending along the bottom surface, and the comparison determines the position of the boundary region relative to the target position.

[0007] According to some embodiments of this disclosure, the label obstructs the visibility of the contents through the obstruction side region of the vial, and the change in the tilt angle moves the boundary region from the obstruction side region to the non-obstruction surface region of the vial where the boundary region is visible.

[0008] According to some embodiments of this disclosure, the target criterion includes a target position along a non-interfering surface region of the vial, and the comparison determines the position of the boundary region relative to the target position.

[0009] According to some embodiments of this disclosure, the target location extends along a portion of the vial surface that is located above or below the label when the vial is upright.

[0010] According to some embodiments of this disclosure, during the period in which the inclination angle is changed, the height of the contents is a nonlinear function of the volume of the contents.

[0011] According to some embodiments of this disclosure, the operation involves rotating the vial while the boundary region remains horizontal.

[0012] According to some embodiments of this disclosure, the operation involves moving the vial so that the angle of the boundary region moves away from the horizontal.

[0013] According to some embodiments of the present disclosure, at least one of comparing and automatically determining includes calculating the volume of the contents of the vial, and automatically determining whether to use or reject the contents of the vial according to how close the volume is to a target volume.

[0014] According to some embodiments of this disclosure, the target criterion defines the target location, and the result of comparison includes the distance between the location of the boundary region and the target location, and the determination is to choose to use or reject the contents of the vial according to the distance.

[0015] According to some embodiments of this disclosure, the boundary region represents the difference in optical properties between the lower material phase of the vial contents and the material above it.

[0016] According to some embodiments of this disclosure, the optical properties are at least one of the refractive index, light absorption coefficient, and turbidity.

[0017] According to some embodiments of this disclosure, at least one image includes a plurality of images taken at different tilt angles of the vial.

[0018] According to some embodiments of this disclosure, the calculation and comparison are performed for each of a plurality of images.

[0019] According to some embodiments of this disclosure, the automatic determination includes determining the parameters of the vial's geometric shape using positional feature identification for each of a plurality of images.

[0020] According to some embodiments of the present disclosure, at least one image is acquired while the tilt angle changes by at least 45° from the upright and stationary position of the vial.

[0021] According to some embodiments of this disclosure, at least one image is acquired while the vial is tilted within 15° from the horizontal.

[0022] According to some embodiments of this disclosure, the contents of the vial include a fluid.

[0023] According to some embodiments of the present disclosure, the vial includes generally a cylindrical lower region, an inwardly curved top region connected to a capped neck, and a rounded bottom surface of the lower region, and the tilt angle is adjusted such that a portion of the boundary region extends along the bottom surface.

[0024] According to some embodiments of the present disclosure, at least one image images the boundary region through the optical irregularities of the bottom surface.

[0025] According to some embodiments of the present disclosure, determining the use of the contents of the vial includes determining an adjustment to the amount of fluid within the vial to correct for the difference between the target position and the positional characterization of the boundary region.

[0026] According to some embodiments of the present disclosure, the method includes manipulating the vial to a new position according to the determined use.

[0027] According to some embodiments of the present disclosure, the new position returns the vial to an upright position.

[0028] According to aspects of some embodiments of the present disclosure, a method of evaluating the fluid contents of a vial containing a pharmaceutical component, the method comprising receiving at least one image of the vial, the at least one image being an image of the vial while tilted to position a portion of a boundary layer of the fluid contents under a labeled portion of the vial surface, using computerized image processing to compare the position of the boundary layer extending along the bottom surface of the vial to a target position corresponding to a target amount of fluid within the vial and the tilt angle of the vial, and automatically determining the use or rejection of the contents of the vial in an automated preparation of a pharmaceutical formulation according to the result of the comparison.

[0029] According to some embodiments of the present disclosure, the fluid contents include a solvent in which the pharmaceutical component is dissolved.

[0030] According to some embodiments of the present disclosure, the comparison includes determining the liquid volume of the contents and comparing the determined volume with the target liquid volume of the contents.

[0031] According to some embodiments of the present disclosure, determining the volume involves measuring at least one parameter of the geometric shape of the vial using at least one image of the vial.

[0032] According to some embodiments of the present disclosure, a method is provided for evaluating the contents of a vial, wherein the contents include a pharmaceutical component, and the method comprises: manipulating the vial to change its tilt angle; acquiring at least one image of the vial during the period in which the tilt angle is changed; detecting the presence or absence of a fluid boundary region in at least one image by image processing using a processing circuit; and automatically determining whether to use or reject the contents of the vial in an automated preparation of a pharmaceutical product according to the results of the detection.

[0033] According to some embodiments of the present disclosure, the inclination angle is selected to position the fluid boundary region to extend along the surface region of the vial that is located above or below the label of the vial when the vial is upright, when the contents of the vial contain a target volume of fluid.

[0034] According to some embodiments of this disclosure, the surface region is located below the label on the vial and extends along the bottom surface of the vial.

[0035] According to some embodiments of the present disclosure, a system for evaluating vial contents containing a pharmaceutical component is provided, the system comprising a processing circuit and a memory, the memory of which commands the processing circuit to control a manipulator to change the tilt angle of the vial with respect to the upper boundary layer of the vial contents; access to at least one image of the vial taken during the period in which the tilt angle is changed; calculate a positional characterization of the boundary region of the vial contents in at least one image; compare the positional characterization of the boundary region with a target position, the target position taking into account the shift of the boundary region due to the tilt angle; and, according to the result of the comparison, command the system to use or reject the vial contents in automated preparation of pharmaceutical preparation.

[0036] According to some embodiments of this disclosure, the system includes a manipulator.

[0037] According to some embodiments of the present disclosure, the instruction instructs a processing circuit to control an imaging device to acquire at least one image of a vial.

[0038] According to some embodiments of the present disclosure, a system for evaluating vial contents containing a pharmaceutical component is provided, the system comprising: a manipulator configured to hold the vial at a variably selectable inclination angle relative to the upright orientation of the vial; an imaging device positioned relative to the manipulator to image the vial while it is held at an inclination angle relative to the upright orientation, including viewing the bottom surface of the vial; a processing circuit; and a memory for storing commands, the commands of which include commands to control the processing circuit to change the inclination angle of the vial relative to the upright orientation; to control the imaging device to acquire at least one image of the vial during the period in which the inclination angle is changed; to calculate a positional characterization of the boundary region of the vial contents in at least one image; to compare the positional characterization of the boundary region with a target position, the target position taking into account the shift of the boundary region due to the inclination angle; and to command the system to use or reject the vial contents in automated preparation of pharmaceutical preparation according to the result of the comparison.

[0039] According to some embodiments of the present disclosure, a method is provided for controlling the dissolution of a solute in a solvent in a vial, wherein the vial is held by a vial holder in a pharmaceutical preparation device, and the method includes: stirring the vial holder with a stirrer operably connected to the vial holder to shake the solute and solvent in the vial held by the vial holder; accessing by a processing circuit at least one image of the vial contents captured after stirring has started; evaluating the features of the vial contents by image processing by the processing circuit; comparing the evaluated features with targeted features of the vial contents; and adjusting the stirring by the stirrer according to the result of the comparison by the processing circuit.

[0040] According to some embodiments of this disclosure, adjustment includes stopping stirring.

[0041] According to some embodiments of this disclosure, adjustment includes restarting stirring.

[0042] According to some embodiments of this disclosure, the adjustment includes modifying at least one parameter of the stirring motion.

[0043] According to some embodiments of this disclosure, the solute is a solid.

[0044] According to some embodiments of this disclosure, the solvent is a fluid.

[0045] According to some embodiments of this disclosure, the evaluated feature is an evaluation of the dissolution of the solute into the solvent, the targeted feature of the vial contents includes a dissolution appearance criterion, and adjustments include stopping or extending the operating period of the stirrer.

[0046] According to some embodiments of the present disclosure, adjustment includes stopping the operation of the agitator while the targeted dissolution appearance criterion remains unmet and issuing a warning.

[0047] According to some embodiments of the present disclosure, the adjustment includes extending the operation of the agitator while the targeted dissolution appearance criterion remains unmet.

[0048] According to some embodiments of this disclosure, the dissolution appearance criterion includes at least one measure of the transparency of the solvent, the color of the solvent, and the clarity of the solvent.

[0049] According to some embodiments of this disclosure, the dissolution appearance criterion includes a measurement of the color of the solvent, selected according to the type of solute.

[0050] According to some embodiments of this disclosure, the evaluated features include evaluating solute adhesion, the targeted features of the solvent in the vial include adhesion appearance criteria, and adjustments include modifying parameters that govern the stirring pattern.

[0051] According to some embodiments of the present disclosure, the movement pattern is adjusted in at least one of the following: amplitude, acceleration, rotation of the vial, and the geometry of the path along which the vial moves.

[0052] According to some embodiments of this disclosure, the evaluated feature assesses the presence of foreign particles in the solvent, the targeted feature of the vial contents includes a foreign particle presence criterion, the adjustment includes stopping stirring, and the processing circuit issues a warning according to the results of the comparison.

[0053] According to some embodiments of this disclosure, the evaluated feature assesses the presence of foreign particles in the solvent, the targeted feature of the vial contents includes a foreign particle presence criterion, the adjustment includes stopping stirring, and the processing circuit issues a warning according to the results of the comparison.

[0054] According to some embodiments of this disclosure, the evaluated feature evaluates the volume of the vial's contents, and the targeted feature of the solvent in the vial contains the expected amount of vial contents. Adjustment includes stopping stirring, and according to the result of comparison, the processing circuit issues a warning.

[0055] According to some embodiments of this disclosure, at least one of evaluating and comparing features includes classifying at least one image according to a pre-trained machine learning model.

[0056] According to some embodiments of the present disclosure, the adjustment includes adjusting the stirring of at least the second vial in accordance with the results of the comparison.

[0057] According to some embodiments of this disclosure, adjustments are made according to multiple comparisons and the respective multiple results.

[0058] According to some embodiments of the present disclosure, at least one image of the vial contents is captured from a position below the vial.

[0059] According to some embodiments of the present disclosure, a system is provided for controlling the dissolution of a solute into a solvent in a vial, wherein the vial is held by a vial holder in a pharmaceutical preparation device, and the system includes a processing circuit configured to control a stirrer operably connected to the vial holder, thereby shaking the solute and solvent in the vial held by the vial holder, accessing at least one image of the vial contents captured after stirring has started, evaluating the characteristics of the vial contents, comparing the evaluated characteristics with targeted characteristics of the solvent in the vial, and adjusting the stirring of the stirrer according to the result of the comparison.

[0060] According to some embodiments of this disclosure, the evaluated feature assesses the dissolution of the solute into the solvent, the targeted feature of the solvent in the vial includes a dissolution appearance criterion, and the processing circuit adjusts the stirring by stopping or extending the operating period of the stirrer.

[0061] According to some embodiments of this disclosure, the evaluated feature assesses solute adhesion, the targeted feature of the solvent in the vial includes adhesion appearance criteria, and the processing circuit adjusts stirring by modifying parameters that govern the movement pattern of the stirrer.

[0062] According to some embodiments of this disclosure, the evaluated feature assesses the presence of heterogeneous particles in the solvent, the targeted feature of the solvent in the vial includes a criterion for the presence of heterogeneous particles, the processing circuit adjusts the stirring by stopping the stirring, and the processing circuit issues a warning according to the result of the comparison.

[0063] According to some embodiments of this disclosure, the evaluated feature assesses the presence of heterogeneous particles in the solvent, the targeted feature of the solvent in the vial includes a criterion for the presence of heterogeneous particles, the processing circuit adjusts the stirring by stopping the stirring, and the processing circuit issues a warning according to the result of the comparison.

[0064] According to some embodiments of this disclosure, the evaluated feature evaluates the volume of solvent in the vial, the targeted feature of the solvent in the vial contains the expected amount of solvent in the vial, the processing circuit adjusts the stirring by stopping the stirring, and the processing circuit issues a warning according to the result of the comparison.

[0065] Unless otherwise defined, all technical and / or scientific terms used herein have the same meaning as those generally understood by those skilled in the art to whom this disclosure relates. Similar or equivalent methods and materials described herein may be used in the implementation or testing of embodiments of this disclosure, but exemplary methods and / or materials are described below. In case of any conflict, including definitions, the patent specification shall prevail. In addition, the materials, methods and examples are illustrative and not necessarily intended to be limiting.

[0066] As will be understood by those skilled in the art, aspects of the present disclosure may be embodied as systems, methods, or computer program products. Accordingly, aspects of the present disclosure may take the form of entirely hardware embodiments, entirely software embodiments (including firmware, resident software, microcode, etc.), or embodiments combining software and hardware embodiments (for example, a method may be implemented using a "computer circuit"), all of which may generally be referred to herein as “circuits,” “modules,” or “systems.” Furthermore, some embodiments of the present disclosure may take the form of computer program products embodied in one or more computer-readable media having computer-readable program code embodied thereon. Implementations of some embodiments of the present disclosure methods and / or systems may include performing and / or completing selected tasks manually, automatically, or in combination thereof. Furthermore, according to the actual instrumentation and equipment of some embodiments of the present disclosure methods and / or systems, some selected tasks may be implemented, for example, using an operating system, by hardware, by software, by firmware, and / or in combination thereof.

[0067] For example, hardware for performing selected tasks according to some embodiments of the present disclosure may be implemented as a chip or circuit. As software, selected tasks according to some embodiments of the present disclosure may be implemented as a set of software instructions executed by a computer using any preferred operating system. In some embodiments of the present disclosure, one or more tasks performed by a method and / or system are performed by a data processor (hereinafter also referred to as a “digital processor” with reference to a data processor that operates using a group of digital bits), such as a computing platform for executing a set of instructions. The instruction execution elements of the processor may comprise, for example, one or more microprocessor chips, ASICs, and / or FPGAs. Optionally, the data processor includes volatile memory for storing instructions and / or data, and / or non-volatile storage devices for storing instructions and / or data, such as magnetic hard disks and / or removable media. Optionally, network connectivity is also provided. A display and / or user input devices such as a keyboard or mouse are also provided optionally. Any of these implementations are referred to herein more generally as instances of computer circuits.

[0068] Any combination of one or more computer-readable media may be used for some embodiments of this disclosure. A computer-readable media may be a computer-readable signal medium or a computer-readable storage medium. A computer-readable storage medium may be, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any preferred combination thereof. More specific examples (a non-exhaustive list) of computer-readable storage media include electrical connections with one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any preferred combination thereof. In the context of this specification, a computer-readable storage medium may be any tangible medium that contains or can store programs for use by, or in connection with, an instruction execution system, apparatus, or device. Computer-readable storage media may also contain or store information for use by such programs, for example, data configured in such a way that a computer program can access it, for example, as one or more tables, lists, arrays, data trees, and / or other data structures, as recorded by the computer-readable storage media. In this specification, computer-readable storage media that record data in a form obtainable as a group of digital bits are also referred to as digital memory. It should be understood that in some embodiments, computer-readable storage media are not inherently read-only, and / or, in the case of computer-readable storage media in a read-only state, they are optionally used as computer-readable storage media as well.

[0069] In this specification, a data processor is said to be “configured” to perform data processing operations insofar as it is coupled to a computer-readable medium in order to receive instructions and / or data therefrom, process them, and / or store the results of the processing in the same or another computer-readable medium. The processing to be performed (optionally on the data) is specified by the instructions, with the effect that the processor operates in accordance with the instructions. The operations of processing may be additionally or alternatively described by one or more other terms, e.g., comparing, estimating, determining, calculating, identifying, associating, storing, analyzing, selecting, and / or transforming. For example, in some embodiments, a digital processor receives instructions and data from digital memory, processes the data in accordance with the instructions, and / or stores the results of the processing in digital memory. In some embodiments, “providing” the results of processing include one or more of transmitting, storing, and / or presenting the results of processing. Presenting includes, optionally, showing on a display, indicating audibly, printing on a printout, or otherwise providing the results in a form accessible to human sensory abilities.

