Methods and systems for magnetometry-based change prediction of anatomical feature configurations

Abstract

Systems and methods for predicting changes in configurations of anatomical features are described. An example method includes receiving position information associated with multiple position tracking objects integrated into a medical device within the body of the patient. The medical device is in a vicinity of a three-dimensional (3D) anatomical feature of interest that is undergoing a quasi-periodic motion within the body of the patient. The method further includes generating, based on the position information, an anatomical motion model of at least a portion of the 3D anatomical feature of interest, and determining, based thereon, a scalar tracking metric associated with the quasi-periodic motion. The method includes performing a tracking operation to track changes in the scalar tracking metric, and generating, based thereon, a predicted time at which the quasi-periodic motion reaches a particular phase. An example system includes at least one processor configured to implement the above-described method.

Description

PCT ApplicationAttorney Docket No.: 123178.8010.WOOOMETHODS AND SYSTEMS FOR MAGNETOMETRY-BASED CHANGE PREDICTION OF ANATOMICAL FEATURE CONFIGURATIONSCROSS-REFERENCE TO RELATED APPLICATION

[0001] This application claims the benefit of U.S. Provisional Patent ApplicationNo. 63 / 708,544 filed October 17, 2025, which is incorporated by reference herein in its entirety.TECHNICAL FIELD

[0002] This document generally relates to magnetic positioning, and more particularly, to predicting change in anatomical feature configurations using magnetometers and beacons.BACKGROUND

[0003] Analysis of the motion of anatomical features of interest in medical imaging present challenges for doctors and other medical professionals. Many anatomical features of interest such as the heart move with quasi-periodic motion which must be accounted for during diagnoses and medical (e.g., interventional and radiotherapy) procedures. For example, the two most common sources of organ motion during imaging are respiratory and cardiac motion. The deformations caused by cardiac and respiratory motion make it difficult to image organs in the thorax and the abdomen.SUMMARY

[0004] Devices, systems, and methods for sensor-based prediction of the motion of objects relative to positioning beacons are described. The disclosed embodiments advantageously allow, among other features and benefits, the physician and / or other systems to predict when a particular object of interest, undergoing quasi-periodic motion, will be in a given configuration of interest, aiding in the timing of medical procedures.

[0005] In an example aspect, a method for predicting a motion of anatomical features of interest is described. The method includes receiving, from a sensor or imaging device, position information associated with multiple position tracking objects integrated into a medical device within the body of the patient. Herein, the medical device is in a vicinity of one or more three- dimensional anatomical features of interest that are undergoing a quasi-periodic motion within the body of the patient. The method further includes generating, based on the positionPCT ApplicationAttorney Docket No.: 123178.8010.WOOO information, an anatomical motion model of at least a portion of the one or more three- dimensional anatomical features of interest, and determining, based on the anatomical motion model, a scalar tracking metric associated with the quasi-periodic motion of the one or more three-dimensional anatomical features of interest. Then, the method includes performing a tracking operation to track changes in the scalar tracking metric, and generating, based on the tracking operation, a predicted time at which the quasi-periodic motion of the one or more three- dimensional anatomical features of interest reaches a particular phase.

[0006] In another example aspect, a system for predicting a motion of anatomical features of interest is described. The system includes multiple position tracking objects integrated into a medical device configured to be within the body of the patient, a sensor or imaging device external to the body of the patient, and one or more processors. Herein, the medical device is in a vicinity of one or more three-dimensional anatomical features of interest that are undergoing a quasi-periodic motion within the body of the patient. In this system, the one or more processors are configured to (a) receive, from the sensor or imaging device, position information associated with the multiple position tracking objects, (b) generate, based on the position information, an anatomical motion model of at least a portion of the one or more three-dimensional anatomical features of interest, (c) determine, based on the anatomical motion model, a scalar tracking metric associated with the quasi-periodic motion of the one or more three-dimensional anatomical features of interest, (d) perform a tracking operation to track changes in the scalar tracking metric, and (e) generate, based on the tracking operation, a predicted time at which the quasi-periodic motion of the one or more three-dimensional anatomical features of interest reaches a particular phase.

[0007] In yet another example aspect, the above-described method may be implemented by an apparatus or device that includes a processor and / or memory.

