System and method for fluoroscopic image based analyis of in-VIVO fluid injections

Abstract

Disclosed herein are system and method embodiments for fluoroscopic image based analysis of in-vivo fluid injections. For example, the method includes: obtaining a fluoroscopic image of an injection site, the fluoroscopic image including a matrix including a plurality of elements, and each element of the matrix including an intensity value; processing the fluoroscopic image to generate a prediction score for each element including a prediction of whether that element includes a fluid delivery depot location; providing a total area of the fluid delivery depot location, the total area of the fluid delivery depot location being determined based on the prediction score for each element of the plurality of elements; generating, based on the total area, at least one predicted parameter associated with the injection; and providing the at least one predicted parameter associated with the injection as a delivery characteristic.

Description

SYSTEM AND METHOD FOR FLUOROSCOPIC IMAGE BASED ANALYIS OF IN- VIVO FLUID INJECTIONSBACKGROUND OF THE INVENTIONField

[0001] The present disclosure relates to a device and a method for analyzing in-vivo fluid injections using fluoroscopic images of injection sites.Description of Related Art

[0002] Wearable medical devices, such as automatic injectors, have a benefit of providing therapy to a patient at a location remote from a clinical facility and / or while being worn discretely under the patient’s clothing. A wearable medical device can be applied to the patient’s skin and configured to automatically deliver a dose of a pharmaceutical composition within a predetermined time period after applying the wearable medical device to the patient’s skin, such as after a 27 hour delay, and / or the like. After the device delivers the pharmaceutical composition to the patient, the patient may subsequently remove and dispose of the device.

[0003] Human subcutaneous tissue is composed of various cell types, extracellular matrix (ECM) constituents, microstructures, and macroscopic arrangements of cells and ECM. These elements contribute to the mechanical properties of the tissue. The tissue may also be composed of lymphatic system and blood vessels, as well as have some intrinsic fluid absorption and retention properties. These characteristics may vary among individuals and locations within the body, and over time they may cause variable degrees of resistance to the infusion of fluids at the injection site. For example, a flow of fluid leaving an infusion device may be impaired by an area of tissue with a high degree of resistance, which can lead to increased pressure in the fluid line of the device, as well as reduced diffusion and dispersal characteristics of the delivery fluid.SUMMARY OF THE INVENTION

[0004] Accordingly, provided are improved systems, devices, products, apparatus, and / or methods for fluoroscopic image based analysis of fluid injections for a drug delivery device.

[0005] According to some non-limiting embodiments or aspects, provided is a method, including: obtaining, with at least one processor, a fluoroscopic image of an injection site for an injection of a fluid on a body of a patient, wherein the fluoroscopic image includes a matrixincluding a plurality of elements, and wherein each element of the matrix includes an intensity value; processing, with the at least one processor, the fluoroscopic image to generate a prediction score for each element of the plurality of elements, wherein the prediction score includes a prediction of whether that element includes a fluid delivery depot location in the body of the patient; providing, with the at least one processor, a total area of the fluid delivery depot location in the body of the patient, wherein the total area of the fluid delivery depot location in the body of the patient is determined based on the prediction score for each element of the plurality of elements; generating, with the at least one processor, based on the total area of the fluid delivery depot location in the body of the patient, at least one predicted parameter associated with the injection of the fluid in the body of the patient; and providing, with the at least one processor, the at least one predicted parameter associated with the injection of the fluid in the body of the patient as a delivery characteristic of the injection.

[0006] In some non-limiting embodiments or aspects, the prediction score for each element further includes a prediction of whether that element includes a diffused region or an undiffused region within the total area of the fluid delivery depot.

[0007] In some non-limiting embodiments or aspects, the prediction score for each element further includes an estimated concentration of the fluid associated with that element, and wherein the method further comprises: providing, with the at least one processor, a total estimated concentration of the fluid in the fluid delivery depot location in the body of the patient, wherein the total estimated concentration of the fluid in the fluid delivery depot location in the body of the patient is determined based on the prediction score for each element of the plurality of elements.

[0008] In some non-limiting embodiments or aspects, the at least one parameter includes a volume of the fluid delivery depot location in the body of the patient, and wherein the volume of the fluid delivery depot location in the body of the patient is determined based on the total area of the fluid delivery depot location in the body of the patient, the total concentration of the fluid in the fluid delivery depot location in the body of the patient, and a known volume of the fluid delivered in the injection.

[0009] In some non-limiting embodiments or aspects, the fluoroscopic image includes a plurality of fluoroscopic images of the injection site captured over a period of time, wherein the at least one parameter includes at least one of an absorption rate of the fluid, a diffusion rate of the fluid, or any combination thereof, and wherein the at least one of the absorption rate of the fluid, the diffusion rate of the fluid, or any combination thereof is determined based on the volume or dispersion of the fluid delivery depot location in the body of the patient over theperiod of time and a measured pressure in a fluid delivery line of a drug delivery device over the period of time.

[0010] In some non-limiting embodiments or aspects, the fluoroscopic image includes a plurality of fluoroscopic images of the injection site captured over a period of time, wherein the at least one parameter includes a fluidic resistance of tissue in the body of the patient to the fluid, and wherein the fluidic resistance of the tissue in the body of the patient to the fluid is determined based on the volume of the fluid delivery depot location in the body of the patient over the period of time and a measured pressure in a fluid delivery line of a drug delivery device over the period of time.

[0011] In some non-limiting embodiments or aspects, the fluoroscopic image includes a plurality of fluoroscopic images of the injection site captured over a period of time, wherein the at least one parameter includes an inferred delivery pressure in the tissue in the body of the patient over the period of time, and wherein the inferred delivery pressure in the tissue in the body of the patient is determined based on the volume of the fluid delivery depot location in the body of the patient over the period of time and a known flow rate of the fluid delivery over the period of time.

[0012] In some non-limiting embodiments or aspects, the fluoroscopic image includes a plurality of fluoroscopic images of the injection site captured over a period of time, wherein the at least one parameter includes an inferred tissue resistance in the tissue in the body of the patient, and wherein the inferred tissue resistance in the tissue in the body of the patient is determined based on the inferred delivery pressure over the period of time in the tissue in the body of the patient and a known flow rate of the delivery.

[0013] In some non-limiting embodiments or aspects, the method further includes: delivering, with a drug delivery device, the fluid to the body of the patient at the injection site, wherein the drug delivery device includes at least one component having known dimensions; capturing, with a fluoroscopic image capture device, the fluoroscopic image of the injection site for the fluid on the body of the patient, wherein the fluoroscopic image includes the at least one component having the known dimensions; and scaling, with the at least one processor, based on the known dimensions of the at least one component, the fluoroscopic image.

[0014] In some non-limiting embodiments or aspects, the method further includes: controlling, with the at least one processor, during the injection of the fluid in the body of the patient with a drug delivery device, the drug delivery device to adjust a delivery rate of the fluid to the patient.

[0015] According to some non-limiting embodiments or aspects, provided is a system, including: at least one processor programmed and / or configured to: obtain a fluoroscopic image of an injection site for an injection of a fluid on a body of a patient, wherein the fluoroscopic image includes a matrix including a plurality of elements, and wherein each element of the matrix includes an intensity value; process the fluoroscopic image to generate a prediction score for each element of the plurality of elements, wherein the prediction score includes a prediction of whether that element includes a fluid delivery depot location in the body of the patient; provide a total area of the fluid delivery depot location in the body of the patient, wherein the total area of the fluid delivery depot location in the body of the patient is determined based on the prediction score for each element of the plurality of elements; generate, based on the total area of the fluid delivery depot location in the body of the patient, at least one predicted parameter associated with the injection of the fluid in the body of the patient; and provide the at least one predicted parameter associated with the injection of the fluid in the body of the patient as a delivery characteristic of the injection.

[0016] In some non-limiting embodiments or aspects, the prediction score for each element further includes a prediction of whether that element includes a diffused region or an undiffused region within the total area of the fluid delivery depot.

[0017] In some non-limiting embodiments or aspects, the prediction score for each element further includes an estimated concentration of the fluid associated with that element, and wherein the at least one processor is further programmed and / or configured to: provide total estimated concentration of the fluid in the fluid delivery depot location in the body of the patient, wherein the total estimated concentration of the fluid in the fluid delivery depot location in the body of the patient is determined based on the prediction score for each element of the plurality of elements.

[0018] In some non-limiting embodiments or aspects, the at least one parameter includes a volume of the fluid delivery depot location in the body of the patient, and wherein the volume of the fluid delivery depot location in the body of the patient is determined based on the total area of the fluid delivery depot location in the body of the patient, the total concentration of the fluid in the fluid delivery depot location in the body of the patient, and a known volume of the fluid delivered in the injection.

