System and method for performing a motor assessment

Abstract

A system and method for performing a motor assessment to assess the posture and motor performance of patients with conditions presenting with symptomatic functional motor dysfunction such as Parkinson's disease. Landmarks on a sequence of images can be defined and tracked to provide quantifiable changes over time that can be compared to a trained motor assessment model and correlated to symptomatic motor dysfunction in a standardized motor assessment test.

Description

SYSTEM AND METHOD FOR PERFORMING A MOTOR ASSESSMENTCROSS-REFERENCE TO RELATED APPLICATIONS

[0001] This application claims priority to United States provisional patent application US63 / 602,413 filed on 23 November 2023, which is hereby incorporated by reference herein in its entirety.FIELD

[0002] The present invention pertains to a system and method for performing a motor assessment of a patient. The motor assessment can be performed to assess the posture, facial expression, gait, and other tests of motor performance of patients with conditions presenting with symptomatic functional motor disturbances, motor fluctuations, motor disruption, or involuntary or abnormal motion.BACKGROUND

[0003] Parkinson’s Disease (PD) is a progressive, degenerative neurological condition whereby the gradual loss of dopamine producing neurons in the brain results in both motor and non-motor functional impairments, resulting in negative effects on muscle control, balance, movement, cognitive ability, autonomic system functioning, and mental health. Slowed movements (bradykinesia) and tremors are typical for people with Parkinson’s disease, usually worsening as the disease advances. Symptoms of PD can begin gradually and progressively worsen over time. Some of the primary motor symptoms associated with PD include tremors, rigidity and / or stiffness, bradykinesia and postural instability.

[0004] Patients with PD often undergo motor assessments to evaluate the patient’s PD progression and severity over time. The motor assessments can also be used to track the patient’s response to medication and other treatments, such as deep brain stimulation (DBS). As well as tracking the disease, eligibility for DBS might also be determined from assessing motor functioning. A motor assessment generally involves a clinician observing the patient while the patient performs a series of motor tasks that are part of the motor assessment. The clinician quantifies the motor assessment by scoring the patient’s performance of the motor tasks according to a clinical rating scale. Two of the most commonly used clinical rating scales for monitoring the progression of PD include the Movement Disorder Society - Unified Parkinson’s Disease Rating Scale (MDS-UPDRS) and the Hoehn and Yahr scale (HY). The MDS-UPDRShas a four-scale structure (Part I, II, III and IV) comprising nonmotor experiences of daily living, motor experiences of daily living, motor examination, and motor complications. Each item on the MDS-UPDRS motor assessment or questionnaire is assigned a score ranging from 0 to 4, where 0 is normal, 1 is slight, 2 is mild, 3 is moderate, and 4 is severe. A clinical evaluator observes the patient, carries out a series of tests, records their observations and assigns a score. Speech, facial expression, rigidity, and postural stability of the patient are also observed. Rigidity and postural stability can also generally require physical contact with the patient.

[0005] Clinical rating scales can be subjective and inconsistent depending on the clinician’s experience and expertise. Systems involving cameras and / or imaging devices and / or other sensors have been proposed as alternative and / or supplementary ways of quantifying a motor assessment. In an example, U.S. Patent No. 10,485,454 to Tas et al. describes a markerless system and method for evaluating motion from body motion video data including a set of 3D coordinates for a plurality of body joints using an active 3D infrared camera and predicting a motion evaluation score based on identified joint positions of the patient in the video data. The active 3D infrared camera includes at least one infrared light emitter that emits infrared light and at least one infrared light detector that detects the infrared light's reflection off of objects located in front of the active 3D infrared camera. In another example of automated PD symptom monitoring, U.S. Patent No. 11,375,945 to Pathak et al. describes a disease and fall risk assessment using depth mapping system comprising analysing data from a motion sensor such a gyroscopic sensor and accelerometer.

[0006] Computational systems for motor assessment typically require an extensive calibration or configuration process to provide accurate and reliable data. Additionally, modeling of body position from video data to create a 3D model or mesh requires significant processing power, which is prohibitive for performing real time analysis. Other systems using motion sensors, such as inertial sensors, require the patient to calibrate or configure the system before performing each motor task of a motor assessment, which can take extra time and may require assistance from a trained technician in order to accurately capture the required data. This can increase the testing time required to complete the motor assessment, increase the cost, and can cause test fatigue for the patient, potentially skewing the results. The requirement for calibration is particularly problematic for a disease such as PD, as accurate evaluation of the patient’s motor functionality is critical to tracking disease progression and providing suitable treatment. Other existingsystems require sensor handling and manipulation by a patient, caregiver or clinician, or other healthcare professional, for example wearable sensors need to be attached to patients’ bodies, or a smartphone or tablet camera needs to be handled or stationed in a fixed position to capture images correctly which takes time and does not enable the easy capture of images for the majority of motor tests in MDS-UPDRS.

[0007] This background information is provided for the purpose of making known information believed by the applicant to be of possible relevance to the present invention. No admission is necessarily intended, nor should be construed, that any of the preceding information constitutes prior art against the present invention.SUMMARY

[0008] An object of the present invention is to provide a system and method for performing a motor assessment of a patient using landmarks obtained from camera image frame data that can be analyzed over time to provide a patient score on a standardized motor assessment test. Another object of the present invention is to provide a system and method that can be used to quantitatively assess the posture and motor performance of patients with conditions presenting with symptomatic functional motor disturbances, motor fluctuations, motor disruption, or involuntary or abnormal motion.

[0009] In an aspect there is provided a method for performing a motor assessment comprising: obtaining a sequence of images of a clinically relevant feature of a patient during a motor assessment test; assigning spatial coordinates in the area of the clinically relevant feature on the sequence of images; defining a landmark in each image in the sequence of images using a selected subset of the assigned spatial coordinates; measuring the landmark across the sequence of images to provide a quantitative measurement of change in the sequence of images over time at the landmark; calculating a parameter that describes the change in the landmark across the sequence of images; comparing the calculated parameter for the landmark to a motor assessment model for the motor assessment test; and assigning a score for the patient for the motor assessment test.

[0010] In an embodiment, parameterizing the landmark data over time further comprises deconvoluting the parameterized landmark data using Fourier transform into a plurality of frequency bands.

[0011] In another embodiment, each of the plurality of frequency bands is associated with a specific movement mode.

[0012] In another embodiment, the motor assessment model is a trained machine learning model trained on human clinician assessment of patients for the motor assessment test.

[0013] In another embodiment, the landmark is derived from a relationship of the selected subset of the assigned spatial coordinates.

[0014] In another embodiment, calculating the parameter comprises: defining the landmark as a boundary box containing the clinically relevant feature; using frame differencing to amplify the change across the images in the boundary box; and parameterizing the frame differencing using optical flow.

[0015] In another embodiment, frame differencing is used to amplify signal motion in the boundary box.

[0016] In another embodiment the method further comprises measuring a plurality of landmarks over time and assigning a score for the patient based on comparing a parameter for each of the plurality of landmarks to the motor assessment model.

[0017] In another embodiment the method further comprises, prior to obtaining a sequence of images, providing the patient with instruction on how to perform the motor assessment test, the instruction comprising one or more of a still image, video image, text, still graphic, animated graphic, audio indicators, or speech.

[0018] In another embodiment, the landmark comprises a centre of mass, angle created between lines of joined spatial coordinates, and ratio of distance between lines defined by spatial coordinates.

[0019] In another embodiment, the spatial coordinates are in two dimensions or three dimensions.

[0020] In another embodiment, each of the selected subset of assigned spatial coordinates are assigned a unique weight in the landmark, and the unique weights are used to define the landmark.

[0021] In another embodiment, the landmark is parameterized using change over time in amplitude or frequency of the landmark.

[0022] In another embodiment, the motor assessment test is a facial expression test, a finger tapping test, a tremor at rest task, a gait test, a leg stomping test, an arising from seating test, aposture test, a postural tremor of hands test, a hand movement test, a pronation-supination test, a toe tapping test, a gait test, or a kinetic tremor of hands test.

[0023] In another embodiment, the method further comprises, during the motor assessment test, a live view image of the patient is displayed in a graphical user interface that is viewable by the patient.

[0024] In another embodiment, the score is based on the Movement Disorder Society - Unified Parkinson’s Disease Rating Scale.

[0025] In another aspect there is provided a system for performing a motor assessment of a user comprising: at least one image capture device; a display device in communication with the image capture device; and at least one processor configured to receive a plurality of images from the image capture device and display the plurality of images on the display device, the system performing a method of: receiving, from the image capture device of the system, a data stream comprising a plurality of images of a patient performing a motor assessment; displaying, on the display device, a live view of the data stream comprising the plurality of images; displaying, on the display device, a configuration boundary overlaid on the live view image, the configuration boundary corresponding to a target location within a field of view of the image capture device at which a target body portion of the user is to be positioned; and capturing a sequence of images of a clinically relevant feature of a patient during the motor assessment test.

[0026] In an embodiment, the motor assessment task comprises a facial expression task, a finger tapping task, a tremor at rest task, a gait task, a leg stomping task, an arising from seating task, a posture task, a postural tremor of hands task, a hand movement task, a pronationsupination, a toe tapping task, a gait task, or a kinetic tremor of hands task.

[0027] In another embodiment, the processor further performs the steps of: defining a landmark in each image in the sequence of images using a selected set of spatial coordinates; measuring the landmark across the sequence of images to provide a quantitative measurement of change in the sequence of images over time at the landmark; calculating a parameter that describes the change in the landmark across the sequence of images; comparing the calculated parameter for the landmark to a motor assessment model for the motor assessment test; and assigning a score for the patient for the motor assessment test.

[0028] In another embodiment, the motor assessment model is a trained machine learning model trained on human clinician assessment of patients for the motor assessment test.

[0029] According to one broad aspect of the teachings herein, in at least one embodiment described herein there is a method of configuring a system for performing a motor assessment of a user, wherein the method includes operating at least one processor of the system for: receiving, from a lower image capture device of the system, a lower image data stream; receiving, from an upper image capture device of the system, an upper image data stream; displaying, on a display device of the system, a lower live view image including a recent image from the lower image data stream; displaying, on the display device of the system, an upper live view image including a recent image from the upper image data stream; displaying, on the display device, a lower configuration boundary overlaid on the lower live view image, the lower configuration boundary corresponding to a lower target location within a field of view of the lower image capture device at which a first target body portion of the user is to be positioned; displaying, on the display device, an upper configuration boundary overlaid on the upper live view image, the upper configuration boundary corresponding to an upper target location within a field of view of the upper image capture device at which a second target body portion of the user is to be positioned; updating the lower live view image with the images from the lower image data stream until the lower live view image shows the first target body portion within the lower configuration boundary; and updating the upper live view image with images from the upper image data stream until the upper live view image shows the second target body portion within the upper configuration boundary.

[0030] In at least one embodiment, the lower image capture device is rotatable along a pitch axis to facilitate the user positioning the first target body portion at the lower target location and showing the first target body portion within the lower configuration boundary.

[0031] In at least one embodiment, an actuator of the system is operable to adjust a height of an adjustable support member to facilitate positioning the second target body portion at the upper target location and showing the second target body portion within the upper configuration boundary.

[0032] In at least one embodiment, the first target body portion includes a hand of the user and the second target body portion includes the user’s head and optionally upper torso.

[0033] In at least one embodiment, a position of the lower image capture device relative to the upper image capture device is maintained for the duration of the method to facilitate configuring the system for the user to perform one or more tasks of the motor assessment at a plurality ofdistances relative to the system and a plurality of body positions of the user without having to reconfigure the system between the one or more tasks of the motor assessment for the user.

[0034] In at least one embodiment, the plurality of distances relative to the system includes a close distance that is in the range of about 24 to 30 inches and a far distance that is in the range of about 105 to 120 inches, the close distance and the far distance being measured from the adjustable support member to a front end of a foot of the user.

[0035] In at least one embodiment, a front edge of a seating apparatus is positioned at one of the close distance and the middle distance, and the user is positioned in a seated position on the seating apparatus.

[0036] In at least one embodiment, the plurality of body positions of the user includes a sitting position captured by at least one of the lower image capture device and the upper image capture device, a standing position captured by the upper image capture device, and a walking position captured by the upper image capture device.

[0037] In at least one embodiment, each of the lower image capture device and the upper image capture device are coupled to the adjustable support member of the system, the lower image capture device being positioned below the upper image capture device.

[0038] In at least one embodiment, the lower image capture device is configured to capture an image of at least a portion of a hand of the user when the user is seated at the close distance and performing a hand motor task of the motor assessment.

[0039] In at least one embodiment, the hand motor task includes a hand movement task, a resting hand tremor task, a pronation and supination task or any combination thereof.

[0040] In at least one embodiment, the upper image capture device is configured to capture an image of at least a portion of the user’s body when the user is at the close distance or the far distance and performing a body motor task.

[0041] In at least one embodiment, the upper image capture device is configured to capture an image of at least a portion of the user’s body when seated or standing at the middle distance and performing a body motor task or the variable distance and performing a gait task.

[0042] In at least one embodiment, the body motor assessment task includes a facial expression task, a finger tapping task, a tremor at rest task, a gait task, a leg stomping task, an arising from seating apparatus task, a posture task or any combination thereof.

[0043] In at least one embodiment, each of the lower image capture device and the upper image capture device includes a depth camera.

