Abstract: This disclosure provides a method for imaging lymph nodes and lymphatic vessels without a contrast agent. The method includes providing, using an optical source, an infrared illumination to a region of a subject having at least one lymphatic component, detecting a reflected portion of the infrared illumination directly reflected from the region using a sensor positioned thereabout, and generating at least one image indicative of the at least one lymphatic component in the subject using the reflected portion of the infrared illumination.

Abstract: The present disclosure relates to the treatment of patients with Parkinson's Disease using subthalmic nucleus deep brain stimulation to a specific region of the brain. By positioning the electrode in the margin of the dorsal-lateral and anterior region of the subthalamic nucleus, improved benefits are obtained.

Abstract: An image processing apparatus, includes a memory; and a processor coupled to the memory and configured to: generate a trained machine learning model by learning a machine learning model using a first set of image data, output an inference result by inputting a second set of image data to the trained machine learning model, and process a region of interest at a time of inference with respect to image data for which an inference result is correct in the second set of image data.

Abstract: Systems and methods are disclosed for identifying a diagnostic feature of a digitized pathology image, including receiving one or more digitized images of a pathology specimen, and medical metadata comprising at least one of image metadata, specimen metadata, clinical information, and/or patient information, applying a machine learning model to predict a plurality of relevant diagnostic features based on medical metadata, the machine learning model having been developed using an archive of processed images and prospective patient data, and determining at least one relevant diagnostic feature of the relevant diagnostic features for output to a display.

Abstract: The present disclosure provides a system and method for motion field generation and image correction. The method may include obtaining a plurality of first sets of magnetic resonance (MR) image data of an object generated based on a plurality of first sets of imaging sequences. The method may include obtaining a motion curve of the object. The method may include obtaining position emission tomography (PET) image data of the object generated in a scanning time period. The method may include generating one or more target motion fields corresponding to the scanning time period based on the plurality of first sets of MR image data and the motion curve. The method may include generating one or more corrected PET images by correcting, based on the one or more target motion fields, the PET image data.

Abstract: Registration of a surgical image acquisition device (e.g. an endoscope) using preoperative and live contour signatures of an anatomical object is described. A control unit includes a processor configured to compare the real-time contour signature to the database of preoperative contour signatures of the anatomical object to generate a group of potential contour signature matches for selection of a final contour match. Registration of an image acquisition device to the surgical site is realized based upon an orientation corresponding to the selected final contour signature match.

Abstract: A specimen holding and positioning apparatus operable to substantially non-movably maintain a specimen (e.g., an excised tissue specimen) in a fixed or stable orientation with respect to the apparatus during imaging operations (e.g., x-ray imaging), transport (e.g., from a surgery room to a pathologist's laboratory), and the like for use in facilitating accurate detection and diagnosis of cancers and/or other abnormalities of the specimen.

Abstract: A robotic surgery system includes: (1) a positioning stage and (2) at least one manipulator arm mounted to the positioning stage, wherein the manipulator arm includes a track and a tool carriage moveably mounted to the track, and the tool carriage includes a base and a pair of light emitting devices mounted to the base.

Abstract: Apparatus and methods for deactivating bronchial nerves extending along the secondary bronchial branches of a mammalian subject to treat asthma and related conditions. An ultrasonic transducer (11) is inserted into the bronchus as, for example, by advancing the distal end of a catheter (10) bearing the transducer into the secondary bronchial section to be treated. The ultrasonic transducer emits circumferential ultrasound so as to heat tissues throughout circular impact volume (13) as, for example, at least about 1 cm3 encompassing the bronchus to a temperature sufficient to inactivate nerve conduction but insufficient to cause rapid ablation or necrosis of the tissues. The treatment can be performed without locating or focusing on individual bronchial nerves. The apparatus and methods utilized for lung tumor ablation.