[0019] In some non-limiting embodiments or aspects, the fluoroscopic image includes a plurality of fluoroscopic images of the injection site captured over a period of time, wherein the at least one parameter includes at least one of an absorption rate of the fluid, a diffusion rate of the fluid, or any combination thereof, and wherein the at least one of the absorption rateof the fluid, the diffusion rate of the fluid, or any combination thereof is determined based on the volume or dispersion of the fluid delivery depot location in the body of the patient over the period of time and a measured pressure in a fluid delivery line of a drug delivery device over the period of time.

[0020] In some non-limiting embodiments or aspects, the fluoroscopic image includes a plurality of fluoroscopic images of the injection site captured over a period of time, wherein the at least one parameter includes a fluidic resistance of tissue in the body of the patient to the fluid, and wherein the fluidic resistance of the tissue in the body of the patient to the fluid is determined based on the volume of the fluid delivery depot location in the body of the patient over the period of time and a measured pressure in a fluid delivery line of a drug delivery device over the period of time.

[0021] In some non-limiting embodiments or aspects, the fluoroscopic image includes a plurality of fluoroscopic images of the injection site captured over a period of time, wherein the at least one parameter includes an inferred delivery pressure in the tissue in the body of the patient over the period of time, and wherein the inferred delivery pressure in the tissue in the body of the patient is determined based on the volume of the fluid delivery depot location in the body of the patient over the period of time and a known flow rate of the fluid delivery over the period of time.

[0022] In some non-limiting embodiments or aspects, the fluoroscopic image includes a plurality of fluoroscopic images of the injection site captured over a period of time, wherein the at least one parameter includes an inferred tissue resistance in the tissue in the body of the patient, and wherein the inferred tissue resistance in the tissue in the body of the patient is determined based on the inferred delivery pressure over the period of time in the tissue in the body of the patient and a known flow rate of the delivery.

[0023] In some non-limiting embodiments or aspects, the system further includes: a drug delivery device configured to deliver the fluid to the body of the patient at the injection site, wherein the drug delivery device includes at least one component having known dimensions; a fluoroscopic image capture device configured to capture the fluoroscopic image of the injection site for the fluid on the body of the patient, wherein the fluoroscopic image includes the at least one component having the known dimensions, wherein the at least one processor is further programmed and / or configured to: scale, based on the known dimensions of the at least one component, the fluoroscopic image.

[0024] In some non-limiting embodiments or aspects, the at least one processor is further programmed and / or configured to: control, during the injection of the fluid in the body of thepatient with a drug delivery device, the drug delivery device to adjust a delivery rate of the fluid to the patient.BRIEF DESCRIPTION OF THE DRAWINGS

[0025] The above-mentioned and other features and advantages of this disclosure, and the manner of attaining them, will become more apparent and the disclosure itself will be better understood by reference to the following descriptions of embodiments of the disclosure taken in conjunction with the accompanying drawings, wherein:

[0026] FIG. 1A is a diagram of non-limiting embodiments or aspects of an environment in which systems, devices, products, apparatus, and / or methods, described herein, may be implemented;

[0027] FIG. IB is a perspective view of a drug delivery device according to one aspect or embodiment of the present disclosure;

[0028] FIG. 2 is a perspective view of the drug delivery device of FIG. 1, with a top cover removed;

[0029] FIG. 3 is a schematic of the drug delivery device of FIG. 1;

[0030] FIG. 4 is a flow chart of a process for fluoroscopic image based analysis of in-vivo fluid injections according to non-limiting embodiments or aspects of the present disclosure;

[0031] FIG. 5 is an example fluoroscopic image of an injection site on a body of a patient;

[0032] FIG. 6 is an example computer system useful for implementing various embodiments.

[0033] Corresponding reference characters indicate corresponding parts throughout the several views. The exemplifications set out herein illustrate exemplary embodiments of the disclosure, and such exemplifications are not to be construed as limiting the scope of the disclosure in any manner.DESCRIPTION OF THE INVENTION

[0034] Spatial or directional terms, such as “left”, “right”, “inner”, “outer”, “above”, “below”, and the like, are not to be considered as limiting as aspects or embodiments of the present disclosure can assume various alternative orientations.

[0035] All numbers used in the specification and claims are to be understood as being modified in all instances by the term “about”. By “about” is meant a range of plus or minus ten percent of the stated value. As used in the specification and the claims, the singular form of “a”, “an”, and “the” include plural referents unless the context clearly dictates otherwise. The terms “first”, “second”, and the like are not intended to refer to any particular order orchronology, but instead refer to different conditions, properties, or elements. By “at least” is meant “greater than or equal to”.

[0036] As used herein, the terms “communication” and “communicate” may refer to the reception, receipt, transmission, transfer, provision, and / or the like of information (e.g., data, signals, messages, instructions, commands, and / or the like). For one unit (e.g., a device, a system, a component of a device or system, combinations thereof, and / or the like) to be in communication with another unit means that the one unit is able to directly or indirectly receive information from and / or transmit information to the other unit. This may refer to a direct or indirect connection that is wired and / or wireless in nature. Additionally, two units may be in communication with each other even though the information transmitted may be modified, processed, relayed, and / or routed between the first and second unit. For example, a first unit may be in communication with a second unit even though the first unit passively receives information and does not actively transmit information to the second unit. As another example, a first unit may be in communication with a second unit if at least one intermediary unit (e.g., a third unit located between the first unit and the second unit) processes information received from the first unit and communicates the processed information to the second unit. In some non-limiting embodiments or aspects, a message may refer to a network packet (e.g., a data packet and / or the like) that includes data. It will be appreciated that numerous other arrangements are possible.

[0037] It will be apparent that systems and / or methods, described herein, can be implemented in different forms of hardware, software, or a combination of hardware and software. The actual specialized control hardware or software code used to implement these systems and / or methods is not limiting of the implementations. Thus, the operation and behavior of the systems and / or methods are described herein without reference to specific software code, it being understood that software and hardware can be designed to implement the systems and / or methods based on the description herein.

[0038] As used herein, the term “computing device” may refer to one or more electronic devices that are configured to directly or indirectly communicate with or over one or more networks. A computing device may be a mobile or portable computing device, a desktop computer, a server, and / or the like. Furthermore, the term “computer” may refer to any computing device that includes the necessary components to receive, process, and output data, and normally includes a display, a processor, a memory, an input device, and a network interface. A “computing system” may include one or more computing devices or computers. An “application” or “application program interface” (API) refers to computer code or otherdata sorted on a computer-readable medium that may be executed by a processor to facilitate the interaction between software components, such as a client-side front-end and / or server-side back-end for receiving data from the client. An “interface” refers to a generated display, such as one or more graphical user interfaces (GUIs) with which a user may interact, either directly or indirectly (e.g., through a keyboard, mouse, touchscreen, etc.). Further, multiple computers, e.g., servers, or other computerized devices, such as an autonomous vehicle including a vehicle computing system, directly or indirectly communicating in the network environment may constitute a “system” or a “computing system”.

[0039] Provided are improved systems, devices, products, apparatus, and / or methods for fluoroscopic image based analysis of fluid injections for a drug delivery device.

[0040] Non-limiting embodiments or aspects of the present disclosure are directed to systems, methods, and computer program products for fluoroscopic image based analysis of fluid injections for a drug delivery device that obtain a fluoroscopic image of an injection site for an injection of a fluid on a body of a patient, wherein the fluoroscopic image includes a matrix including a plurality of elements, and wherein each element of the matrix includes an intensity value; process the fluoroscopic image to generate a prediction score for each element of the plurality of elements, wherein the prediction score includes a prediction of whether that element includes a fluid delivery depot location in the body of the patient; provide a total area of the fluid delivery depot location in the body of the patient, wherein the total area of the fluid delivery depot location in the body of the patient is determined based on the prediction score for each element of the plurality of elements; generate, based on the total area of the fluid delivery depot location in the body of the patient, at least one predicted parameter associated with the injection of the fluid in the body of the patient; and provide the at least one predicted parameter associated with the injection of the fluid in the body of the patient as a delivery characteristic of the injection.

[0041] In this way, non-limiting embodiments or aspects of the present disclosure may use image analysis techniques to relate fluoroscopic data to delivery volume, fluid density, and / or infusion resistance and / or pressures, thereby enabling analysis of delivery characteristics (e.g., delivery volume, diffusion / dispersal of a fluid or drug over time in the subcutaneous tissue resistance to fluid flow over time, etc.) of devices that deliver fluid into the subcutaneous tissue.

[0042] Referring now to FIG. 1A, FIG. 1A is a diagram of an example environment 100 in which systems, methods, products, apparatuses, and / or devices described herein, may be implemented. As shown in FIG. 1, environment 100 may include drug delivery device 10,fluoroscopic imaging system 102, image processing system 104, and / or communication network 106.