[0044] In at least one embodiment, the method further includes operating the at least one processor for assigning labels to the image capture devices before a first step of configuring the system by: receiving a first image data stream from one of the lower image capture device or the upper image capture device; displaying, on the display device, a first live view image including a most recent image from the first image data stream; assigning, based on user input, a first label to one of the lower image capture device or the upper image capture device identifying which of the lower image capture device or the upper image capture device is providing the first live view image; receiving a second image data stream from one of the lower image capture device or the upper image capture device that was not assigned a label previously; displaying, on the display device, a second live view image including a most recent image from the second image data stream; and assigning a second label to one of the lower image capture device or the upper image capture device identifying the lower image capture device or the upper image capture device based on the second live view image. In at least one embodiment, a third image capture device of the system is positioned below the upper image capture device and above the lower image capture device.

[0045] In at least one embodiment, the method further includes operating the at least one processor to: receive a third image data stream from the third image capture device of the system; display, on the display device, a third live view image including a most recent image from the third image data stream; and assign a third label to the third image capture device identifying the third image capture device based on the third live view image.

[0046] In another aspect, there is provided at least one embodiment of a system for performing a motor assessment of a user, wherein the system includes: an adjustable support member oriented in a generally vertical orientation; a plurality of image capture devices; an upper arm extending outwardly from the adjustable support member; a lower arm extending outwardly from the adjustable support member, the lower arm positioned below the upper arm; an upper housing coupled to a distal end of the upper arm for housing at least one of the plurality of image capture devices; a lower housing coupled to a distal end of the lower arm for housing at least one of the plurality of image capture devices; a display device in communication with the processor and coupled to the adjustable support member; and at least one processor that is configured toreceive images from the plurality of image capture devices and display the images on the display device.

[0047] In at least one embodiment, the system further includes an actuator for adjusting a height of the adjustable support member along a substantially vertical axis.

[0048] In at least one embodiment, the lower housing is rotatable along a pitch axis, wherein the pitch axis is approximately perpendicular to a longitudinal axis defined by the lower arm.

[0049] In at least one embodiment, the lower arm is positioned at a fixed distance below the upper arm and the image capture devices located in each upper and lower arm are substantially aligned in a vertical direction.

[0050] In at least one embodiment, the fixed distance is in a range of about 13.5 to about 19.5 inches. In at least one embodiment, a length of the lower arm is in a range of about 12 inches to 14 inches or of between about 14 inches to 20 inches, and a length of the upper arm is in a range of about 3 inches to 12 inches or about 12 inches to 14 inches or of between about 14 inches to 20 inches. In at least one embodiment, a distance from the face / lens of the lower camera (facing upward) to the lens of the upper camera facing outward has a range of between 14 inches to about 20 inches. In at least one embodiment, a length of the lower arm is in a range of about 12 inches to 14 inches and a length of the upper arm is in a range of about 3 inches to 6 inches, about 12 inches to 14 inches, or about 3 inches to 14 inches.

[0051] In at least one embodiment, the at least one processor is configured for performing the method of configuring a system for performing a motor assessment of a user as described herein.

[0052] It will be appreciated that the foregoing summary sets out representative aspects of embodiments to assist skilled readers in understanding the following detailed description. Other features and advantages of the present application will become apparent from the following detailed description taken together with the accompanying drawings. Embodiments of the present invention as recited herein may be combined in any combination or permutation. It should be understood, however, that the detailed description and the specific examples, while indicating preferred embodiments of the application, are given by way of illustration only, since various changes and modifications within the scope of the application will become apparent to those skilled in the art from this detailed description.BRIEF DESCRIPTION OF THE DRAWINGS

[0053] For a better understanding of the various embodiments described herein, and to show more clearly how these various embodiments may be carried into effect, reference will be made, by way of example, to the accompanying drawings which show at least one example embodiment, and which are now described. The drawings are not intended to limit the scope of the teachings described herein.

[0054] Figure 1 illustrates a method for performing a motor assessment of a patient as described herein.

[0055] Figure 2 illustrates the mapping of quantitative frequency bands in a motor assessment to qualitative clinical assignments.

[0056] Figure 3 illustrates an example method for assigning landmarks to clinically relevant features of eye and around eye movement.

[0057] Figure 4A illustrates an example method for assigning a mouth aspect ratio landmark to assess mouth movement.

[0058] Figure 4B illustrates an example method for performing a centre of mass calculation to assess jaw movement.

[0059] Figure 4C illustrates an example method for performing a centre of mass calculation to assess cheek movement.

[0060] Figure 5 provides raw landmark data from a data acquisition of a clinically relevant feature in a finger tapping motor assessment test.

[0061] Figure 6 provides deconvoluted frequency data showing frequency distributions in a motor assessment test.

[0062] Figure 7 illustrates integrated power spectral density distribution across frequency bands in a motor assessment test.

[0063] Figure 8 illustrates assignment of a centre of mass landmark and an angular measurement landmark to different motion assessment tests.

[0064] Figure 9 illustrates the assignment of spatial coordinates on a hand to provide selected spatial coordinates for defining a selection of different landmarks.

[0065] Figure 10A illustrates landmark identification for quantitative gait assessment.

[0066] Figure 10B illustrates landmark identification for quantitative leg and body positioning in a gait assessment.

[0067] Figure 10C illustrates landmark identification for quantitative arm positioning in a gait assessment.

[0068] Figure 11 A illustrates a front view of relative limb angle landmark identification for quantitative posture assessment.

[0069] Figure 1 IB illustrates a front view of shoulder offset angle landmark identification for quantitative posture assessment.

[0070] Figure 11C illustrates a side view of relative limb and trunk angle landmark identification for quantitative posture assessment.

[0071] Figure 1 ID illustrates a top view of relative limb and trunk angle landmark identification for quantitative posture assessment.

[0072] Figure 12 illustrates an example of using frame differencing to amplify subtle motion and calculation of optical flow for quantitative analysis of a clinically relevant feature in a motor assessment test.

[0073] Figure 13 shows a perspective view of an example embodiment of the system for performing a motor assessment in accordance with the teachings herein.

[0074] Figure 14 shows a side view of an example system for performing a motor assessment.

[0075] Figure 15 is a block diagram of an example embodiment of the electronic hardware for a system for performing a motor assessment.

[0076] Figure 16 is a flowchart of an example embodiment of a method for configuring a system for performing a motor assessment.

[0077] Figure 17 illustrates an example graphical user interface displayed on a display device of a system for performing a motor assessment for assigning image capture device labels.

[0078] Figure 18 illustrates an example graphical user interface displayed on a display device of a system for performing a motor assessment for configuring image capture devices.

[0079] Figure 19A illustrates an example of a user in a sitting position at a near distance in front of a system for performing a motor assessment.

[0080] Figure 19B illustrates an example of a user in a sitting position at a far distance in front of a system for performing a motor assessment.

[0081] Figure 20A illustrates an example of a user in a standing position at a far distance in front of a system for performing a motor assessment.

[0082] Figure 20B illustrates an example of a user performing a walking task at a far distance in front of a system for performing a motor assessment.

[0083] Further aspects and features of the example embodiments described herein will appear from the following description taken together with the accompanying drawings.DETAILED DESCRIPTION OF THE EMBODIMENTS

[0084] The headings and Abstract of the Disclosure provided herein are for convenience only and do not interpret the scope or meaning of the embodiments. Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. Working examples provided herein are considered to be non-limiting and merely for purposes of illustration. Various embodiments in accordance with the teachings herein will be described below to provide examples of at least one embodiment of the claimed subject matter. No embodiment described herein limits any claimed subject matter. The claimed subject matter is not limited to devices, systems or methods having all of the features of any one of the devices, systems or methods described below or to features common to multiple or all of the devices, systems or methods described herein. It is possible that there may be a device, system or method described herein that is not an embodiment of any claimed subject matter. Any subject matter that is described herein that is not claimed in this document may be the subject matter of another protective instrument, for example, a continuing patent application, and the applicants, inventors or owners do not intend to abandon, disclaim or dedicate to the public any such subject matter by its disclosure in this document.

[0085] Furthermore, it will be appreciated that for simplicity and clarity of illustration, where considered appropriate, reference numerals may be repeated among the figures to indicate corresponding or analogous elements or steps. In addition, numerous specific details are set forth in order to provide a thorough understanding of the embodiments described herein. However, it will be understood by those of ordinary skill in the art that the embodiments described herein may be practiced without these specific details. In other instances, well-known methods, procedures and components have not been described in detail so as not to obscure the embodiments described herein. Also, the description is not to be considered as limiting the scope of the embodiments described herein.

[0086] As used herein, the terms “coupled” and “coupling” can have several different meanings depending on the context in which these terms are used. For example, the terms coupled or coupling can have a mechanical, electrical or communicative connotation. For example, as used herein, the terms coupled and coupling can indicate that two elements or devices can be directly connected to one another or connected to one another through one or more intermediate elements or devices via an electrical element, electrical signal or a mechanical element depending on the particular context.

[0087] As used herein, the terms “connect” and “connected” refer to any direct or indirect physical association between elements or features of the present disclosure. Accordingly, these terms may be understood to denote elements or features that are partly or completely contained within one another, attached, coupled, disposed on, joined together, in communication with, operatively associated with, etc., even if there are other elements or features intervening between the elements or features described as being connected.

[0088] Unless the context requires otherwise, throughout the specification and claims which follow, the word “comprise” and variations thereof, such as, “comprises” and “comprising” are to be construed in an open, inclusive sense, that is, as “including, but not limited to”.

[0089] Various terms used throughout the present description may be read and understood as follows, unless the context indicates otherwise: singular articles and pronouns as used throughout include their plural forms, and vice versa; similarly, gendered pronouns include their counterpart pronouns so that pronouns should not be understood as limiting anything described herein to use, implementation, performance, etc. by a single gender. Further definitions for terms may be set out herein; these may apply to prior and subsequent instances of those terms, as will be understood from a reading of the present description.

[0090] It should also be noted that, as used herein, the wording “and / or” is intended to represent an inclusive-or. That is, “X and / or Y” is intended to mean X or Y or both, for example. As a further example, “X, Y, and / or Z” is intended to mean X or Y or Z or any combination thereof. As another example, the phrases “any combination of A, B and C” or “A, B, C or any operable combination thereof’ is mean to cover any combination of elements A, B and C that provides utility which may, for example, include A, B, C, A and B, A and C, B and C, or A, B and C.

[0091] Terms of degree such as “substantially”, “about” and “approximately” as used herein mean a reasonable amount of deviation of the modified term such that the end result is not significantly changed. These terms of degree may also be construed as including a deviation of the modified term, such as by 1%, 2%, 5% or 10%, for example, if this deviation does not negate the meaning of the term it modifies.

[0092] The recitation of numerical ranges by endpoints herein includes all numbers and fractions subsumed within that range (e.g., 1 to 5 includes 1, 1.5, 2, 2.75, 3, 3.90, 4, and 5). It is also to be understood that all numbers and fractions thereof are presumed to be modified by the term "about" which means a variation of up to a certain amount of the number to which reference is being made if the end result is not significantly changed, such as 1%, 2%, 5%, or 10%, for example.

[0093] Reference throughout this specification to “one embodiment”, “an embodiment”, “at least one embodiment” or “some embodiments” means that one or more particular features, structures, or characteristics may be combined in any suitable manner in one or more embodiments, unless otherwise specified to be not combinable or to be alternative options.

[0094] As used in this specification and the appended claims, the singular forms “a,” “an,” and “the” include plural referents unless the content clearly dictates otherwise. It should also be noted that the term “or” is generally employed in its broadest sense, that is, as meaning “and / or” unless the content clearly dictates otherwise.

[0095] The term “communicative” as in “communicative pathway,” “communicative coupling,” and in variants such as “communicatively coupled,” is generally used to refer to any engineered arrangement for transferring and / or exchanging information. Examples of communicative pathways include, but are not limited to, electrically conductive pathways (e.g., electrically conductive wires, physiological signal conduction), electromagnetically radiative pathways (e.g., radio waves), or any combination thereof. Examples of communicative couplings include, but are not limited to, electrical couplings, magnetic couplings, radio couplings, or any combination thereof.

[0096] Throughout this specification and the appended claims, infinitive verb forms are often used. Examples include, without limitation: “to detect,” “to provide,” “to transmit,” “to communicate,” “to process,” “to route,” and the like. Unless the specific context requiresotherwise, such infinitive verb forms are used in an open, inclusive sense, that is as “to, at least, detect,” to, at least, provide,” “to, at least, transmit,” and so on.

[0097] A portion of the example embodiments of the systems, devices, or methods described in accordance with the teachings herein may be implemented as a combination of hardware or software. For example, a portion of the embodiments described herein may be implemented, at least in part, by using one or more computer programs, executing on one or more programmable devices comprising at least one processing element, and at least one data storage element (including volatile and non-volatile memory). These devices may also have at least one input device (e.g., a keyboard, a mouse, a touchscreen, and the like) and at least one output device (e.g., a display screen, a printer, a wireless radio, and the like) depending on the nature of the device. It should also be noted that there may be some elements that are used to implement at least part of the embodiments described herein that may be implemented via software that is written in a high-level procedural language such as object-oriented programming. The program code may be written in C, C++or any other suitable programming language and may comprise modules or classes, as is known to those skilled in object-oriented programming. Alternatively, or in addition thereto, some of these elements implemented via software may be written in assembly language, machine language, or firmware as needed. At least some of the software programs used to implement at least one of the embodiments described herein may be stored on a storage media or a device that is readable by a general or special purpose programmable device. The software program code, when read by the programmable device, configures the programmable device to operate in a new, specific and predefined manner in order to perform at least one of the methods described herein.