[0008] In yet another example aspect, this method may be embodied in the form of processor-executable instructions and stored on a computer-readable program medium.

[0009] The subject matter described in this patent document can be implemented in specific ways that provide one or more of the following features.BRIEF DESCRIPTION OF THE DRAWINGS

[0010] FIG. 1 is a flow diagram of an example method for predicting a motion of anatomicalPCT ApplicationAttorney Docket No.: 123178.8010.WOOO features of interest, in accordance with the disclosed embodiments.

[0011] FIG. 2 illustrates an example of the placement of beacons on an invasive medical device within a patient’s heart.

[0012] FIG. 3A illustrates an example embodiment of a beacon, which includes a permanent magnet, integrated into an invasive medical device.

[0013] FIG. 3B illustrates another example embodiment of a beacon, which includes an electromagnet, integrated into an invasive medical device.

[0014] FIG. 3C illustrates yet another example embodiment of a beacon, which includes both an electromagnet and a permanent magnet, integrated into an invasive medical device.

[0015] FIG. 4 illustrates an example embodiment of an array of sensors capable of sensing beacons incorporated into an invasive medical device.

[0016] FIG. 5 is a flow diagram for an example method for single-magnet localization.

[0017] FIG. 6 is a flow diagram for an example refinement process in magnet localization.

[0018] FIGS. 7A-7C illustrate examples of times-series data for X-axis, Y-axis, and Z-axis motion, respectively, for a beacon.

[0019] FIGS. 8 A and 8B illustrate examples of times-series data for azimuthal angle motion and elevation angle motion, respectively, for a beacon.

[0020] FIG. 9 illustrates an example embodiment with a magnetic sensor integrated into an invasive medical device, and configured to detect magnetic fields produced by field generators external to the patient.

[0021] FIG. 10 illustrates an example of a radiopaque beacon, attached to an invasive medical device, imaged under X-ray.

[0022] FIGS. 11A and 1 IB illustrate a rendering of multiple beacons placed in a porcine heart for different cardiac volumes.

[0023] FIGS. 12A and 12B illustrate polygons for subspace projections of the multiple beacons for the different cardiac volumes illustrated in FIGS. 11 A and 1 IB, respectively.

[0024] FIG. 13 illustrates a time series of an example scalar tracking metric that is annotated to identify times corresponding to the different cardiac volumes.

[0025] FIG. 14 illustrates an example area-based scalar tracking metric being compared to a coincident electrocardiogram (ECG) recording.

[0026] FIG. 15 illustrates an example implementation of a phase-locked loop for tracking.PCT ApplicationAttorney Docket No.: 123178.8010.WOOO

[0027] FIG. 16 illustrates an example of the output of a metric tracking loop and a discrete system output generated from the tracked output.

[0028] FIG. 44- 1 illustrates a flowchart of an example method of predicting changes in a configuration of anatomical features within a body of a patient.

[0029] FIG. 18 is a block diagram illustrating an example system configured to implement embodiments of the disclosed technology.DETAILED DESCRIPTION

[0030] Section headings are used in the present document to improve readability of the description and do not in any way limit the discussion, the embodiments, and / or implementations to the respective sections only.

[0031] 1 Introduction

[0032] Many medical procedures are performed on moving anatomy. Examples include, but are not limited to, a beating heart, anatomical features that move during breathing, or muscular movement. However, this motion often imposes additional complexity or difficulty to the procedure. In one example, the physician may need to look for a specific anatomical feature while the surrounding tissue is in motion, exerting significant mental effort to locate and track the feature separate from the general motion of the surrounding tissue. In another example, the physician may need to insert an object, such as a biopsy needle or catheter, at an appropriate phase of the motion and needs to use their judgement to time the physical insertion.

[0033] In many cases, such as a beating heart or breathing, the motion is quasi-periodic. That is, the motion occurs at regular intervals, but not necessarily with a fixed frequency or phase as these parameters are adjusted by physiological feedback loops responsible for regulating said motion processes. However, the quasi-periodicity provides an opportunity to model and / or predict the frequency and phase over some future period of time with a sufficient level of accuracy to aid the physician in carrying out a particular procedure.