[0043] Drug delivery device 10 may be configured to deliver a fluid, such as dose of a pharmaceutical composition (e.g., any desired medicament), and / or the like into a body of a patient at an injection site on the body of the patient by a subcutaneous injection (e.g., at a slow, controlled injection rate, etc.). Drug delivery device 10 may include one or more devices capable of receiving information and / or data from fluoroscopic imaging system 102 and / or image processing system 104 (e.g., via communication network 106, etc.) and / or communicating information and / or data to fluoroscopic imaging system 102 and / or image processing system 104 (e.g., via communication network 106, etc.). For example, drug delivery device 10 may include a computing device, such as a microcontroller, a wireless transmitter / receiver, and / or other like devices. Further details regarding non-limiting embodiments or aspects of drug delivery device 10 are provided below with regard to FIGS. IB-3.

[0044] Fluoroscopic imaging system 102 may include a fluoroscopic image capture device configured to capture one or more fluoroscopic images of an injection site on a body of a patient. For example, fluoroscopic imaging system 102 may include equipment capable of acquiring cross sectional images of an injection site using techniques such as but not limited to impedance tomography, x-ray, computed tomography (CT), magnetic resonance imaging (MRI), ultrasound, and / or fluoroscopy. As an example, fluoroscopic imaging system 102 may include a CT scanner, a fluoroscope, an ultrasound scanner, a MRI scanner, any combination thereof, and / or the like. Fluoroscopic imaging system 102 may include one or more devices capable of receiving information and / or data from drug delivery device 10 and / or image processing system 104 (e.g., via communication network 106, etc.) and / or communicating information and / or data to drug delivery device 10 and / or image processing system 104 (e.g., via communication network 106, etc.). For example, fluoroscopic imaging system 102 may include a computing device, such as a server, a group of servers, and / or other like devices.

[0045] Image processing system 104 may include one or more devices capable of receiving information and / or data from drug delivery device 10 and / or fluoroscopic imaging system 102 (e.g., via communication network 106, etc.) and / or communicating information and / or data to drug delivery device 10 and / or fluoroscopic imaging system 102 (e.g., via communication network 106, etc.). For example, image processing system 104 may include a computing device, such as a server, a group of servers, and / or other like devices.

[0046] Communication network 106 may include one or more wired and / or wireless networks. For example, communication network 106 may include a cellular network (e.g., a long-term evolution (LTE) network, a third generation (3G) network, a fourth generation (4G) network, a fifth generation (5G) network a code division multiple access (CDMA) network, etc.), a public land mobile network (PLMN), a local area network (LAN), a wide area network (WAN), a metropolitan area network (MAN), a telephone network (e.g., the public switched telephone network (PSTN)), a private network, an ad hoc network, an intranet, the Internet, a fiber optic -based network, a cloud computing network, and / or the like, and / or a combination of these or other types of networks.

[0047] The number and arrangement of devices and systems shown in FIG. 1A is provided as an example. There may be additional devices and / or systems, fewer devices and / or systems, different devices and / or systems, or differently arranged devices and / or systems than those shown in FIG. 1A. Furthermore, two or more devices and / or systems shown in FIG. 1A may be implemented within a single device and / or system, or a single device and / or system shown in FIG. 1A may be implemented as multiple, distributed devices and / or systems. Additionally, or alternatively, a set of devices and / or systems (e.g., one or more devices or systems) of environment 100 may perform one or more functions described as being performed by another set of devices and / or systems of environment 100.

[0048] Referring now to FIGS. IB-3, drug delivery device 10 may include reservoir 12, power source 14, insertion mechanism 16, control electronics 18, cover 20, and / or base 22. In some non-limiting embodiments or aspects, drug delivery device 10 may be a wearable automatic injector, such as an insulin or bone marrow stimulant delivery device. Drug delivery device 10 may be mounted onto the skin of a patient and triggered to inject a pharmaceutical composition from reservoir 12 into the patient. Drug delivery device 10 may be pre-filled with the pharmaceutical composition, or drug delivery device 10 may be filled with the pharmaceutical composition by the patient or medical professional prior to use.

[0049] Drug delivery device 10 may be configured to deliver a dose of a pharmaceutical composition (e.g., any desired medicament) into the patient’ s body by a subcutaneous injection at a slow, controlled injection rate. Exemplary time durations for the delivery achieved by drug delivery device 10 may range from about 5 minutes to about 60 minutes, but are not limited to this exemplary range. Exemplary volumes of the pharmaceutical composition delivered by drug delivery device 10 may range from about 0.1 milliliters to about 10 milliliters, but are not limited to this exemplary range. The volume of the pharmaceutical composition delivered to the patient and / or the time duration for the delivery thereof may be adjusted.

[0050] Referring again to FIGS. 1-3, in some non-liming embodiments or aspects, power source 14 includes a DC power source including one or more batteries. Control electronics 18 may include microcontroller 24, sensing electronics 26, pump and valve controller 28, sensing electronics 30, and / or deployments electronics 32, which may control the actuation of the drug delivery device 10. Drug delivery device 10 may include a fluidics sub-system that includes reservoir 12, volume sensor 34 for reservoir 12, reservoir fill port 36, and / or metering system 38 including pump and valve actuator 40 and pump and valve mechanism 42. The fluidic subsystem may further include occlusion sensor 44, deploy actuator 46, cannula 48 for insertion into a patient’s skin, and / or fluid line 50 in fluid communication with reservoir 12 and cannula 48. In some non-limiting embodiments or aspects, occlusion sensor 44 includes a pressure sensor. In some non-limiting embodiments or aspects, insertion mechanism 16 is configured to move cannula 48 from a retracted position positioned entirely within drug delivery device 10 to an extended position where cannula 48 extends outside of drug delivery device 10. Drug delivery device 10 may operate in the same manner as discussed in U.S. Patent No. 10,449,292 to Pizzochero et al, the entire contents of which are incorporated herein by reference.

[0051] In some non-limiting embodiments or aspects, a fluid pathway is formed by reservoir 12, pump and valve mechanism 42 downstream of reservoir 12, and fluid line 50 downstream of pump and valve mechanism 42. For example, reservoir 12 may be configured to receive a fluid, and pump and valve mechanism 42 may be configured to deliver the fluid from reservoir 12 to fluid line 50.

[0052] Referring now to FIG. 4, FIG. 4 is a flowchart of non-limiting embodiments or aspects of a process 400 for fluoroscopic image based analysis of in-vivo fluid injections. In some non-limiting embodiments, one or more of the steps of process 400 can be performed (e.g., completely, partially, etc.) by image processing system 104 (e.g., one or more devices of image processing system 104). In some non-limiting embodiments or aspects, one or more of the steps of process 400 can be performed (e.g., completely, partially, etc.) by another device or a group of devices separate from or including image processing system 104, such as fluoroscopic imaging system 102 (e.g., one or more devices of fluoroscopic imaging system 102), and / or drug delivery device 10 (e.g., one or more devices of a system of drug delivery device 10).

[0053] As shown in FIG. 4, at step 402, process 400 includes obtaining a fluoroscopic image of an injection site for a fluid on a body of a patient. For example, image processing system 104 may obtain a fluoroscopic image of an injection site for a fluid on a body of a patient. As an example, the fluoroscopic image capture device of fluoroscopic imaging system 102 may capture the fluoroscopic image of the injection site for the fluid on the body of the patient. Insuch an example, fluoroscopic imaging system 102 may provide the fluoroscopic image to image processing system 104.

[0054] Referring also to FIG. 5, which is an example fluoroscopic image of an injection site on a body of a patient, a fluoroscopic image of an injection site for a fluid on a body of a patient may include the body of the patient surrounding the injection site and / or components of an injection device (e.g., components of drug delivery device 10, etc.) used to deliver the fluid to the patient. In such an example, and as also shown in FIG. 5, the fluoroscopic image may include fluoroscopy image data of a fluid delivery depot formed in the subcutaneous tissue of the patient during and / or after an in-vivo injection of the fluid.

[0055] In some non-limiting embodiments or aspects, the fluoroscopic image may include a plurality of fluoroscopic images captured over a period of time. For example, the fluoroscopic image capture device of fluoroscopic imaging system 102 may capture and / or the fluoroscopic image may include at least one of the following: one or more images of the injection site for the fluid on the body of the patient before the injection device (e.g., drug delivery device 10, etc.) is applied to the injection site (e.g., one or more images without the injection device, etc.), one or more images of the injection site for the fluid on the body of the patient after the injection device (e.g., drug delivery device 10, etc.) is applied to the injection site but before the injection device is used to deliver the fluid to the patient (e.g., before fluid delivery is initiated, etc.), one or more images of the injection site for the fluid on the body of the patient during the in-vivo injection of the fluid (e.g., a continuous series of images of the injection site over the course of the delivery of the fluid to the patient, etc.), one or more images of the injection site for the fluid on the body of the patient after the in-vivo injection of the fluid is completed and / or after the injection device is removed, or any combination thereof.