[0098] Furthermore, at least some of the programs associated with the systems and methods of the embodiments described herein may be capable of being distributed in a computer program product comprising a computer readable medium that bears computer usable instructions, such as program code, for one or more processors. The program code may be preinstalled and embedded during manufacture and / or may be later installed as an update for an already deployed computing system. The medium may be provided in various forms, including non-transitory forms such as, but not limited to, one or more diskettes, compact disks, tapes, chips, and magnetic and electronic storage. In alternative embodiments, the medium may be transitory in nature such as, but not limited to, wire-line transmissions, satellite transmissions, internet transmissions (e.g.,downloads), media, digital and analog signals, and the like. The computer useable instructions may also be in various formats, including compiled and non-compiled code. Accordingly, any module, unit, component, server, computer, terminal or device described herein that executes software instructions may include or otherwise have access to computer readable media such as storage media, computer storage media, or data storage devices (removable and / or nonremovable) such as, for example, magnetic disks, optical disks, or tape. Computer storage media may include volatile and non-volatile, removable and non-removable media implemented in any method or technology for storage of information, such as computer readable instructions, data structures, program modules, or other data. Examples of computer storage media include RAM, ROM, EEPROM, flash memory or other memory technology, CD-ROM, digital versatile disks (DVD) or other optical storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other medium which can be used to store the desired information, and which can be accessed by an application, module, or both. Any such computer storage media may be part of the device or accessible or connectable thereto.

[0099] The terms “user” and “patient” as used herein refers to a person or individual who is undergoing and / or performing a motor assessment. In some cases, the user can be an individual that is performing the motor assessment in a medical setting such as a clinic or a hospital, for example. In other cases, the user can be an individual that is performing the motor assessment in their home or in a non-medical setting. The user can be a human, or a non-human animal.

[0100] The term “motor assessment” as used herein refers to a motor task performed by an individual to assess one or more motor functionalities of the individual (e.g., the user or patient). The motor assessment can be based on known clinical rating scales such as the Movement Disorder Society - Unified Parkinson’s Disease Rating Scale (MDS-UPDRS) or its predecessor the Unified Parkinson’s Disease Rating Scale (UPDRS), for example. In other cases, the motor assessment can be based on a clinician’s or individual’s experience and expertise. Although reference is made to motor assessments related to Parkinson’s Disease, the systems and methods described herein are not so limited. For example, motor assessments can be performed in relation to any suitable motor disease or disorder, following similar rating scales as MDS-UPDRS but specific to each disease or condition, e.g., Unified Huntington's Disease Rating Scale (UHDRS).

[0101] The term “spatial coordinate” as used herein refers to a two-dimensional or three- dimensional location that identify a specific locus on a body. The spatial coordinate can berepresented, for example, in two dimensional (2D) cartesian coordinates (x,y), three dimensional (3D) cartesian coordinates (x,y,z), radial coordinates, or a combination of cartesian and radial coordinates.

[0102] The term “clinically relevant feature” as used herein refers to an observable clinical sign of interest on a patient body which can be the subject of a motor assessment test. The clinically relevant feature can be observed at a location on the body of the user to quantifiably to detect motion patterns. The clinically relevant feature can also include the whole body. Examples of clinically relevant features include but are not limited to eye blinking, gait, posture, facial movement or frozen face, body tremor, limb tremor, facial tremor, lip tremor, whole body tremor, involuntary movements, and motor tasks such as hand, limb, foot, and leg movements.

[0103] The term “landmark” as used herein refers to a quantifiable descriptor of the clinically relevant feature at the location on the body being examined. A landmark is derived from the relationship of one or more selected spatial coordinates in an image frame, and one or more parameter can be used to describe the landmark as a change in the landmark across image frames captured during a motor assessment. Some non-limited examples of landmarks include centre of mass of a set of spatial coordinates, ratio of distances between spatial coordinates and intersections of spatial coordinates, distance between spatial coordinates, angle formed by three spatial coordinates or intersections between spatial coordinates, pixel luminosity, and pixel colour. The state of the landmark(s) over time can be used to describe patient motion at the clinically relevant feature.

[0104] The term “configuring” as used herein refers to preparing and / or calibrating a system for performing a motor assessment. For example, configuring can include positioning one or more image capture devices and / or sensors based on a user’s particular body measurement, such as the user’s height, arm length and / or arm reach, for example. Configuring can further include, for example, positioning and / or orienting the system components appropriately so that once the system components are so positioned they can be used to capture data of the motor assessment regardless of whether the user is at various distances from the system and / or in different body positions.

[0105] Herein is described a system and method for performing a motor assessment test which extrapolates motion obtained from landmarks on the body derived from selected spatialcoordinates. By measuring the landmark in a plurality of images and deconvoluting the change over time of the landmark, the present system and method can provide a rapid and computationally efficient way of extracting motion data for a motor test assessment. Patterns provided by the extrapolated data can be compared to a motor assessment model such that the results of the motor assessment test can be mapped to existing scores on a standard scale, such as the Movement Disorder Society - Unified Parkinson’s Disease Rating Scale (MDS-UPDRS). Without being bound by theory, it is noted that using identified landmarks at the site of a clinically relevant feature to measure motion over time can reduce the amount of data required to provide an assessment of clinical symptoms that align with the same motor assessment tests evaluated by human clinicians. Reducing the data intensity of signal extraction and processing thereby enables real time or near real time patient assessment with a low-cost tool for quality patient monitoring, which can lead to effective treatment, disease management, and improved care.

[0106] Figure 1 illustrates a method for performing a motor assessment of a patient as described herein. Using at least one image capture device, a sequence of images is obtained of a patient at a clinically relevant feature during a motor assessment 50. During the motor assessment test the patient is provided with instruction on how to do the test, and preferably a display is provided to provide the instructions and also display the real time images taken of the patient by the image capture device. This ensures that the region of interest on the body is within the image capture frame of the camera or image capture device. A plurality of spatial coordinates are then automatically assigned in the area of the clinically relevant feature on the sequence of images 52. From the plurality of spatial coordinates a landmark can be defined using one or more selected spatial coordinates 54 from the plurality of spatial coordinates assigned to the area of the clinically relevant feature. Landmarks can be defined using, for example, one or more of spatial coordinate mapping, and frame differencing with optical flow. The clinically relevant feature is then measured in the plurality of images as defined by the landmark 56 and a parameter can be calculated that describes the change over time over the plurality of images as defined by the landmark 58. Some landmark parameters that can be used are quantifiable measures of amplitude and frequency, which can be converted into power spectral density as a measurement of landmark change over time. Other landmark parameters can include change in the colour and / or luminosity of pixels over time inside a boundary box defined by three or more spatialcoordinates. Various motor assessments can be used with this method and system, including but not limited to facial expression, finger tapping, postural tremor of hands, hand movements, pronation-supination, tremor at rest, leg stomping, toe tapping, arising from chair, posture, gait, and kinetic tremor of hands.

[0107] In spatial coordinate mapping a plurality of cartesian or radial spatial coordinates are assigned to a body part in the area of the clinically relevant feature for each image in the sequence of images for a particular motor assessment test. For example, in a blinking test a set of spatial coordinates are selected around each eye, and in a mouth movement test a set of spatial coordinates are selected around the mouth. The selected set of spatial coordinates for the specific motor assessment test are used to define a landmark that has been found to be indicative of a movement mode around the clinically relevant feature or area of interest on the body. In an example, in analysis of blepharospasm, an eye aspect ratio based on spatial coordinate landmarks can be used to extract quantitative data around eye movement over time.

[0108] In frame differencing and optical flow mapping a clinically relevant region can be identified in a bounding box in the sequence of images, where the bounding box is defined by the selected spatial coordinates. Changes in the pixel colour between the images can be used to amplify any subtle motion. In a frame differencing analysis, a first image frame is compared with a second image frame to see how much the scene has changed. The pixels in the bounding box of the first image can be compared to pixels in the bounding box of the second image of the hand at a different location, and the difference in location of the hand over the time between the image frames can provide a quantitative and amplified indication of the hand tremor. In one example, the change in pixel luminosity and / or colour at a particular location inside the image bounding box can be compared across consecutive images to identify regions of movement. By subtracting the pixel values in the bounding box of one image frame from the corresponding pixel values in the bounding box of another next image frame the pixel differences between the two frames can be highlighted to amplify subtle changes and isolate and analyze motion. The pixel difference can be also quantified as a blend of the pixel values from the first and second image frames to can emphasize subtle movements, such as tremors, which can manifest as variations in pixel density across the sequence of frames. The quantitative data can thereby provide a measure the degree and location of motion, providing valuable insights into the movement occurring between frames. Optical flow can then be used to track the movement of pixels between two consecutiveframes to quantify both the frequency and amplitude of the movement, how much movement occurred, in which direction.

[0109] The parameterized landmark can identify, in a deconvoluted signal representation, symptomatic motor movements of the patient, including by not limited to slowness, hesitation, halts, freezes, decrementing amplitude of movement, jerkiness, and tremor. The parameter data can then compared to a motor assessment model 60 which has been trained based on data obtained from a training set of patients along with the score assigned by a clinician for the particular motor assessment test. Based on the comparison, the quantitative motion of the landmark over time can be assigned a score for the motor assessment test based on the correlation to the motor assessment model 62.

[0110] Figure 2 illustrates the mapping of quantitative frequency bands in a motor assessment to qualitative clinical assignments. The motor assessment model is trained on a data set comprising the parameterized landmarks for a set of patients across a range of motor assessment tests in a standardized model, such as the MDS-UPDRS scale. In the training set the patient is observed by a clinician while performing a motor assessment and the clinician provides a qualitative score for the motor assessment test. In this example, a gait assessment can be used to providing a mapping of qualitative data obtained from a traditional assessment done by a clinician to a qualitative assessment obtained using the present system and method. To map the quantitative data onto the qualitative data for a gait assessment, the method as described in Figure 1 is performed, and an energy spectral density is calculated for meaningful frequency bands for one or more landmarks extracted from a gait motor assessment image set. Parameters such as, for example, mean, median, maximum, quartile range, skewness, kurtosis, and standard deviation can be calculated for frequency and amplitude, and deconvoluted with Fast Fourier Transform (FFT) quantifications for other similar parameters. The energy spectral density can then be split up into frequency bands, where each frequency band is correlated to a set of symptomatic features of motor dysfunction as it relates to gait. In an example, a frequency band of a particular gait landmark between 2.5 and 8.0 Hz corresponds to a jerky adjustment that patients make for balance correction, which may not be observed by a clinician due to humanerror and / or subtlety of motion. Once the motor assessment model is trained, new patient data for the same motor assessment test can be compared along the energy spectral density data in themotor assessment model for gait to match the patient data and assign a score on the standardized scoring system.

[0111] Figure 3 illustrates an example method for assigning landmarks to clinically relevant features of eye and around eye movement. In any particular motor assessment test, the landmark(s) will be selected prior to performing the motor assessment on the patient based on the trained motor assessment model. During or after the motor assessment of the patient, images of the patient can be processed to assign the spatial coordinate(s) which contribute to the landmark onto the patient images such that the quantitative landmark data can be extracted.

[0112] In an example, eyebrow motion can be a clinically relevant feature for the assessment of masked face, facial paralysis, or decreased facial movement. In a motor assessment test for facial movement, the movement of an eyebrow can be quantified by tracking the centre of mass of the eyebrow over time, where the centre of mass serves as a trackable landmark. To define the centre of mass as an eyebrow landmark on a particular patient, spatial coordinates are assigned in the area of the clinically relevant feature in the sequence of images, in this case, the eyebrow. Spatial coordinates are preferably assigned automatically using software for face landmark detection. Once spatial coordinates are assigned around the clinically relevant feature, here the eyebrow, a subset of these spatial coordinates are selected Pi, P2, P3, P4, P5, and identified in the plurality of captured video images. In one embodiment each of the selected spatial coordinates can be assigned a weight, and the centre of mass of the eyebrow can be identified based on the location and the weights of each of the selected spatial coordinates around the eyebrow. The centre of mass (COM), which is the identified landmark, can then be used to extract the horizontal movement of left and right eyebrows in the x-direction, and the vertical movement of left and right eyebrows in the y-direction in the sequence of images. This can be done by assigning the COM for each eyebrow as cartesian coordinates, with the COM of the left eyebrow having coordinates (L eyebrow X, L eyebrow Y), and the COM of the right eyebrow having coordinates (R eyebrow X, R eyebrow Y). Once the landmark is identified in each of the plurality of images, in this case of the eyebrow centre of mass, movement of the COM landmark can be tracked over the time course of the motor assessment as captured by the video data stream over the sequence of images. In some cases, such as with cheek motion, selected spatial coordinates near the face centre are given more weight than others since that is the area where the motion is more prominently visible. In other cases, such as with eyebrows, spatialcoordinates in the middle of the face can be assigned less weight to provide an anchor point for the eyebrow landmark. Quantitative parameters enable detection and quantitation of eyebrow motion while at rest (to detect tremor) and during motion, for example while speaking or during a facial motor assessment. Quantitative analysis of smoothness of a raising eyebrow can enable detection of tremor or hesitation, and the differencing of signals assists in analyzing the symmetry of motion across the face.