Abstract: The present invention relates to a device, system and method for less obtrusively determining a tissue characteristic of a subject, the device comprises a first control unit (11) configured to control an electromechanical transducer (31) by a first control signal (21) to transfer mechanical waves varying in a frequency range or with varying frequency content to an exposed tissue area of the subject; a second control unit (12) configured to control an electromagnetic radiation emitter (32) by a second control signal (22) to emit electromagnetic radiation towards the exposed tissue area of the subject; a radiation signal input (13) configured to obtain a radiation signal (23) indicative of electromagnetic radiation reflected from the exposed tissue area of the subject; and a processor (14) configured to determine a tissue characteristic signal (24) indicative of a tissue characteristic of the exposed tissue area of the subject derived from a frequency response or a frequency transfer function obtained from the

Abstract: In measuring a dimension of an object to be measured W made of a single material, a plurality of transmission images of the object to be measured W are obtained by using an X-ray CT apparatus, and then respective projection images are generated. The projection images are registered with CAD data used in designing the object to be measured W. The dimension of the object to be measured W is calculated by using a relationship between the registered CAD data and projection images. In such a manner, high-precision dimension measurement is achieved by using several tens of projection images and design information without performing CT reconstruction.

Abstract: A method for adjusting a medical device is provided. The method includes obtaining an initial trajectory of a component of the medical device. The initial trajectory of the component includes a plurality of initial positions. For each of the plurality of initial positions, the method further includes determining whether a collision is likely to occur between a subject and the component according to the initial trajectory of the component. In response to the determination that the collision is likely to occur, the method further includes updating the initial trajectory of the component to determine an updated trajectory of the component.

Abstract: For training for and performance of patient modeling from surface data in a medical system, a progressive multi-task model is used. Different tasks for scanning are provided, such as landmark estimation and patient pose estimation. One or more features learned for one task are used as fixed or constant features in the other task. This progressive approach based on shared features increases efficiency while avoiding reductions in accuracy for any given task.

Abstract: A method of registering a real-time image feed from an imaging device inserted into a steerable catheter using a navigation system is provided. The method includes inserting the imaging device into a working channel of the steerable catheter and generating a real-time image feed of one or more reference points, wherein the orientation of the reference points is known. The method further includes orienting a handle of the steerable catheter to a neutral position, displaying the real-time image feed on a display of the navigation system, and registering the real-time image feed to the steerable catheter by rotating the displayed image so that the reference points in the real-time image feed are matched to the known orientation of the reference points.

Abstract: Devices, systems, and methods of imaging a blood vessel are provided. For example, the method can include obtaining fluoroscopic image data of a region of interest in a blood vessel using an x-ray source; obtaining intravascular ultrasound (IVUS) data at a plurality of positions across the region of interest using an IVUS component disposed on an intravascular device; processing the fluoroscopic image data and IVUS data, including: determining, using the fluoroscopic image data, a position of the intravascular device with respect to the x-ray source at each of the plurality of positions across the region of interest; co-registering the fluoroscopic image data and the IVUS image data; and generating, a model of the region of interest including position information of a border of a lumen of the blood vessel at each of the plurality of locations; and outputting a visual representation of the model of the region of interest.

Abstract: A surgical vision system for imaging heat capacity and cooling rate of tissue has an infrared source configured to provide infrared light to tissue, the infrared light sufficient to heat tissue, and an infrared camera configured to provide images of tissue at infrared wavelengths. The system also has an image processing system configured to determine, from the infrared images of tissue, a cooling or heating rate at pixels of the images of tissue at infrared wavelengths and to display images derived from the cooling rate at the pixels.

Abstract: In a laser cataract procedure that also corrects for astigmatism, an iris registration method compares an iris image of a patient's eye taken when the eye is not docked to a patient interface device with an iris image of the same eye that is docked to the patient interface, to calculate a rotation angle between the two images. The astigmatism axis of the eye is measured when the eye is not docked, and the measured axis is rotated by the calculated rotation angle to obtain a rotated astigmatism axis relative to the iris image of the docked eye. The laser cataract procedure is performed based on the rotated astigmatism axis. The rotation angle is calculated by optimizing a transformation that transforms the undocked iris image to match the docked iris image, where the transformation includes a dilation factor that accounts for different pupil dilation of the two iris images.

Abstract: A system and method for estimating vascular flow using CT imaging include a computer readable storage medium having stored thereon a computer program comprising instructions, which, when executed by a computer, cause the computer to acquire a first set of data comprising anatomical information of an imaging subject, the anatomical information comprises information of at least one vessel. The instructions further cause the computer to process the anatomical information to generate an image volume comprising the at least one vessel, generate hemodynamic information based on the image volume, and acquire a second set of data of the imaging subject. The computer is also caused to generate an image comprising the hemodynamic information in combination with a visualization based on the second set of data.