[0056] A fluoroscopic image may include a matrix (e.g., a grid, a rectangular array, a multidimensional grid, a multi-dimensional array, a set of rows and columns, etc.) that has a plurality of elements (e.g., units, cells, pixels, etc.). Each element of the matrix may include an intensity value associated with the image. For example, each element of a fluoroscopic image may be associated with three dimensions. As an example, a first dimension of an element may be a width of the element, a second dimension of the element may be a length of the element, and a third dimension of the element may be a value associated with the intensity or image data of the element.

[0057] In some non-limiting embodiments or aspects, a size and / or a location of one or more elements of a matrix of an image and a size and / or a location of one or more elements of a matrix of another image correspond to a same size and / or a same location of the subject matterof the image in the real world. For example, a first location of one or more elements in a matrix of a first image may represent a subject matter in the real world and a second location of one or more elements in a matrix of a second image may represent the same subject matter in the real world.

[0058] In some non-limiting embodiments, a size and / or a location of one or more elements of a matrix of an image and a size and / or a location of one or more elements of a matrix of another image correspond to a different size and / or a different location of the subject matter of the image in the real world. For example, a first location of one or more elements in a matrix of a first image may represent a subject matter in the real world and a second location of one or more elements in a matrix of a second image may represent different subject matter in the real world.

[0059] In some non-limiting embodiments or aspects, the size of an element of the matrix corresponds to the size of the subject matter of the image based on a scale (e.g., the ratio of the size of an element to the corresponding size in the real world) of the image. For example, the size of one element corresponds to a shape with a predetermined dimension (e.g., a .1 m by .1 m square, a 1 m by 1 m square, a triangle with sides having a length of .1 m, etc.) in the real world. As an example, known dimensions of a pressure sensor (e.g., occlusion sensor 44 as shown in FIG. 5, etc.) and / or another component included in drug delivery device 10, which may be used to deliver the fluid to the body of the patient at the injection site, may be captured in the fluoroscopic image of the injection site and used to set the scale for the fluoroscopic image (e.g., the fluoroscopic image may be scaled based on the known dimensions of the component included in the drug delivery device 10 and captured in the image, etc.). In such an example, the pressure sensor (e.g., occlusion sensor 44 as shown in FIG. 5, etc.) may be positioned or located in drug delivery device 10 such that the fluoroscopic image of the injection site on the body of the patient includes the pressure sensor adjacent or proximate to the injection site in the image (e.g., as shown in FIG. 5, etc.).

[0060] As shown in FIG. 4, at step 404, process 400 includes processing the fluoroscopic image to identify a fluid delivery depot in the body of the patient. For example, image processing system 104 may process the fluoroscopic image to identify a fluid delivery depot in the body of the patient. As an example, image processing system 104 may process the fluoroscopic image to generate a prediction score for each element of the plurality of elements of the fluoroscopic image. In such an example, a prediction score may include a prediction of whether an element includes a fluid delivery depot location in the body of the patient. In such an example, the prediction score for each element (e.g., for each element predicted to includea fluid delivery depot location, etc.) may further include an estimated concentration of the fluid at that fluid delivery depot location in the body of the patient.

[0061] Image processing system 104 may scale the fluoroscopic image based on known dimensions of a pressure sensor (e.g., occlusion sensor 44, etc.) and / or another component included in drug delivery device 10 that is captured in the fluoroscopic image. For example, a pixel dimension (e.g., a pixel width, a pixel height, etc.) of the pressure sensor and / or other component in the image may be correlated with the known dimensions of the pressure sensor and / or the other component, and based on this correlation and a pixel dimension (e.g., a pixel width, a pixel height, etc.) of other subject matter in the image (e.g., a diffused region, a delivered fluid area, etc.), the size of the other subject matter in the real world may be determined. As an example, drug delivery device 10 may deliver the fluid to the body of the patient at the injection site, the drug delivery device including at least one component having known dimensions, and a fluoroscopic image capture device of fluoroscopic imaging system 102 may capture the fluoroscopic image(s) of the injection site for the fluid on the body of the patient, the fluoroscopic image including the at least one component having the known dimensions. In such an example, image processing system 104 may scale, based on the known dimensions of the at least one component, the fluoroscopic image(s).

[0062] Image processing system 104 may process the fluoroscopic image by comparing the intensity value of each element to one or more threshold intensity values to generate the prediction of whether that element includes a fluid delivery depot location in the body of the patient. For example, differences in pixel intensity in a fluoroscopic image may be used to distinguish between delivered fluid and biological tissue. As an example, the one or more threshold intensity values may be determined based on intensity values of one or more historical or training images. In such an example, an element associated with an intensity value that satisfies the one or more threshold intensity values may be predicted to include a fluid delivery location in the body of the patient, and another element associated with another intensity value that fails to satisfy the one or more threshold intensity values may be predicted to not include a fluid delivery location in the body of the patient (e.g., to include biological tissue without delivered fluid, etc.).

[0063] Image processing system 104 may process the fluoroscopic images using an interpolation (e.g., a linear interpolation, etc.) between a first known pixel intensity associated with a first element or area (e.g., a first element or area having a maximum concentration of the fluid, such as at an element or area known to have a pure depot, etc.) and a second known pixel intensity associated with a second element or area (e.g., a second element or area havinga minimum concentration of the fluid, such as at an element or area in the biological tissue known to not include the fluid delivery depot, etc.) to determine an estimated concentration of the fluid at each other element or area. For example, image processing system 104 may apply or plot the intensity value of an element or area to the interpolation to generate the estimated concentration of the fluid associated with that element or area. As an example, a local depot concentration may be estimated from pixel intensity as a linear or other type of interpolation between maximum concentration at a site known to have pure depot and minimum concentration in the tissue.

[0064] In some non-limiting embodiments or aspects, image processing system 104 generates the prediction scores based on a machine learning technique (e.g., a pattern recognition technique, a data mining technique, a heuristic technique, a supervised learning technique, an unsupervised learning technique, etc.). For example, image processing system 104 may generate a model (e.g., an estimator, a classifier, a prediction model, a fluid depot location prediction model, etc.) based on a machine learning algorithm (e.g., a decision tree algorithm, a gradient boosted decision tree algorithm, a neural network algorithm, a convolutional neural network algorithm, etc.). In such an example, image processing system 104 may generate the prediction scores using the model.

[0065] Image processing system 104 may generate the model based on training data including one or more training images of one or more injection sites for one or more fluids on one or more bodies of one or more patients. For example, the model may be designed to receive, as an input, image data associated with the one or more images (e.g., intensities of elements of the one or more images, etc.), and provide, as an output, a prediction (e.g., a probability, a binary output, a yes-no output, a score, a prediction score, etc.) as to whether the one or more images (e.g., the entire image, an area of the image, an element of the image, etc.) includes one or more fluid delivery locations and / or an estimated concentration of the fluid at the one or more fluid delivery locations (e.g., an estimated concentration of the entire image, an estimated concentration of an area of the image, an estimated concentration of an element of the image, etc.). As an example, image processing system 104 may analyze the training data using machine learning techniques to generate the model (e.g., a prediction model). The machine learning techniques may include, for example, supervised and / or unsupervised techniques, such as decision trees (e.g., gradient boosted decision trees), logistic regressions, artificial neural networks (e.g., convolutional neural networks), Bayesian statistics, learning automata, Hidden Markov Modeling, linear classifiers, quadratic classifiers, association rule learning, and / or the like. In some non-limiting embodiments or aspects, image processingsystem 104 generates or trains the model using the machine learning techniques to optimize an objective or loss function (e.g., an objective or loss function that depends on an output of the model and one or more labels for the entire image, an area of the image, an element of the image, etc.). In some non-limiting embodiments or aspects, image processing system 104 stores the trained model (e.g., stores the trained model for later use). In some non-limiting embodiments or aspects, image processing system 104 stores the trained model in a data structure (e.g., a database, a linked list, a tree, etc.). In some non-limiting embodiments or aspects, the data structure is located within image processing system 104 or external (e.g., remote from) image processing system 104.

[0066] As shown in FIG. 4, at step 406, process 400 includes determining a total area and / or an estimated concentration of the fluid delivery depot. For example, image processing system 104 may determine a total area and / or an estimated concentration of the fluid delivery depot. As an example, image processing system 104 may provide or output the total area and / or the estimated concentration of the fluid delivery depot.