[0113] In another example, for the eye region to detect blinking motion, one landmark that can be assigned is the eye aspect ratio which corresponds to an eye blink motion, which is the clinically relevant feature for blinking. To define the landmark, spatial coordinates Pi, P2, P3, P4, P5, Pe, are selected from a plurality of landmarks in and around the eye. Data can then be extracted from eye aspect ratio landmark change over time from video images captured during the motor assessment. In one example, the motor assessment model can interpret the eye aspect ratio amplitude, which is the distance between upper eyelid and lower eyelid Di divided by distance between left corner and right corner of eye D2, and the eye aspect ratio speed, which is derivative of the amplitude with respect to time. Each frame of the video will give a value for this landmark eye aspect ratio, and tracking this landmark value over time through the set of frames captured in the motor assessment test provides the amplitude signal and speed signal for each landmark. Quantitative parameters can be calculated from the eye aspect ratio amplitude signal and eye aspect ratio speed signal such as, for example median, quartile range, mean, minimum, maximum, standard deviation, root mean square, crest factor, skewness, and kurtosis, which can be deconvoluted using Fast Fourier Transform (FFT). Table 1 provides a relationship between quantitative eye landmark measurement of eye aspect ratio z and eye aspect ratio speed to qualitative observations of eye movement for quantitative diagnostics for a eye motor assessment.

[0114] Table 1 : Frequency Band Measurement for Eye Landmarks

[0115] Figures 4A, 4B, and 4C illustrate landmarks used in a motor assessment test for facial expression. In a facial expression test the patient sits still in front of the camera for a first period of time, for example 5-20 seconds, and then recites the alphabet during a second period of time, such as for about 10-40 seconds. The facial expression test can detect facial motor features such as decreased or increased blinking, masked face, parting of lips, facial tremor, and transitions between facial expressions. Spatial coordinates on the face can be used to map facial features, and landmarks can then be defined based on one or more spatial coordinate to provide movement data of the landmark over time.

[0116] Figure 4A illustrates an example method for assigning a mouth aspect ratio landmark to assess mouth movement. Similar to eye measurement, for the mouth, a mouth aspect ratio can be used as the landmark that corresponds to opening of mouth while sitting still and speaking. The relationship between spatial coordinates selected in and around the mouth define the mouth aspect ratio serves as the landmark, which can be measured in a plurality of video frames and tracked over the time course of the motor assessment. In one embodiment, a mouth aspect ratio can be calculated by summing up the distances between Ta-Ba, Ma-Mb, Tb-Bb divided by the distance between left and right comer of the mouth Sa-Sb. From the mouth aspect ratio landmark, the mouth aspect ratio amplitude, which is the magnitude of the mouth aspect ratio measured over the time course, and the mouth aspect ratio speed, which is the derivative of the mouth aspect ratio amplitude with respect to time, can be used to quantitatively categorize a mouth-based motor assessment. Similar quantitative parameters can be measured, such as for example: median, quartile range, mean, minimum, maximum, standard deviation, root mean square, crest factor, skewness, kurtosis, as well as Fast Fourier Transform (FFT) quantitation for similar parameters. The graph in Figure 4A illustrates the measurement of mouth aspect ratio over time, where time is represented by frame number in the sequence of images.

[0117] Figure 4B illustrates an example method for performing a centre of mass calculation to assess jaw movement. The movement of the jaw can be measured by tracking the centre of mass of the jaw, which can be assigned by selecting a plurality of spatial coordinated around the jaw and optionally weighting the selected spatial coordinates to provide a jaw centre of mass. Asshown, the weight of each of the selected special coordinates is shown with a grey circle, where spatial coordinated having a larger grey circle indicate a stronger weight in the centre of mass landmark calculation, identified with a star. This centre of mass (COM) is then used to extract a signal for the movement of the jaw in the x-direction (Jaw_X) and a signal for the movement of the jaw in the y-direction (Jaw_Y). Parameters can be calculated from Jaw_X and Jaw_Y signals, as well as combinations and derivatives thereof, such as, for example: median, quartile range, mean, minimum, maximum, standard deviation, root mean square, crest factor, skewness, kurtosis, and these can be deconvoluted using Fast Fourier Transform (FFT) quantitation. In the shown case, the closer the spatial coordinate is to the chin, the higher the weight value it has in the centre of mass calculation. Weighting the spatial coordinates has been found to assist in focusing on the main region which is usually affected by motor disruption or abnormal motion.

[0118] Figure 4C illustrates an example method for performing a centre of mass calculation to assess cheek movement in a face motor assessment test. A cheek signal can be calculated in a similar way as a jaw signal, with a centre of mass landmark selected (shown as a star) for each of the right cheek and left cheek based on a set of selected spatial coordinates with pre-assigned weighting. In one preferable weighting assignment, it has been found that good qualitative landmark data can be extracted by giving a higher weight to spatial coordinates closer to the nose. The centre of mass (COM) for each cheek can then used to extract the movement of the COM for each of the left cheek and right cheek using the location of the COM on a cartesian (x,y) coordinate map. The COM for the left cheek can be defined as (L cheek X, L cheek Y) and the COM for the right cheek can be defined as (R cheek X, R cheek Y). The relationship between the X and Y coordinates between the cheeks can also be calculated as the difference between the x-values for the left cheek compared to the right cheek (diff Cheek X), the difference between the y-values for the left cheek compared to the right cheek (diff Cheek Y), or as the absolute distance between the left and right centres of mass using the left and right cheek (x,y) coordinates. Parameters can be calculated from Left / Right / Diff cheek signals such as, for example: median, quartile range, mean, minimum, maximum, standard deviation, root mean square, crest factor, skewness, kurtosis, as well as Fast Fourier Transform (FFT) quantitation for similar parameters. Similar parameters can be calculated from the Left / Right / Diff cheek speed of movement. These parameters provide quantitative detection of cheek motion while at rest, and during movement while speaking, to detect facial motion control.Parameter analysis of cheek movement can also provide quantitative analysis for smoothness of motion, detection of tremor, and detection of motion hesitation or jerkiness. The differencing of signals also enables analysis of symmetry of motion across the face.

[0119] Figure 5 provides raw data from landmark frequency data acquisition of a clinically relevant feature in a finger tapping motor assessment test. In a finger tapping motor assessment test the patient is asked to tap their finger and thumb together as quickly as possible for a set period of time, generally between about 5 to 20 seconds. A camera records a multi-frame video of the hand during the finger tapping motor assessment such that a landmark can be extracted from the frames of the video. In the example shown, an assignment of spatial coordinates is performed to the hand as shown in image D in Figure 9. For this example test, the landmark is selected as the distance between a spatial coordinate on the first finger and a spatial coordinate on the thumb, however other methods of landmarking can also be used, including frame differencing and optical flow. A raw data set of amplitude of distance between the finger and thumb spatial coordinates, as the landmark, is captured and can be represented in an amplitude graph, as shown. From this data, the number of counts, or number of times per time period that the patient can touch their first finger and thumb together, can be calculated by first passing the landmark signal through a wavelet decomposition process and then reconstructing it to make a smoother version signal. In the control graph it can be easily observed that the amplitude and frequency of the finger tapping is relatively consistent over the time period of the test.

[0120] Based on this raw data a threshold can be calculated based on median absolute deviation of the reconstructed signal. This threshold can provide an indication of the start and end of a plateau, or changes in amplitude of the landmark over the test duration. A freeze condition can be identified when there is plateau for more than a threshold number of frames or for longer than threshold period of time. In one example, a freeze condition can be identified if there is an interruption over more than 30-60 image frames or more than 0.5 to 2 seconds. In one embodiment, a feature freeze condition is quantitatively determined by considering deviation of the landmark behaviour from a wavelet decomposed version of the data to uncover plateaus of more than a threshold period of time, for example 2 seconds. In the graph for patient 1, a first freeze can be easily identified between frames 200-250 and a second freeze can be identified between frames 300-375. Similarly, in the graph for patient 2, a freeze is evident between frames 50-120. An interruption can also be defined when the plateau occurs for greater than a thresholdnumber of frames or more than a threshold amount of time. Other parameters can be used to analysis the amplitude change over time. In one example, fitness and slope can be used assessed how well a linear regression model describes relation between time and amplitude, where the sign of the amplitude value (+ / -) represents and incrementing or decrementing signal and the magnitude represents strength of increment or decrement. The feature of amplitude decrement can be calculated from the difference between a linear regression model and a plurality of measured amplitudes. In another example, an end-to-mean parameter can be used to calculate the difference between the mean amplitude and last peak amplitude, where a higher value signifies that last peak is significantly lower than average suggesting a downward trend. In another example a last-to-first-half parameter can be used to calculate the difference between mean amplitude of first half and last half, where a positive value means that the first half is bigger than second half, suggesting decrementing amplitude. This feature of amplitude decrement can be calculated from the difference between the mean slope of early measurements and the mean slope of later measurements. Other parameters can be detected such as, for example, change in speed, change in acceleration, jerkiness, and other motor characteristics indicating nonsmoothness or difficulty that the patient is having with the finger tapping task.

[0121] Figure 6 provides deconvoluted frequency data from the raw data shown in Figure 5 showing frequency distributions in the finger tapping motor assessment test. A fast Fourier transform (FFT) transforms the raw time-domain data into the frequency domain by deconstructing the signal into its individual parts. In a Fourier analysis, the power spectrum signal can be decomposed or deconvoluted into a number of discrete frequencies, or a spectrum of frequencies over the continuous range. These frequency bands can then be used to deconvolute modes of motion exhibited during a motor assessment test to provide insight into a patient’s motion at different frequencies. The raw data shown in Figure 5 is shown in FFT form in Figure 6, with transformed data for the control, patient 1, and patient 2 for the finger tapping motor assessment test. The magnitude of the signal varies by frequency, and frequency bands can be assigned to the FFT. In this case, a low frequency band is assigned to 0.1 - 1 Hz, a medium frequency band is assigned to 1 - 2.5Hz, a high frequency band is assigned to 2.5 - 8.0 Hz, and a very high frequency band is assigned to 8.0 - 13.0 Hz.

[0122] Figure 7 illustrates the integrated power spectral density distribution across frequency bands in the finger tapping motor assessment test using data as shown in Figure 6. To obtain theintegrated power spectral density for a given frequency band, the power within each band is calculated by integrating the power spectral density (PSD) values over the frequency range of the band. The PSD is derived from the Fourier Transform of the signal and represents how the signal’s power is distributed across different frequencies. In the graphs shown, the integrated power spectral density is plotted on the y-axis, while the frequency bands (e.g., low, medium, high, and very high) are shown on the x-axis. The signal is divided into these frequency bands, and the total power within each band is computed by summing the PSD values within the respective range. The specific frequency ranges and the number of bands can vary based on the requirements of the motor assessment test and the trained motor assessment model. The motor assessment model is calibrated using a training set assigned by human clinicians to provide accurate scoring for the patient and the frequency bands in the model set are the same as used in the patient set to match the patient to the trained model. Each frequency band may also correspond to a specific mode of motion during the motor assessment test. For example, freezing motion is typically associated with low-frequency bands, while tremor is often linked to higher- frequency bands. In this example, a low frequency band can be defined as 0.1-1.0 Hz, where low-frequency oscillations can capture slow modulations in the tapping amplitude, such as gradual changes or drifts in the tapping pattern. A medium frequency band can be defined as 1.0- 2.5 Hz, referred to as delta oscillations, which are relevant for capturing slow fluctuations in the tapping amplitude, especially during extended tapping tasks. A high frequency band at 2.5-8.0 Hz and very high frequency band at 8.0-13.0 Hz can be used to capture mu rhythm often associated with sensorimotor cortex activity and motor planning. These higher frequencies may also be relevant for analyzing the preparatory and anticipatory phases of finger tapping movements.

[0123] Figure 8 illustrates assignment of a centre of mass landmark and an angular measurement landmark to a motion assessment test. In image A of Figure 8, in a motor assessment test of a patient arising from a seated position, the system uses a body pose estimation model for identifying spatial coordinates for locating the body in the image. For the test, the patient is asked to sit in a chair with their arms across their chest touching their shoulders, and then stand up. If the patient can not stand up, they can use the arms of the chair for support. In severe cases, the patient can be assisted. The model measures slowness in arising and using of arms for support as factors contributing to the score on the motor assessment test.For this test a body pose estimation model can be used that is able to track multiple people in the image frame, which is helpful in isolating the patient from any other person when they need assistance while performing the test. To extract a centre of mass (COM) landmark from the body pose estimation model, selected spatial coordinates (shown in white) for each of the left shoulder, right shoulder, left hip, right hip, left and right knees and left and right feet are identified, as well as nose or other location on the head. Other spatial coordinates can also be identified, such as, for example, one or more spatial coordinates for each arm and for the head. The selected shoulder and hip spatial coordinates are then assigned a weight that is different and higher from the other identified spatial coordinates, and the COM landmark is identified as centre of mass of the person based on the weighted spatial coordinates. In the example shown, more weight is given to the spatial coordinates of the upper body, which has been shown to provide good representative data for analyzing and scoring this motor assessment test as these regions tend to have maximum movement during arising from chair. More weight for the shoulder and hip spatial coordinates is shown as assigned to the landmarks with larger circles. Landmark data is collected by tracking the location of the COM while the patient is arising from the chair. Other landmark data can be collected if the patient uses one or more arm rest or assistive support by collecting data on a landmark ratio of distance between wrists and distance between shoulders.

[0124] An “arising-up-signal” can be used to track the motion of COM at least along the y-axis, providing a vertical motion measurement over time. The use of an assistive feature or person can be tracked, for example, by finding the quantile value of shoulder-to-wrist ratio, or the distance between wrists divided by distance between shoulders over time. To calculate the time it took for the patient to arise from the chair, a short time Fourier transform can be used to measure the time duration during which the frequencies corresponding to the motion of standing up are observed. Parameters on the movement of each landmark over time can be calculated and used for training the motor assessment model. From the landmark COM signal, for example, skewness and kurtosis can be calculated, as well as the number of tries it took for the patient to stand up by finding the peaks in the landmark COM signal. Skewness and kurtosis represent the shape of COM signal over time, which gives insights into the arising motion compared to a control or asymptomatic patient. The number of tries can be calculated by finding any peaks in the skewness and kurtosis signal to detect a vertical ascending motion followed by verticaldescending motion in the COM, where the descending motion is indicative of a reversal or failure to arise. Arising time can be calculated, for example, using a Short Time Fourier Transform that detects the frequencies in motion and calculates the time it took for the person to stand up, even after multiple attempts. A chair use quantile can also be calculated by finding a percentile of the signal, for example wrist- to-shoulder ratio, which can identify extreme movement, for example using an arm rest or other person for support to stand up after unfolding arms from the initial position.