[0070] A computer-readable signal medium may include, for example, a propagating data signal having computer-readable program code embodied therein, either in the baseband or as part of a carrier wave. Such a propagating signal may take any of various forms, including but not limited to electromagnetic, optical, or any preferred combination thereof. A computer-readable signal medium may be any computer-readable medium, rather than a computer-readable storage medium, that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device.

[0071] Program code and / or data used thereby, as embodied on a computer-readable medium, may be transmitted using any suitable medium, including but not limited to wireless, wired, fiber optic cable, RF, or any preferred combination thereof.

[0072] Computer program code for performing operations for some embodiments of this disclosure may be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java, Smalltalk, and C++, and conventional procedural programming languages ​​such as the C programming language or similar programming languages. Additionally or alternatively, sequences of logical operations (optionally, logical operations corresponding to computer instructions) may be embedded in the design of the ASIC and / or the configuration of the FPGA device. The program code may be executed entirely on the user's computer, partially on the user's computer (e.g., as a standalone software package), partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the latter scenario, the remote computer may be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or the connection may be made to an external computer (e.g., via the Internet using an Internet service provider).

[0073] Some embodiments of the present disclosure may be described below with reference to flowchart examples and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the present disclosure. It will be understood that each block in the flowchart examples and / or block diagrams, and combinations of blocks in the flowchart examples and / or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to the processor of a general-purpose computer, a dedicated computer, or another programmable data processing device to generate a machine such that instructions executed via the processor of the computer or other programmable data processing device create means for implementing the functions / operations specified in the blocks (single) or blocks (plural) of the flowchart and / or block diagram.

[0074] These computer program instructions may also be stored in computer-readable media that can instruct a computer, other programmable data processing device, or other device to function in a particular way, such as generating a product containing instructions that implement the functions / operations specified in a block(s) or block(s) of a flowchart and / or block diagram.

[0075] Computer program instructions can also be loaded into a computer, another programmable data processing device, or other device to cause a series of operational steps to be executed on the computer, another programmable device, or other device, thereby generating a computer-implemented process such that the instructions executed on the computer or other programmable device provide a process for implementing the functions / operations specified in the blocks(s) or blocks(plural) of a flowchart and / or block diagram.

[0076] Some of the methods described herein may, in general, be designed for use by computer only and may not be feasible or practical to be performed purely manually by a human expert. A human expert who wishes to perform a similar task, such as inspecting an object, manually may be expected to use a completely different method, for example, one that leverages expertise and / or the pattern recognition capabilities of the human brain, which would be far more efficient than manually going through the steps of the methods described herein. [Brief explanation of the drawing]

[0077] Some embodiments of the present disclosure are described herein only as examples, with reference to the accompanying drawings. It is emphasized hereby that, with specific reference to the drawings, the details shown are illustrative and intended for illustrative purposes of the embodiments of the present disclosure. In this regard, the descriptions taken together with the drawings will make it clear to those skilled in the art how embodiments of the present disclosure may be carried out.

[0078] Brief explanation of the drawing [Figure 1] A schematic illustration of a block diagram of an exemplary system 100 configured for the controlled dissolution of a solid into a fluid, according to several embodiments of the subject matter of this disclosure. [Figure 2A] Examples of various methods for controlling the dissolution of solids in liquids, based on several embodiments of the subject matter of this disclosure, are illustrated. [Figure 2B] Some embodiments of the subject matter of this disclosure illustrate other examples of various methods for controlling the dissolution of solids in liquids. [Figure 2C] Some embodiments of the subject matter of this disclosure illustrate yet another example of various methods for controlling the dissolution of a solid into a liquid. [Figure 2D] Some embodiments of the subject matter of this disclosure illustrate yet another example of various methods for controlling the dissolution of a solid into a liquid. [Figure 2E] Some embodiments of the subject matter of this disclosure illustrate yet another example of various methods for controlling the dissolution of a solid into a liquid. [Figure 2F] Some embodiments of the subject matter of this disclosure illustrate yet another example of various methods for controlling the dissolution of a solid into a liquid. [Figure 3] This disclosure illustrates a flowchart of an exemplary general method for monitoring and controlling the process of dissolving a solid into a fluid, and optionally detecting and reporting defects, as part of the pharmaceutical preparation process in a robotic pharmaceutical preparation system, according to several embodiments of the subject matter of this disclosure. [Figure 4A] These are photographic images (captured from below the vial) of vials in which solid deposits are present, according to some embodiments of the subject matter of this disclosure. [Figure 4B] These are photographic images of vials containing heterogeneous particles, according to some embodiments of the present disclosure. [Figure 5A] These are photographic images of the same vial having solid deposits according to some embodiments of the subject matter of this disclosure. [Figure 5B] These are photographic images of the same vial having solid deposits according to some embodiments of the subject matter of this disclosure. [Figure 5C] These are difference images obtained by subtracting (by absolute value) the images in Figures 5A to 5B from each other, according to some embodiments of the subject matter of this disclosure. [Figure 6A] These are photographic images of vials containing heterogeneous particles, according to some embodiments of the present disclosure. [Figure 6B] These are photographic images of vials containing heterogeneous particles, according to some embodiments of the present disclosure. [Figure 6C] These are absolute difference images constructed from the images in Figures 6A-6B according to some embodiments of this disclosure. [Figure 7] This flowchart schematically illustrates an image-based inspection method for determining the volume of fluid contained in a vial, according to some embodiments of the subject matter of this disclosure. [Figure 8] This flowchart schematically illustrates a method for image-based inspection of a vial to determine the presence of fluid, according to some embodiments of the subject matter of this disclosure. [Figure 9A]The images reproduce photographs of fluid-containing vials held by gripping portions having an inclination angle of approximately 90°, according to some embodiments of the subject matter of this disclosure. [Figure 9B] The images reproduce photographs of solid-containing vials held by gripping portions having an inclination angle of approximately 90°, according to some embodiments of the subject matter of this disclosure. [Figure 9C] The images reproduce photographs of fluid-containing vials held by gripping portions having an inclination angle of approximately 90°, according to some embodiments of the subject matter of this disclosure. [Figure 10A] A schematic side cross-sectional view of a fluid-containing vial 115 having an oblique inclination angle α, according to some embodiments of the subject matter of this disclosure, is shown. [Figure 10B] A schematic bottom view of a fluid-containing vial 115 having an oblique inclination angle α, according to some embodiments of the subject matter of this disclosure, is shown. [Figure 11] A schematic cross-sectional side view of a fluid-containing vial having a varying inclination angle α, according to some embodiments of the subject matter of this disclosure, is shown. [Figure 12A] A schematic cross-sectional side view of a labeled fluid-containing vial 115 according to several embodiments of the subject matter of this disclosure is shown. [Figure 12B] A schematic side view of a labeled fluid-containing vial 115 according to several embodiments of the subject matter of this disclosure is shown. [Figure 12C] A schematic cross-sectional side view of a fluid-containing vial having a 90° inclination angle α, according to some embodiments of the subject matter of this disclosure, is shown. [Figure 13] This is a schematic diagram of vial geometric shape parameters according to some embodiments of the subject matter of this disclosure. [Modes for carrying out the invention]

[0079] In some embodiments, the present invention relates to the field of devices for the robotic preparation of pharmaceuticals, and more specifically, to the mixing of substances by such devices, though not exclusively.

[0080] [overview] <Monitoring and control of pharmaceutical substance mixtures> Some embodiments of the subject matter of this disclosure relate to the automated monitoring and control of the mixing of pharmaceutical substances. Specifically, the dissolution of pharmaceutical substances into solutes is described. Monitoring and control of mixing into the form of suspensions (e.g., emulsifications) is not excluded and may be modified as needed and / or in relation to specific embodiments (e.g., a standard of uniform turbidity and / or opacity may be required instead of a standard of transparency). In some embodiments, monitoring and control are carried out by a robotic pharmaceutical preparation system that operates to create a pharmaceutical preparation by measured transfer of fluids between multiple containers.

[0081] In some embodiments, for the initial or intermediate state of a container used in automated pharmaceutical preparation, the container contains a solute that is not yet dissolved and its intended solvent. For example, the solvent may be added to the solute (or the solute to the solvent) at the latest, and / or a fraction of the solute may be precipitated from the solvent (e.g., precipitated during a period of refrigeration). The solute may be in either liquid or solid form.

[0082] The time and amount of action required to dissolve a solute are potentially variable, depending on, for example, the chemical identity of the solute and / or solvent, the presence of other solutes in the solvent, the initial size of the solute particles, and / or the temperature of the solute / solvent mixture, and / or other parameters. Furthermore, different mixing behaviors potentially contribute to different mixing rates, depending on the nature of the contents, such as whether the solids are solidified or readily suspended.

[0083] In some embodiments, the dissolution method first involves monitoring the dissolution in one or more vials with several pauses in stirring to enable imaging to measure the state of solute dissolution in the solvent. Once a sufficient total period for dissolution has been determined, the method continues mixing one or more further vials, omitting one or more of the pauses. In some embodiments, the first pause in mixing one or more further vials occurs after the total period expected to result in sufficient dissolution of the solute in the solvent.

[0084] In some embodiments, there is concern about detecting and responding to exceptional circumstances (e.g., mitigating these circumstances and / or issuing warnings). Examples of exceptional circumstances include fluid loss (e.g., due to insufficient sealing and / or container damage), failure of solid dissolution as expected (e.g., to expected integrity and / or within expected time), and / or residual particles that do not meet the expected visual characteristics of the solid being dissolved (e.g., solid contaminants, e.g., beads, glass fragments, filter debris, metallic particles, or other types of heterogeneous particles).

[0085] Indicators and measurements of the mixed state of pharmaceutical substances In some embodiments, a key indicator of the progress and / or completion of mixing is the reduction and / or substantial disappearance of solid-phase material from the mixing vial as the solute dissolves in its solvent. The reduction / disappearance of the solute is optionally monitored optically, for example, by imaging the vial and / or by measuring the light interacting with the vial and its contents. The measurements (e.g., images and / or other measurements) optionally characterize the vial in motion and / or while stationary. Measurements of a stationary vial optionally include measuring the light interacting with the vial and its solute and / or solvent contents, whether the solute is completely dissolved, mechanically mixed with the solute but not yet completely dissolved (e.g., suspended), or completely or partially solidified and / or settled from the solute.

[0086] Optionally (whether additional or alternative), non-optical measurements of the mixed state are performed. For example, the measurement may use ultrasound as the source of radiant energy, and the measurement may take the form of an image or another form of evaluating the interaction of sound energy with the contents of the vial. In some embodiments, the mixed state is evaluated using another method, for example, by measuring the temperature change resulting from dissolution.

[0087] Optionally, the evaluation of the mixing state may include determining the turbidity of the solution. Depending on the measurement method, there may be a period during which turbidity reduction is not measurable. Optionally, there may be a period during which the measured values ​​show a change in turbidity (e.g., turbidity reduction).

[0088] For solutes expected to dissolve completely in the solute, the assessment of the mixing state optionally includes determining whether the contents to be contained have become completely clear. In some embodiments, as mixing progresses toward completion, there may be shifts (e.g., changes in color) in the absorption, transmission, and / or reflectance spectra of the vial contents. Optical measurements optionally measure the spectral shift. Optionally, the amount of spectral shift is quantified as part of assessing the mixing state of the vial contents.

[0089] Optionally, the evaluation of the mixing state includes determining whether there is a residual portion of undissolved solute based on the material that gathers during sedimentation after stirring (e.g., after a resting period that allows such sedimentation, e.g., 1-10 seconds, 1-30 seconds, 1-60 seconds, or another period) and / or remains unaffected by stirring (e.g., adhering to the vial surface). In some embodiments, unmixed material may also gather during stirring, for example, due to density separation in the vortex of the vial contents. Optionally, monitoring the mixing state includes obtaining measurements of the material in the area where such vortices are expected to gather it.

[0090] In some embodiments, there may be a mixing stage in which the substantially clear fluid contents nevertheless include the presence of a small number of particles that are either still undissolved (e.g., large crystals of solute) or actually insoluble (e.g., impurities or other inclusions). In some embodiments, measurements are performed to identify such particles and evaluate them according to their importance to the state of contents mixing. For example, a threshold for particle number and / or size may exist, and if it is below this threshold, the vial contents may be considered mixed even if the particle number does not reach zero.

[0091] In some embodiments, images of vials that are themselves used in pharmaceutical preparation are used to help set system requirements. In some embodiments, the system operator approves the results of system operations to mix pharmaceutical preparations, for example, approving the final result, and images taken during mixing are optionally treated as representing valid results of intermediate pharmaceutical preparation operations. Additionally or alternatively, the system operator approves images or other measurements that directly show the results of intermediate operations. For example, the system operator examines images of the boundary layer in a fluid vial and approves them as a standard for comparison. Additionally or alternatively, the system operator certifies that the starting conditions are valid, and images of the vial are accepted, based on the certification, as a correlation indicator of the valid amount of fluid in the vial. The system operator may be, for example, a person who gives direct commands to the system or a person who acts as an auxiliary monitor of system operation. In some embodiments, another automated system is provided instead of the system operator, for example, an automated system specifically configured to verify pharmaceutical preparations according to preferred criteria of measured volume, composition, and / or other inputs.

[0092] In some embodiments, operations such as stirring of subsequent vials are adjusted according to expectations set during the stirring of one or more initial vials. In particular, the stirring of one or more preceding vials may be monitored more closely (e.g., divided into more sub-periods while stirring is paused to allow imaging), while the stirring of subsequent vials may be performed more continuously, potentially relatively reducing their processing time.

[0093] Factors that potentially interfere with measurements Furthermore, in some embodiments, a situation may potentially occur where a portion of the solvent in the vial is clearly visible, while one or more significant solute particles remain elsewhere in the vial. In such cases, a sampling window containing only a portion of the vial contents may not be sufficient to determine the overall state of the vial contents to be mixed. Optionally, this scenario can be mitigated and / or avoided by performing the measurement using an image that includes substantially the entire contents of the vial.

[0094] One or more significant particles may contain solute that is "adhered" (many smaller particles adhere to it, dissolve in the solvent, sinter, or otherwise bond together). Adhered solute may adhere to the surface of the vial so as not to move relative to the vial during stirring, and / or may move freely in the solvent. In some embodiments, adhesion is assessed to confirm that they cover the entire volume range of the vial by examining the shape of the transparent portion of the vial. In some embodiments, the presence of adhered particles and / or other residual particles is assessed by looking for areas of contrasting measured light levels and / or areas that receive measured light changes indicating one or more particles moving through them.

[0095] Potentially, the vial contents may contain existing and / or gaseous contaminants (bubbles and / or foam) generated by mixing and stirring. In some embodiments, the potential confounding effect of such bubbles and / or foam on measurements is mitigated, for example, by observing the bubble behavior (e.g., rising instead of settling over a period of time, the position of the bubbles in the interfacial layer), and / or by predicting bubble formation and / or foaming, for example, based on calibrated predictions for a particular solute-solvent system and / or mixing conditions.

[0096] It should be noted that different methods of measuring mixing progress are subject to different potential advantages and disadvantages. For example, measurements performed during ongoing fluid agitation have potential advantages in that they do not interrupt the mixing process being performed and potentially allow mixing to continue to completion more quickly. However, optionally, the mixing movement is temporarily slowed down and / or adjusted to present a preferred configuration of the vial to a camera or other imaging and / or measuring device. In some embodiments, the evaluation of mixing progress is performed while the fluid contents and / or solids in the vial are moving, for example, while vortices remain in the contents and / or while the contents are splashing within the vial.

[0097] There are potential artifacts that can occur in images of such moving systems; for example, motion blur can obscure particles, while bubbles can be particularly difficult to distinguish from particles, and / or may be more common overall. In some embodiments, stroboscopic illumination may be used, for example, to partially mitigate motion blur, while retaining the potential advantage of allowing the mixing motion to continue. Conversely, measurements performed in the solution after stirring has stopped are potentially preferable to collect information about the solute particles remaining as concentrates by allowing them to settle and / or to slow their movement so that they can be better tracked and evaluated.

[0098] In some embodiments, the measurement regime is selected so that a measurement method that promotes uninterrupted mixing (but is potentially susceptible to confounding effects) is used during the initial part of the mixing process. A determination to estimate the progress of mixing is then, at an optional choice, used to select when a different (e.g., confirming and / or potentially more reliable) measurement method should be used.