Abstract: For patient model estimation from surface data in a medical system, a stream or sequence of depth camera captures are performed. The fitting of the patient model is divided between different times or parts of the sequence, using the streaming capture to distribute processing and account for patient movement. Less manual involvement may be needed due to the regular availability of image captures. Subsequent fitting may benefit from previous fitting.

Abstract: Systems and methods are provided for performing intraoperative fusion of two or more volumetric image datasets via surface-based image registration. The volumetric image datasets are separately registered with intraoperatively acquired surface data, thereby fusing the two volumetric image datasets into a common frame of reference while avoiding the need for complex and time-consuming preoperative volumetric-to-volumetric image registration and fusion. The resulting fused image data may be processed to generate one or more images for use during surgical navigation.

Abstract: Radar based HR and BR measurements by simultaneous decoding is a technical problem due to presence of intermodulation of BR and HR harmonics, which degrades simultaneous decoding. Embodiments herein provide a method and system for unobtrusive liveliness detection and monitoring of a subject using a Dual Frequency Radar (DFR) in an IOT network. The system has the capability to completely process the captured raw signals onboard to by applying required signal conditioning and extraction of relevant information using unique signal processing techniques for determining the HR and the BR of the subject accurately. The intermodulation of BR and HR harmonics is eliminated by the system by performing frequency spectrum averaging of both radars signals, which improves the accuracy. Further, the system is configured with a light MQTT protocol and encoding modules for any data to be shared for off board processing, ensuring data security and privacy compliance.

Abstract: A collision monitoring apparatus can include a camera to acquire a video image of surroundings of at least one target protection component on the C-arm X-ray machine system; an image processor to determine a scene of the surroundings of the at least one target protection component according to the video image; and a controller to control a C-arm X-ray machine system to stop moving or slow down when it is determined that a possible collision exists according to the scene of the surroundings of the at least one target protection component. Advantageously the apparatus effectively prevents patients, operators, patient examination beds and other obstacles from suffering a serious collision with the C-arm itself.

Abstract: An optical source sweeps a source light over an optical wavelength range. An interferometer splits the source light into sample light and reference light, delivers the sample light into an anatomical structure, such that the sample light is scattered by the anatomical structure, resulting in physiological-encoded signal light that exits the anatomical structure, and combines the signal light and the reference light into an interference light pattern having an array of spatial components and a plurality of oscillation frequency components. An optical detector array detects intensity values of the array of spatial components.

Abstract: A tomographic imaging system, including a data processing component having a memory and at least one processor configured to: access scattering parameter data representing electromagnetic waves scattered by features within an object and originating from a plurality of antennas disposed around the object on a boundary S; process the scattering parameter data to generate a reconstructed image representing a spatial distribution of features within the object, said processing including: solving an electromagnetic inverse problem, wherein forward and inverse steps of the inverse problem are represented and solved as respective differential equations involving an electric field to determine values for the electric field; and process the determined values of the electric field to generate reconstructed image data representing one or more spatial distributions of one or more electromagnetic properties within the object.

Abstract: In a method and system, a medical imaging modality and the parameters to be deployed for the determined imaging modality are determined to produce an image of an examination object using the determined imaging modality and the determined parameters. Information from the preliminary examination(s) of the examination object can be automatically classified to generate classification results corresponding to interfering influence(s) resulting from the production of the image. The classification results can be analyzed to evaluate the classification results. The medical imaging modality and the parameter(s) is determined, based on the evaluated results, to minimize an influence of the interfering influences of the classification results in image(s) of the examination object generated using the determined medical imaging modality and the determined one or more parameters. The image(s) may then be generated using the determined medical imaging modality and the determined parameter(s).

Abstract: The invention relates to a method of MR imaging of an object (10). It is an object of the invention to enable MR imaging in the presence of motion of the imaged object, wherein full use is made of the acquired MR signal and a high-quality MR image essentially free from motion artefacts is obtained. The method of the invention comprises the steps of: generating MR signals by subjecting the object (10) to an imaging sequence comprising RF pulses and switched magnetic field gradients; acquiring the MR signals as signal data over a given period of time (T); subdividing the period of time into a number of successive time segments (SO, S1, S2, . . . Sn); deriving a geometric transformation (DVF1, DVF2, . . . DVFn) in image space for each pair of consecutive time segments (S0, S1, S2, . . . Sn), which geometric transformation (DVF1, DVF2, . . .