[0125] In image B in Figure 8, the assignment of selected spatial coordinates on the body define a landmark that can be used to evaluate leg stomp motor assessment test. In this test a signal can be extrapolated by the landmark created by the angle formed between a horizontal line passing through the ankle at rest and the line joining ankle of both legs. In a similar motor assessment test based on toe tapping, the angle between the horizontal and the line extending from the end of one foot to the end of the tapping foot can be used as a landmark to model motion during the test. As shown, a plurality of spatial coordinates can be identified on the body of the patient performing the leg stomp motor assessment test, and these can be used to identify the ankle points, which are used to provide the selected spatial coordinates used to define the landmark from which the motion signal is extracted. The landmark signal over time can then be used to calculate parameters for the amplitude and / or frequency domain, or other parameters. The power spectral density is calculated for each frequency band which can then be used to quantify, for example, bradykinesia during this test. In one example, frequency bands can be assigned into four frequency bands, ranging from low to very high. These parameters and associated frequency bands can be used to train the motor assessment model, which can then provide frequency band patterns to positively associate particular motor assessment patterns to the UP-DRS scale in an automated clinical assessment.

[0126] Figure 9 illustrates the assignment of spatial coordinates on a hand to define a selection of different landmarks. In image A, in a pronation-supination motor assessment test, a plurality of spatial coordinates can be assigned to the hand. From those spatial coordinates a subset of selected spatial coordinates are used for defining landmark, in this case the angle formed between a vertical line passing through wrist and the line joining the wrist and thumb. A motion signal can then extracted from the change for this landmark angle over time across a sequence of images. Image B illustrates an assignment of spatial coordinates for a hand movement motorassessment test, wherein the landmark signal is extrapolated from the distance between a first selected spatial coordinate on the middle finger and a second selected spatial coordinate on the wrist over a series of image frames collected during the motor assessment test. The landmark parameter is measured as the change in distance between these two spatial coordinates over time.

[0127] In image C of Figure 9, a spatial coordinate identification is done for a motor assessment on the postural tremor of hands. The assignment of key spatial coordinates, one on each finger, can be used to track landmark change on the hand over time for postural tremor. During the motor assessment the patient sits still with hands stretched in front and palm facing downwards towards the bottom camera. This test quantifies the tremor of hands in this position using the translation over time of each of the selected fingertip spatial coordinates. In one specific example, hand pose estimation is used to capture 2D spatial coordinates, and the 2D coordinates can be used to obtain the z coordinate from a depth frame captured by a 3D depth camera. Spatial coordinates corresponding to fingertips and thumb can also optionally be converted from the cartesian form of coordinates into a polar form. In PD, tremor is often described as “pin rolling” tremor and polar coordinates (r, 9) have been found to better for quantifying the finger rolling motion associated with this tremor type. The motion of a plurality of spatial coordinates during the motor assessment test is used to provide a quantitative description of the movement of the spatial coordinates across the set of images during the time course of the test. Statistics corresponding to amplitude and frequency for both r and 9 for a landmark comprising fingertip and thumb coordinates can then be calculated. Power spectral density for each signal is deconvoluted into a plurality of frequency bands from the raw signal. Since postural tremor usually presents in the range of 4-6 Hz, high integrated power spectral density in the frequency band in the 4-6 Hz range will be indicative of significant postural tremor. For postural tremor, the movement of landmark in x-axis and y-axis, or converted to a polar / radial form of distance r at angle 9, is extracted from the images over time. The amplitude and frequency parameters can be extrapolated from the landmarks over time, where amplitude and frequency parameters can include but are not limited to mean, median, interquartile range, maximum, minimum, zero crossing rate, standard deviation, root mean square, crest factor, skewness, and kurtosis. Frequency bands are then selected according to symptomatic expression of tremor frequency, which is generally found between 4-6Hz. Frequency bands, shown in Table2, are assigned which cover this range, with + / -2 Hz around the tremor frequency expression to ensure capturing of tremor and also edge cases.

[0128] Table 2: Postural Tremor Frequency Bands

[0129] In Figure 9, image D illustrates an assignment of spatial coordinates for a finger tap motor assessment test, wherein the landmark signal is extrapolated from the distance between thumb and index finger over a series of image frames collected during the motor assessment test.

[0130] Figures 10A, 10B, and 10C illustrate landmark parameterization for a gait analysis, where: figure 10A illustrates landmark identification for quantitative stride assessment; figure 10B illustrates landmark identification for quantitative leg and body positioning in a gait assessment; and figure 10C illustrates landmark identification for quantitative arm positioning in a gait assessment. In a gait analysis full body pose estimation is used to collect movement data for spatial coordinates over time in a plurality of images while the patient walks back and forth in front of one or more cameras. Stride amplitude, speed, foot lift, turning, and arm swinging can all be measured using parameterized landmarks based on spatial coordinates as assigned to each image. During a gait motor assessment test spatial coordinates can be collected from shoulders, wrists, hips, knees, and ankles, which can be used to parameterize landmarks on the patient for the time course of the video assessment. In an example, the following landmarks can be quantified using one or more of the spatial coordinates itemized in Table 3, with landmarks shown in Figures 10A-C.

[0131] Table 3 : Example landmarks for gait quantitative analysis

[0132] From this landmark data other quantitative parameters can be extracted, including but not limited to: stride speed, which is the derivative of dl over time; turning amplitude which can be measured as distance between left and right hip over time; smoothness turning motion or smooth turning amplitude, which can be done using a Savitzky Golay filter; and turning speed, which can be measured as the derivative of turning amplitude with respect to time. Raw movement data can be extracted as for each landmark as the quantitative parameter over time and interpreted or deconvoluted as, for example, amplitude, frequency, and power spectral density. Amplitude and frequency measurements for each parameterized landmark can be calculated, which can include, for example: median, quartile range, mean, minimum, maximum, standard deviation, root mean square, crest factor, skewness, and kurtosis for each of amplitude and frequency. The deconvoluted parameterized landmark data can then be compared to a motor assessment model for classification and scoring. Table 4 provides an example integrated power spectral density (PSD) classification for a gait motor assessment test. Based on the individual patent results, the PSD classification pattern can be used to compare against a motor assessment model for patient scoring in a standardized motor assessment scoring system.

[0133] Table 4: Integrated Power Spectral Density Frequencies for Gait Motor Assessment

[0134] Figures 11 A, 1 IB, 11C, and 1 ID illustrate postural analysis landmarks, where: figure 11 A illustrates a front view of relative limb angle landmark identification for quantitative posture assessment; figure 1 IB illustrates a front view of shoulder offset angle landmark identification for quantitative posture assessment; figure 11C illustrates a side view of relative limb and trunk angle landmark identification for quantitative posture assessment; and figure 1 ID illustrates a top view of relative limb and trunk angle landmark identification for quantitative posture assessment. In a pose estimation patients are asked to stand still in front of a camera while performing the test with their arms on their side and facing the system. This model measures poor posture including scoliosis, flexion, leaning, and other posture indicators that deviate from normal. A front view is shown with identified spatial coordinates that serve as the basis for identifying a plurality of landmarks on the body that can be used to quantify posture. The spatial coordinates are preferably 3D coordinates, captured either with a 2D camera with an extrapolated depth calculation algorithm, or with a 3D camera. Spatial coordinates are captured for the nose, shoulders, elbows, wrists, hips, knees, and ankles, the following landmarks can be quantified using one or more of the spatial coordinates itemized in Table 5, with landmarks shown in Figures 11A-D.

[0135] Table 5: Example landmarks for posture quantitative analysis

[0136] For each quantitative parameter locational data is collected across the plurality of images in a video data stream of a patient during the postural test to provide a data set of the landmark over time. Amplitude and frequency measurements for each parameterized landmark can be calculated, which can include, for example: median, quartile range, mean, minimum, maximum, standard deviation, root mean square, crest factor, skewness, and kurtosis for each of amplitude and frequency. This data can then be used to parameterize each landmark for a particular patient. The parameterized data can then be applied to the motor assessment model for assigning a score to the patient based on the parameterized landmarks. Calculating frequencies for this largely static movement test which measures the posture of a person who is trying to stand still is helpful in the case of Parkinson’s patients as their posture may deteriorate, sway, illustrate tremor, or generally change over time, even if the intention of the patient is to remain still. A similar analysis can be done in a sitting analysis of tremor at rest, during which pose estimation can be done by measuring different parameters based on spatial coordinates on the body while the patient is sitting in a chair with arms resting. Cognitive tasks provided to the patient can also assist with differentiating Parkinson’s tremor from, for example, essential tremor, as the cognitive task can have an effect on the expression of tremor. Some cognitive tasks that can be used are, for example, reciting the months of year backwards, or spelling a word backwards.

[0137] Figure 12 illustrates an example of using frame differencing to amplify subtle motion and calculation of optical flow for quantitative analysis of a clinically relevant feature in a motor assessment test. Frame differencing can be used to amplify movement and is especially useful for use during resting tremor tests. Frame differencing has been found to be computationally inexpensive compared to other methods, such as Euler video magnification, and is an efficientway of quantifying subtle tremors than landmarking using points in a point cloud or 3D mesh, and can be done in real time with good results. Rigidity, which is presently assessed by a clinician while rotating the patient’s arm at the elbow and feeling for a cog-wheel effect which is an indicator of rigidity in joints may also be a subject of a landmark. Illustrated is a graph of right arm motion signal over time across a plurality of frames in a sequence of images. Also shown are two images of the patient’s right hand during the motor assessment test as extracted from a bounding box as defined by four spatial coordinates in the image frame, where frame A is the original image in the bounding box and frame B is an amplified version of hand. In image B, white highlighting around the hand provides a visualization of amplified tremor. In an optical flow analysis, frame differencing can be used to provide an indication of movement over time between frames in a video of a motor assessment of a clinically relevant feature. To perform an optical flow analysis, spatial coordinates are used to define a bounding box within the image frame. Frame differencing can then be applied to amplify any subtle motion, such as, for example, in a motor assessment for postural tremor of hands as shown. In a motor assessment of tremor at rest, for example, a patient sits still in front of a camera with arms resting on the armrest. In a frame differencing analysis, a first image frame is compared with a second image frame to see how much the scene has changed. In an example of a motor assessment for tremor at rest, for example, a first image of a hand in a bounding box defined by a set of spatial coordinates at the clinically relevant feature (i.e. the trem oring hand) can be compared to a second image of the hand in the same bonding box defined by the spatial coordinates, and the difference in location of the hand over the time difference between the image frames can provide a quantitative and amplified indication of the hand tremor. In one method, the change in pixel luminosity at a particular spatial location in the image can be compared across consecutive images to identify regions of movement. In one example method of frame differencing, the pixel values from within the boundary box in a firm image frame is subtracted from the corresponding pixel values in the boundary box in a second image frame, where the difference in pixel value at the same location in the boundary box in each frame highlights the difference between the images in the two frames. To refine this process, a weighted combination of the two frames can be used, where the difference is computed as a blend of the pixel values from the first and second image frames. This approach can amplify subtle changes, making it easier to isolate and analyze motion. By isolating these differences, frame differencing can emphasize subtle movements,such as tremors, which manifest as variations in pixel density across the sequence of frames. These changes can then be quantified to measure the degree and location of motion, providing valuable insights into the movement occurring between frames.

[0138] Optical flow can then be used to track the movement of pixels between two consecutive frames. The combination of frame differencing and optical flow can be used to quantify both the frequency and amplitude of the movement, but also how much movement occurred and in which direction the movement occurred. To calculate optical flow, in one example, an optical flow Farneback algorithm can be used to calculate the difference between where pixels are located in a first image frame compared to the position of the same pixels in a second image frame. In a resting tremor assessment, this can be modeled, for example, by identifying the greyscale pixel outline of a hand in a first image frame, identifying the same outline in a second image frame, and then comparing the distance between the outline pixels between the two image frames. Other methods using colour can also be used. The output is a two-channel array representing horizontal motion and vertical motion, which provides the magnitude of motion across the frames. The horizontal and vertical motion can then be calculated and quantified for analysis by the motor assessment model.

[0139] Figure 13 is a perspective view of an example embodiment of a system 100 for performing a motor assessment. In accordance with the teachings herein, there are provided various embodiments for configuring a system for performing a motor assessment of a user such that the configuration is effective for the entirety of the motor assessment, including for various positions of the user relative to the system and for various body positions of the user. For example, the configured system is effective for one or more motor tasks of the motor assessment, without requiring re-configuration of the system between tasks. Previously, systems for performing a motor assessment of a user, for example, those involving image capture devices and / or other sensors, typically required configuration or calibration procedures to be performed at several instances throughout the motor assessment. For example, configuration or calibration procedures were required to be performed between each motor task based on what body part of the user was being assessed in the subsequent motor task and / or what body position the user was required to be in for the subsequent motor task (e.g., sitting, standing, walking, etc.). Each time another calibration or configuration procedure is required, the total time required to complete the motor assessment increases. This is particularly problematic for users who may have a motordisease or disorder, as increased motor assessment timing can result in testing fatigue. Testing fatigue can, for example, manifest as seemingly poorer scores on motor tasks towards the end of a motor assessment, where the poorer scores are due to testing fatigue rather than true motor functionality. It is believed that the methods of configuring a system for performing a motor assessment of the user, in accordance with the teachings herein, will provide an improved motor assessment experience and reliability by facilitating configuration of the system that is effective for the duration of the motor assessment such that a configuration or calibration process is not necessary at multiple instances throughout the motor assessment based on the different types of motor tasks being performed.