[0099] Dynamic system response to mixed progression The operation of the mixing subsystem itself and / or the entire robotic pharmaceutical preparation system is optionally adjusted in response to a measurement indicating any of the states.

[0100] In some embodiments, the estimated time to completion of mixing is calculated based on measurements of mixing progress during the initial stages of mixing. This estimated time to completion is optionally used as a basis for selecting further actions, including those of the vial and / or the mixing subsystem itself, and / or other elements of the overall function of the pharmaceutical preparation system.

[0101] For example, persistent deposits can be optionally identified early in the mixing process, allowing the vial to be replaced relatively efficiently with a new one, minimizing loss time (optionally, the vial is returned to use after a period of “pre-soaking” or another mitigation action). In some embodiments, the estimated time to complete mixing is used to estimate the value (in terms of time saved) particularly for periods of vigorous shaking, which nevertheless may lead to foaming and / or foam formation, generating an additional period to wait for sedimentation. In some embodiments, the foam formation rate and / or foam dissipation rate are tracked along with the material mixing to reach a properly energy-mixed regime without more post-mixing sedimentation time than saved by increasing the rate of mixing itself. In some embodiments, a delay period for transport or other preparation after the completion of active mixing and stirring is relied upon as a period to complete mixing, e.g., a period to allow the final remaining crystals of the solute to dissolve. In some embodiments, a measurement of the mixing rate is used to calculate the amount of final mixing that can be expected to occur during the expected period of such delay.

[0102] In another embodiment, the coordination with activities further aligned with the pharmaceutical preparation process is optionally adjusted to take into account the expected time for mixing to be complete. For example, the time for removing the reagent from refrigeration and / or radioactive shielding is optionally adjusted so that the reagent reaches a state and / or position to interact with the mixed contents of the vial as soon as it is ready.

[0103] In some embodiments, the progress of mixing is tracked over time and is related to the manner and / or events that may have occurred during the previous handling of the vial. For example, the positioning and movement parameters associated with the early injection of the solvent into the vial of the dry solute are optionally modified according to the results indicating which injection method is most effective in resulting in rapid mixing. Embodiments of this include adjusting the relative depth of injection cannula penetration into the vial, and / or the relative reorientation of the vial and cannula to direct the fluid jet towards the walls and / or corners of the vial. Optionally, at least partially arbitrary variations of these parameters are performed as a matter of course during device operation, and successful motion deformations are facilitated for greater use (and potentially additional variations). Optionally, a period of initial experimentation is performed, for example, using different batches of vials, according to an injection pattern determined to be potentially preferred.

[0104] non-solution mixture In some embodiments, mixing is used to form and / or homogenize a mixture (e.g., an emulsification and / or suspension) without necessarily resulting in an optically clear solution. In some embodiments, an optically clear solution is the intended outcome, but potentially there is a step in the operation where the solute and solvent are in a suspension that is completely mixed, which may depend on being sufficiently homogenized to terminate active stirring (e.g., so that dissolution is completed on its own, given the available time). Optionally, this has the potential advantage of reducing processing time and enabling more efficient use of pharmaceutical preparation equipment.

[0105] In some embodiments, measuring the state of mixing determines whether the insoluble (e.g., suspended) material is sufficiently uniform in its distribution so that mixing can be considered complete. In some embodiments, this involves imaging the texture of a portion of the suspended material that can be visualized on the surface of a turbid mixture. For example, the texture of the visible surface of the mixture can optionally be determined to be uniformly composed of particles below a certain size over a period of time (and optionally motion and / or stirring) long enough so that what is visualized on the surface is considered to adequately represent the entire volume.

[0106] <Monitoring the fluid contents of vials> Some embodiments of the subject matter of this disclosure relate to the automatic verification of the volume of fluid contents in a vial during the automatic mixing of pharmaceutical preparations.

[0107] In the case of vials provided and / or operated as containers for pharmaceutical substances, requirements for verifying fluid volume may arise as part of the operation in which the contained pharmaceutical substance is used. For example, the contained pharmaceutical substance may be dispensed in a solid form intended to dissolve in a certain amount of injected liquid (e.g., saline solution) before removal from the vial (e.g., removal at a known and expected dissolution concentration). In automated systems, there may be an assessed risk requiring mitigation that the wrong amount of liquid may be injected into the vial for this purpose. Additionally or alternatively, there may be an assessed risk requiring mitigation that a solids vial may be inadvertently replaced with a dissolved contents vial.

[0108] As a mitigation measure and / or as part of sensing for control, non-visual means (e.g., scales) are a typical solution for use in automatically verifying the volume of fluid contents. This offers potential advantages for highly sensitive and quantitative verification of material movement within a system. However, related issues include potential calibration problems, the sensitivity of the sensors involved, and the system time used to position the material and / or allow scale readings to settle.

[0109] Some embodiments of the subject matter of this disclosure use optically identifiable (visual) indicators of the volume of liquid contents in a clear-walled container. An important type of such indicator involves contrasting boundary regions at the interface between the liquid phase of the vial contents and the (typical) gaseous phase (e.g., air or another gas) of the vial contents. In some embodiments (additionally or alternatively, to the gaseous phase), there are liquid / liquid boundaries between unmixed liquids, e.g., boundaries between a denser liquid, such as an aqueous solution, and a less dense liquid, such as oil or other non-aqueous liquids. Boundary regions are also referred to herein as “upper” boundaries, insofar as they are boundary regions above the bottom of the vial and boundary regions above the material phases of the vial contents. It is not necessarily the “topmost” boundary, and for example, there may be three material phases in a vial, with boundary layers between each pair of consecutive material phases.

[0110] In images of vials acquired using an optical camera, boundary regions may be visible at locations extending across the inner surface of the vial's transparent wall. While visible, these locations may be somewhat imprecisely localized. For example, their appearance may be distorted by the optical properties of the container wall and / or influenced by the 3D shape of the fluid meniscus formed by the liquid on its surface. The meniscus shape is curved according to the balance between the fluid surface tension and the attractive force of the liquid to the container wall. These forces can vary depending on any particular characteristic; for example, they can sometimes even be influenced by a relatively small amount of solute in the liquid.

[0111] The visibility of the boundary region (i.e., its effect on pixel intensity in the vial image) is a result of differences in one or more optical properties of the material phases constituting the vial's contents. Examples include differences in refractive index (particularly at one or more wavelengths, specifically at the boundary between optically transparent materials), light absorption, scattering, and / or reflection. Differences in refractive index between the liquid contents and the material of the container wall itself also affect the actual shape and / or the imaged shape of the boundary region. The effect of refraction also potentially introduces uncertainty into the container's structure, as can be inferred from the image alone. For example, the wall thickness of the vial can be optically distorted, and the amount of distortion depends jointly on the vial's geometry and the refractive index of its material.

[0112] Furthermore, the usefulness of visual assessment (e.g., verification) of fluid volume using boundary regions is potentially hindered by the presence of labels that obscure a large portion of the vial wall. If there are gaps in the labels, they can be small and / or oriented inconveniently and / or unpredictably. This, along with the confounding effects mentioned above, makes the visual assessment of the vial's liquid contents potentially unreliable.

[0113] Nevertheless, the inventors of this disclosure have determined that, under certain conditions of potential importance in the field of automated pharmaceutical preparation, image-based evaluation of the fluid volume in a vial (including labeled vials) can be performed in a manner that potentially reduces or eliminates the requirement for quantification and / or otherwise secondary verification of the fluid volume in the vial.

[0114] In short, image-based evaluation involves, in some embodiments, imaging of the vial while the boundary region is oriented obliquely and / or perpendicularly to the bottom of the vial. This is also referred herein to as a change in the inclination angle of the vial relative to the boundary region. Typically, the vial itself is inclined away from its vertical (upright) orientation (e.g., the boundary region remains horizontal). However, it is not excluded that the vial may undergo a movement (e.g., rotational movement) that exerts a force causing the boundary region itself to be oriented obliquely to the direction of gravity, whether or not the vial itself is inclined away from its upright orientation. The inclination angle is selected, for example, as described herein, to position at least a portion of the boundary layer outside the area obscured by labeling, and / or optionally, to satisfy other circumstances of the imaging, calibration, and / or processing algorithms. In some embodiments, the inclination angle is selected to position the boundary layer where it is visible (and / or expected to be visible) through the bottom of the vial.

[0115] To the extent that a boundary region is detected, even slightly, it is an indicator that the vial contains fluid. This allows, for example, verification that a vial of an originally dry substance placed in a pharmaceutical preparation system has gone through a step prior to receiving fluid. The boundary layer can be identified, for example, by its characteristic shape, by its characteristic intensity profile, and / or by its characteristic behavior in response to the movement of the vial, for example, when assuming different inclination angles of the vial, and / or when the vial is subjected to acceleration. These are examples of target criteria from which the images can be compared.

[0116] In some embodiments, the position of the boundary region, along with the inclination angle of the vial (and optionally, with preferred assumptions about the internal geometry of the vial), can be used to estimate the volume of the fluid contents of the vial. This estimation is optionally performed at a selectable level of expected accuracy.

[0117] For example, even a roughly estimated volume (e.g., within ±20% of the exact figure) may often be sufficient for verification purposes. The target volume (optionally expressed as a range and / or tolerance specification) is also an embodiment of a target criterion on which measurements derived from the image can be compared, and for example, the location of the boundary layer in the image may optionally be involved in the comparison, according to its transformation to the relevant volume estimate using a suitable calculation.

[0118] The original pharmaceutically active substance in the vial may be a separately validated (e.g., well validated on its own) amount of solid, and the role of the added fluid is primarily to dissolve it. Slight deviations in the amount of fluid can be ignored (e.g., when the entire contents of the vial are used at once in a much larger volume anyway), adjusted during the remaining steps in the preparation of the drug, and / or adjusted at the time of drug administration.

[0119] In some embodiments, the calibration state of one or more calibration vials and / or vials known and / or confirmed to contain a particular (e.g., targeted) fluid volume and / or composition is used as a reference. This allows the fluid volume in other imaged vials and / or vial states to be evaluated based solely on boundary region position and vial angle.

[0120] The calibration state can be expressed as, optionally, the location of the boundary layer, the result of comparing images representing the boundary layer (e.g., by subtracting, correlating, or otherwise comparing two images to establish a metric for similarity or difference), or as another state. In some embodiments, the comparison is performed using machine learning results, for example, machine learning results trained on evaluating boundary layer locations. Each of these is also an embodiment of a target criterion on which the boundary layer location can be compared.

[0121] In some embodiments, images of vials that are themselves used in pharmaceutical preparation are used to help set system requirements for risk scenarios where there is concern to mitigate rare or intermittent deviations from typical fluid volumes. In some embodiments, the system operator approves the results of system operations to mix pharmaceutical preparations, for example, approving the final result, and images taken during mixing are optionally treated as representing valid results of intermediate pharmaceutical preparation operations. Additionally or alternatively, the system operator approves images or other measurements that directly show the results of intermediate operations. For example, the system operator examines images of the boundary layer in the fluid vial and approves them as a standard for comparison. Additionally or alternatively, the system operator certifies that the starting conditions are valid, and images of the vial are accepted as a correlation indicator of the valid amount of fluid in the vial based on the certification. The system operator may be, for example, a person who gives direct commands to the system or a person who acts as an auxiliary monitor of system operation. In some embodiments, another automated system is provided in place of the system operator, for example, an automated system specifically configured to verify pharmaceutical preparations according to preferred criteria for measured volume, composition, and / or other inputs.

[0122] Additionally or alternatively, the accuracy of volume estimation (optionally, with or without the use of calibration vials) can be improved by optionally taking into account more potential confounding factors, such as parameters of the vial internal geometry and / or fluid meniscus geometry. This has the potential advantage of allowing flexibility between quantitative and qualitative verification levels (optionally, with variable accuracy), as it allows for adjusting the time and / or effort applied to the measurements to meet specific requirements for verification and / or risk mitigation.

[0123] If further characterization of the vial's “upright” orientation is required to clear up any doubts, this orientation can be identified by features such as being oriented to allow the vial to rest stably on a substantially horizontal bottom or part thereof (when unsupported), e.g., a flat surface, a full or partial ring, and / or a small protrusion such as a bump or knob. Additionally or alternatively, if the vial is provided with a septum, the septum is at the top and typically oriented horizontally. Typically, but not always, the vial in the upright position includes a lower contents-containing volume that is cylindrical or prismatic (e.g., with a constant cross-section, ignoring slight volumetric deviations such as a bottom recess). The cross-section is typically circular, but other cross-sectional shapes, e.g., oval, elliptical, triangular, quadrilateral, or other shapes are not excluded. In such cases, at least when the vial has a flat bottom and a horizontally oriented bottom, the longitudinal axis of the cylinder or prismatic extends along the vertical orientation when the vial is upright. Optionally, the orientation of vial labeling, such as text, provides an indicator of vial orientation.

[0124] In some embodiments, one or more automated actions performed using a vial are carried out based on an image-based evaluation of the vial's contents, for example, based on the presence and / or amount of fluid (e.g., liquid fluid). In some embodiments, the automated action is determined as either using one or more of the vial contents, or refusing to use the vial contents. In some preferred embodiments, use / refusal relates to the use of contents in an automated preparation of a pharmaceutical preparation. For example, there may be uncertainty as to whether to continue using the vial while suspending verification of the amount of fluid contents in the vial.

[0125] In some embodiments, the determined use of a vial includes use in conjunction with additional adjustments to the vial's contents. For example, use may optionally include adding more fluid to compensate for deficiencies. Alternatively, (for example, if a component is found to be overdiluted in too large a volume), the fluid is combined with the contents of another vial, the added volume of fluid being intentionally or accidentally reduced, so that the combined concentration is thereby corrected to a target level. In some embodiments, the determined use of a vial includes an action to reset the vial orientation to a specific position in preparation for further activity. For example, the vial is returned to an upright position to allow fluid to be dispensed from it, or is placed in a fully inverted position for the same purpose. In some embodiments, the vial is returned to an upright position, moved to be placed in a rejection area, or returned to its original position (as rejection) without further use.

[0126] <Terminology> The subject matter of this disclosure generally relates to robotic pharmaceutical preparation systems, and more specifically, to fluid transfer stations within robotic pharmaceutical preparation systems. For brevity and clarity, the embodiments described herein (referencing the drawings and other documents) are understood to refer to subsets of components of a pharmaceutical preparation system, e.g., specific aspects of the overall fluid transfer device assembly. Furthermore, embodiments directly similar to those described herein should be understood to be included within the scope of this disclosure. This includes, for example, specific implementations and / or combinations of elements and / or subsystems that differ in detail from those expressly described but are similar in function and / or functional role.

[0127] Pharmaceutical preparation system Embodiments of robotic pharmaceutical preparation systems and their fluid transfer stations described herein are configured to perform operations related to the transfer of pharmaceuticals between different fluid transfer devices.

[0128] A robotic pharmaceutical preparation system (which may be alternatively referred to as a "robotic system") according to the subject matter of this disclosure includes elements and / or subsystems such as a robotic station, a robotic arm, motors, control units, and / or other mechanisms that operate to perform, control, and / or verify fluid transfers. These elements are optionally configured to constitute and / or be designed and / or described to constitute units and / or subsystems that operate to perform activities related to the preparation of a pharmaceutical product designated for administration to a patient. For example, a robotic system may include one or more automated or partially automated subsystems, each comprising at least one manipulator at least partially controlled by a controller unit (which may be equivalently referred to as a controller or control unit). The controller units themselves may be arranged to communicate with one another, for example, hierarchically and / or within a network, to coordinate the overall functionality of the pharmaceutical preparation system.