[0034] To aid physicians in predicting important points in these quasi-periodic motions, systems have been developed to predict upcoming events in these types of quasi-periodic motions, based on measured data. Some existing implementations use electrocardiogram (ECG)- based monitoring to predict a patient’s upcoming R-peak within the heart’s QRS complex. This can be used to trigger another device based on the R-peak position. However, this system reliesPCT ApplicationAttorney Docket No.: 123178.8010.WOOO on ECG measurements, which suffer from high-frequency noise caused by muscles and low- frequency noise due to body movement and breathing. These can result in missed or inaccurate R-peak detection, thereby reducing the quality of results. The system also measures the electrical characteristics of the heart to act as a proxy for mechanical motion. While the heart’s electrical and mechanical characteristics are closely correlated, the bandwidth and dynamics of the two signals have important differences. In other existing implementations, a respirator is triggered based on pressure feedback from the lungs using a statistical model prediction. However, this system relies on indirect measurements such as pressure of the lungs to make predictions, rather than actual mechanical motion.

[0035] Embodiments of the disclosed technology, among other features and benefits, overcome at least the following limitations of current methods and systems:

[0036] - The anatomical motion is inferred using proxy data, such as electrical readings, instead of direct position data of the anatomy of interest. These information proxies do not always convey a direct mapping to the motion of interest, either missing certain aspects of the motion or including features which do not correspond to actual motion. This can result in false positives and negatives in the predictor’s outputs.

[0037] - Using proxy data can require additional inference and modelling, reducing the quality and accuracy of the system output compared to information obtained by direct measurement of the motion.

[0038] - Proxy measurements may not occur directly at the site of interest, leading to additional artefacts and errors in the predictor output relative to the actual motion of interest.

[0039] - Computing motion estimates of anatomical feature or features of interest using motion observed directly in a two- or three-dimensional space is computationally intensive.

[0040] - Proxy data may contain additional noise elements which are difficult to remove, thereby corrupting the predictor.

[0041] Embodiments of the disclosed technology provide, amongst other features and benefits, the following:

[0042] - Two- and / or three-dimensional position information at multiple points on one or more anatomical features of interest.

[0043] - Estimates of shape and volume changes of anatomical features of interest.PCT ApplicationAttorney Docket No.: 123178.8010.WOOO

[0044] - Transformation of two- or three-dimensional information of the shape and volume of the anatomical features of interest into scalar tracking metric values.

[0045] - Tracking of shape changes of the anatomical features of interest and modelling of how these changes can affect changes in the future.

[0046] - Predictive information about what the expected shape changes of the anatomical features of interest will be at points in the future.

[0047] - An output used as a trigger event for when anatomical features approach a shape configuration of interest, or an output indicating when such a configuration is expected.

[0048] According to some embodiments of the disclosed technology, and as shown in the example flow diagram of the process in FIG. 1, time-series position data for points on the anatomical features of interest, such as the heart, are obtained from beacon position data (110). Subsequent to pre-processing the time-series position data (120), a scalar tracking metric representing a change in area or volume is generated using one or more processors from the plurality of beacon positions (130). Changes in the scalar tracking metric value are tracked (140) using a tracking model and an output is generated which corresponds to the time in the future when the anatomical feature is expected to be in a particular configuration (150).

[0049] 2 Examples of position measurement and tracking

[0050] Embodiments of the disclosed technology include one or more position tracking objects including, but not limited to, beacons, sensors and fiducial markers, which are used to track the two- or three-dimensional positions of points of interest. The two- or three-dimensional positions of the objects are determined at regular or irregular intervals, forming one or more time-series. In many applications, these points are locations on the anatomical features of interest.

[0051] Examples of tracked objects include, but are not limited to, magnetic sources tracked with a magnetic positioning system, magnetic sensors measuring an external field, radiopaque objects tracked with X-ray based imaging, sonically contrasting objects imaged with ultrasound, and electric sources tracked with an impedance measurement system.

[0052] 2.1 Examples of magnetic sources

[0053] In some embodiments, the tracked objects are magnetic sources placed at the points of interest, measured by a plurality of sensors located outside the body. Examples of magnetic source embodiments include, electromagnets, permanent bar magnets, or both. These beaconsPCT ApplicationAttorney Docket No.: 123178.8010.WOOO may be placed on invasive medical devices which may carry other treatment devices and payloads, or on separate devices which are placed within the patient’s body. FIG. 2 shows an example of an arrangement where two beacons have been integrated into the distal end of two invasive guidewires and placed in coronary arteries for targeting a treatment within the heart.