[0140] The example motor assessment system as shown in Figure 13 comprises a support member 102, at least two image capture devices 104, 106, 108, and a display device 110. The system 100 can further include an electronic computing device (not shown), the structure of which is described in more detail with reference to Figure 15. It will be appreciated that the configuration of the system 100 shown in Figure 13 is provided for illustration purposes only and other configurations that provide the same functionality may be possible. The support member 102 can be oriented in a generally vertical manner. In some embodiments, the support member 102 can have a length and / or height in the range of about 18.5 inches to about 32.25 inches such that it can support the image capture devices 104, 106, 108 and display device 110 at a suitable height for image capture and display. Software and hardware can also be used to change the angle and field of view of the captured images, which enables stationary mounting of the image capture device(s). A lower end of the support member 102 can be coupled to a base 128. In some embodiments, the base 128 can include a plurality of feet 129a-d extending outwardly, for example, two, three, four, five, or more feet. Each foot 129a-d of the base can optionally include a caster wheel 130a-d. In some embodiments, the base 128 does not include any wheels. In some embodiments, the base 128 includes a single structure without feet that is shaped and sized to provide sufficient support and / or balance to the system 100. Image capture devices 104, 106, 108 can optionally be capable of folding action that allows for easier storage. In other embodiments the system can further comprise a mobile power supply, uninterruptible power supply, or wired connection to a power supply. In other embodiments the system 100 can further comprise one or more of a microphone to capture audio or sound and a speaker to play audio or sound. The display device 110 can be coupled to an upper end of the support member 102. The displaydevice 110 can be any device capable of any combination of displaying images, retrieving images, and storing images. For example, the display device 110 can be a display screen, a tablet, and / or a projector. Other display devices are possible. The display device 110 can include but is not limited to one or more screens, and / or any other suitable device with display functionalities. In some embodiments, the display device 110 can include or be connected to a dedicated processor and / or a dedicated data storage component which can be on or connected to the support member, or accessed through a wireless connection to a wirelessly connected or cloud computing device. In some embodiments, the display device 110 can be in communication with an optional display-mounted image capture device 112 that is separate from image capture devices 104, 106, 108. For example, the optional display-mounted image capture device 112 can include a webcam mounted to the display device 110. In some embodiments, the displaymounted image capture device 112 and the display device 110 can together be used for videoconferencing.

[0141] The image capture devices 104, 106, and 108 can be any device capable of any combination of capturing images, generating images, and storing images. For example, the image capture device 104, 106, and 108 can be one or more of a 2D camera, 3D camera, time of flight camera, depth camera, video recorder, high speed camera, optical flow sensor, light detection and ranging (LiDAR) camera, plenoptic camera, or any other suitable image capture device. In some embodiments, the image capture device 104, 106, and 108 includes a depth camera and / or a 3D camera. In some embodiments, each of the image capture devices 104, 106, and 108 can be configured for capturing images within a particular range of distances from a lens position of the image capture device 104, 106, and 108. For example, in some embodiments, the image capture device 104, 106, and 108 can be configured to capture images at about 25-546 cm (9.8 inches to about 214.9 inches) from the lens position of the image capture device 104, 106, and 108. Other image capture device configurations are possible to facilitate image capturing at other suitable distances from the lens of the image capture device 104, 106, and 108. Although not shown, in some embodiments, the image capture devices 104, 106, and 108 can each include a dedicated processor and / or a dedicated storage component. In some embodiments, image capture device 108 can be configured to capture images of a hand of the user while performing a motor task of the motor assessment involving the user’s hand (e.g., a hand motor task). For example, in some embodiments, image capture device 108 is configured to capture images of theuser’s hand that is positioned in a generally upward direction from image capture device 108. In some embodiments, the hand motor assessment task comprises a hand movement task, a postural tremor of hands task, and / or a pronation and supination task. The image capture device 108 can be referred to as the hand task image capture device or the lower image capture device. In some embodiments, image capture devices 104 and 106 can be configured to capture images of at least a portion of the user’s body while performing a motor task of the motor assessment involving one or more portions of the user’s body (e.g., a body motor task). For example, in some embodiments, image capture device 104 is configured to capture images of the user’s head and / or face while the user is performing a motor task of the motor assessment. In some embodiments, image capture device 106 is configured to capture images of the user’s whole body while performing a motor task of the motor assessment. In some embodiments, image capture device 104 is configured to capture images of a hand of the user while performing a motor task of the motor assessment. In some embodiments, the body motor task comprises a facial expression task, a finger tapping task, a tremor at rest task, a gait task, a leg stomping task, an arising from seating apparatus task, and / or a posture task. Reference to the user’s body herein, can accordingly, refer to any portion and / or portions of the user’s body including, for example, the user’s entire body. Although Figure 13 shows an example embodiment including three image capture devices 104, 106, and 108 (not including the display-mounted image capture device 112), other numbers of image capture devices may be possible. For example, in some embodiments, the system 100 can include two image capture devices (not including the displaymounted image capture device 112). In embodiments having two image capture devices, the two image capture devices can include lower image capture device 108 and a second higher image capture device that provides the functionality of both image capture devices 104 and 106 as described above. As another example, in some embodiments, the system 100 can include more than three image capture devices.

[0142] The system 100 can further optionally include two or more support arms 118 and 120 coupled to and extending outwardly from the support member 102. The two or more support arms 118 and 120 can include, for example, an upper arm 118 and a lower arm 120. The support arms 118 and 120 can be substantially aligned in a vertical direction. For example, the support arms 118 and 120 can extend outwardly from the support member 102 in approximately the same direction. The support arms 118 and 120 can be coupled to the support member 102 at agenerally fixed relative distance with respect to one another. For example, the lower support arm 120 can be coupled to the support member 102 in a range of about 13.5 to about 49.5 cm (about 13.5 inches to 19.5 inches) below a lower surface of the upper support arm 118. In some embodiments, the lower support arm 120 has approximately the same length as the upper support arm 118. For example, in some embodiments, the lower support arm 120 has a length in the range of about 12 inches to about 14 inches and the upper support arm 118 has a length in the range of about 30.5 to 35.5 cm (12 inches to 14 inches). In some embodiments, the ratio of the upper support arm length to the lower support arm length is about 1. In some embodiments, the support arm 118 is coupled to a housing (described in more detail below) including two image capture devices 104 and 106. In some embodiments, the support arms 118 and 120 can be coupled to a housing including only one image capture device 104, 106 or 108. In some embodiments, the support arms 118 and 120 can be coupled to a housing including three or more image capture devices 104, 106 and 108. In some embodiments, the number of support arms corresponds to the number of image capture devices (not including the display-mounted image capture device). In some embodiments, support arm 120 is in a fixed position on support member 102. In some embodiments, the position of support arm 120 is vertically adjustable along the length of support member 102. For example, in some embodiments, support arm 120 is removably coupled to support member 102, allowing the height of support arm 120 relative to the floor to be adjusted. In some embodiments, support arm 120 is removably coupled to support member 102 via one or more removable fasteners such as a bolt, or extendable and / or adjustable fastener such as a cam, gear, friction fit, or pivot, for example. In some embodiments, the position of support arm 120 along the length of support member 102 can be vertically adjusted via an actuator (not shown). For example, in some embodiments, an actuator can be mounted to the portion of the system 100 on which the display device 110 is supported and can extend in a generally downward direction. The actuator can include an actuator motor (not shown) that is controlled by a controller (not shown). In some embodiments, a person (e.g., the user, the user’s caregiver, a healthcare professional etc.) can operate the controller to control the actuator motor. In some embodiments, the system 100 can automatically operate the controller to control the actuator motor without requiring any human input. The system 100 can further include two or more housings 114 and 116 for housing the image capture devices 104, 106 and 108. The housings 114 and 116 can be coupled to a distal end of the support arms 118 and 120. Eachhousing 114 and 116 can include an opening for a lens or viewing aperture of the image capture devices 104, 106 and 108. Each opening can be sized and shaped appropriately for the corresponding image capture device 104, 106 and 108 housed in the housing 114 and 116. The housing 116 is preferably rotatable along a pitch axis 124, where the pitch axis 124 is approximately perpendicular to a longitudinal axis defined by the support arm 120 coupled to the rotatable housing 116. The direction of rotation is shown as 126. The rotatable housing 116 can include an adjustable component 122 for adjustably fixing the rotatable housing 116 in a rotated position. In some embodiments, the rotatable housing 116 can be rotated to accommodate different arm lengths and / or different mobilities of different users. In some embodiments, the rotatable housing 116 can be manually rotated by a person (e.g., the user, the user’s caregiver, a healthcare professional etc.). In some embodiments, the system 100 can include a rotating mechanism (e.g., actuator, not shown) and a rotating mechanism or controller 105 (e.g., microprocessor, not shown) for automatically rotating the rotatable housing 116. For example, in some embodiments, the system 100 can operate to determine that a rotation of rotatable housing 116 is required and to send instructions to the rotating mechanism controller to cause the rotating mechanism to rotate the rotatable housing 116. The housing 114 can be fixed relative to the support arm 118.

[0143] The lower image capture device can be rotated along the pitch axis 124 to facilitate positioning of the target body portion for the lower image capture device at the target location for the lower image capture device and the target body portion within the lower configuration boundary can be shown in the corresponding live view image. For example, rotating the lower image capture device along the pitch axis 124 allows the system 100 to accommodate different arm lengths and / or different mobilities of different users. For example, a user with a longer arm length can rotate the lower image capture device in a clockwise direction (e.g., around pitch axis 124) in order to position their hand at the target location for the lower image capture device. As another example, a user with a shorter arm length and / or less arm mobility can rotate the lower image capture device in a counterclockwise direction (e.g., around pitch axis 124) in order to position their hand at the target location for the lower image capture device. A user’s arm mobility can, for example, refer to the user’s ability to fully outstretch their arm or to hold their arm in a raised position in front of their torso. In some embodiments, the lower image capturedevice can be rotated by the user, a caregiver accompanying the user, and / or automatically by the system 100, as described herein.

[0144] Figure 14 is a side view of an example embodiment of a system 100 for performing a motor assessment. Although not shown in Figure 14, the system 100 can include an actuator for moving the support member 102 in a generally vertical direction 132 relative to base member 103 in a telescoping manner. It should be noted that the actuator for moving the support member 102 is distinct from the actuator described with reference to support arm 120 for adjusting the position of support arm 120 along the length of support member 102. For example, in some embodiments, the actuator for moving the support member 102 includes an actuator motor (not shown). In some embodiments, the actuator motor is located inside the support member 102, which is coupled to a base 128. In some embodiments, the actuator motor is located outside of the support member 102 (e.g., behind the display device 110). Adjustable component 126 on support arm 120 can adjust the location of lower image capture device 108 up and down, for example, in the direction of rotation is shown as 126. The actuator motor can be controlled by a controller 105. The actuator motor can be in communication with the controller 105 via a wired connection or via a wireless connection. In some embodiments, the system 100 includes a mechanism for storing the controller 105 when the controller 105 is not in use. For example, in some embodiments, the controller 105 can be slotted into a storage component of the system 100. For example, in some embodiments, the storage component can include a dovetail slot for receiving the controller 105. In some embodiments the controller 105 includes a rocker switch, a button, a joystick, a touchpad, a touchscreen, or any other suitable control mechanism for operating the controller that allows a person (e.g., the user, the user’s caregiver, a healthcare professional etc.) to control movement of the actuator. In some embodiments, the controller 105 can be controlled by the system 100 to automatically control movement of the actuator without requiring intervention from a person. For example, in some embodiments, the system 100 can operate to determine that a height adjustment is required and to send instructions to the controller to move the actuator accordingly. For example, the actuator can move the support member 102 in an upward direction or a downward direction to adjust the height of the support member 102 and the support arms 118 and 120 coupled to the support member 102 relative to the floor. Accordingly, in some embodiments, the support member 102 can be referred to as an adjustable support member 102. This generally vertical movement 132 facilitates an adjustment of theheight of the upper image capture devices 104 and lower image capture device 108 to accommodate different body measurements of different users such as, for example, the user’s height. Although the generally vertical movement 132 of the support member 102 facilitates an adjustment of the height of the image capture devices 104, 108, the relative distance and / or position between the image capture devices 104, 108 is maintained. An optional actuator of the system 100 is operable to adjust the height of the support member 102 to facilitate positioning of the target body portion for the upper image capture device at the target location for the upper image capture device and showing the target body portion within the upper configuration boundary. In some embodiments, the height of the support member 102 can be adjusted by the user controlling the actuator, a caregiver of the user controlling the actuator, and / or automatically by the system 100 controlling the actuator, as described herein.