[0129] The pharmaceutical preparation systems described herein perform fluid transfer between a designated fluid transfer device, comprising a container and a fluid transfer unit, the latter often acting as an intermediate element (typically, but not necessarily, an “active” element, e.g., an element that generates pressure resulting in fluid movement), while the former is considered a fluid source or fluid receiver element (typically, not necessarily an “passive” element). Fluid transfer may be assisted by fluid transfer connectors. However, the intermediate fluid transfer unit may, nevertheless, optionally act as an initial fluid source (e.g., in the form of a pre-filled syringe provided at the start of pharmaceutical preparation) and / or as a final container for the fluid (e.g., in the form of a filled unit that passes forward to another process, such as delivery to a patient, storage, or another purpose). Nor is it ruled out that the container may play an intermediate role as both a fluid source and a fluid receiver.

[0130] Embodiments of a transfer device may comprise, for example, one or more conduits, pumps, syringes, vials, intravenous bags, adapters, and / or needles. Optionally, these elements are consumables and / or accessories of a pharmaceutical preparation system. Optionally, such elements are nevertheless considered components of a pharmaceutical preparation system. The term vial is used herein, in particular, as a container into which contents beginning in a solid and / or relatively concentrated form are first dissolved and / or diluted. In other embodiments, a vial contains a certain amount of fluid, whether it was originally a container for a solid and / or concentrate. In other embodiments, a vial may still retain the substance in its solid and / or concentrated form. However, the term vial is not limited to this list of exemplary cases.

[0131] fluid As used herein, “fluid” typically includes pharmaceuticals, diluents, saline solutions, water, or any other fluids used in the preparation of pharmaceuticals. While fluids may be understood more specifically to be provided as liquids, the use of gaseous fluids is not excluded, insofar as the characteristics of gaseous fluids are consistent with those described herein.

[0132] fluid transfer "Fluid transfer" is performed between the container assembly and the fluid transfer assembly through openings formed in the ports of the container assembly or the fluid transfer assembly, and / or through openings formed in the partitions of the container assembly or the fluid transfer assembly.

[0133] bulkheadIn this specification, “partition” generally refers to a membrane configured to close off access to a part of the device to which it belongs. Partitions on a container or container connector (also referred to as container partitions) can seal the container. Partitions on a fluid transfer assembly (also referred to as fluid transfer connector partitions) can prevent or resist access to and / or by fluid transfer conduits. Typically, partitions are made of an elastic, perforable material. Such materials may be polymers having elastic properties such as rubber. Vials are, for example, often supplied with a cap that has an integrated partition.

[0134] container :When performing fluid transfer, a robotic system operating in accordance with this disclosure may optionally manipulate and / or inspect various embodied containers. As described herein, “container” means, optionally, one or more of syringes, IV bags, elastomer pumps, vials, bottles, ampoules, syringes, conduits, pipes, or any container or vessel generally suitable for holding fluids or liquids. It will be further understood that a container may be any other element that functions as a component of a fluid transfer device, with or without connectors (or “adapters”) for establishing fluid communication with other fluid transfer components of the container. For example, a container may be a vial with a vial adapter, or an intravenous bag with a spike adapter. A container may be accessible via a container partition, which may be a partition in the container lid or part of a connector. In a process of fluid transfer performed using fluid pressure changes and / or differences, a container characteristically experiences fluid transfer due to pressure changes generated in and / or through the fluid transfer assembly to which the container is connected.

[0135] vialAs used herein, “vial” (for example, referring to a particular container) may include, for example, a resealable container made of glass or plastic, such as an ampoule or bottle, that contains a pharmaceutical product in liquid or powder form. Vials may be single-use or multi-use vials. Vials may be tubular or bottle-shaped, having a neck portion close to the vial opening. Vials may have a cap, for example, a cap with a septum, covering the top. Vials are typically fixed in shape, specifically fixed in a certain internal volume, although the volume can be filled to a greater or lesser extent. Vials are also, in some embodiments, preparation vessels, in which the substance they supply is dissolved, diluted, and / or reconstituted in preparation for further operations, such as transfer to a syringe. Thus, operations performed on a vial generally include either or both of injecting a fluid and / or removing a fluid. In between, there may be mixing operations in which the originally contained substance is dissolved and / or diluted with the injected fluid. Vials are often supplied for use in manual preparation options and are not necessarily standardized in size. While vials may have labels suitable for manual operation, they have potential drawbacks for automated operations, such as the disadvantage of obscuring the view of the vial's contents.

[0136] Container assemblyAs used herein, “container assembly” may include a container alone or a container with a container connector attached. The term “vial assembly” is used interchangeably, but embodiments embodying aspects of this disclosure do not necessarily include a vial in a strict sense (e.g., an ampoule may be present instead). A partition for at least partially sealing access to the vial may be located as part of the vial itself and / or as part of a container connector (equivalently referred to as “vial adapter” or “container adapter”). A container connector may include a device attachable to a vial to facilitate the transfer of the vial itself (by gripping the adapter instead of the vial) and / or to facilitate the transfer of fluid to or from the vial. A container connector may provide protected (e.g., “closed” and / or sterile) access to the contents of the vial. A container connector may be a single-use or multi-use sterile device. The vial within the container assembly may be partially obscured from view by an element attached to it, such as a manipulator that holds it for operations such as shaking or fluid exchange.

[0137] manipulatorAs used herein, “manipulator” may include a structure and / or mechanism configured to controllly interact with at least one container (e.g., a container loaded into a system) and / or other components or structures of a pharmaceutical preparation system. A manipulator may be configured to move at least one container. A manipulator may be configured to cause or facilitate a fluid transfer process, e.g., the transfer of fluid from one container to another, including, for example, the extraction and / or insertion of fluid (e.g., injection). A manipulator may comprise a robotic arm, platform, robotic station, or a combination thereof configured to operate the container and / or fluid transfer assembly. A manipulator may include actuators, e.g., motors to facilitate its operation. Certain manipulators are also referred to herein as “agitators.” In some embodiments, an agitator comprises a manipulator provided with a specific capability for agitation (e.g., the capability for oscillating motion separate from the manipulator’s capability for selectively positioning a container to be operated to a targeted position). In some embodiments, the agitator is characterized more simply by being able to fix the container (e.g., a vial) while it is moving in a stirred manner, for example, while vibrating in a predetermined position to impart motion to the contents of the container. In some embodiments, the agitator moves to impart vortex motion to the fluid contents of the container. In some embodiments, the agitator moves to break up the surface boundary region of the fluid contents of the container, for example, to cause splashing and / or instantaneous droplet separation. In some embodiments, the agitator generates flow in the fluid contents of the container. In some embodiments, the agitator mixes two material phases of the contents of the vial, for example, suspending a solid material in a liquid material, and / or suspending two liquid materials in a common material phase, and / or imparting motion to the contents of the vial that induces dissolution.

[0138] A manipulator is not necessarily implemented as an “arm,” even when described in relation to such terminology. Fluid transfer can occur while a container is engaged (e.g., gripped) by the manipulator. In embodiments, the manipulator (e.g., “gripping section” or “plunger arm”) may include one or more actuators used to engage with a syringe and / or pull or push the plunger of the syringe. The syringe may, in turn, engage with a vial. The manipulator may optionally be configured to manipulate other types of fluid containers, such as vials, IV bags, tubes, and / or other suitable containers.

[0139] controller In this specification, the equivalent terms “controller” and “controller unit” generally refer to a circuit configured to command several aspects of the behavior of a controlled element, such as the operation of an actuator (which, in turn, may be an actuator of a manipulator), the operation of a sensor, and / or the operation of an imaging device. In some embodiments, the controller comprises a computerized circuit (also referred to herein as “processing circuit”) configured to perform operations according to a set of instructions stored in a memory readable by the controller, which may be executed, for example, by a central processing unit (CPU), one or more processors, a processor unit, and / or a microprocessor. Additionally or alternatively, in some embodiments, the controller uses a digital signal processor (DSP), a field-programmable gate array (FPGA), a dedicated application-specific integrated circuit (ASIC), or another device. Additionally or alternatively, in some embodiments, the controller or controller unit includes one or more analog (e.g., amplifier feedback-based) and / or low-level logic gate-based control circuits. In some embodiments, the control unit may include one or more mechanical controllers. The controller unit may include any means for controlling elements within the robotic pharmaceutical preparation system, and may include at least one of an analog control circuit, a synchronization unit, and a processor.

[0140] Imaging device In this specification, the term “imaging device” refers to any device that operates to produce images of several targets. “Optical” imaging can typically be understood to include imaging of light, including visible light, but this is not necessarily required. For example, infrared and / or ultraviolet wavelengths may be used in imaging, additionally or alternatively to visible light wavelengths, as needed. Embodiments of imaging devices are optical cameras, e.g., cameras equipped with one or more transparent lenses and light sensors that can be read out to produce digital images. Optionally, scanning imaging methods are used, e.g., imaging of reflectance returned to the sensor from laser illumination scanned over the target. Optionally, interferometric imaging is used, e.g., to track small deformations and / or movement. Imaging using radiant energy other than visible light, e.g., acoustic energy, electromagnetic wavelengths outside the visible spectrum, and / or particle radiation imaging (with mass) is not excluded. Optionally, contact imaging is performed, e.g., a contact probe is moved along the imaged target to verify the accuracy of its positioning and / or measure one or more contours of its shape.

[0141] In this specification, features and / or values ​​may be referred to as “expected” or “targeted.” It should be understood that these terms refer to the technically embodied representation of the respective appropriate state and / or quantity. Optionally, such representations are numerical, for example, in the case of a target stored by a digital computing circuit. Optionally, such representations are analog and / or mechanical, and are represented, for example, by a pointer, knob, weight, or other element or arrangement of elements.

[0142] Before describing in detail at least one embodiment of this disclosure, it should be understood that the application of this disclosure is not necessarily limited to the structural and arrangement details of the components and / or methods illustrated in the following description and / or drawings and / or given in the drawings of the embodiments. Features described in this disclosure, including features of the present invention, may be in other embodiments or may be implemented or performed in various ways.

[0143] [Visual inspection of solute dissolution in solvent] Referring here to Figure 1, Figure 1 schematically illustrates a block diagram of an exemplary system 100 configured for the controlled dissolution of a solid into a fluid, according to several embodiments of the subject matter of the present disclosure. In some embodiments, system 100 is a subsystem of a robotic pharmaceutical preparation system that operates to create pharmaceutical preparations by measured transfer of fluids between multiple containers.

[0144] In some embodiments, vial 115 is a container for holding a fluid-solid mixture. It is introduced for operation by system 100, for example, by robotic picking from a storage area and / or by manual placement.

[0145] In some embodiments, vial 115 initially contains a powder (e.g., lyophilized and / or pulverized) and / or crystalline material. This can be mixed with a fluid solvent (e.g., saline or Ringer's solution), for example, the fluid solvent injected into vial 115 in the initial stages of processing by a robotic pharmaceutical preparation system.

[0146] In some embodiments, the vial manipulator / stirrer 110 comprises a mechanical component 110A that operates to grip (or otherwise hold, e.g., house) and move a vial 115. In a non-limiting embodiment, the vial manipulator / stirrer 110 may be a robotic arm having a gripping device mounted at its end that is suitable for gripping and manipulating vials.

[0147] In some embodiments, the stirring components of the vial manipulator / stirrer 110 are operable to impart looping (e.g., circular) and / or reciprocating rotational motion to the vial 115, for example, on one, two, or three axes; in clockwise or counterclockwise directions; and in movement from 0 to 360 degrees (or more in the case of repeating loops).

[0148] In a non-limiting embodiment, the vial manipulator / stirrer 110 rotates the vial 115 by alternating movements, starting with moving the vial 115 90° clockwise in the x-direction, then 180° clockwise counterclockwise in the x-direction, and finally 90° clockwise back to its original position, which can be optionally repeated for any preferred number of times.

[0149] In a further non-limiting embodiment, the vial manipulator / stirrer 110 may rotate the vial 115 360° in the z direction, for example, by rotating it to invert the vial 115, and then continuing to rotate it to restore the vial 115 to its original orientation.

[0150] In some embodiments, the stirring components of the vial manipulator / stirrer 110 can displace the operated vial 115 in the forward and / or reverse directions (i.e., reciprocating motion) (e.g., linearly) on one, two, or three axes. The distance and speed are of any choice and any preferred magnitude.

[0151] In some embodiments, the vial manipulator / stirrer 110 is operable to move the manipulated vial 115 simultaneously and / or sequentially in a sequence including any of the above-described movements.

[0152] As used herein, the term “shaking” refers to any type of movement applied to vial 115 that may be suitable for accelerating the rate at which a solid or fluid solute dissolves in a fluid solvent. Such acceleration of the dissolution rate may be at least in part due to the movement of the solvent through a material that washes away the solute as it dissolves, thereby maintaining a relatively steep concentration gradient in which the remaining material continues to diffuse. Optionally, the acceleration of the dissolution rate may be at least in part due to the action of mechanical forces (e.g., shear forces and / or impact forces) on the solute, which fragments the solute and / or increases its effective surface area. The latter modes of acceleration tend to yield potentially variable effectiveness, depending, for example, how the fluid is moved within its container and / or how the material being dissolved responds to the mechanical forces.

[0153] Optionally, the illumination 125 is positioned to illuminate the contents 160 of the vial 115. For example, the illumination 125 optionally comprises ring illumination surrounding the vial 115. Optionally, the illumination 125 is supplied from another light source, such as a panel or spot source. In any configuration, the illumination 125 provides illumination suitable for enabling an imaging device 120 (e.g., an optical camera) to capture an image of the fluid 160A and / or solid 160B contained in the vial 115.

[0154] The imaging device 120 can be any suitable type of digital camera or other imaging device. The imaging device 120 can be positioned, for example, below the vial 115 to view the contents of the vial from its bottom. This has the potential advantage of avoiding blockage by labels or other materials on the walls of the vial 115. In some embodiments, the imaging device 120 is positioned in another suitable location.

[0155] The processing circuit 130 can be operably connected to the imaging device 120 and the vial manipulator / stirrer 110. In some embodiments, the processing circuit 130 can, for example, instruct the imaging device 120 to capture an image of the vial 115 and then receive the captured image.

[0156] In some embodiments, the processing circuit 130 can instruct the vial manipulator / stirrer 110 to start or stop shaking, or to change the parameters of shaking.

[0157] The processing circuit 130 may include a processor 150 and a memory 155. In some embodiments, instructions executed by the processor 150 to perform one or more of the methods of this disclosure are provided on a non-temporary digital storage medium. In particular, it should be understood that any of the computer execution operations described in relation to Figures 2A-3 and / or Figures 7-8 are optionally associated with corresponding instructions executed by the processor 150 provided on a non-temporary digital storage medium.

[0158] The processor 150 can be a suitable hardware-based electronic device with data processing capabilities, such as a general-purpose processor, a digital signal processor (DSP), a dedicated application-specific integrated circuit (ASIC), or one or more cores in a multi-core processor. The processor 150 can also consist of, for example, multiple processors, multiple ASICs, virtual processors, or combinations thereof.

[0159] The memory 155 can be, for example, a suitable type of volatile and / or nonvolatile storage device, and may include, for example, a single physical memory component or multiple physical memory components. The memory 155 may also include virtual memory. The memory 155 can be configured to store, for example, various data used for calculations.

[0160] The processing circuit 130 can be configured to execute several functional modules according to computer-readable instructions implemented on a non-temporary computer-readable storage medium. Such functional modules are hereafter referred to as being included in the processing circuit. These modules may include, for example, a stirring control unit 142, a global control unit 145, a fluid analysis subsystem 135, and a machine learning model 140.

[0161] The global control unit 145 can perform global control functions, such as moving the vial 115 to a different location in the pharmaceutical preparation device after the dissolution of the solid into the fluid is complete.

[0162] The stirring control unit 142 can perform control of the vial manipulator / stirrer 110.

[0163] The fluid analysis subsystem 135 can perform image processing on the captured image of the fluid in the vial 115 and determine from the image whether the fluid and / or solid exhibit certain features. The processing of the vial 115 can then be continued according to appropriate handling for the determined features of the fluid, as described in detail below.

[0164] In non-limiting embodiments, the fluid analysis subsystem 135 can determine one or more of the following types of features of fluids and / or solids in various embodiments. Transparency or lack of transparency of a fluid / solid mixture. For example, an image can be analyzed to the extent to which illumination passing through the vial decreases in intensity (less decrease correlates with higher transparency). This may include, if necessary, measuring the intensity of light passing from the backlight through the vial to the imaging device, light entering the vial from the side of the imaging device and then returning to the imaging device, and / or light taking other paths.