[0054] In some embodiments, as shown in FIG. 3 A, the beacon is a permanent magnet, e.g., rare earth magnets and magnetized sections of catheter wire. In other embodiments, as shown in FIG. 3B, the beacon can be an electromagnet. In embodiments containing electromagnets, power is delivered from outside the body, along wires embedded in the catheter structure, to the coil. These electromagnets emit a constant magnetic field or a time-varying, alternating current (AC) field, e.g., a sinusoid oscillating a single frequency, spread spectrum signals such as Gold codes or Zadoff-Chu sequences, and the like.

[0055] In yet other embodiments, multiple sources can be configured within a particular arrangement acting as a single beacon, and both permanent magnets and electromagnets can be incorporated into the invasive medical device. For example, two magnets arranged along and perpendicular to the catheter axis, referred to as the “cross axis” and “long axis” respectively, can be used. In some examples, a permanent magnet with an axis pointing along the long axis and an AC magnet along the cross axis are used. In other examples, the AC magnet points along the long axis and the DC magnet along the cross axis. An example of the latter configuration is illustrated in FIG. 3C.

[0056] Embodiments using magnetic sources are localized as described below, providing location and orientation information for the beacons as well as information regarding the motion of the surrounding tissue. This enables tracking of the surrounding tissue even as it moves, without additional imaging equipment.

[0057] Embodiments of the disclosed technology can be configured to track magnetic beacons within the body. These are located by means of a plurality of sensors placed external to the patient, as illustrated in FIG. 4.

[0058] In some embodiments, the beacon’s magnetic field approximates that of a magnetic dipole source, with the field obeying the equation:_ p03r(m • r) — m S(r) = - - - ■4n r3

[0059] Since the magnetic dipole strength |m| is known, the above equation is solved for thePCT ApplicationAttorney Docket No.: 123178.8010.WOOO position of the beacon r and its orientation in. In some examples, the vector r is stored as a set of three coordinates x, y, and z. In other examples, the unit vector m is stored as the azimuthal and elevation angles 0 and 4> respectively.

[0060] FIG. 5 is a flow diagram of an example method for localization of a magnetic beacon. As illustrated therein, the localization procedure begins with initializing the sensor array state, and loading the constraints and initial parameter estimates for a magnetic field model. In an example, the data collection rate is every millisecond. In some embodiments, each datum that is collected may be processed. In other embodiments, the collected data may be downsampled (or upsampled) prior to processing. In the case of embodiments with time- varying magnetic signals, processing may include a demodulation step to obtain DC magnetic field levels.

[0061] As shown in FIG. 5, if the most recently computed convergence metric is less than a predetermined threshold, then a refinement procedure (further detailed in FIG. 6) is performed. If not, then the following series of operations (which constitute the geometric feature extraction process) are performed prior to performing the refinement procedure:

[0062] (a) an initial pole axis search is performed with a constrained orientation range;

[0063] (b) the residual error minimization along the target axis is performed.

[0064] The refinement procedure is followed by estimating the magnetic field model parameters (e.g., x, y, z, 0, and c])) and the convergence metric. The estimated parameters are used to update the predicted sensor measurements in the feedback path illustrated in FIG. 5.