[0145] Figure 15 is a block diagram of an example embodiment of an electronic device 300 that may be used with the system for performing a motor assessment. The electronic device 300 is provided as an example and there can be other embodiments of the electronic device 300 with different components or a different configuration of the components described herein. The electronic device 300 includes a processing unit 308, a display device 304, a user interface 314, an interface unit 306, input / output (I / O) hardware 312, a communication unit 302, a power supply unit 316, and a memory unit 310. The memory unit 310 includes random access memory (“RAM”) and non-volatile storage for storing data files 330 and software code for various programs such as those used to provide a Graphical User Interface (GUI) engine 320, an operating system 322 and other software programs 324 as well as software modules such as a motor assessment application 326, an I / O module 328, files 330 and one or more databases 332 that collectively are used to perform various functions related to performing calibration and a motor assessment. Various components of the electronic device 300 may be connected by a communication bus to facilitate communication therebetween and a power bus to receive power from the power supply unit 316. Various components of the electronic device 300 can be mounted to a microprocessor board so that it may be housed within the motor assessment system. In other embodiments, the electronic device 300 may have a different configuration and / or include other components or not include all of the components shown in Figure 13 or Figure 14 while still providing the motor assessment functions discussed herein. The processing unit 308 controls the operation of the electronic device 300 and can be any suitable processor,controller or digital signal processor that can provide sufficient processing power processor depending on the configuration, purposes and requirements of the electronic device 300 as is known by those skilled in the art. For example, the processing unit 308 may be a high- performance general processor. In alternative embodiments, the processing unit 308 may include more than one processor with each processor being configured to perform different dedicated tasks. In alternative embodiments, specialized hardware can be used to provide some of the functions provided by the processing unit 308. The display device 304 can be any suitable display as discussed. The user interface 314 enables a user to provide input via one or more input devices, which may include, but is not limited to, a mouse, a keyboard, a trackpad, a thumbwheel, a trackball, voice recognition, a touchscreen, one or more push buttons, a scroll wheel, a remote controller, and / or a mobile device, for example, depending on the implementation of the electronic device 300. The user interface 314 can also output information to one or more output devices, which may include, for example, the display device 304, a printer and / or a speaker. In some cases, the display device 304 may be used to provide one or more GUIs through an Application Programming Interface. A user may then interact with the one or more GUIs via the user interface for configuring the electronic device 300 to operate in a certain fashion and / or provide input data. For example, the user may input data for system parameters that are used for proper operation of hardware and software that is used for performing a motor assessment, such as calibration data and operating parameters.

[0146] The interface unit 306 can be any interface that allows the electronic device 300 to send and receive signals with other devices external to the electronic device 300 such as sensors, signal processing hardware, other electronic devices including computers, mobile devices, tablets, servers and the like. For example, the interface unit 306 can include at least one of a serial port, a parallel port or a USB port that provides USB connectivity. The interface unit 306 can also include wired or wireless capability for connection to at least one of an Internet, a Local Area Network (LAN), an Ethernet, a Firewire, a modem, a cloud computing platform, or a digital subscriber line connection. In some embodiments, various combinations of these elements may be incorporated within the interface unit 306. The interface unit 306 can allow the electronic device 300 to send control signals to and receive data from the image capture devices 318. The communication unit 302 can be a radio that communicates utilizing CDMA, GSM, GPRS or Bluetooth protocol according to standards such as IEEE 802. I la, 802.1 lb, 802.11g, or 802.1 In.The communication unit 302 can be used by the electronic device 300 to communicate with other devices or computers. The communication unit 302 can be a radio that communicates utilizing CDMA, GSM, GPRS or Bluetooth protocol according to standards such as IEEE 802.11a, 802.11b, 802.11g, or 802.1 In. The communication unit 302 can provide the processing unit 308 with a way of communicating wirelessly with various devices that may be remote from the electronic device 300. In some embodiments, the communication unit 302 may be optional. The power supply unit 316 can be any suitable power source such as a battery, or power conversion hardware to a wired power supply that provides power to the various components of the electronic device 300. The power supply unit 316 may be a power adaptor or a rechargeable battery pack depending on the implementation of the electronic device 300 as is known by those skilled in the art. In some cases, the power supply unit 316 may include a surge protector that is connected to a mains power line and a power converter that is connected to the surge protector (both not shown). The surge protector protects the power supply unit from any voltage or current spikes in the main power line and the power converter converts the power to a lower level that is suitable for use by the various elements of the electronic device 300. In other embodiments, the power supply unit 316 may include other components for providing power or backup power as is known by those skilled in the art.

[0147] The memory unit 310 includes a non-volatile storage such as ROM, one or more hard drives, one or more flash drives or some other suitable data storage elements. The non-volatile storage may be used to store software instructions, including computer-executable instructions, for implementing the operating system 322, the software programs 324 and other software modules, as well as storing any data used by these software modules. The data may be stored in the database(s) 332 and / or data files 330, such as for data relating to users that are performing a motor assessment using the system. The data files 330 can be used to store data for the electronic device 300 such as, but not limited to, device settings, parameter settings, calibration data, raw image capture device data, and processed image capture device data, for example. The files 330 can also store other data required for the operation of the motor assessment application or the operating system such as dynamically linked libraries and the like. The I / O (input / output) module 328 includes software instructions that, when executed by the processor(s) of the processing unit 308, can configure the processor(s) to receive image data, store data in the files 330 or database(s) 332 and / or retrieve data from the data files 330 or database(s) 332. Forexample, the I / O module 328 may be used to receive one or more image data streams from image capture devices 318. In another aspect, the I / O (input / output) module 328 includes software instructions that, when executed by the processor(s) of the processing unit 308, configure the processor(s) to store any input data from the user, such as control inputs, operational parameters and / or user data (such as, but not limited to, identity, age, sex, ethnicity, geographical location and / or medical conditions) that is received through one of the GUIs. In addition, any received and / or processed image data may be provided through use of the input / output module 328 in a user interface from the GUI engine for viewing by the user on the display device 304. Alternatively, or in addition thereto, such data may be provided through use of the input / output module 328 to the communication unit 302 or interface unit 306 for transmission to another electronic device and / or a remote storage device. For example, the results of a motor assessment may be organized into a report that may be transmitted to another electronic device, for example or to a cloud-based data store. In at least one embodiment, the motor assessment application 326 can include various software instructions that, when executed by at least one of the processor(s) of the processing unit 308, configure the electronic device 300 to receive commands from the user for performing various functions, such as, but not limited to, guiding the user through a calibration process and / or performing a motor assessment.

[0148] The GUI engine 320 includes software instructions that, when executed by the processor(s) of the processing unit 308, configure the processor(s) to generate various GUIs that are then output on the display device 304, or another visual output device, to allow the user to perform various functions such as displaying instructions related to the motor assessment, displaying raw and / or processed data and / or results from the motor assessment application 326. The image capture device 318 can be any image capture device as described herein, and in particular, as described previously with reference to Figures 13 and 14. For example, image capture device 318 can include or be one or more image capture device as previously described. For ease of understanding, certain aspects of the methods described herein are described as being performed by the processor(s) of the processing unit 308 when executing software instructions for the motor assessment application 326, for example. It should be noted, however, that these methods are not limited in that respect, and the various aspects of the methods described herein may be performed by other hardware and software components for performing a motor assessment.

[0149] Figure 16 is a flowchart of an example embodiment of a method 400 for configuring the system 100 for performing a motor assessment. To assist with the description of method 400, reference will be made simultaneously to Figures 17, 18, 19A, 19B, 20A, 20B. The method 400 can be implemented by an electronic device, such as the electronic device described in Figure 15, having at least one processor, such as a processor or processing unit. Method 400 can begin at 402 when the processor receives an image data stream from at least one of a lower image capture device and an upper image capture device. Each image data stream can include image data representing a stream of images of the scene in the field of view of each image capture device. For example, an image capture device can capture an image of the current scene (i.e., a live view) in the image capture device’s field of view at a given image capture rate, and generate an image data stream for that image capture device. In some embodiments, the image capture devices can have an image capture rate of at least about 30 frames per second. A position of the lower image capture device relative to the upper image capture device is maintained for the duration of the method 400 to facilitate configuring the system for the user to perform one or more tasks of the motor assessment at a plurality of distances relative to the system and a plurality of body positions of the user without having to recalibrate or reconfigure the system in between these different tasks performed at different distances. For example, in some embodiments, the plurality of distances relative to the system includes a first distance (e.g., close distance) that is in the range of about 61 to 76 cm (24 to 30 inches) between the user position and the centre of the support member of the system and a second distance (e.g., far distance) that is in the range of about 266 to 305 cm (105 to 120 inches) between the user position and the centre of the support member of the system. In some embodiments, the close distance and the far distance are measured from about the centre of the support member of the system to a front end of a foot of the user. Other distances are possible. For a gait test, for example, the patient walks toward the camera, keeping the whole body within the visual frame (head to toes), and turns to walk away from the camera for a distance of about 10 to 30 feet, or about 20 feet, turns again, and continues walking back and forth for between about 20 to 30 seconds. By way of another example, for seated tests requiring a full body view for assessing the toe tapping, leg stomping, and arising from chair a distance of about 60 to 80 inches is suitable, and the same distance is suitable for the posture test which requires a full body view (head to toes).

[0150] Each image data stream can have a most recent image, corresponding to the most recent image captured by the image capture device. Each image from each image data stream can have any acceptable number of pixels. Each image from each data stream can be any acceptable size and any acceptable resolution. In some embodiments, as a first step, the processor or processing unit assigns a label to each image capture device of the system. At 402, the processor receives at least one data a stream from an image capture device. In some embodiments, for example, the lower image capture device can be an image capture device as shown in Figure 13 or 14, and the upper image capture device can be one of the image capture device and image capture device as shown in Figure 13 or 14. Each of the lower image capture device and the upper image capture device can be configured as described above with reference to Figures 13 and 14. At 404, the processor displays, on the display device, for the image capture device, a live view image. The live view image, for the lower image capture device and / or the upper image capture device, can include an image or the most recent image from the respective image data stream of each image capture device on a graphical user interface (GUI). In some embodiments, the live view image corresponding to the lower image capture device is referred to as the lower live view image, and the live view image corresponding to the upper image capture device is referred to as the upper live view image. At 406, the processor displays, on the display device, for each of the live view images displayed at 404, a configuration boundary (e.g., calibration boundary) overlaid on each live view image. At 408, the processor updates each live view image with the most recent image from the corresponding image data stream until each live view image shows the corresponding target body portion of the user within the corresponding configuration boundary. For example, the processor can continuously update the lower live view image with the most recent image from the lower image data stream until the lower live view image shows the target body portion for the lower image capture device within the lower configuration boundary. For example, the processor can continuously update the upper live view image with the most recent image from the upper image data stream until the upper live view image shows the target body portion for the upper image capture device within the upper configuration boundary. In some embodiments, the live view image for one image capture device can display the corresponding target body portion within the corresponding configuration boundary before, after, or simultaneously to the live view image of another image capture device displaying the corresponding target body portion within the corresponding configuration boundary. For example, in one embodiment, theupper live view image can display the user’s head within the upper configuration boundary and subsequently, the lower live view image can display one of the user’s hands in the lower configuration boundary. In some embodiments, the lower live view image can display one of the user’s hands in the lower configuration boundary and subsequently, the upper live view image can display the user’s head within the upper configuration boundary. In some embodiments, the upper live view image can display the user’s head within the upper configuration boundary simultaneously with the lower live view image displaying one of the user’s hands in the lower configuration boundary.

[0151] Figure 17 is an illustration of an example graphical user interface (GUI) 500 on a system for performing a motor assessment for assigning image capture device labels and displaying these on a display device. Each image capture device can be configured to capture images during certain motor assessment tasks or test. This calibration step ensures that the correct image capture device is used for the correct motor assessment task. In some embodiments, this can include receiving user input to assign a label to each image capture device. In some embodiments, this step is performed automatically by the system, without requiring user input. In some embodiments, this step is performed upon initially powering up the system. That is, in some embodiments, this step is performed only when the system is initially powered on and does not need to be performed between motor assessments if the system remains powered on. GUI 500 displayed on the display device can include a live view image 504 from one of the upper, middle, or lower image capture devices or cameras 508a, 508b, 508c. For example, the processor can receive an image data stream from one of the image capture devices or cameras 508a, 508b, 508c. The processor can display, on the display device, a live view image 504 including a recent image or the most recent image from the image data stream. The live view image 504 can, for example, show the user 506 if the user is positioned in the field of view of the image capture device corresponding to the displayed live view image 504. As shown, the GUI 500 can further include one or more labels for cameras 508a-508c for the user to select from to assign a label to each image capture device. Based on the user’s selection, the processor can assign the selected label to the image capture device corresponding to the displayed live view image 504. For example, in the embodiment shown, three labels are displayed: upper camera 508a, middle camera 508b, and lower camera 508c, each corresponding to a different image capture device of the system, for example. Although the embodiment illustrated shows threepossible labels 508a-508c, some embodiments can include more labels or fewer labels depending on the number of image capture devices. For example, in some embodiments, the GUI 500 can include two labels. For example, in some embodiments, the labels can include upper camera 508a and lower camera 508c. Although the labels illustrated each refer to a camera, it is understood that the labels can refer to any image capture device as described herein. Once a label is assigned to the live view image 504, the processor can receive another image data stream from another image capture device of the system that does not yet have a label assigned. The processor can display, on the display device, a live view image including the most recent image from the image data stream. The user can select the appropriate label and the processor can assign the selected label to the image capture device corresponding to the displayed live view image. This process can be repeated for any remaining image capture devices of the system.

[0152] As shown in Figure 17, the GUI 500 can further include one or more instructions 502 to the user. For example, the instructions 502 can include text to indicate to the user that the user should select an image capture device label for cameras 508a-508c that corresponds to the image capture device from which the live view image 504 is displayed. For example, if the live view image 504 corresponds to the upper camera 508a, the user can select the upper camera 508a for that live view image 504. As another example, if the live view image 504 corresponds to the lower camera 508c, the user can select the lower camera 508c for that live view image 504. Although the instructions illustrated in Figure 17 refer to a camera, it is understood that the instructions can refer to any image capture device as described herein. Although Figure 17 illustrates an embodiment in which one of labels for cameras 508a-508c is assigned to one live view image 504 at a time, in some embodiments, a live view image from each of a plurality of image capture devices can be displayed on the display device simultaneously and the user can select a corresponding label for each displayed live view image simultaneously rather than sequentially.