[0165] The fluid clarity of a fluid / solid mixture, or whether the fluid / solid mixture meets a certain required fluid clarity. Under some lighting conditions, a decrease in light intensity may be expected when clarity decreases, while under other lighting conditions, the light intensity may increase, for example, as more light is reflected from a cloudy suspension. Optionally, the uniformity of the image, e.g., particle size, particle velocity, or uniformity of another metric, is also evaluated. For example, under agitation, particles in a suspension may reflect a laser speckle pattern that undergoes changes with shared and / or characteristic time-dependent statistics. The exposure time or another parameter is optionally selected to distinguish between "blurred" and unblurred areas of the laser speckle motion. Unblurred areas may indicate regions that are compressed by the substance rather than suspended.

[0166] It should be noted that fluid clarity refers to the amount of light that can pass through an opaque fluid. For example, fluid clarity is potentially an indicator of whether there is any adhesion on the inner surface of vial 115.

[0167] Additionally or alternatively, there may be a discrepancy between the observed fluid color and the expected or targeted fluid color. This could indicate, for example, that the type of solid is incorrect, or that the amount of solid or fluid is incorrect. It should be noted that the expected fluid color may itself be variable, for example, depending on the type of solid and / or fluid in the vial.

[0168] In another embodiment, the fluid analysis subsystem 135 is configured to measure the presence of heterogeneous particles in the fluid. This potentially indicates contamination of the solution or damage to the internal components of the vial. Heterogeneous particles may be, for example, particles having a size, shape, or color not otherwise described. They may be particles that remain in the vial after other particles have dissolved. Optionally, such particles are distinguished from bubbles, for example, according to their apparent density (e.g., settling instead of rising) and / or lack of transientity.

[0169] In another embodiment, there may be a discrepancy between the fluid level and the expected fluid level. This potentially indicates leakage from the vial.

[0170] It should be noted that the expected (target) fluid level may be variable, for example, selectable depending on the amount of fluid initially present in the vial.

[0171] In some embodiments, the fluid analysis subsystem 135 utilizes a machine learning model 140. In this case, the machine learning model 140 can be pre-trained to classify images when needed.

[0172] For example, the machine learning model 140 can be trained with images of transparent and opaque fluids (with appropriate labeling, e.g., if a supervised model is used). The fluid analysis subsystem 135 can then classify the runtime images to determine whether they are transparent or opaque. In some embodiments, the training (and therefore the classification) may be specific to a particular solid type (i.e., a particular drug) or a particular fluid type.

[0173] In various embodiments, the machine learning model 140 can similarly be trained to perform classification to distinguish between fluids that meet a certain level of fluid clarity and fluids that do not meet that level of clarity. Similarly, the machine learning model 140 can be trained to identify the presence of heterogeneous particles, the color or shade of the fluid, and the presence of adhesions on the vial 115. In some embodiments, the fluid analysis subsystem 135 and / or the machine learning model 140 are used in methods such as those shown in Figures 2A-2F and / or Figure 3.

[0174] Additionally or alternatively, the fluid analysis subsystem 135 may use mechanisms known in the art to estimate the amount of fluid. In some embodiments, the estimation uses a machine learning model 140 trained to perform classification to distinguish the presence and / or fluid level of fluid in the vial. In some embodiments, the fluid analysis subsystem 135 and / or the machine learning model 140 are used in methods such as those shown in Figures 7-8.

[0175] In some embodiments, the fluid analysis subsystem 135 uses a non-machine learning image processing method on the captured image to determine the characteristics of the fluid.

[0176] In some embodiments, the fluid analysis subsystem 135 uses measurement and / or analysis arrangements as described herein in connection with visual inspection of the presence and / or volume of the fluid.

[0177] Figures 2A-2F illustrate various methods for controlling the dissolution of solids in liquids. Note that various embodiments may utilize some or all of these methods, or a combination of different methods.

[0178] Figure 2A illustrates a flow diagram of an exemplary method for ensuring the dissolution of a solid into a fluid as part of the drug preparation process in a robotic drug preparation system, according to several embodiments of the subject matter of this disclosure.

[0179] The method illustrated in Figure 2A may be suitable for the preparation of medical solutions, for example, that are completely transparent and result from the complete dissolution of a powdered substance in a fluid (such as saline or glucose solution).

[0180] The method illustrated in Figure 2A can, for example, operate on a vial containing a powdered substance into which an appropriate amount of fluid has been injected.

[0181] The processing circuit 130 (for example, the stirring control unit 142) can control the vial manipulator / stirrer 110 to shake the vial 115 held by the vial manipulator / stirrer 110 (205A).

[0182] For example, after the expiration of a specific time interval (e.g., enough time for a particular solid to dissolve in a particular fluid), the processing circuit 130 (e.g., the fluid analysis subsystem 135) can evaluate whether the fluid is now transparent (e.g., by machine learning classification, as described above herein) (210A). In another embodiment, transparency is evaluated by checking the ratio of light scattering to light passing straight through the vial. In yet another embodiment, transparency is evaluated according to the contrast and / or readability of an image target positioned on the opposite side of the vial.

[0183] It should be noted that in some embodiments, a transparent fluid may be colored. In such embodiments, there may be spectral parameters that characterize the dissolved fluid and / or its concentration, such as the ratio of light measured at two different wavelengths.

[0184] Next, if the processing circuit 130 (e.g., the fluid analysis subsystem 135) determines that the fluid in the vial 115 is indeed clear, the processing circuit 130 (e.g., the global control unit 145) can control the vial manipulator / stirrer 110 to continue to the next stage of the pharmaceutical preparation process (215A).

[0185] Alternatively, if the processing circuit 130 (e.g., the fluid analysis subsystem 135) determines that the fluid is not transparent (at least according to the transparency criteria used), the processing circuit 130 (e.g., the global control unit 145) may issue a warning (e.g., by displaying a message on the control display unit) (220A) indicating that the solid did not dissolve favorably in the fluid. In some embodiments, (additionally or alternatively) other forms of exception handling are performed, for example, the use of the vial may be rejected, and an alternative vial may be selected to continue operation at the discretion of the user.

[0186] Please note that the teachings of the subject matter of this disclosure are not constrained by the flowchart illustrated in Figure 2A. Furthermore, although the flowchart is drawn with reference to the system elements of Figure 1, this is not binding, and operations may be performed by elements other than those described herein.

[0187] Figure 2B illustrates a flow diagram of another exemplary method for controlling the dissolution of a solid into a fluid as part of the drug preparation process in a robotic drug preparation system, according to some embodiments of the subject matter of this disclosure.

[0188] The method illustrated in Figure 2B may be suitable, for example, for preparing medical solutions that are not completely transparent after completely dissolving a powdered substance in a fluid.

[0189] Therefore, the steps of the method in Figure 2B are the same as those of the method in Figure 2A. However, following the shaking and the expiration of the time interval (205B), the processing circuit 130 (e.g., the fluid analysis subsystem 135) can evaluate whether the fluid clarity meets the fluid clarity criteria (e.g., by machine learning classification, as described above herein) (210B).

[0190] If so, the processing circuit 130 (e.g., the global control unit 145) can then continue processing (215B); otherwise, the processing circuit 130 (e.g., the global control unit 145) can issue a warning (220B). In some embodiments (additionally or alternatively), other forms of exception handling are performed, for example, the use of a vial may be rejected, or, at the discretion of the user, another vial may be selected to continue the operation.

[0191] Please note that the teachings of the subject matter of this disclosure are not constrained by the flowchart illustrated in Figure 2B. Furthermore, although the flowchart is drawn with reference to the system elements of Figure 1, this is not binding, and operations may be performed by elements other than those described herein.

[0192] Herein, referring briefly to Figure 4B, which is a photographic image of a vial containing heterogeneous particles according to some embodiments of the present disclosure. Under the present lighting conditions, clear (transparent) areas appear as black, while heterogeneous particles appear as granules such as particle 160B. Identification of these particles is optionally performed using machine vision methods such as edge detection, thresholding, and / or particle size filtering. Optionally, machine learning methods are used to train the distinction between heterogeneous particles and other image elements of less particular interest, such as small bubbles and reflections from the vial surface.

[0193] Furthermore, referring briefly to Figures 6A-6B, these are photographic images of vials containing heterogeneous particles according to several embodiments of the present disclosure. Further referring briefly to Figure 6C, this is an absolute difference image constructed from the images in Figures 6A-6B, according to several embodiments of the present disclosure. While the presented features and imaging conditions differ (for example, with illumination 125 located in the lower left of Figures 6A-6B, and a large bright label 610 surrounding the vial 115), the presence of large particles is still easily distinguishable in Figure 6C. Additional processing is optionally performed, for example, to mask, filter, and / or otherwise enhance the visibility of particles. Optionally, machine learning classification is performed on raw and / or pre-processed images to enhance the visibility of potential defects.

[0194] Figure 2C illustrates a flow diagram of an additional exemplary method for controlling the dissolution of a solid into a fluid as part of the drug preparation process in a robotic drug preparation system, according to some embodiments of the subject matter of this disclosure.

[0195] Optionally, the method illustrated in Figure 2C is used to optimize the processing time used for dissolving a solid into a fluid and to detect dissolution failures. Additionally or alternatively, the method illustrated in Figure 2C is used to dissolve a solid into a fluid in situations where the dissolution time is unknown or variable.

[0196] The processing circuit 130 (for example, the stirring control unit 142) can control the vial manipulator / stirrer 110 to start shaking the vial 115 held by the vial manipulator / stirrer 110 (205C).

[0197] Periodically, the processing circuit 130 (e.g., the fluid analysis subsystem 135) may evaluate whether the fluid is currently transparent (210C) (e.g., by machine learning classification, as described above herein). In embodiments where the resulting fluid is not expected to be transparent, the processing circuit 130 (e.g., the fluid analysis subsystem 135) may instead evaluate whether the fluid clarity meets the fluid clarity criterion.

[0198] Next, if the processing circuit 130 (e.g., the fluid analysis subsystem 135) determines that the fluid in the vial 115 is indeed clear (or its clarity meets the clarity criteria), the processing circuit 130 (e.g., the stirring control unit 142) may stop shaking the vial 115 by the vial manipulator / stirrer 110 (215C). Then, the processing circuit 130 (e.g., the global control unit 145) may control the vial manipulator / stirrer 110 to continue to the next stage of the pharmaceutical preparation process.

[0199] Alternatively, if the processing circuit 130 (e.g., the fluid analysis subsystem 135) determines that the fluid is not transparent (or its clarity does not meet the clarity criteria), the processing circuit 130 (e.g., the global control unit 145) may evaluate whether the shaking limit (e.g., time limit) has been reached (220C), in which case the processing circuit 130 (e.g., the global control unit 145) may issue a warning (225C). If the shaking limit has not been reached, the processing circuit 130 (e.g., the fluid analysis subsystem 135) may continue shaking the vial 115 (205C), and then re-evaluate whether the fluid is transparent (or whether its clarity meets the clarity criteria).

[0200] Therefore, the method illustrated in Figure 2C allows the shaking period to closely match the actual time required for the solid to dissolve in the fluid. Note that the method illustrated in Figure 2C utilizes the capabilities of the fluid analysis subsystem 135 to evaluate fluid transparency / clearance during shaking, thereby providing an efficient process that maintains continuity of the process and reduces the time for dissolution compared to conventional systems that evaluate fluid transparency / clearance while the vial 115 is stationary.

[0201] Please note that the teachings of the subject matter of this disclosure are not constrained by the flowchart illustrated in Figure 2C. Furthermore, although the flowchart is drawn with reference to the system elements of Figure 1, this is not binding, and operations may be performed by elements other than those described herein.

[0202] Figure 2D illustrates a flow chart of an exemplary method for handling solid adhesion on a vial surface during dissolution of a solid into a fluid as part of the process of pharmaceutical preparation in a robotic pharmaceutical preparation system, according to several embodiments of the subject matter of this disclosure.

[0203] The processing circuit 130 (for example, the stirring control unit 142) can control the vial manipulator / stirrer 110 to shake (205D) the vial 115 held by the vial manipulator / stirrer 110.

[0204] For example, after the expiration of a specific time interval (e.g., enough time for a specific solid to dissolve in a specific fluid), the processing circuit 130 (e.g., the fluid analysis subsystem 135) can evaluate whether there is any solid adhering to the vial surface (210D) (e.g., by machine learning classification, as described above herein). It should be noted that in some embodiments, the processing circuit 130 (e.g., the fluid analysis subsystem 135) can also evaluate other conditions (e.g., fluid transparency or clarity) (continuously or simultaneously).

[0205] Referring now to Figure 4A, Figure 4A is a photographic image (captured from below the vial) of a vial in which solid deposits are present, according to several embodiments of the subject matter of this disclosure. The image is an example of image measurement acquired by the imaging device 120, looking up at the contents from a position located below the vial 115. Referring now to Figures 5A-5B, Figures 5A-5B are photographic images of the same vial with solid deposits, according to several embodiments of the subject matter of this disclosure. Furthermore, referring to Figure 5C, Figure 5C is a difference image obtained by subtracting (in absolute value) the images of Figures 5A-5B from each other, according to several embodiments of the subject matter of this disclosure.

[0206] In some embodiments, the processing circuit 130 (e.g., the fluid analysis subsystem 135) determines whether solids are stuck (with appropriate labeling) according to the classification of the vial images, using a machine learning model pre-trained with images of the vials.

[0207] In some other embodiments, the processing circuit 130 (e.g., the fluid analysis subsystem 135) determines that solidification is present if dissolution is not complete (e.g., the fluid is not transparent). For example, the (absolute) difference image in Figure 5C shows a "white" motion signal due to a fine-scale difference in reflectivity in the circulating fluid contents 160A, while the solid 160B remains dark because there is no relative motion here.

[0208] It should be further noted that in some embodiments, the processing circuit 130 (e.g., the stirring control unit 142) can stop shaking the vial 115 after the expiration of the time interval and before evaluating whether or not adhesion is present, while in other embodiments, shaking can continue during the evaluation of whether or not adhesion is present.

[0209] Next, if the processing circuit 130 (e.g., the fluid analysis subsystem 135) determines that the fluid in the vial 115 is not solidified, the processing circuit 130 (e.g., the stirring control unit 142) may, if necessary, stop shaking the vial 115 by the vial manipulator / stirrer 110. Then, the processing circuit 130 (e.g., the global control unit 145) may control the vial manipulator / stirrer 110 to continue to the next stage of the pharmaceutical preparation process (215D).

[0210] Alternatively, if the processing circuit 130 (e.g., the fluid analysis subsystem 135) determines that a blockage is present, the processing circuit 130 (e.g., the stirring control unit 142) can change the parameters of the shaking behavior of the vial manipulator / stirrer 110. For example, the vial can be stirred with a larger amplitude, a larger acceleration, and / or a pattern of motion that has been altered (e.g., in a figure-eight pattern, circular motion, a randomized pattern, or another shaking pattern along the axis from the bottom to the top of the vial).

[0211] In a non-limiting embodiment, if the vial manipulator / stirrer 110 shakes the vial 115 in a linear motion in the x and z planes at a specific angle, the manipulator / stirrer 110 may change the angle of agitation (220D) to remove and dissolve the adhering solid and continue shaking. Optionally, if continued shaking does not resolve the adhering, the processing circuit 130 (e.g., the fluid analysis subsystem 135) may issue a warning indicating that the solid did not dissolve favorably in the fluid.

[0212] Please note that the teachings of the subject matter of this disclosure are not constrained by the flowchart illustrated in Figure 2D. Furthermore, while the flowchart is drawn with reference to the system elements of Figure 1, this is not binding, and operations may be performed by elements other than those described herein.

[0213] Figure 2E illustrates a flow diagram of an additional exemplary method for controlling the dissolution of a solid into a fluid as part of the drug preparation process in a robotic drug preparation system, according to several embodiments of the subject matter of this disclosure.