[0065] In some embodiments, the operations in the flow diagrams illustrated in FIG. 5 and FIG. 6 include:1) Magnetic field measurements are taken at each sensor within the sensor array.2) Earth and environmental magnetic fields are removed from each set of sensor measurements.In an example, for improved accuracy, each magnetometer can be individually calibrated with 6- or 10-parameter calibration for hard and soft iron impairments.3) An approximate initial solution, based on the measurement of geometric parameters of the system, is generated. a) In some embodiments, specific features corresponding to system geometry are found within the sensor array data, leading to initial position and orientation estimates. This approach applies to systems with one or more magnetic beacons.PCT ApplicationAttorney Docket No.: 123178.8010.WOOO b) In some embodiments, a best fit for the one or more magnetic beacons is determined from a look-up table (LUT). c) In some embodiments, (a) the geometric features and (b) the position and orientation estimates determined using the table lookup method are blended.4) A parameterized magnetic field model representing estimated magnetic beacon position parameters is generated. In some embodiments, e.g., FIG. 5 shows a magnetic field model with 5 parameters, representing x, y, and z position of a single cylindrical dipole magnet plus azimuth and elevation. In the case of a magnetic dipole, the rotation about the magnet axis does not change the resulting magnetic field, so this parameter does not need to be modeled. By the convention chosen, for zero theta (yaw rotation about z-axis), the magnetic poles are aligned in the sensor reference frame x-direction, with x position of the positive magnetic pole being less than the x position of the negative magnetic pole.5) Candidate magnetic field model parameters can be used to predict the corresponding locations of each magnetic pole and the resulting magnetic field measurements at each sensor in the receive sensor array.6) A convergence metric, representing the difference between the set of field measurements at each element of the sensor array and the predicted field measurement for each element of the sensor array, is calculated. The convergence metric is a function of the set of differences between the measured values and the predicted values. a) In some embodiments, the convergence metric is a nonlinear function. b) In some embodiments, the initial location estimates of position and orientation are a blend of the geometric feature analysis and the table lookup method, with the relative weights of each method determined by the convergence metric.7) After initial position and orientation estimates have been made, precise estimates are made using the refinement stage (e.g., illustrated in FIG. 6) which successively updates the best candidate magnetic field model parameters using the set of partial derivatives of the convergence metric relative to changes in each parameter, such that the system attempts to drive the convergence metric toward zero. a) In some embodiments, the absolute magnetic field strengths of the magnetic beacon or magnets are used in the convergence metric.PCT ApplicationAttorney Docket No.: 123178.8010.WOOO b) In some embodiments, the measured and predicted magnetic fields are normalized relative to each other such that the total energy in the set of measured field value matches the total energy in the set of predicted field values.8) In the case where the amount of motion from one snapshot in time to the next is small, the initial geometric estimator can be skipped, and the system can proceed directly to the refinement stage. This is analogous to the continuous tracking mode following initial acquisition for a GPS navigation system. a) In some embodiments, the choice of whether to perform full position acquisition or continue with tracking mode is made by calculating the convergence metric between the last estimated location and the new set of measurements. The tracking mode is used if this metric is below a threshold.

[0066] FIGS. 7A-7C and 8A-8B show an example of the five beacon parameters. In FIGS. 7A-7C, times-series data for the x, y, and z positions, respectively, of a magnetic beacon incorporated into an invasive medical device placed within a porcine heart are shown. The beating of the heart and breathing can be seen. FIG. 8A shows times-series data for the azimuthal angle of the beacon orientation, and FIG. 8B shows time-series data for the elevation angle.

[0067] 2.2 Examples of magnetic sensing objects

[0068] In some embodiments, a magnetic sensor is attached to an invasive device and placed at a position on (or in the vicinity of) the anatomical feature or features of interest. The magnetic sensor being in the vicinity of the anatomical features of interest is based on, for example, the specific anatomical feature of interest (e.g., 0mm-2mm for cardiac or respiratory applications and / or 0mm-5mm for gastric applications). The sensor then measures an external magnetic field, generated by one or more field generators placed outside the patient’s body. The measured field is used to determine the position and orientation of the magnetic sensor. The one or more field generators create a position-dependent magnetic field detected by the magnetic sensor in situ. One or more processing units determine the position that minimizes the error between the measured field and the field expected if the sensor was at the given position and with the given orientation.

[0069] An example embodiment is illustrated in FIG. 9. As shown therein, a magnetic sensor is attached to the invasive medical device and placed in a location within the patient’ s heart. Two magnetic field generators outside the body produce magnetic fields, which are detected by thePCT ApplicationAttorney Docket No.: 123178.8010.WOOO magnetic sensor, and analyzed by a processing unit (not shown in FIG. 9).