Abstract: An image acquisition unit acquires a plurality of projection images corresponding to a plurality of radiation source positions at the time of tomosynthesis imaging, the plurality of projection images being generated by causing an imaging apparatus to perform tomosynthesis imaging. A positional shift amount derivation unit derives a positional shift amount between the plurality of projection images based on body movement of the subject with a reference projection image generated at a radiation source position where an optical axis of the radiation emitted from the radiation source is perpendicular to a detection surface of the detection unit, among the plurality of projection images, as a reference. A reconstruction unit generates a tomographic image of at least one tomographic plane of the subject by reconstructing the plurality of projection images while correcting the positional shift amount.

Abstract: In a magnetic field source detecting apparatus, a magnetic sensor unit detects an intensity and a direction of a measurement target magnetic field on or over a surface of a test target object; and a position estimating unit estimates a position in a depth direction of a magnetic field source that exists at an unspecified position inside a test target object on the basis of the intensities and the directions of the measurement target magnetic field detected by the magnetic sensor at at least two 2-dimensional positions of the surface.

Abstract: A powered user interface for a robotic surgical system having a manipulator and a surgical instrument mounted to the manipulator includes a base and a linkage assembly that includes two two-bar linkage mechanisms. The linkage assembly is rotatably mounted to the base at a base joint, and a handle mounted to each of the two-bar linkage mechanisms. Sensors and actuators are arranged to measure and actuate the position and orientation of the user interface.

Abstract: Embodiments of the present disclosure provide an interrogation device that is operable to apply one or more source signals to one or more coils surrounding a volume, where a material is disposed within the volume. Each of the one or more source signals may excite one of the one or more coils, and the behavior of each the one or more coils responsive to the exciting may be monitored. One or more parameters may be determined based on the behavior of each the one or more coils, and the one or more parameters may be utilized to generate a signature for the material within the volume. The signature may be compared to one or more signatures of known materials to identify the material within the volume.

Abstract: Some embodiments provide systems, assemblies, and methods of analyzing patient anatomy including providing an analysis of a patient's spine. The systems, assemblies, and/or methods can include obtaining initial patient data, and acquiring spinal alignment contour information. Further, the systems, assemblies, and/or methods can assess localized anatomical features of the patient, and obtain anatomical region data. The system, assemblies, and/or method can analyze the localized anatomy and therapeutic device location and contouring. Further, the system, assemblies, and/or method can output localized anatomical analyses and therapeutic device contouring data and/or imagery on a display.

Abstract: A scanner includes a camera, a light source for generating a probe light incorporating a spatial pattern, an optical system for transmitting the probe light towards the object and for transmitting at least a part of the light returned from the object to the camera, a focus element within the optical system for varying a position of a focus plane of the spatial pattern on the object, unit for obtaining at least one image from said array of sensor elements, unit for evaluating a correlation measure at each focus plane position between at least one image pixel and a weight function, a processor for determining the in-focus position(s) of each of a plurality of image pixels for a range of focus plane positions, or each of a plurality of groups of image pixels for a range of focus plane positions, and transforming in-focus data into 3D real world coordinates.

Abstract: An example method may include acquiring images from cameras, each having a known position and orientation with respect to a spatial coordinate system of an augmented reality (AR) device. The acquired images may include portions of a multi-modal marker device that includes at least one tracking sensor having a three-dimensional position that is detectable in a coordinate system of a tracking system. A three-dimensional position is estimated for the portions of the multi-modal marker device with respect to the spatial coordinate system of the AR device based on each of the respective acquired images and the known position and orientation of the cameras with respect to the spatial coordinate system of the AR device. The method also includes computing an affine transform configured to register the coordinate system of the tracking system with a visual space of a display that is in the spatial coordinate system of the AR device.

Abstract: Disclosed is a content-based image retrieval (CBIR) system and related methods that serve as a diagnostic aid for diagnosing whether a dermoscopic image correlates to a skin cancer type. Systems and methods according to aspects of the invention use as a reference a set of images of pathologically confirmed benign or malignant past cases from a collection of different classes that are of high similarity to the unknown new case in question, along with their diagnostic profiles. Systems and methods according to aspects of the invention predict what class of skin cancer is associated with a particular patient skin lesion, and may be employed as a diagnostic aid for general practitioners and dermatologists.