[0214] The method illustrated in Figure 2E may be suitable, for example, for the preparation of certain medical solutions resulting from the complete dissolution of a powdered substance in a fluid, in which the dissolution of the solid continues even after the shaking has stopped.

[0215] In non-limiting examples, cyclophosphamide is a drug used in chemotherapy. In some examples, cyclophosphamide may fail to dissolve completely and immediately. In this case, it is recommended to leave the vial for a certain period of time.

[0216] The processing circuit 130 (e.g., the stirring control unit 142) can control the vial manipulator / stirrer 110 to shake the vial 115 held by the vial manipulator / stirrer 110 for a certain period of time (e.g., a suitable time for a particular solid to dissolve in the fluid) (205E).

[0217] After a specific time interval (for example, enough time for a particular solid to dissolve in a particular fluid), the processing circuit 130 (for example, the stirring control unit 142) can then wait for a certain duration to elapse (210E) to allow the solution to "settle" (210E). In some embodiments, the settling time is 0.

[0218] The processing circuit 130 (for example, the fluid analysis subsystem 135) can then evaluate whether the fluid is currently transparent (215E) (or, in some embodiments, whether the fluid's clarity meets the clarity criteria) (for example, by machine learning classification as described above herein).

[0219] Next, if the processing circuit 130 (e.g., the fluid analysis subsystem 135) determines that the fluid in the vial 115 is indeed clear, the processing circuit 130 (e.g., the global control unit 145) can control the vial manipulator / stirrer 110 to continue to the next stage of the pharmaceutical preparation process (220E).

[0220] Alternatively, if the processing circuit 130 (e.g., the fluid analysis subsystem 135) determines that the fluid is not transparent (or, where appropriate, does not meet the clarity criteria), the processing circuit 130 (e.g., the global control unit 145) may issue a warning (225E) indicating that the solid did not dissolve favorably in the fluid.

[0221] It should be noted that in some embodiments, the processing circuit 130 (e.g., the fluid analysis subsystem 135) may evaluate transparency (or clarity criteria) multiple times (e.g., with pauses in between) before issuing a warning that the solid has not dissolved.

[0222] Please note that the teachings of the subject matter of this disclosure are not constrained by the flowchart illustrated in Figure 2E. Furthermore, although the flowchart is drawn with reference to the system elements of Figure 1, this is not binding, and operations may be performed by elements other than those described herein.

[0223] Figure 2F illustrates a flowchart of an exemplary method for detecting and reporting defects in the process of dissolving a solid into a fluid as part of the pharmaceutical preparation process in a robotic pharmaceutical preparation system, according to some embodiments of the subject matter of this disclosure.

[0224] The processing circuit 130 (for example, the stirring control unit 142) can control the vial manipulator / stirrer 110 to shake (205F) the vial 115 held by the vial manipulator / stirrer 110.

[0225] The processing circuit 130 (for example, the fluid analysis subsystem 135) can evaluate whether a specific defect has occurred (210F).

[0226] In a non-limiting embodiment, the processing circuit 130 (e.g., the fluid analysis subsystem 135) can evaluate one or more of the following types of defects: • Discrepancy between the fluid color and the expected fluid color (this may indicate that the type of solid is incorrect, or that the amount of solid or fluid is incorrect). Note that the expected fluid color may vary depending on the type of solid and / or fluid in the vial. The presence of foreign particles (e.g., particles that have fallen from the partition) in the fluid (this can indicate contamination of the solution or damage to the internal components of the vial). For example, Figure 4B shows an exemplary image of a vial containing foreign particles (captured from the bottom of the vial). • Discrepancy between the fluid level and the expected fluid level (this may indicate leakage from the vial). In some embodiments, an imaging device may be placed next to vial 115 to monitor the fluid volume. In some embodiments, a method such as that described in relation to Figure 7 (and other related figures) is used to evaluate the fluid level.

[0227] It should be noted that the expected fluid level may be variable and may depend, for example, on the amount of fluid initially in the vial, the amount of fluid ordered to be injected into the vial and / or observed, and / or the amount adjusted to account for operations to remove fluid from the vial.

[0228] The processing circuit 130 (for example, the fluid analysis subsystem 135) can evaluate whether one or more of these defects have occurred by machine learning classification, for example, as described above in this specification.

[0229] If the processing circuit 130 (e.g., the fluid analysis subsystem 135) determines that a malfunction has actually occurred, the processing circuit 130 (e.g., the global control unit 145) may issue a warning (215F) indicating that a malfunction has occurred (including details of the malfunction in some embodiments).

[0230] Please note that the teachings of the subject matter of this disclosure are not constrained by the flowchart illustrated in Figure 2F. Furthermore, although the flowchart is drawn with reference to the system elements of Figure 1, this is not binding, and operations may be performed by elements other than those described herein.

[0231] Figure 3 illustrates an exemplary general method for monitoring and controlling the process of dissolving a solid into a fluid, and optionally detecting and reporting defects, as part of the pharmaceutical preparation process in a robotic pharmaceutical preparation system, according to some embodiments of the subject matter of this disclosure.

[0232] The processing circuit 130 (for example, the stirring control unit 142) can control the vial manipulator / stirrer 110 to start stirring (305) the vial 115 held by the vial manipulator / stirrer 110.

[0233] Next, the processing circuit 130 (for example, the fluid analysis subsystem 135) can receive the image of the fluid in the vial 115 captured by the camera (310).

[0234] It should be noted that in some embodiments, the processing circuit 130 (e.g., the stirring control unit 142) can stop shaking the vial 115 before image capture, while in other embodiments, shaking can continue during image capture and, in some embodiments, during subsequent image processing.

[0235] The processing circuit 130 (e.g., fluid analysis subsystem 135) can then classify the received image (315) to determine the fluid / solid features within the vial 115. Optionally, features are determined by measuring features such as image shape features, intensity features, and dynamic features (e.g., the magnitude of the difference between two or more images), or by other means.

[0236] In a non-limiting embodiment, the processing circuit 130 (e.g., the fluid analysis subsystem 135) can determine the presence of one or more of the following types of features of the fluid and / or solid. • Transparency or lack of transparency of a fluid / solid mixture. • The clarity of a fluid / solid mixture, or whether a fluid / solid mixture meets a specific required level of clarity. • Is there any adhesion on the inner surface of vial 115? • Discrepancy between the fluid color and the expected fluid color (this may indicate that the type of solid is incorrect, or that the amount of solid or fluid is incorrect). Note that the expected fluid color may vary depending on the type of solid and / or fluid in the vial. The presence of foreign particles indicates their presence in the fluid (this can indicate contamination of the solution or damage to the internal components of the vial). • Discrepancy between the fluid level and the expected fluid level (this may indicate leakage from the vial).

[0237] It should be noted that the expected fluid level is variable and may depend on the amount of fluid initially present in the vial.

[0238] As described in detail above, with reference to Figure 1, in some embodiments, the processing circuit 130 (e.g., the fluid analysis subsystem 135) performs image classification using a trained machine learning model to determine the presence of one or more features.

[0239] In some other embodiments, the processing circuit 130 (e.g., the fluid analysis subsystem 135) uses other image processing methods to determine the presence of one or more features.

[0240] Next, the processing circuit 130 (for example, the stirring control unit 142 or the global control unit 145) can perform the following steps (320) according to the determined characteristics.

[0241] In non-limiting embodiments, the processing circuit 130 (for example, the stirring control unit 142 or the global control unit 145) may perform one or more of the following steps in response to the determined features. Stop stirring by the agitator. For example, modify the operating parameters of the agitator 110, such as changing the shaking angle. • Move vial 115 to the next stage of the preparation process (for example, control the robotic arm to remove the vial from the vial holder). Issue a warning.

[0242] Figures 2A–2F illustrate an exemplary method for controlling the dissolution of a solid into a liquid, which involves performing specific steps in response to the determination of specific fluid characteristics.

[0243] Please note that the teachings of the subject matter of this disclosure are not constrained by the flowchart illustrated in Figure 3. Furthermore, although the flowchart is drawn with reference to the system elements of Figure 1, this is not binding, and operations may be performed by elements other than those described herein.

[0244] [Visual inspection of the presence and / or volume of fluid] <Image evaluation of liquid vial contents> Referring now to Figure 7, Figure 7 is a flowchart schematically illustrating an image-based inspection method for determining the amount of fluid contained in a vial, according to some embodiments of the subject matter of this disclosure. Also referring now to Figure 8, Figure 8 is a flowchart schematically illustrating an image-based inspection method for determining the presence of fluid in a vial, according to some embodiments of the subject matter of this disclosure. The two methods are described in parallel, with reference to specific blocks as necessary. Optionally, they are both performed. Optionally, they are performed simultaneously (e.g., using the same image of the vial). Optionally, these two methods are performed separately, or only one of them is performed.

[0245] <Vial tilt angle for imaging contents> In block 705 (Figure 7) and / or block 805 (Figure 8), in some embodiments, an inspection image of the vial is acquired and / or accessed. The inspection image shows the vial with a tilt angle applied. The tilt angle tilts the vial away from vertical orientation, so that the bottom of the vial is oriented perpendicular to the direction of gravitational acceleration. The inspected vial is expected to contain a certain amount of liquid content, and the calculated image analysis of the inspection image is used to verify that the amount is within specifications. Optionally, in the case of Figure 8, the inspected vial is expected to contain no liquid content, in which case the operation is reversed with the reported result, if necessary.

[0246] Briefly referring to Figures 12A-12B, Figures 12A-12B schematically represent cross-sectional side views (Figure 12A) and side views (Figure 12B) of a labeled fluid-containing vial 115 according to several embodiments of the subject matter of the present disclosure. The vial 115 is vertically upright and not inclined. A fluid 160 is present, forming an optically distinct boundary region 600A, but the presence of the label 610 leaves no gap, or only a small gap 611, that allows a side view of the vial 115 to visualize the boundary region 600A. The boundary region is formed due to features of the vial contents, such as the difference in optical density between the fluid and the gas, and / or other features, such as those described in the abstract.

[0247] Even if present, the gap 611 is positioned and / or placed in a potentially unreliable manner, and is too narrow for reliable automatic detection of the boundary region 600A. However, it can be understood that once the boundary region 600A is identified, the volume of the fluid 160 can be determined, at least approximately, from knowledge of the internal vial radius r602 and the boundary region height h601 above the internal bottom of the vial 115.

[0248] In some embodiments, the inclined vial 115 is imaged through the surface of the vial bottom 115B, which is typically circular and flat enough to allow the vial to be placed upright on a surface. Deviations from the ideal flatness of the bottom surface that may potentially affect image quality include texturing (e.g., having raised areas or dots around the rim), slight depressions, prominent or raised markings (e.g., lettering, numbering, and / or logos), and / or manufacturing defects. Despite these potential deficiencies for use in through-content imaging, it should be noted that the bottom of the vial generally remains clear of any labeling, such as label 610.

[0249] Therefore, instead of appearing vertically as shown in Figures 12A-12B, the vial is tilted so as to be away from the vertical by an angle α.

[0250] Furthermore, referring briefly to Figure 12C, which schematically represents a side cross-sectional view of a fluid-containing vial 115 with a 90° inclination angle α according to several embodiments of the subject matter of this disclosure. This has the effect of reducing the height h601 in Figures 12A-12B to a height h″601B as the fluid 160 spreads into a larger containment area. The label 610 still obscures most of the side view (although it is removed in the cross-sectional view).

[0251] Typically, the inclination angle of the vial in the image is chosen so that the boundary region 600A is positioned where it crosses (or is expected to cross) a visible area in the inspection image of the vial. For example, in the shown embodiment, it crosses the vial bottom 115B from a vantage point of the imaging device 620 and within the imaging device's field of view 621. Thus, in some embodiments, the measurement area of ​​the vial surface forms the bottom or top of a cylinder or prism, but not itself along the rising wall of this shape.

[0252] In some embodiments, the measurement area on the vial surface (beyond which the boundary region is imaged) does not form part of the main right cylindrical or right prism-shaped portion of the vial. For example, the boundary region 600A may be partially visible through the vial top 605 in the region that would be above the more regular cylindrical portion of the vial 115 (in the upright position of the vial 115).

[0253] Briefly referring to Figure 9A, Figure 9A reproduces a photograph of a fluid-containing vial 115 held by a grip 110 having an inclination angle of about 90°, according to several embodiments of the subject matter of the present disclosure. The presence (considering Figure 8) and / or level (considering Figure 7) of the fluid contents 160A is automatically determined according to the presence and / or location of a boundary region 600A, which is visualized by the difference in refractive index between the fluid contents 160A and the gas filling the rest of the vial 115.

[0254] Briefly referring to Figure 9B, Figure 9B reproduces a photograph of a solid-containing vial 115 held by a grip 110 having an inclination angle of about 90°, according to several embodiments of the subject matter of this disclosure. The absence of fluid contents is automatically determined according to the absence of boundary regions and / or according to image features indicating the presence of solid 160B.

[0255] Briefly referring to Figure 9C, Figure 9C reproduces a photograph of a fluid-containing vial 115 held by a grip 110 having an inclination angle of about 90°, according to several embodiments of the subject matter of the present disclosure. The presence (considering Figure 8) and / or level (considering Figure 7) of the fluid contents 160A is automatically determined according to the presence and / or location of a boundary region 600A, which is visualized by the difference in color (i.e., optical density at at least one wavelength) between the fluid contents 160A and the gas filling the rest of the vial 115.

[0256] Returning to blocks 705 and 805, in embodiments using bottom view images, the inclination angle is optionally any angle that deviates the vial from the vertical enough to position the boundary region of interest in expected contact (transparent and visible) with the bottom of the vial. This situation is preferably selected to apply when the vial is filled with liquid as specified during the preparation of the pharmaceutical preparation, for example, at least 20%, at least 30%, at least 50% (mostly filled), or another relative (or absolute) filling amount of its volume.

[0257] The inclination angle can be, for example, about 90° (i.e., the vial is oriented toward its side, as shown in Figure 12C and / or Figures 9A-9C).

[0258] Additional or alternative tilt angles may be used. In some embodiments, for example, tilt angles of 75° to 90° are used, and in some embodiments, the tilt angle away from the vertical is at least 45°, at least 60°, or at least 75°. In some embodiments, tilt angles that partially invert, i.e., tilt angles greater than 90°, are used. For example, tilt angles of 90° to 105° are used.

[0259] Optionally, images of the vial are acquired for multiple tilt angles to help ensure, for example, that at least one tilt angle indicates a boundary region in a position suitable for image processing measurements. The tilt angles are optionally selected according to the expected volume of liquid in the vial and / or according to procedural presets.

[0260] Referring briefly to Figure 11, Figure 11 schematically represents a side section view of a fluid-containing vial 115 having a varying inclination angle α according to several embodiments of the subject matter of the present disclosure. At position 801, the inclination angle is approximately 60°, and at position 802, the inclination angle is approximately 90°. The graph between the two illustrated positions represents the variation in height h from height 801A at position 801 to height 802A at position 802. Optionally, imaging occurs at any one, two, or more positions within this range. Each of these positions should indicate a boundary region 600A intersecting the vial bottom 115B.

[0261] Returning to blocks 705 and 805, using an inclination angle that positions the boundary region within the visible area of ​​the vial offers potential advantages, for example, insofar as a large portion of the vial wall may be obscured by the labeling and therefore unreliable and / or unavailable for use in verifying the presence and / or volume of the fluid contents.

[0262] In some embodiments, the tilt angle actually applied to the vial (i.e., used when evaluating the presence / amount of the fluid content) is known from data separate from the image of the boundary layer. For example, the tilt angle is set by the operation of the pharmaceutical preparation system and is known based on encoder measurements, weight sensing, or another data source. Optionally, the tilt angle is determined by pre-arrangement. For example, the processing algorithm is designed under the assumption that the images it receives always correspond to vials held at a particular tilt angle, or alternatively, that the images are guaranteed to correspond to a predetermined tilt angle.

[0263] Additionally or alternatively, in some embodiments, the tilt angle is inferred and / or confirmed from the image itself, for example, based on the apparent eccentricity of the rounded vial bottom due to image foreshortening. As a potential advantage of relying on the inference of the tilt angle from the imaged shape of the vial, this can advantageously separate the operation of the vial manipulation from the imaged observations of the vial, for example, to reduce the risk of data distortion and / or to provide an independent verification that the mechanical aspects of the operation are within the intended parameters.