[0067] Image processing system 104 may determine, based on the prediction score for each element of the plurality of elements, the total area of the fluid delivery depot location in the body of the patient. For example, image processing system 104 may aggregate each element predicted to include a fluid delivery location in the body of the patient and scale the aggregated elements as described herein to determine the total area of the fluid delivery location in the body of the patient. In such an example, image processing system 104 may provide or output the total area of the fluid delivery depot location in the body of the patient.

[0068] Referring again to FIG. 5, in some non-limiting embodiments or aspects, image processing system 104 may determine an area of a diffused region within a total area of the fluid delivery depot. For example, image processing system 104 may determine, based on the prediction score for each element of the plurality of elements predicted to include a fluid delivery location in the body of the patient, a first depot area including elements associated with darker or lower intensity values (e.g., satisfies a first intensity threshold, etc.) as an undiffused or concentrated fluid area and a second depot area including elements associated with lighter or higher intensity values (e.g., satisfies a second intensity threshold higher than the first intensity threshold, etc.) as a diffused fluid area. As an example, a ratio of the diffused fluid area to the total area of the fluid delivery depot (and / or a ratio of the undiffused area to the total area of the fluid delivery depot) for correlation to characteristics of a delivery pressure profile are described herein below in more detail. In such an example, the prediction score for eachelement may further include the prediction of whether that element includes a diffused region or an undiffused region within the total area of the fluid delivery depot.

[0069] In some non-limiting embodiments or aspects, the prediction score for each element further includes an estimated concentration of the fluid associated with that element. For example, image processing system 104 may determine, based on the prediction score for each element of the plurality of elements, a total estimated concentration (e.g., an overall concentration, an average concentration, etc.) of the fluid in the fluid delivery depot location in the body of the patient. For example, image processing system 104 may aggregate and / or average the estimated concentration of each element predicted to include a fluid delivery location in the body of the patient and divide the aggregated and / or averaged concentration by the total area of the fluid delivery location to determine the total estimated concentration of the fluid in the fluid delivery depot location in the body of the patient. In such an example, image processing system 104 may provide or output the estimated concentration of the fluid in the fluid delivery depot location in the body of the patient.

[0070] As shown in FIG. 4, at step 408, process 400 includes generating at least one predicted parameter associated with the injection of the fluid in the body of the patient based on the total area of the fluid delivery depot location in the body of the patient. For example, image processing system 104 may generate at least one predicted parameter associated with the injection of the fluid in the body of the patient based on the total area of the fluid delivery depot location in the body of the patient. As an example, the at least one parameter may include at least one of the following parameters: a volume of the fluid delivery depot location in the body of the patient, an absorption rate of the fluid in the body of the patient (e.g., an absorption rate of the fluid into the bloodstream of the patient, etc.), a diffusion or dispersion rate of the fluid in the body of the patient (e.g., a movement rate of the fluid from a region of higher concentration to a region of lower concentration, etc.), a fluidic resistance of tissue in the body of the patient to the fluid, an inferred delivery pressure in the tissue in the body of the patient over a period of time, an inferred tissue resistance in the tissue in the body of the patient, or any combination thereof. For example, image processing system 104 may use imaging processing techniques on 2-D fluoroscopic data to distinguish between radiopaque delivery solutions and biological tissue, thereby enabling assessment of properties of the biological tissue to absorb fluid, the tissue’s resistance to fluid flow, and how the tissue’s properties relate to infusion pressure.

[0071] Image processing system 104 may determine a volume of the fluid delivery depot location in the body of the patient based on the total area of the fluid delivery depot location inthe body of the patient, the total estimated concentration of the fluid in the fluid delivery depot location in the body of the patient, and / or a known volume of the fluid delivered in the injection. For example, image processing system 104 may determine the volume of the fluid delivery depot location in the body of the patient based on the number of the plurality of elements predicted to include the fluid delivery depot location, the intensity values of the plurality of elements predicted to include the fluid delivery depot location, the scaled size of each element, and / or the volume of the fluid delivered in the injection. As an example, using training datasets, a pixel area or a sum of a number of pixels of a fluid delivery depot in one or more training images and intensities of the pixels in the fluid delivery depot in the one or more training images may be correlated with a volume or dispersion of the fluid delivered in the injection. This relationship can be used to approximate depot volume at any stage of delivery or absorption (e.g., for any fluoroscopic image of a plurality of fluoroscopic images captured over the period of time, etc.). The scale of known pixel size and intensity can be used for reference between images.

[0072] In some non-limiting embodiments or aspects, image processing system 104 determines a volume of the fluid delivery depot location in the body of the patient based on a machine learning technique (e.g., a pattern recognition technique, a data mining technique, a heuristic technique, a supervised learning technique, an unsupervised learning technique, etc.). For example, image processing system 104 may generate a model (e.g., an estimator, a classifier, a prediction model, a fluid depot location prediction model, etc.) based on a machine learning algorithm (e.g., a decision tree algorithm, a gradient boosted decision tree algorithm, a neural network algorithm, a convolutional neural network algorithm, etc.). In such an example, image processing system 104 may generate the volume of the fluid delivery depot location in the body of the patient using the model.

[0073] Image processing system 104 may generate the model based on training data including one or more training images of one or more injection sites for one or more fluids on one or more bodies of one or more patients. For example, the model may be designed to receive, as an input, the total area of the fluid delivery depot location in the body of the patient, the total estimated concentration of the fluid in the fluid delivery depot location in the body of the patient, a known volume of the fluid delivered in the injection, and / or image data associated with the one or more images (e.g., intensities of elements of the one or more images, etc.), and provide, as an output, a predicted volume or dispersion of the fluid delivery depot location in the body of the patient. As an example, image processing system 104 may analyze the training data using machine learning techniques to generate the model. The machine learningtechniques may include, for example, supervised and / or unsupervised techniques, such as decision trees (e.g., gradient boosted decision trees), logistic regressions, artificial neural networks (e.g., convolutional neural networks), Bayesian statistics, learning automata, Hidden Markov Modeling, linear classifiers, quadratic classifiers, association rule learning, and / or the like. In some non-limiting embodiments or aspects, image processing system 104 generates or trains the model using the machine learning techniques to optimize an objective or loss function (e.g., an objective or loss function that depends on an output of the model and / or one or more labels for the input and / or the entire image, an area of the image, an element of the image, etc.). In some non-limiting embodiments or aspects, image processing system 104 stores the trained model (e.g., stores the trained model for later use). In some non-limiting embodiments or aspects, image processing system 104 stores the trained model in a data structure (e.g., a database, a linked list, a tree, etc.). In some non-limiting embodiments or aspects, the data structure is located within image processing system 104 or external (e.g., remote from) image processing system 104.

[0074] Image processing system 104 may determine at least one of an absorption rate of the fluid in the body of the patient, a diffusion rate of the fluid in the body of the patient, or any combination thereof based on the total area of the fluid delivery depot location in the body of the patient, the total estimated concentration of the fluid in the fluid delivery depot location in the body of the patient, the volume of the fluid delivery depot location in the body of the patient over the period of time, and / or a measured pressure in a fluid delivery line of a drug delivery device over the period of time (e.g., a measured pressure in fluid line 50 of drug delivery device 10 measured by sensor 44 of drug delivery device 10, etc.). As an example, the fluoroscopic image may include a plurality of fluoroscopic images of the injection site captured over the period of time, and image processing system 104 may determine the volume or dispersion of the fluid delivery depot location in the body of the patient over the period of time for each image of the plurality of images. For example, the pixel to volumetric relationship used to determine the volume of the fluid delivery depot location in the body of the patient may be combined with a series of fluoroscopic images captured over a period of time at set increments to approximate absorption and / or diffusion rate of the injected fluid in tissue under investigation. The scale of known pixel size and intensity can be used for reference between images.

[0075] In some non-limiting embodiments or aspects, image processing system 104 determines at least one of an absorption rate of the fluid in the body of the patient, a diffusion rate of the fluid in the body of the patient, or any combination thereof based on a machinelearning technique (e.g., a pattern recognition technique, a data mining technique, a heuristic technique, a supervised learning technique, an unsupervised learning technique, etc.). For example, image processing system 104 may generate a model (e.g., an estimator, a classifier, a prediction model, a fluid depot location prediction model, etc.) based on a machine learning algorithm (e.g., a decision tree algorithm, a gradient boosted decision tree algorithm, a neural network algorithm, a convolutional neural network algorithm, etc.). In such an example, image processing system 104 may generate the at least one of the absorption rate of the fluid in the body of the patient, the diffusion rate of the fluid in the body of the patient, or any combination thereof using the model.