[0153] Figure 18 is an illustration of an example GUI 600 on a system for performing a motor assessment for configuring image capture devices of the system that is displayed on a display device. The GUI 600 can include one or more instructions to the user 602, two or more live view images 604a-604b, and configuration boundaries 606a-606b overlaid on corresponding live view images 604a-604b. In some embodiments, the live view images 604a-604b can correspond to the lower image capture device and the upper image capture device, respectively. The upper liveview image 604a can display a portion of the user’s body, for example, the user’s upper torso 610 and head 608. The lower live view image 604b can display a portion of one of the user’s hands. As shown, the lower live view image can display a palm side 614 of the user’s left hand 612. Each of the configuration boundaries 606a-606b overlaid on a respective live view image 604a-604b can correspond to a target location within the field of view of the corresponding image capture device at which a target body portion of the user is to be positioned. In the embodiment shown, the configuration boundary 606a overlaid on the upper live view image 604a corresponds to a target location in the field of view of the upper image capture device at which an upper target body portion of the user is to be positioned. The target body portion for the upper image capture device can also include the user’s head 608. A configuration boundary 606b overlaid on the lower live view image 604b corresponds to a target location in the field of view of the lower image capture device at which another target body portion of the user is to be positioned. For example, the target body portion for the lower image capture device can include one of the user’s hands 612. In some embodiments, the configuration boundary 606b overlaid on the lower live view image is referred to as the lower configuration boundary. In some embodiments, the configuration boundary 606a overlaid on the upper live view image is referred to as the upper configuration boundary. The GUI 600 can further include one or more instructions 602 to the user. For example, an instruction 602 to the user can indicate that the user should ensure that the user’s head 608 and hand 612 are each positioned within the respective configuration boundaries 606a-606b in corresponding live view images 604a-604b. Instructions to the user can comprise one or more of a still image, video image, text, still graphic, animated graphic, and can also be accompanied by non-speech audio indicators such as beeps or sound, or oral or speech based instructions in the language of the patient and / or clinician. Although the instruction illustrated in Figure 18 refers to a camera, it is understood that the instruction can refer to any image capture device described herein. In some embodiments, the one or more instructions 602 to the user can indicate that the user should adjust the height of the image capture device corresponding to live view image 604a (e.g., via the actuator) to ensure that the user’s head 608 is positioned within configuration boundary 606a. In some embodiments, the one or more instructions 602 to the user can indicate that the user should rotate the image capture device corresponding to live view image 604b (e.g., via the rotatable housing) to ensure that the user’s hand 612 is positioned within configuration boundary 606b. Although the embodimentshown illustrates the user’s head and one of the user’s hands as the target body portions, it is understood that other target body portions are possible. Although the embodiment shown illustrates two live view images, one corresponding to the upper image capture device and one corresponding to the lower image capture device, it is understood that other numbers of live view images (and accordingly configuration boundaries) are possible.

[0154] Figures 19A, 19B, 20A, and 20B are for illustration purposes only, and other configurations of system 700 are possible. For example, in some embodiments, the system 700 can include two image capture devices instead of three image capture devices 704, 706, and 708. For example, in some embodiments, system 700 can include image capture device 708 and a second image capture device. Instead of including image capture devices 704 and 706, the second image capture device can include one image capture device that provides the functionality of both image capture devices 704 and 706 as described herein. In such embodiments, the second image capture device can be positioned in the housing shown for image capture devices 704 and 706.

[0155] Figure 19A provides an illustration of an example user in a seated position 701 at a predetermined distance 712a in front of the system 700. In some embodiments, for example, the plurality of body positions of the user comprises a sitting position captured by at least one of the lower image capture device and the upper image capture device, a standing position captured by the upper image capture device, and a walking position captured by the upper image capture device. As shown, the user 718 can be positioned in a sitting position 701 on a seating apparatus 714 (e.g., chair or stool). In the embodiment illustrated, the seating apparatus 714 is positioned at a predetermined distance 712a from the system 100 corresponding to the first (e.g., close) distance as described previously. For example, the predetermined distance 712a can be measured from about the centre 710 of the support member 702 of the system 700 to the front edge 716 of the seating apparatus 714. In some embodiments, the predetermined distance 712a can range from about 24 inches to about 30 inches. The upper image capture device 704 can be configured for capturing images of the user’s head, face and / or hand when held upwards in the field of view of the upper image capture device 704. Similarly, the lower image capture device 708 can be configured for capturing images of one and / or both of the user’s hands when the user holds one and / or both hands in the field of view of the lower image capture device 708. For example, in some embodiments, the lower image capture device 708 can be used to capture images of oneand / or both of the user’s hands when performing any combination of a hand movement task, a resting hand tremor task, and a pronation and supination task. In some embodiments, for example, the image capture device 704 can be used to capture images of the user’s face when performing a facial expression task. In some embodiments, for example, the upper image capture device 704 can be used to capture images of one and / or both of the user’s hands when performing a finger tapping task.

[0156] Figure 19B illustrates an example user in a sitting position 720 at a predetermined distance 712b in front of the system 700. The user 718 can be positioned in a sitting position 720 on a seating apparatus 714. The seating apparatus 714 is positioned at a predetermined distance 712b from the system 700 corresponding to the second (e.g., far) distance described previously. The predetermined distance 712b can be measured from about the centre 710 of the support member 702 of the system 700 to the front edge 716 of the seating apparatus 714. In some embodiments, the predetermined distance 712b can be in the range of about 105 inches to about 120 inches. In the example embodiment illustrated, the middle image capture device 706 is already configured / positioned for capturing images of the user’s body, which can include, for example, the user’s entire body, based on the previous configuring or calibration of the system. No further calibration or reconfiguring is needed even though the user is at a greater distance away from the system. This is at least in part due to a wider field of view of the image capture device being used at the second (e.g., far) distance and the generally insignificant height variation between users in a seated position at the second (e.g., far) distance For example, in some embodiments, the middle image capture device 706 can be used to capture images of the user’s body when performing at least one of: an arising from seating apparatus task and a leg stomping task.

[0157] Figure 20A illustrates an example user in a standing position 722 at a predetermined distance 712c in front of the system 700. As shown, the user 718 can be positioned in a standing position 722 at a predetermined distance 712c from the system 700 corresponding to the second (e.g., far) distance described previously where the predetermined distance 712c can be measured from about the centre 710 of the support member 702 of the system 700 to a front end of a foot 724 of the user 718. The front end of a foot 724 of the user can be, for example, a front end of the user’s toe. In the example embodiment, the middle image capture device 706 does not need to be reconfi gured / recalibrated for capturing images of the user’s body, which can include, forexample, the user’s entire body as was explained previously. For example, in some embodiments, the middle image capture device 706 can be used to capture images of the user’s body when performing at least one of: a tremor at rest task, and a posture task.

[0158] Figure 20B illustrates an example user performing a walking task 726 at a predetermined distance 712d in front of the system 700. As shown, the user 718 can perform the walking task 726 at a predetermined distance 712d from the system 700 corresponding to the farther distance described previously. The predetermined distance 712d can be measured from about the centre 710 of the support member 702 of the system to a side of a foot 725 of the user 718. The side of a foot 725 of the user can be, for example, the outside side of the user’s foot nearest to the system 700. In the example embodiment illustrated, the middle image capture device 706 does not need to be reconfigured / recalibrated for capturing images of the user’s body, which can include, for example, the user’s entire body, for reasons given previously. For example, in some embodiments, the middle image capture device 706 can be used to capture images of the user’s body when performing one or more walking tasks. In some embodiments, the user 718 performs the walking task 726 in a direction perpendicular to an axis defined by a lens of one of the image capture devices 704, 706, and 708.

[0159] All publications, patents and patent applications mentioned in this specification are indicative of the level of skill of those skilled in the art to which this invention pertains and are herein incorporated by reference. The reference to any prior art in this specification is not, and should not be taken as, an acknowledgement or any form of suggestion that such prior art forms part of the common general knowledge.

[0160] While the applicant’s teachings described herein are in conjunction with various embodiments for illustrative purposes, it is not intended that the applicant's teachings be limited to such embodiments. On the contrary, the applicant's teachings described and illustrated herein encompass various alternatives, modifications, and equivalents, without generally departing from the embodiments described herein. For example, while the teachings described and shown herein may comprise certain elements / components and steps, modifications may be made as is known to those skilled in the art. For example, selected features from one or more of the example embodiments described herein in accordance with the teachings herein may be combined to create alternative embodiments that are not explicitly described. All values and sub-rangeswithin disclosed ranges are also disclosed. The subject matter described herein intends to cover and embrace all suitable changes in technology.

[0161] The invention being thus described, it will be obvious that the same may be varied in many ways. Such variations are not to be regarded as a departure from the scope of the invention, and all such modifications as would be obvious to one skilled in the art are intended to be included within the scope of the following claims.

Claims

CLAIMS1. A method for performing a motor assessment comprising: obtaining a sequence of images of a clinically relevant feature of a patient during a motor assessment test; assigning spatial coordinates in the area of the clinically relevant feature on the sequence of images; defining a landmark in each image in the sequence of images using a selected subset of the assigned spatial coordinates; measuring the landmark across the sequence of images to provide a quantitative measurement of change in the sequence of images over time at the landmark; calculating a parameter that describes the change in the landmark across the sequence of images; comparing the calculated parameter for the landmark to a motor assessment model for the motor assessment test; and assigning a score for the patient for the motor assessment test.

2. The method of claim 1, wherein parameterizing the landmark data over time further comprises deconvoluting the parameterized landmark data using Fourier transform into a plurality of frequency bands.

3. The method of claim 2, wherein each of the plurality of frequency bands is associated with a specific movement mode.

4. The method of any one of claims 1-3, wherein the motor assessment model is a trained machine learning model trained on human clinician assessment of patients for the motor assessment test.

5. The method of any one of claims 1-4, wherein the landmark is derived from a relationship of the selected subset of the assigned spatial coordinates.

6. The method of claim 1, wherein calculating the parameter comprises: defining the landmark as a boundary box containing the clinically relevant feature; using frame differencing to amplify the change across the images in the boundary box; and parameterizing the frame differencing using optical flow.

7. The method of claim 6, wherein frame differencing is used to amplify signal motion in the boundary box.

8. The method of any one of claims 1-7, further comprising measuring a plurality of landmarks over time and assigning a score for the patient based on comparing a parameter for each of the plurality of landmarks to the motor assessment model.

9. The method of any one of claims 1-8, further comprising, prior to obtaining a sequence of images, providing the patient with instruction on how to perform the motor assessment test, the instruction comprising one or more of a still image, video image, text, still graphic, animated graphic, audio indicators, or speech.

10. The method of any one of claims 1-9, wherein the landmark comprises a centre of mass, angle created between lines of joined spatial coordinates, and ratio of distance between lines defined by spatial coordinates.

11. The method of any one of claims 1-10, wherein the spatial coordinates are in two dimensions or three dimensions.

12. The method of any one of claims 1-11, wherein each of the selected subset of assigned spatial coordinates are assigned a unique weight in the landmark, and the unique weights are used to define the landmark.

13. The method of any one of claims 1-12, wherein the landmark is parameterized using change over time in amplitude or frequency of the landmark.

14. The method of any one of claims 1-13, wherein the motor assessment test is a facial expression test, a finger tapping test, a tremor at rest task, a gait test, a leg stomping test, an arising from seating test, a posture test, a postural tremor of hands test, a hand movement test, a pronationsupination test, a toe tapping test, a gait test, or a kinetic tremor of hands test.

15. The method of any one of claims 1-14 further comprising, during the motor assessment test, a live view image of the patient is displayed in a graphical user interface that is viewable by the patient.

16. The method of any one of claims 1-15, wherein the score is based on the Movement Disorder Society - Unified Parkinson’s Disease Rating Scale.

17. A system for performing a motor assessment of a user comprising: at least one image capture device; a display device in communication with the image capture device; and at least one processor configured to receive a plurality of images from the image capture device and display the plurality of images on the display device, the system performing a method of:receiving, from the image capture device of the system, a data stream comprising a plurality of images of a patient performing a motor assessment; displaying, on the display device, a live view of the data stream comprising the plurality of images; displaying, on the display device, a configuration boundary overlaid on the live view image, the configuration boundary corresponding to a target location within a field of view of the image capture device at which a target body portion of the user is to be positioned; and capturing a sequence of images of a clinically relevant feature of a patient during the motor assessment test.

18. The system of claim 17, wherein the motor assessment task comprises a facial expression task, a finger tapping task, a tremor at rest task, a gait task, a leg stomping task, an arising from seating task, a posture task, a postural tremor of hands task, a hand movement task, a pronationsupination, a toe tapping task, a gait task, or a kinetic tremor of hands task.

19. The system of any one of claims 17 or 18, wherein the processor further performs the steps of: defining a landmark in each image in the sequence of images using a selected set of spatial coordinates; measuring the landmark across the sequence of images to provide a quantitative measurement of change in the sequence of images over time at the landmark; calculating a parameter that describes the change in the landmark across the sequence of images; comparing the calculated parameter for the landmark to a motor assessment model for the motor assessment test; and assigning a score for the patient for the motor assessment test.

20. The system of any one of claims 17-20, wherein the motor assessment model is a trained machine learning model trained on human clinician assessment of patients for the motor assessment test.

Images