[0264] Referring briefly to FIGS. 10A - 10B, FIGS. 10A - 10B schematically represent a side cross-sectional view (FIG. 10A) and a bottom view (FIG. 10B) of a fluid-containing vial 115 having an oblique tilt angle α according to some embodiments of the subject matter of the present disclosure. In the illustrated embodiment, α is about 60°. The fluid 160 fills the vial 115 to level h´601A. It may be noted that the oblique angle selectively provides a foreshortened view of the vial bottom 115B in FIG. 10B along the vertical axis. This eccentricity, along with the assumption that the vial bottom 115B is actually circular, allows the tilt angle to be estimated from measurements of the vertical and horizontal axes of the vial bottom 115B. Depending on the field-of-view settings used for imaging, the recession of the vial bottom 115B in the lower part of the image can affect the imaged geometry. This is also optionally taken into account.

[0265] Returning to the operation of blocks 705 and 805, in some embodiments, the inclined vial is imaged with its contents in positional equilibrium; that is, the vial is not moving relative to the imaging device, is not accelerating (except to the extent that gravity acts upon it), and more specifically, the boundary region of interest remains in a stable position during image exposure. This has potential advantages in terms of measurement accuracy and reproducibility.

[0266] However, positional equilibrium is not always necessary. For example, if the vial itself is in a stable, non-accelerating position after a recent stop, residual sloshing of a certain amount of fluid contents (and in particular, movement of the boundary region on the bottom view of the vial) can be adapted by measuring images sufficient to determine the characteristics of this movement. For example, the center point of the range can be determined, and / or the settling state to which the movement of the vial contents tends to go can be determined. Conversely, the absence of such a moving boundary can, optionally, be used as evidence of complete fluid depletion.

[0267] In another embodiment, the vial may be dynamically rotated over a range of angles α (for example, around an internal point of the vial), and this image may be acquired with different exposure periods during this rotation. The rotation speed is optionally low enough so that the non-equilibrium aspects of the situation can be ignored in the calculation.

[0268] Alternatively (returning to blocks 705 and 805), dynamic effects can be compensated for entirely or partially during the calculation. Potential advantages of imaging during the dynamic movement of the vial include a faster measurement process and / or integration of the measurement process into other operations performed by the pharmaceutical preparation system, where a vial position potentially suitable for use in the measurement can be generated incidentally and / or without any impact on procedure time as might be required by a separately implemented volumetric measurement step.

[0269] In some embodiments, the vial is accelerated during image exposure. For example, it is accelerated linearly and / or moves through an arc centered on a point outside the vial (e.g., a circular motion like that of a centrifuge). This can result in a boundary region displacement that moves away from perpendicular to the direction of gravity acting independently, even if the vial itself remains vertically oriented. The camera used for imaging is optionally synchronized with the motion of the vial in any preferred manner, for example, panning to track the motion of the vial or fixed on a manipulator that also moves the vial.

[0270] In some embodiments (for example, as mentioned in relation to Figure 12C), an image providing a view of the top of the vial is optionally used to verify the presence of fluid and / or that fluid volume requirements are met. Optionally, this can replace a bottom view image. Bottom views have potential advantages, insofar as the shape of the bottom of the vial is typically relatively flat and regular (circular) compared to the curved (e.g., ellipsoidal) surface of the top of the vial, and this may also include any interruptions, including the vial's neck and cap. In particular, at lower inclination angles, more fluid contents may be retained in the cylindrical region of the vial, which potentially reduces the number of assumptions required to account for the shape inside the vial in volume estimation. Also, while the top of the vial may be obscured while being held for manipulation, gripping the bottom and / or side walls of the vial is not excluded from implementation.

[0271] However, top-side views, if available, can provide useful information for determining the presence of fluid, for example, if the boundary region exceeds the level of the label obscuring it. Quantitative volume estimates can be obtained if the vial shape is adequately modeled and / or can be modeled. Similarly, side views of the vial are optionally used (optionally exclusively) for estimating the fluid contents, insofar as the boundary region (e.g., the region where the fluid meniscus contacts the vial wall) is displaced by tilting so that it can be viewed. Furthermore, any of these views can be optionally used in combination. Combinations of captured views potentially provide information to help achieve a more accurate determination of the fluid volume, for example, as described in relation to block 710.

[0272] Optionally, in the case of block 805 and the method in Figure 8, the vial is not tilted, but rather is viewed from an angle from which any potential solids in the vial are expected to be lifted against an unobstructed area of ​​the vial wall. For example, the vial is held vertically and viewed from the bottom. In any case, the potential advantages of tilting the vial include this allowing the movement of powder within the vial (an indicator of the presence of solid material), and / or this allowing the presence of boundary areas to be confirmed.

[0273] <Determination of Fluid Volume Index> In blocks 710 (Figure 7) and / or 810 (Figure 8), in some embodiments, the fluid volume index is determined from one or more images acquired and / or accessed in blocks 705 and 805.

[0274] In this specification, the term “fluid volume index” refers to an index of how much fluid is in the vial, either absolutely (e.g., in volume units proportional to milliliters) or otherwise specified with respect to a fluid volume requirement (e.g., a reference volume). In some embodiments of Block 715 (Figure 7), the fluid volume index is in accordance with the requirements.

[0275] The two blocks in Figure 7 are introduced together because the definition of the fluid volume index is related to the implementation of compliance with operating requirements. In particular, the implementations of the two classes can be characterized as a "relative volume" implementation and an "absolute volume" implementation.

[0276] Relative volume implementation In some embodiments of relative volumetric implementation, the fluid volume index includes the position of the boundary region relative to the visible surface area of ​​the vial itself. For example, for a particular inclination angle and model of the vial (i.e., a particular internal vial geometry), it may be predetermined that the targeted fluid volume results in a specific position of the boundary region relative to a vial surface marker (e.g., the circular outer circumference of the vial bottom). For example, the vial bottom and / or other vial surface markers may be identified using image segmentation techniques. In some embodiments, the position of the boundary region is identified with respect to another criterion, e.g., coordinate axes established by the mechanical arrangement of the pharmaceutical preparation system itself (e.g., vertical axes with known relative positions of the gripping part that holds the vial and the camera that images the vial).

[0277] The boundary region itself can be identified as a linear (narrow rectangular) region extending transversely (or otherwise as expected) across the bottom of the vial, characterized, for example, by a sharp contrast gradient (for lines), by two such contrast gradients (for bright or dark lines), or otherwise, using an edge detector or other image processing algorithm that is selected and implemented at the discretion of the lighting and imaging conditions used. Optionally, the boundary region detector is selected to be robust to the normal level of field distortion imposed by the relatively small irregularities of the vial wall portion from which it is visible.

[0278] If the image of the boundary region is not generally linear in shape (for example, when the boundary region is expected to be captured where it contacts the curved top or side of the vial), the image processing algorithm may optionally model the boundary region as a appropriately parameterized curve. For example, the curve may be parameterized as needed with respect to the intersections of the slope with the cylindrical and / or ellipsoidal wall portions projected onto the camera's imaging plane. In some embodiments, the image itself is geometrically transformed to normalize the shape of the captured boundary region (e.g., to make it more linear) before applying the detection algorithm.

[0279] The targeted locations of the boundary region are optionally defined, for example, as lines or curves that the boundary region includes (or crosses), areas where the boundary region intersects, or in another manner.

[0280] Without necessarily having access to data indicating the actual volume of the target fluid contents (e.g., in milliliters), an image processing algorithm can determine whether geometrically specified criteria are met based on this volume.

[0281] Therefore, as part of the operation of block 715, the fluid volume index can be converted into a pass / fail index. Optionally, additional categories are added to such determinations (e.g., "too empty" or "too full"). Optionally, the amount of deviation from the expected value is provided as an index, for example, as a positional deviation. Optionally, such deviations are reported statistically, for example, with respect to a multiple of the standard deviation or other statistical measure. Optionally, the positional deviation is calibrated otherwise, for example, in percentages and / or in absolute volume units such as milliliters.

[0282] In some embodiments, the calibration is roughly calculated to indicate overfilling or underfilling, for example, as the distance of the deviation in the boundary region increases, this can become increasingly inaccurate, but the deviation from the targeted position of the boundary region in millimeters is converted to a difference in milliliters by a linear scale. It can be appreciated that the type and number of corrections applied to the relative volume implementation can be increased according to this approach until it becomes an instance of the class of absolute volume implementations described in the following additional details.

[0283] The acceptability of a purely relative and / or roughly calibrated assessment of the fluid quantity can vary depending on the type of pharmaceutical preparation being mixed, regulatory requirements, reagent values, and / or other parameters. Thus, it is a potential advantage that the calibration procedure and / or the amount of prior knowledge used can be adjusted according to such requirements.

[0284] Optionally, the reference against which the fluid quantity indicator is evaluated is determined as part of the normal operation of the pharmaceutical preparation system, which is one of the potential advantages of the relative volume implementation. For example, the system can be run for a period during which several vials are handled while the fluid quantity indicators are accumulated from each. Assuming that errors during this period are rare, non-existent, or otherwise negligible and / or excludable, these results can be used (e.g., statistically) for one or both of evaluating the amount of fluid content in the vials imaged during the period and setting a reference for evaluating the fluid quantity indicators in other vials. In particular, during the handling of future vials, warnings and / or mitigation actions can be taken immediately when a relative discrepancy in the fluid content is detected, optionally even when there is no direct representation of the targeted and / or current volume of fluid contained in the vial in milliliters.

[0285] Absolute volume implementation Now, turning to the absolute volume implementation classes of blocks 710 and 715, the amount of the target liquid contents is optionally specified as a volume requirement proportional to milliliters (e.g., a specific volume, a specific volume with an acceptable range of error, and / or a range of volumes). In the following description, it is assumed that the calibration between image pixels and their size in space is known and / or calculable from system dimensions, reference marks, and / or other preferred constraints.

[0286] The determination of the fluid volume index can begin, as described for relative volume implementation, by finding the position of the boundary region in the image relative to the visible surface region. To convert this to milliliter proportional volume, the operation of block 710 optionally uses any preferred combination of modeled and measured parameters that describe (at least approximately) the internal geometry of the vial. These parameters can more or less accurately approximate the actual internal vial geometry, depending on the requirements.

[0287] A simple case is applicable, for example, when the fluid volume is relatively low compared to the height of the generally cylindrical portion of the vial. The internal volume of the vial can be simply modeled as a straight cylinder with a circular cross-section extending infinitely upward from its bottom.

[0288] The circular cross-section is optionally determined from the image of the bottom of the vial, assuming, for example, that the diameter used is approximately equal to the maximum horizontal width of the vial (as imaged) minus twice the "reasonable" vial wall thickness (e.g., 1.5 mm, or another value, e.g., also estimated from the image). Optionally, any or all vial geometric shape model values ​​are provided separately from the image, for example, according to a known model of the vial being used.

[0289] For relatively low incline angles (i.e., as long as the "upper" range of the boundary region does not extend beyond the cylindrical region of the vial), the amount of fluid contained can be calculated as the volume of a model cylinder lying beneath a plane parallel to the boundary region, extending through the boundary region.

[0290] Where low-volume / low-slope conditions are not applicable, the vial model can be enhanced, for example, by assuming a maximum height, a curved (e.g., ellipsoidal) upper portion, and / or a cylindrical neck for the vial, as needed. Optionally, any of these parameters are measured by imaging, although directly measuring the vial wall thickness is potentially error-prone due to optical distortion. Even in this case, the wall thickness correction is optionally determined based on a physical model incorporating empirical measurements and / or reasonable assumptions about the refractive index of the vial wall material. Optionally, any of these parameters are provided separately from the images, for example, as parameters describing a known model of the vial. The model can be further extended as needed to include corrections for container irregularities, such as meniscus shape and / or recesses at the bottom of the vial. In a sufficiently complete model performed in this manner or in another manner, any slope angle and imaged location of the boundary region can be correlated to a specific fluid volume expressed in milliliters proportionally. Optionally, refinement of the model is limited to parameters that have a meaningful effect within a specific range of slope angles.

[0291] Furthermore, it should be noted that if the model has free (unknown) parameters (e.g., wall thickness), there are potential sources of information available that can help assign values ​​to them by measuring how the position of the boundary region changes as a function of the tilt angle. For example, given the external dimensions of the vial (optionally determined directly from the image), an unknown constant vial wall thickness, and the image-measured dependence of the position of the boundary region on the tilt angle (e.g., for at least two tilt angles), it may be possible to fix the wall thickness to a value (or a constrained range of values) such that the calculated volume remains the same as a function of the change in tilt angle.

[0292] Briefly referring to Figure 13, Figure 13 is a schematic diagram of vial geometric parameters according to some embodiments of the present disclosure. The internal volume geometric parameters of vial 115 with a bottom radius r602 are described in relation to Figure 12A. In some embodiments, one or more additional geometric parameters of the vial are described and / or considered when calculating the fluid content volume. For example, in some embodiments, the vial wall thickness W1907 is subtracted from the outer vial radius to reach an estimated value of the bottom radius r602. Optionally, the internal height of the cylindrical portion of vial 115 is calculated by subtracting the estimated, known, or image-measured vial bottom thickness W2906 from the total (outside) height measured in the image of the cylindrical portion. In some embodiments, parameters of other parts of the internal geometry of vial 115, e.g., the height radius r of the top portion of vial 115. t 903 is estimated. In some embodiments, the volume calculation takes into account a correction function ε2(r,θ,α)904 for strain due to the fluid meniscus shape of the boundary region, where θ is a parameter of the angle around the vial wall parallel to the plane in contact with the vial wall, and α is the inclination angle. In some embodiments, the correction takes into account the deviation from the planar shape of the bottom inner surface of vial 115ε2(r,θ)906, where θ is a parameter of the angle around the vial wall.

[0293] <Response to fluid volume index> In block 720, in some embodiments, a determination is made as to whether the fluid volume index is as expected (as required), based on the result of matching the fluid volume index to the requirements in block 715. If so, then in block 730, the process continues using the now verified contents of the vial. Alternatively, an exception occurs in block 725.

[0294] The exception in block 725 is optionally functionally linked to one or more outcomes related to the function of the pharmaceutical preparation system. For example, the exception triggers one or more of the following: User warnings that signal to the device operator that attention is required (for example, by visual, tactile, auditory, or other signaling, optionally using the system's own hardware and / or remotely connected hardware in which the signals are transmitted wirelessly). An internal fault that causes the system to stop operating (or at least bypass the suspected faulty function) until the problem is resolved. For example, a self-check to determine whether an unexpected fluid volume indicator can be traced back to a specific situation. For example, adjustments to correct the volume in the vial by injecting more fluid or removing fluid, to discard the vial or place it in a special storage area, and / or to access a replacement vial and retry the failed portion of the pharmaceutical mixing procedure.

[0295] System self-checks and / or adjustments are optional operations that the system can perform on its own, but it should be noted that they are sufficiently resource-intensive that they are not normally performed until an exception occurs, such as the exception in block 725. This gives the operation of the method in Figure 7 status as a gating method for other operations, enabling the system to self-recover and / or potentially reducing the direct monitoring requirement for some other system components. For example, when it has reached the end of its rated capacity, a saline reservoir bag may be in a state of partial uncertainty regarding how much saline can be drawn from it. Rather than replacing the bag prematurely, it may be used until the insufficient fluid situation is clearly identified by the operation in Figure 7, at which point the system may proceed through defined operations to correct (and re-verify, if necessary) both the empty saline reservoir situation and the incomplete filling of the vial.

[0296] [General] When used herein in reference to a quantity or value, the term “approximately” means “within ±10%.”

[0297] The terms "comprises," "comprising," "includes," "including," and "having," as well as their conjugations, all mean "to include, but not limited to."

[0298] The term "consisting of" means "including and limited to."

[0299] The term “essentially derived from” means that the composition, method, or structure may include additional components, steps, and / or parts, but only if the additional components, steps, and / or parts do not substantially alter the basic and novel features of the claimed composition, method, or structure.