[0076] Image processing system 104 may generate the model based on training data including a plurality of training images of one or more injection sites for one or more fluids on one or more bodies of one or more patients over one or more periods of time. For example, the model may be designed to receive, as an input, the total area of the fluid delivery depot location in the body of the patient, the total estimated concentration of the fluid in the fluid delivery depot location in the body of the patient, a known volume of the fluid delivered in the injection, the volume of the fluid delivery depot location in the body of the patient over the period of time, the measured pressure in the fluid delivery line of the drug delivery device over the period of time, and / or image data associated with the plurality of images (e.g., intensities of elements of the one or more images, etc.), and provide, as an output, at least one of an absorption rate of the fluid in the body of the patient, a diffusion rate of the fluid in the body of the patient, or any combination thereof. As an example, image processing system 104 may analyze the training data using machine learning techniques to generate the model. The machine learning techniques may include, for example, supervised and / or unsupervised techniques, such as decision trees (e.g., gradient boosted decision trees), logistic regressions, artificial neural networks (e.g., convolutional neural networks), Bayesian statistics, learning automata, Hidden Markov Modeling, linear classifiers, quadratic classifiers, association rule learning, and / or the like. In some non-limiting embodiments or aspects, image processing system 104 generates or trains the model using the machine learning techniques to optimize an objective or loss function (e.g., an objective or loss function that depends on an output of the model and one or more labels for the input and / or the entire image, an area of the image, an element of the image, etc.). In some non-limiting embodiments or aspects, image processing system 104 stores the trained model (e.g., stores the trained model for later use). In some nonlimiting embodiments or aspects, image processing system 104 stores the trained model in a data structure (e.g., a database, a linked list, a tree, etc.). In some non-limiting embodimentsor aspects, the data structure is located within image processing system 104 or external (e.g., remote from) image processing system 104.

[0077] Image processing system 104 may determine a fluidic resistance of tissue in the body of the patient to the fluid based on the total area of the fluid delivery depot location in the body of the patient, the total estimated concentration of the fluid in the fluid delivery depot location in the body of the patient, the volume of the fluid delivery depot location in the body of the patient over the period of time, a measured pressure in a fluid delivery line of a drug delivery device over the period of time (e.g., a measured pressure in fluid line 50 of drug delivery device 10 measured by sensor 44 of drug delivery device 10, etc.), and / or a known flow rate of the delivery over the period of time. As an example, the fluoroscopic image may include a plurality of fluoroscopic images of the injection site captured over the period of time, and image processing system 104 may determine the volume of the fluid delivery depot location in the body of the patient over the period of time for each image of the plurality of images. For example, the pixel to volumetric relationship used to determine the volume of the fluid delivery depot location in the body of the patient may be combined with a series of fluoroscopic images captured over a period of time at set increments to approximate fluidic resistance of the injected fluid in tissue under investigation. The scale of known pixel size and intensity can be used for reference between images.

[0078] In some non-limiting embodiments or aspects, image processing system 104 determines a fluidic resistance of tissue in the body of the patient to the fluid based on a machine learning technique (e.g., a pattern recognition technique, a data mining technique, a heuristic technique, a supervised learning technique, an unsupervised learning technique, etc.). For example, image processing system 104 may generate a model (e.g., an estimator, a classifier, a prediction model, a fluid depot location prediction model, etc.) based on a machine learning algorithm (e.g., a decision tree algorithm, a gradient boosted decision tree algorithm, a neural network algorithm, a convolutional neural network algorithm, etc.). In such an example, image processing system 104 may generate the fluidic resistance of tissue in the body of the patient using the model.

[0079] Image processing system 104 may generate the model based on training data including a plurality of training images of one or more injection sites for one or more fluids on one or more bodies of one or more patients over one or more periods of time. For example, the model may be designed to receive, as an input, the total area of the fluid delivery depot location in the body of the patient, the total estimated concentration of the fluid in the fluid delivery depot location in the body of the patient, a known volume of the fluid delivered in theinjection, the volume of the fluid delivery depot location in the body of the patient over the period of time, the measured pressure in the fluid delivery line of the drug delivery device over the period of time, and / or image data associated with the plurality of images (e.g., intensities of elements of the one or more images, etc.), and provide, as an output, a tissue resistance of tissue in the body of the patient to the fluid. As an example, image processing system 104 may analyze the training data using machine learning techniques to generate the model. The machine learning techniques may include, for example, supervised and / or unsupervised techniques, such as decision trees (e.g., gradient boosted decision trees), logistic regressions, artificial neural networks (e.g., convolutional neural networks), Bayesian statistics, learning automata, Hidden Markov Modeling, linear classifiers, quadratic classifiers, association rule learning, and / or the like. In some non-limiting embodiments or aspects, image processing system 104 generates or trains the model using the machine learning techniques to optimize an objective or loss function (e.g., an objective or loss function that depends on an output of the model and one or more labels for the entire image, an area of the image, an element of the image, etc.). In some non-limiting embodiments or aspects, image processing system 104 stores the trained model (e.g., stores the trained model for later use). In some non-limiting embodiments or aspects, image processing system 104 stores the trained model in a data structure (e.g., a database, a linked list, a tree, etc.). In some non-limiting embodiments or aspects, the data structure is located within image processing system 104 or external (e.g., remote from) image processing system 104.

[0080] Image processing system 104 may determine an inferred delivery pressure in the tissue in the body of the patient over the period of time (e.g., when a measured pressure is unavailable, such as when a delivery device used for the injection does not include a pressure sensor, etc.) based on the total area of the fluid delivery depot location in the body of the patient, the total estimated concentration of the fluid in the fluid delivery depot location in the body of the patient, the volume of the fluid delivery depot location in the body of the patient over the period of time, a known volume of the fluid delivered in the injection, and / or a known flow rate of the fluid delivery. As an example, the fluoroscopic image may include a plurality of fluoroscopic images of the injection site captured over the period of time, and image processing system 104 may determine the inferred delivery pressure over the period of time for each image of the plurality of images. For example, the pixel to volumetric relationship used to determine the volume of the fluid delivery depot location in the body of the patient and / or the known flow rate may be combined with a series of fluoroscopic images captured over a period of time atset increments to approximate inferred delivery pressure in tissue under investigation. The scale of known pixel size and intensity can be used for reference between images.

[0081] In some non-limiting embodiments or aspects, image processing system 104 determines an inferred delivery pressure based on a machine learning technique (e.g., a pattern recognition technique, a data mining technique, a heuristic technique, a supervised learning technique, an unsupervised learning technique, etc.). For example, image processing system 104 may generate a model (e.g., an estimator, a classifier, a prediction model, a fluid depot location prediction model, etc.) based on a machine learning algorithm (e.g., a decision tree algorithm, a gradient boosted decision tree algorithm, a neural network algorithm, a convolutional neural network algorithm, etc.). In such an example, image processing system 104 may generate the inferred delivery pressure using the model.

[0082] Image processing system 104 may generate the model based on training data including a plurality of training images of one or more injection sites for one or more fluids on one or more bodies of one or more patients over one or more periods of time. For example, the model may be designed to receive, as an input, the total area of the fluid delivery depot location in the body of the patient, the total estimated concentration of the fluid in the fluid delivery depot location in the body of the patient, a known volume of the fluid delivered in the injection, the volume of the fluid delivery depot location in the body of the patient over the period of time, the known flow rate, and / or image data associated with the plurality of images (e.g., intensities of elements of the one or more images, etc.), and provide, as an output, a tissue resistance of tissue in the body of the patient to the fluid. As an example, image processing system 104 may analyze the training data using machine learning techniques to generate the model. The machine learning techniques may include, for example, supervised and / or unsupervised techniques, such as decision trees (e.g., gradient boosted decision trees), logistic regressions, artificial neural networks (e.g., convolutional neural networks), Bayesian statistics, learning automata, Hidden Markov Modeling, linear classifiers, quadratic classifiers, association rule learning, and / or the like. In some non-limiting embodiments or aspects, image processing system 104 generates or trains the model using the machine learning techniques to optimize an objective or loss function (e.g., an objective or loss function that depends on an output of the model and one or more labels for the input and / or the entire image, an area of the image, an element of the image, etc.). In some non-limiting embodiments or aspects, image processing system 104 stores the trained model (e.g., stores the trained model for later use). In some non-limiting embodiments or aspects, image processing system 104 stores the trained model in a data structure (e.g., a database, a linked list, a tree, etc.). In some non-limitingembodiments or aspects, the data structure is located within image processing system 104 or external (e.g., remote from) image processing system 104.