Abstract: An intelligent monitoring system for pelvic fracture reduction, comprising a sample fracture model database, a patient pelvic fracture data acquisition unit, a reduction situation monitoring unit and a mixed reality data fusion processing unit, the sample fracture model database stores a plurality of sample fracture models, the patient pelvic fracture data acquisition unit uses magnetic navigation and positioning technology to collect patient pelvic location information data in real-time and upload it to the mixed reality data fusion processing unit, the mixed reality data fusion processing unit automatically invokes the sample fracture model in the sample fracture model database corresponding to patient pelvic fracture condition and matches the patient pelvic location information data with the sample fracture model using mixed reality technology to form an intelligent fracture model for the patient's pelvic fracture state, the reduction situation monitoring unit loads and displays images of the intelligent f

Abstract: A photoacoustic apparatus according to the present invention is a photoacoustic apparatus for obtaining image data based on an acoustic wave generated by irradiating an object with light of a first wavelength and light of a second wavelength which is different from the first wavelength, the photoacoustic apparatus including a processing unit configured to: obtain a first image data group corresponding to the first wavelength generated based on an acoustic wave generated by irradiating the object with light of the first wavelength a plurality of times, obtain first positional deviation information corresponding to an irradiation timing with the light of the first wavelength on the basis of a first image data group corresponding to the first wavelength, and obtain second positional deviation information corresponding to an irradiation timing with the light of the second wavelength on the basis of the first positional deviation information.

Abstract: Systems and methods are disclosed that utilize a robotic device supporting and moving a cutting tool in at least three degrees of freedom. A control system commands the robotic device to control or constrain movement of the cutting tool. A first tracker is coupled to the robotic device and a second tracker is coupled to an anatomy. The second tracker includes three markers that generate optical signals and a non-optical sensor that generates non-optical signals. A navigation system with an optical sensor is in communication with the control system. The navigation system receives, with the optical sensor, the optical signals from one or more of the three markers and receives the non-optical signals from the non-optical sensor. The navigation system communicates position data indicative of a position of the anatomy to the control system to control cutting of the anatomy based on the received optical and non-optical signals.

Abstract: A multipulse elastography method for the quantitative measurement of at least one mechanical property of a viscoelastic medium having an ultrasonic signal after ultrasonic illumination, the method including defining characteristics of at least two mechanical pulses; generating the at least two mechanical pulses for which characteristics are defined in a viscoelastic medium; monitoring a propagation of at least two shear waves generated by the at least two mechanical pulses using acquisition and emission of ultrasonic signals, in the viscoelastic medium, and calculating at least one mechanical property of said viscoelastic medium using said acquisitions of said ultrasonic signals.

Abstract: Controlling an image appearance in ultrasound system comprises: providing a set of image appearance feature control parameters, each of which relates to an image appearance feature according to a pre-defined relation between a value scale of the said image appearance feature control parameter and an image appearance related to a certain condition of the corresponding image appearance feature; generating a function between the value of each image feature control parameter and the value of the standard workflow setting parameters of a combination of standard workflow setting parameters influencing the said image appearance feature; and varying automatically the value of the one or more of the standard workflow setting parameters of the combination of standard workflow setting parameters influencing an image appearance feature as a function of a variation of the value of the corresponding image appearance feature control parameters for obtaining the requested image appearance feature variation.

Abstract: In an aspect, a method for imaging a target comprises steps of: performing optical coherence tomography (OCT) scanning on the target with one or more beams of source light, the one or more beams of source light comprising a plurality of wavelengths; wherein performing OCT scanning comprises: providing the source light to a reference optical path and to a sample optical path, wherein providing the source light to a sample optical path comprises illuminating the target with the source light; and recording interference data corresponding to an interaction of a light from the reference optical path and a light from the sample optical path; processing the interference data; and identifying blood or one or more blood-features in the target based on an optical attenuation of light in or associated with the sample optical path by the blood or the one or more blood-features.

Abstract: A method and a related device to determine the kinetic state of a subject includes the steps of determining a signal indicative of the acceleration trend on the three Cartesian axes; processing the signal to limit the frequency band and preferably reduce artifacts and compensate the offset of the output signals from a multi-axial measurement system; analyzing frequency and spectrum through the transformation of the signal with the Fournier transform; computing the power spectral density for each Cartesian axis; and comparing the spectral density with a characteristic pattern of a movement.