[0300] As used herein, the singular forms “a,” “an,” and “the” include multiple references unless the context explicitly indicates otherwise. For example, the terms “a compound” or “at least one compound” may include multiple compounds, including mixtures thereof.

[0301] The terms “Example” and “Illustrative” are used herein to mean “functioning as an example, instance, or illustration.” Any embodiment described as “Example” or “Illustrative” should not necessarily be construed as being preferable or advantageous to other embodiments, and / or should not be excluded from incorporating features from other embodiments.

[0302] The term “optional” is used herein to mean “provided in some embodiments and not provided in other embodiments.” Any particular embodiment of this disclosure may include several “optional” features, to the extent that such features do not conflict.

[0303] As used herein, the term “method” means any method, means, techniques, and procedures for accomplishing a given task, including but not limited to methods, means, techniques, and procedures that are known to those skilled in the art of the fields of chemistry, pharmacology, biology, biochemistry, and medicine, or that are readily developed from known methods, means, techniques, and procedures.

[0304] As used herein, the term “treat” includes invalidating, substantially inhibiting, delaying, or reversing the progression of a condition, substantially improving the clinical or aesthetic symptoms of a condition, or substantially preventing the appearance of the clinical or aesthetic symptoms of a condition.

[0305] Throughout this application, embodiments may be presented by reference to a range form. It should be understood that the range form is provided solely for convenience and brevity and should not be interpreted as an inflexible limitation to the scope of the disclosure. Therefore, a range description should be considered to specifically disclose all possible subranges and individual numbers within that range. For example, a range description such as "1-6" should be considered to have specifically disclosed subranges such as "1-3," "1-4," "1-5," "2-4," "2-6," and "3-6," as well as individual numbers within that range, e.g., 1, 2, 3, 4, 5, and 6. This applies regardless of the breadth of the range.

[0306] Whenever a numerical range (for example, "10 to 15", "from 10 to 15", or any pair of numbers linked by these other such range indicators) is shown herein, unless the context explicitly indicates otherwise, it means that it includes the range limit, including any numbers (fractions or integers) within the indicated range limit. The phrases “between range / ranging / ranges” between the first and second indicator numbers, and “from range / ranging / ranges” from the first indicator number to the second indicator number “to”, “up to”, “until”, or “through” (or other such range indicator terms)” are used interchangeably herein and mean the first and second indicator numbers, as well as all fractions and integers between them.

[0307] While the description in this disclosure is provided in conjunction with specific embodiments, it will be obvious that many alternatives, modifications, and variations will be apparent to those skilled in the art. Therefore, it is intended to encompass all such alternatives, modifications, and variations that fall within the spirit and broad scope of the appended claims.

[0308] For clarity, it is understood that certain features described in the context of separate embodiments may also be provided in combination in a single embodiment. Conversely, various features briefly described in the context of a single embodiment may be provided separately, in any preferred subcombination, or as suitable in any other described embodiment of this disclosure. Certain features described in the context of different embodiments are not considered essential features of those embodiments unless the embodiments would not function without those elements.

[0309] All publications, patents, and patent applications referenced herein are incorporated herein by reference to the same extent as each individual publication, patent, or patent application is specifically and individually indicated when it is mentioned that it will be incorporated herein by reference. In addition, any citation or identification of any reference in this application should not be construed as an admission that such reference is available as prior art to the disclosure. Paragraph headings, to the extent that they are used, should not necessarily be construed as restrictive. In addition, any priority documents of this application are incorporated herein by reference in their entirety.

Claims

1. A method for evaluating the contents of a vial, wherein the contents include a pharmaceutical ingredient, and the method is Manipulating the vial to change the inclination angle of the vial with respect to the boundary region of the contents of the vial, During the period in which the tilt angle is changed, at least one image of the vial is acquired. The position of the boundary region in at least one image is calculated by image processing using a processing circuit, The comparison involves comparing the position of the boundary region with a target reference, wherein the target reference takes into account the shift in the position of the boundary region due to the inclination angle. A method comprising automatically determining whether to use or reject the contents of the vial in an automated preparation of a pharmaceutical product, in accordance with the results of the comparison described above.

2. The method according to claim 1, wherein the operation involves changing the inclination angle such that the boundary region in at least one image of the vial extends along the bottom surface of the vial.

3. The method according to claim 2, wherein the target criterion includes a target position extending along the bottom surface, and the comparison determines the position of the boundary region relative to the target position.

4. The method according to any one of claims 1 to 3, wherein the label obstructs the visibility of the contents through a visibility-obstructing side region of the vial, and the change in the inclination angle moves the boundary region from the visibility-obstructing side region to a non-obstructing surface region of the vial where the boundary region is visible.

5. The method according to claim 4, wherein the target criterion includes a target position along the non-interfering surface region of the vial, and the comparison determines the position of the boundary region relative to the target position.

6. The method according to claim 5, wherein the target position extends along a portion of the vial surface that is located above or below the label when the vial is upright.

7. The method according to any one of claims 1 to 6, wherein during the period in which the inclination angle is changed, the height of the contents is a nonlinear function of the volume of the contents.

8. The method according to any one of claims 1 to 7, wherein the operation includes rotating the vial while the boundary region remains horizontal.

9. The method according to any one of claims 1 to 7, wherein the operation includes moving the vial so as to change the angle of the boundary region away from the horizontal.

10. The method according to any one of claims 1 to 9, wherein at least one of the comparison and the automatic determination includes calculating the volume of the contents of the vial, and the automatic determination selects to use or reject the contents of the vial according to how close the volume is to a target volume.

11. The method according to any one of claims 1 to 9, wherein the target criterion defines a target position, the result of the comparison includes the distance between the position in the boundary region and the target position, and the determination selects to use or reject the contents of the vial according to the distance.

12. The method according to any one of claims 1 to 11, wherein the boundary region indicates a difference in optical properties between the lower material phase of the contents of the vial and the material above it.

13. The method according to claim 12, wherein the optical property is at least one of refractive index, light absorption coefficient, and turbidity.

14. The method according to any one of claims 1 to 13, wherein the at least one image includes a plurality of images obtained at different tilt angles of the vial.

15. The method according to claim 14, wherein the calculation and comparison are performed for each of the plurality of images.

16. The method according to claim 14, wherein the automatic determination includes determining the parameters of the geometric shape of the vial using the positional feature for each of the plurality of images.

17. The method according to any one of claims 1 to 16, wherein at least one image is acquired while the tilt angle is changed by at least 45° from the upright and stationary position of the vial.

18. The method according to claim 17, wherein at least one image is obtained while the vial is tilted within 15° from the horizontal.

19. The method according to any one of claims 1 to 17, wherein the contents of the vial include a fluid.

20. The method according to any one of claims 1 to 19, wherein the vial includes a generally cylindrical lower region, an inwardly curved upper region connected to a capped neck, and a rounded bottom surface of the lower region, the inclination angle is adjusted so that a portion of the boundary region extends along the bottom surface.

21. The method according to claim 20, wherein the at least one image captures the boundary region through the optical irregularity of the bottom surface.

22. The method according to any one of claims 1 to 21, wherein determining the use of the contents of the vial includes determining an adjustment to the amount of fluid in the vial in order to compensate for the difference between the target position and the positional characterization of the boundary region.

23. The method according to any one of claims 1 to 22, comprising manipulating the vial to a new position in accordance with the determined use.

24. The method according to claim 23, wherein the new position returns the vial to an upright position.

25. A method for evaluating the fluid contents of a vial containing a pharmaceutical ingredient, wherein the method is: Receiving at least one image of the vial, wherein the at least one image is an image of the vial while it is tilted to position a portion of the boundary layer of the fluid contents beneath a labeled portion of the vial surface. Using computerized image processing, the position of the boundary layer extending along the bottom surface of the vial is compared with a target position corresponding to the target amount of fluid in the vial and the inclination angle of the vial. A method comprising automatically determining whether to use or reject the contents of the vial in an automated preparation of a pharmaceutical product, in accordance with the results of the comparison described above.

26. The method according to claim 19, wherein the fluid contents include a solvent in which the pharmaceutical component is dissolved.

27. The method according to any one of claims 19 to 26, wherein the comparison includes determining the liquid volume of the contents and comparing the determined volume with the target liquid volume of the contents.

28. The method according to claim 27, wherein determining the volume includes measuring at least one parameter of the geometric shape of the vial using the at least one image of the vial.

29. A method for evaluating the contents of a vial, wherein the contents include a pharmaceutical ingredient, and the method is Manipulating the vial to change its tilt angle, During the period in which the tilt angle is changed, at least one image of the vial is acquired. The presence or absence of a fluid boundary region in at least one of the images is detected by image processing using a processing circuit, A method comprising automatically determining whether to use or reject the contents of the vial in an automated preparation of a pharmaceutical product, in accordance with the results of the aforementioned detection.

30. The method according to claim 29, wherein the inclination angle is selected to position the fluid boundary region to extend along a surface region of the vial that is located above or below the label of the vial when the vial is upright, when the contents of the vial contain a targeted volume of fluid.

31. The method according to claim 30, wherein the surface region is located below the label of the vial and extends along the bottom surface of the vial.

32. A system for evaluating the contents of a vial containing pharmaceutical components, the system comprising a processing circuit and a memory, the memory being connected to the processing circuit, Controlling the manipulator to change the inclination angle of the vial with respect to the upper boundary layer of the vial contents, Accessing at least one image of the vial acquired during the period in which the tilt angle is changed, To calculate the positional characterization of the boundary region of the vial contents in at least one of the aforementioned images, The comparison involves comparing the positional characterization of the boundary region with the target position, wherein the target position takes into account the shift of the boundary region caused by the inclination angle. A system including commands to instruct the system to use or reject the vial contents in the automated preparation of pharmaceutical products, in accordance with the results of the comparison described above.

33. The system according to claim 32, comprising the manipulator.

34. The system according to claim 32, comprising an imaging device, wherein the command instructs a processing circuit to control the imaging device to acquire at least one image of the vial.

35. A system for evaluating the contents of a vial containing pharmaceutical ingredients, wherein the system is A manipulator configured to hold the vial at a variably selectable inclination angle relative to the upright orientation of the vial, An imaging device positioned relative to the manipulator to image the vial while it is held at an inclined angle with respect to the upright orientation, including viewing the bottom surface of the vial; It comprises a processing circuit and a memory for storing instructions, and the instructions are transmitted to the processing circuit. Controlling the manipulator to change the inclination angle of the vial relative to the upright orientation, Controlling the imaging device to acquire at least one image of the vial during the period in which the tilt angle is changed, To calculate the positional characterization of the boundary region of the vial contents in at least one of the aforementioned images, The comparison involves comparing the positional characterization of the boundary region with the target position, wherein the target position takes into account the shift of the boundary region caused by the inclination angle. A system including commands to instruct the system to use or reject the vial contents in the automated preparation of pharmaceutical products, in accordance with the results of the comparison described above.

36. A method for controlling the dissolution of a solute in a solvent within a vial, wherein the vial is held by a vial holder in a pharmaceutical preparation device, and the method is The vial holder is stirred by a stirrer operably connected to the vial holder, thereby shaking the solute and solvent in the vial held by the vial holder. The processing circuit accesses at least one image of the vial contents captured after the stirring has started, The image processing performed by the aforementioned processing circuit evaluates the characteristics of the vial contents, The evaluated features are compared with the targeted features of the vial contents, A method comprising adjusting the stirring by the stirrer according to the results of the comparison performed by the processing circuit.

37. The method according to claim 36, wherein the adjustment includes stopping the stirring.

38. The method according to claim 36, wherein the adjustment includes restarting stirring.

39. The method according to claim 36, wherein the adjustment includes modifying at least one parameter of the stirring motion.

40. The method according to any one of claims 36 to 39, wherein the solute is a solid.

41. The method according to any one of claims 36 to 40, wherein the solvent is a fluid.

42. The method according to claim 36, wherein the evaluated feature evaluates the dissolution of the solute in the solvent, the targeted feature of the vial contents includes a dissolution appearance criterion, and the adjustment includes stopping or extending the operating period of the stirrer.

43. The method according to claim 42, wherein the adjustment includes stopping the operation of the stirrer and issuing a warning while the targeted dissolution appearance criterion remains unmet.

44. The method according to claim 42, wherein the adjustment includes extending the operation of the stirrer while the targeted dissolution appearance criterion remains unmet.

45. The aforementioned dissolution appearance criteria are: The transparency of the aforementioned solvent, The color of the solvent, and The method according to claim 42, comprising at least one measure of the clarity of the solvent.

46. The method according to claim 45, wherein the dissolution appearance criterion includes a measurement of the color of the solvent, selected according to the type of solute.

47. The method according to claim 36, wherein the evaluated features evaluate the adhesion of the solute, the targeted features of the solvent in the vial include adhesion appearance criteria, and the adjustment includes modifying parameters governing the movement pattern of the stirrer.

48. The aforementioned movement pattern is, amplitude, acceleration, The rotation of the vial, and The method according to claim 47, wherein the vial is adjusted in at least one of the geometric shapes of the path along which it moves.

49. The method according to claim 36, wherein the evaluated feature evaluates the presence of foreign particles in the solvent, the targeted feature of the vial contents includes a criterion for the presence of foreign particles, the adjustment includes stopping stirring, and the processing circuit issues a warning according to the result of the comparison.

50. The method according to claim 36, wherein the evaluated feature evaluates the presence of foreign particles in the solvent, the targeted feature of the vial contents includes a criterion for the presence of foreign particles, the adjustment includes stopping stirring, and the processing circuit issues a warning according to the result of the comparison.

51. The method according to claim 36, wherein the evaluated feature evaluates the volume of the contents of the vial, the targeted feature of the solvent in the vial contains an expected amount of the contents of the vial, the adjustment includes stopping stirring, and the processing circuit issues a warning according to the result of the comparison.

52. The method according to any one of claims 36 to 51, wherein at least one of evaluating and comparing the features includes classifying the at least one image according to a pre-trained machine learning model.

53. The method according to claim 36, wherein the adjustment includes adjusting the stirring of at least the second vial in accordance with the results of the comparison.

54. The method according to claim 53, wherein the adjustment is made according to the plurality of results of each of the plurality of comparisons.

55. The method according to claim 36, wherein the at least one image of the vial contents is taken from a position below the vial.

56. A system for controlling the dissolution of a solute in a solvent within a vial, wherein the vial is held by a vial holder in a pharmaceutical preparation device, and the system is Control a stirrer operably connected to the vial holder, thereby shaking the solute and solvent in the vial held by the vial holder. Access at least one image of the vial contents captured after the agitation has started, The characteristics of the vial contents are evaluated, The evaluated features are compared with the targeted features of the solvent in the vial. A system comprising a processing circuit configured to adjust the stirring of the agitator according to the results of the comparison.

57. The system according to claim 56, wherein the evaluated feature evaluates the dissolution of the solute in the solvent, the targeted feature of the solvent in the vial includes a dissolution appearance criterion, and the processing circuit adjusts the stirring by stopping or extending the operating period of the stirrer.

58. The system according to claim 56, wherein the evaluated features evaluate the adhesion of the solute, the targeted features of the solvent in the vial include adhesion appearance criteria, and the processing circuit adjusts stirring by modifying parameters that govern the movement pattern of the stirrer.

59. The system according to claim 56, wherein the evaluated feature evaluates the presence of foreign particles in the solvent, the targeted feature of the solvent in the vial includes a criterion for the presence of foreign particles, the processing circuit adjusts the stirring by stopping the stirring, and the processing circuit issues a warning according to the result of the comparison.

60. The system according to claim 56, wherein the evaluated feature evaluates the presence of foreign particles in the solvent, the targeted feature of the solvent in the vial includes a criterion for the presence of foreign particles, the processing circuit adjusts the stirring by stopping the stirring, and the processing circuit issues a warning according to the result of the comparison.

61. The system according to claim 56, wherein the evaluated feature evaluates the volume of solvent in the vial, the targeted feature of the solvent in the vial contains the expected amount of solvent in the vial, the processing circuit adjusts the stirring by stopping the stirring, and the processing circuit issues a warning according to the result of the comparison.

Images