[0083] Image processing system 104 may determine an inferred delivery resistance in the tissue in the body of the patient over the period of time (e.g., when a measured pressure is unavailable, such as when a delivery device used for the injection does not include a pressure sensor, etc.) based on the volume of the fluid delivery depot location in the body of the patient over the period of time, the inferred delivery pressure over the period of time in the tissue in the body of the patient, and / or a known flow rate of the delivery. In such an example, a delivery or tissue resistance may be equal to a delivery pressure divided by a delivery flow rate. As an example, the fluoroscopic image may include a plurality of fluoroscopic images of the injection site captured over the period of time, and image processing system 104 may determine the inferred delivery or tissue resistance over the period of time for each image of the plurality of images. For example, the pixel to volumetric relationship used to determine the volume of the fluid delivery depot location in the body of the patient and thereby the inferred delivery pressure and / or the known flow rate may be combined with a series of fluoroscopic images captured over a period of time at set increments to approximate inferred delivery or tissue resistance in tissue under investigation. The scale of known pixel size and intensity can be used for reference between images.

[0084] In some non-limiting embodiments or aspects, image processing system 104 determines an inferred delivery or tissue resistance based on a machine learning technique (e.g., a pattern recognition technique, a data mining technique, a heuristic technique, a supervised learning technique, an unsupervised learning technique, etc.). For example, image processing system 104 may generate a model (e.g., an estimator, a classifier, a prediction model, a fluid depot location prediction model, etc.) based on a machine learning algorithm (e.g., a decision tree algorithm, a gradient boosted decision tree algorithm, a neural network algorithm, a convolutional neural network algorithm, etc.). In such an example, image processing system 104 may generate the inferred delivery or tissue resistance using the model.

[0085] Image processing system 104 may generate the model based on training data including a plurality of training images of one or more injection sites for one or more fluids on one or more bodies of one or more patients over one or more periods of time. For example, the model may be designed to receive, as an input, the total area of the fluid delivery depot location in the body of the patient, the total estimated concentration of the fluid in the fluid delivery depot location in the body of the patient, a known volume of the fluid delivered in the injection, the volume of the fluid delivery depot location in the body of the patient over theperiod of time, the known flow rate, the inferred delivery pressure, and / or image data associated with the plurality of images (e.g., intensities of elements of the one or more images, etc.), and provide, as an output, an inferred delivery or tissue resistance. As an example, image processing system 104 may analyze the training data using machine learning techniques to generate the model. The machine learning techniques may include, for example, supervised and / or unsupervised techniques, such as decision trees (e.g., gradient boosted decision trees), logistic regressions, artificial neural networks (e.g., convolutional neural networks), Bayesian statistics, learning automata, Hidden Markov Modeling, linear classifiers, quadratic classifiers, association rule learning, and / or the like. In some non-limiting embodiments or aspects, image processing system 104 generates or trains the model using the machine learning techniques to optimize an objective or loss function (e.g., an objective or loss function that depends on an output of the model and one or more labels for the input and / or the input and / or the entire image, an area of the image, an element of the image, etc.). In some non-limiting embodiments or aspects, image processing system 104 stores the trained model (e.g., stores the trained model for later use). In some non-limiting embodiments or aspects, image processing system 104 stores the trained model in a data structure (e.g., a database, a linked list, a tree, etc.). In some non-limiting embodiments or aspects, the data structure is located within image processing system 104 or external (e.g., remote from) image processing system 104.

[0086] As shown in FIG. 4, at step 410, process 400 includes providing the at least one predicted parameter associated with the injection of the fluid in the body of the patient as a delivery characteristic of the injection. For example, image processing system 104 may provide the at least one predicted parameter associated with the injection of the fluid in the body of the patient as a delivery characteristic of the injection. As an example, image processing system 104 may provide the least one predicted parameter associated with the injection of the fluid in the body of the patient for comparison against device performance of the drug delivery device used for the injection and / or tissue characteristics of the location of the injection and / or of the specific patient.

[0087] In some non-limiting embodiments or aspects, image processing system 104 controls, during the injection of the fluid in the body of the patient with drug delivery device 10, drug delivery device 10 to adjust (e.g., increase, decrease, etc.) a delivery rate of the fluid to the patient. For example, in response to the at least one parameter satisfying a threshold associated with that parameter, image processing system 104 may control drug delivery device 10 to adjust the delivery rate of the fluid to better match tissue characteristics of the specific patient and / or delivery characteristics of the specific drug delivery device.

[0088] Various embodiments can be implemented, for example, using one or more computer systems, such as computer system 700 shown in FIG. 6. Computer system 700 can be any computer capable of performing the functions described herein.

[0089] Computer system 700 includes one or more processors (also called central processing units, or CPUs), such as a processor 704. Processor 704 is connected to a communication infrastructure or bus 706.

[0090] One or more processors 704 may each be a graphics processing unit (GPU). In an embodiment, a GPU is a processor that is a specialized electronic circuit designed to process mathematically intensive applications. The GPU may have a parallel structure that is efficient for parallel processing of large blocks of data, such as mathematically intensive data common to computer graphics applications, images, videos, etc.

[0091] Computer system 700 also includes user input / output device(s) 703, such as monitors, keyboards, pointing devices, etc., that communicate with communication infrastructure 706 through user input / output interface(s) 702.

[0092] Computer system 700 also includes a main or primary memory 708, such as random access memory (RAM). Main memory 708 may include one or more levels of cache. Main memory 708 has stored therein control logic (i.e., computer software) and / or data.

[0093] Computer system 700 may also include one or more secondary storage devices or memory 710. Secondary memory 710 may include, for example, a hard disk drive 712 and / or a removable storage device or drive 714. Removable storage drive 714 may be a floppy disk drive, a magnetic tape drive, a compact disk drive, an optical storage device, tape backup device, and / or any other storage device / drive.

[0094] Removable storage drive 714 may interact with a removable storage unit 718. Removable storage unit 718 includes a computer usable or readable storage device having stored thereon computer software (control logic) and / or data. Removable storage unit 718 may be a floppy disk, magnetic tape, compact disk, DVD, optical storage disk, and / or any other computer data storage device. Removable storage drive 714 reads from and / or writes to removable storage unit 718 in a well-known manner.

[0095] According to an exemplary embodiment, secondary memory 710 may include other means, instrumentalities or other approaches for allowing computer programs and / or other instructions and / or data to be accessed by computer system 700. Such means, instrumentalities or other approaches may include, for example, a removable storage unit 722 and an interface 720. Examples of the removable storage unit 722 and the interface 720 may include a program cartridge and cartridge interface (such as that found in video game devices), a removablememory chip (such as an EPROM or PROM) and associated socket, a memory stick and USB port, a memory card and associated memory card slot, and / or any other removable storage unit and associated interface.

[0096] Computer system 700 may further include a communication or network interface 724. Communication interface 724 enables computer system 700 to communicate and interact with any combination of remote devices, remote networks, remote entities, etc. (individually and collectively referenced by reference number 728). For example, communication interface 724 may allow computer system 700 to communicate with remote devices 728 over communications path 726, which may be wired and / or wireless, and which may include any combination of LANs, WANs, the Internet, etc. Control logic and / or data may be transmitted to and from computer system 700 via communication path 726.

[0097] In an embodiment, a tangible, non-transitory apparatus or article of manufacture comprising a tangible, non-transitory computer usable or readable medium having control logic (software) stored thereon is also referred to herein as a computer program product or program storage device. This includes, but is not limited to, computer system 700, main memory 708, secondary memory 710, and removable storage units 718 and 722, as well as tangible articles of manufacture embodying any combination of the foregoing. Such control logic, when executed by one or more data processing devices (such as computer system 700), causes such data processing devices to operate as described herein.

[0098] Based on the teachings contained in this disclosure, it will be apparent to persons skilled in the relevant art(s) how to make and use embodiments of this disclosure using data processing devices, computer systems and / or computer architectures other than that shown in FIG. 6. In particular, embodiments can operate with software, hardware, and / or operating system implementations other than those described herein.

[0099] Although aspects or embodiments have been described in detail for the purpose of illustration based on what is currently considered to be the most practical and preferred embodiments, it is to be understood that such detail is solely for that purpose and that aspects or embodiments of the present disclosure are not limited to the disclosed embodiments, but, on the contrary, are intended to cover modifications and equivalent arrangements that are within the spirit and scope of the appended claims. For example, it is to be understood that the present disclosure contemplates that, to the extent possible, one or more features of any embodiment can be combined with one or more features of any other embodiment.