Abstract: Systems and methods for orthognathic surgical planning are described herein. An example computer-implemented method can include generating a composite three-dimensional (3D) model of a subject's skull, defining a global reference frame for the composite 3D model, performing a cephalometric analysis on the composite 3D model to quantify at least one geometric property of the subject's skull, performing a virtual osteotomy to separate the composite 3D model into a plurality of segments, performing a surgical simulation using the osteotomized segments, and designing a surgical splint or template for the subject.

Abstract: A system and method for generating a parametric map of a subject's brain includes receiving non-contrast computed tomography (NCCT) imaging data and receiving computed tomography perfusion (CTP) data. The method further includes creating a baseline image by utilizing the NCCT data and generating a parametric map using the CTP data and the baseline image.

Abstract: The present invention provides transseptal puncture devices configured to access structures on the left side of the heart from the right side of the heart without requiring open-heart surgery. The devices have adjustable stiffness to enter the vasculature in a flexible, atraumatic fashion, then become rigid once in place to provide a stable platform for penetration of the fossa ovalis. The devices are further configured to controllably and stably extend a needle to puncture the FO. The devices include an indwelling blunt stylus that can extend perpendicularly from the device to increase the accuracy of placement near the fossa ovalis.

Abstract: An ultrasonic diagnostic apparatus in an embodiment includes processing circuitry. The processing circuitry is configured to cause an ultrasonic probe to perform an ultrasound scan of a subject. The processing circuitry is configured to generate a shadow image by assigning at least one of hue, saturation, and lightness depending on a feature of an acoustic shadow that has appeared in the result of the ultrasound scan.

Abstract: A photoacoustic remote sensing system (NI-PARS) for imaging a subsurface structure in a sample, has an excitation beam configured to generate ultrasonic signals in the sample at an excitation location; an interrogation beam incident on the sample at the excitation location, a portion of the interrogation beam returning from the sample that is indicative of the generated ultrasonic signals; an optical system that focuses at least one of the excitation beam and the interrogation beam with a focal point that is below the surface of the sample; and a detector that detects the returning portion of the interrogation beam.

Abstract: Methods and systems are provided for automated protocol recommendation and selection in a medical imaging system. In one example, a method may include receiving, from a hospital-specific user interface, a standard procedure ID, determining a medical imaging procedure based on the standard procedure ID, and, responsive to having previously received the standard procedure ID, generating one or more protocol recommendations based at least on the determined medical imaging procedure, and performing the determined medical imaging procedure based on at least one of the one or more protocol recommendations.

Abstract: A light-emitting device (100) is disclosed. The light-emitting device (100) comprises a plurality of light-emitting elements (135) or light sources and a power module (120) adapted to selectively convey, supply or provide electrical power to the light-emitting elements (135). The power module (120) may be dimensioned such as to be able to power only a proper subset of the light-emitting elements (135) of the light-emitting device (100) at a given time, the subset having a maximum number of light-emitting elements (135) included therein with respect to the number of light-emitting elements (135) included in the all subsets of the light-emitting elements (135) of the light-emitting device (100).

Abstract: A plurality of image projections are acquired at faster than cardiac rate. A spatiotemporal reconstruction of cardiac frequency angiographic phenomena in three spatial dimensions is generated from two dimensional image projections using physiological coherence at cardiac frequency. Complex valued methods may be used to operate on the plurality of image projections to reconstruct a higher dimensional spatiotemporal object. From a plurality of two spatial dimensional angiographic projections, a 3D spatial reconstruction of moving pulse waves and other cardiac frequency angiographic phenomena is obtained. Reconstruction techniques for angiographic data obtained from biplane angiography devices are also provided herein.

Abstract: Embodiments may include a method to estimate motion data based on test image data sets. The method may include receiving a training data set comprising a plurality of training data elements. Each element may include an image data set and a motion data set. The method may include training a machine learning model using the training data set, resulting in identifying one or more parameters of a function in the machine learning model based on correspondences between the image data sets and the motion data sets. The method may further include receiving a test image data set. The test image data set may include intensities of pixels in a deep-tissue image. The method may include using the trained machine learning model and the test image data set to generate output data for the test image data set. The output data may characterize motion represented in the test image data set.