Claims

WHAT IS CLAIMED IS1. A method for fluoroscopic image based analysis, comprising: obtaining, with at least one processor, a fluoroscopic image of an injection site for an injection of a fluid on a body of a patient, wherein the fluoroscopic image includes a matrix including a plurality of elements, and wherein each element of the matrix includes an intensity value; processing, with the at least one processor, the fluoroscopic image to generate a prediction score for each element of the plurality of elements, wherein the prediction score includes a prediction of whether that element includes a fluid delivery depot location in the body of the patient; providing, with the at least one processor, a total area of the fluid delivery depot location in the body of the patient, wherein the total area of the fluid delivery depot location in the body of the patient is determined based on the prediction score for each element of the plurality of elements; generating, with the at least one processor, based on the total area of the fluid delivery depot location in the body of the patient, at least one predicted parameter associated with the injection of the fluid in the body of the patient; and providing, with the at least one processor, the at least one predicted parameter associated with the injection of the fluid in the body of the patient as a delivery characteristic of the injection.

2. The method for fluoroscopic image based analysis of claim 1, wherein the prediction score for each element further includes a prediction of whether that element includes a diffused region or an undiffused region within the total area of the fluid delivery depot location.

3. The method for fluoroscopic image based analysis of claim 1, wherein the prediction score for each element further includes an estimated concentration of the fluid associated with that element, and wherein the method further comprises: providing, with the at least one processor, a total estimated concentration of the fluid in the fluid delivery depot location in the body of the patient, wherein the total estimated concentration of the fluid in the fluid delivery depot location in the body of the patient is determined based on the prediction score for each element of the plurality of elements.

4. The method for fluoroscopic image based analysis of claim 3, wherein the at least one parameter includes a volume of the fluid delivery depot location in the body of the patient, and wherein the volume of the fluid delivery depot location in the body of the patient is determined based on the total area of the fluid delivery depot location in the body of the patient, the total estimated concentration of the fluid in the fluid delivery depot location in the body of the patient, and a known volume of the fluid delivered in the injection.

5. The method for fluoroscopic image based analysis of claim 4, wherein the fluoroscopic image includes a plurality of fluoroscopic images of the injection site captured over a period of time, wherein the at least one parameter includes at least one of an absorption rate of the fluid, a diffusion rate of the fluid, or any combination thereof, and wherein the at least one of the absorption rate of the fluid, the diffusion rate of the fluid, or any combination thereof is determined based on the volume or dispersion of the fluid delivery depot location in the body of the patient over the period of time and a measured pressure in a fluid delivery line of a drug delivery device over the period of time.

6. The method for fluoroscopic image based analysis of claim 4, wherein the fluoroscopic image includes a plurality of fluoroscopic images of the injection site captured over a period of time, wherein the at least one parameter includes a fluidic resistance of tissue in the body of the patient to the fluid, and wherein the fluidic resistance of the tissue in the body of the patient to the fluid is determined based on the volume of the fluid delivery depot location in the body of the patient over the period of time and a measured pressure in a fluid delivery line of a drug delivery device over the period of time.

7. The method for fluoroscopic image based analysis of claim 4, wherein the fluoroscopic image includes a plurality of fluoroscopic images of the injection site captured over a period of time, wherein the at least one parameter includes an inferred delivery pressure in the tissue in the body of the patient over the period of time, and wherein the inferred delivery pressure in the tissue in the body of the patient is determined based on the volume of the fluid delivery depot location in the body of the patient over the period of time and a known flow rate of the fluid delivery over the period of time.

8. The method for fluoroscopic image based analysis of claim 7, wherein the fluoroscopic image includes a plurality of fluoroscopic images of the injection site captured over a period of time, wherein the at least one parameter includes an inferred tissue resistance in the tissue in the body of the patient, and wherein the inferred tissue resistance in the tissue in the body of the patient is determined based on the inferred delivery pressure over the period of time in the tissue in the body of the patient and a known flow rate of the delivery.

9. The method for fluoroscopic image based analysis of claim 1, further comprising: delivering, with a drug delivery device, the fluid to the body of the patient at the injection site, wherein the drug delivery device includes at least one component having known dimensions; capturing, with a fluoroscopic image capture device, the fluoroscopic image of the injection site for the fluid on the body of the patient, wherein the fluoroscopic image includes the at least one component having the known dimensions; and scaling, with the at least one processor, based on the known dimensions of the at least one component, the fluoroscopic image.

10. The method for fluoroscopic image based analysis of claim 1, further comprising: controlling, with the at least one processor, during the injection of the fluid in the body of the patient with a drug delivery device, the drug delivery device to adjust a delivery rate of the fluid to the patient.

11. A system for fluoroscopic image based analysis, comprising: at least one processor programmed and / or configured to: obtain a fluoroscopic image of an injection site for an injection of a fluid on a body of a patient, wherein the fluoroscopic image includes a matrix including a plurality of elements, and wherein each element of the matrix includes an intensity value; process the fluoroscopic image to generate a prediction score for each element of the plurality of elements, wherein the prediction score includes a prediction of whether that element includes a fluid delivery depot location in the body of the patient;provide a total area of the fluid delivery depot location in the body of the patient, wherein the total area of the fluid delivery depot location in the body of the patient is determined based on the prediction score for each element of the plurality of elements; generate, based on the total area of the fluid delivery depot location in the body of the patient, at least one predicted parameter associated with the injection of the fluid in the body of the patient; and provide the at least one predicted parameter associated with the injection of the fluid in the body of the patient as a delivery characteristic of the injection.

12. The system for fluoroscopic image based analysis of claim 11, wherein the prediction score for each element further includes a prediction of whether that element includes a diffused region or an undiffused region within the total area of the fluid delivery depot location.

13. The system for fluoroscopic image based analysis of claim 11, wherein the prediction score for each element further includes an estimated concentration of the fluid associated with that element, and wherein the at least one processor is further programmed and / or configured to: provide total estimated concentration of the fluid in the fluid delivery depot location in the body of the patient, wherein the total estimated concentration of the fluid in the fluid delivery depot location in the body of the patient is determined based on the prediction score for each element of the plurality of elements.

14. The system for fluoroscopic image based analysis of claim 13, wherein the at least one parameter includes a volume of the fluid delivery depot location in the body of the patient, and wherein the volume of the fluid delivery depot location in the body of the patient is determined based on the total area of the fluid delivery depot location in the body of the patient, the total estimated concentration of the fluid in the fluid delivery depot location in the body of the patient, and a known volume of the fluid delivered in the injection.

15. The system for fluoroscopic image based analysis of claim 14, wherein the fluoroscopic image includes a plurality of fluoroscopic images of the injection site captured over a period of time, wherein the at least one parameter includes at least one of an absorption rate of the fluid, a diffusion rate of the fluid, or any combination thereof, and wherein the atleast one of the absorption rate of the fluid, the diffusion rate of the fluid, or any combination thereof is determined based on the volume or dispersion of the fluid delivery depot location in the body of the patient over the period of time and a measured pressure in a fluid delivery line of a drug delivery device over the period of time.

16. The system for fluoroscopic image based analysis of claim 14, wherein the fluoroscopic image includes a plurality of fluoroscopic images of the injection site captured over a period of time, wherein the at least one parameter includes a fluidic resistance of tissue in the body of the patient to the fluid, and wherein the fluidic resistance of the tissue in the body of the patient to the fluid is determined based on the volume of the fluid delivery depot location in the body of the patient over the period of time and a measured pressure in a fluid delivery line of a drug delivery device over the period of time.

17. The system for fluoroscopic image based analysis of claim 14, wherein the fluoroscopic image includes a plurality of fluoroscopic images of the injection site captured over a period of time, wherein the at least one parameter includes an inferred delivery pressure in the tissue in the body of the patient over the period of time, and wherein the inferred delivery pressure in the tissue in the body of the patient is determined based on the volume of the fluid delivery depot location in the body of the patient over the period of time and a known flow rate of the fluid delivery over the period of time.

18. The system for fluoroscopic image based analysis of claim 17, wherein the fluoroscopic image includes a plurality of fluoroscopic images of the injection site captured over a period of time, wherein the at least one parameter includes an inferred tissue resistance in the tissue in the body of the patient, and wherein the inferred tissue resistance in the tissue in the body of the patient is determined based on the inferred delivery pressure over the period of time in the tissue in the body of the patient and a known flow rate of the delivery.

19. The system for fluoroscopic image based analysis of claim 11, further comprising: a drug delivery device configured to deliver the fluid to the body of the patient at the injection site, wherein the drug delivery device includes at least one component having known dimensions; anda fluoroscopic image capture device configured to capture the fluoroscopic image of the injection site for the fluid on the body of the patient, wherein the fluoroscopic image includes the at least one component having the known dimensions, wherein the at least one processor is further programmed and / or configured to: scale, based on the known dimensions of the at least one component, the fluoroscopic image.

20. The system for fluoroscopic image based analysis of claim 11, wherein the at least one processor is further programmed and / or configured to: control, during the injection of the fluid in the body of the patient with a drug delivery device, the drug delivery device to adjust a delivery rate of the fluid to the patient.

Images