[0070] 2.3 Examples of radiopaque marker tracking

[0071] Radiopaque fiducial markers are objects which exhibit high X-ray absorbance relative to surrounding tissue, thereby presenting with high contrast under time-series X-ray imaging. These markers may be attached to an invasive medical device. Examples of radiopaque markers include, but are not limited to, tantalum and iodine impregnated materials where the high atomic number of the material exhibits a strong X-ray attenuation. X-ray imaging modalities include, but are not limited to, fluoroscopy and fast computed tomography scanning. An example of a radiopaque beacon attached to an invasive medical device, and imaged under X-ray, is shown in FIG. 10.

[0072] In some embodiments, the markers are identified within an image using a segmentation algorithm, bounding the pixels comprising the beacons. Example implementations of segmentation algorithms include, but are not limited to, pixel level intensity and edge detection thresholding, and neural network architectures, e.g., convolutional neural networks.

[0073] Segmented regions may be mapped to positions either within the pixel image space, or in physical space using a calibrated imaging system. Two- or three-dimensional coordinate positions are determined for each marker with each image taken at a given time sample. In some examples, a coordinate position is associated with the center of the segmented marker pixels. In other examples, a particular feature on the marker such as a corner or edge is assigned a coordinate position.

[0074] 2.4 Examples of ultrasonic marker tracking

[0075] Ultrasonically contrasting materials including, but not limited to, metallic objects or gas-filled microbubbles can be used as fiducial markers for embodiments where ultrasound is the imaging modality. These materials provide a high ultrasonic impedance difference relative to the surrounding tissue.

[0076] In some embodiments, fiducial markers are identified using an image segmentation algorithm. Example aspects and implementations of segmentation and beacon coordinate determination for image-based systems are referenced in the previous sections.

[0077] 3 Examples of data pre-processing

[0078] In some embodiments, position data may be pre-processed before determining the scalar tracking metric value. Pre-processing steps may include, but are not limited to, de-PCT ApplicationAttorney Docket No.: 123178.8010.WOOO meaning and applying bandpass filtering to remove energy at frequencies not relevant to the motion of interest, e.g., the motion of the three-dimensional anatomical features of interest.

[0079] In some embodiments, the bandwidth of the physical motion may be informed by additional sensors. For example, in a cardiac application, the additional sensors can include an ECG sensor or optical heart rate sensor monitoring the patient’s heart rate. In the example of a pulmonary application, the patient’s breathing rate may be monitored by an external sensor.

[0080] In some embodiments, the bandwidth may be determined by including information from previous scans obtained from the patient or from a dataset containing multiple other patients who are expected to present similar biological behavior within the domain of the application. For example, using a statistical estimate of expected heartrates for patients with a particular condition, based on a corpus of previous medical data.

[0081] In some embodiments, the filter has a configurable bandwidth that is adjusted in real time to match changes in the frequency or phase of the quasi-periodic motion. Updates may be determined using information from sources including, but not limited to, outputs from the anatomical motion model and data from the beacons, sensors, detected markers, or magnetic field model. In some examples, the center frequency of the passband is adjusted in response to changes in the anatomical motion model’s estimated frequency. In other examples, the width of the passband is adjusted based on the variance of the frequency estimate — widening as the variance increases and narrowing as it decreases. In yet another example, the frequency parameters of the filter are adjusted based on data obtained from additional sensors such as an ECG sensor, a breathing sensor, or a magnetoencephalography (MEG) sensor.

[0082] 4 Examples of modeling the object of interest

[0083] In the described embodiments, the two- or three-dimensional positions of the position tracking objects are used to form a scalar tracking metric based on the area or volume of the anatomical features of interest as measured by the position tracking objects. This scalar tracking metric acts as a proxy for the periodic motion of the object of interest.

[0084] In some embodiments, three-dimensional positions for each time sample are projected into a two-dimensional subspace that captures the majority of the motion. The projected points are used to form a polygon whose area is used to determine the scalar tracking metric.

[0085] In an example of determining the scalar tracking metric, the positions of the beacons are first determined for different cardiac volumes - FIGS. 11 A and 1 IB illustrate renderings ofPCT ApplicationAttorney Docket No.: 123178.8010.WOOO the beacon positions placed in a porcine heart at a minimum in the time-varying cardiac volume and a maximum in the cardiac volume, respectively. Each beacon’s center corresponds to a point Pt used in the anatomical motion model. Subspace projections of each point are determined to form polygons whose areas are depicted in FIGS. 12A and 12B for the minimum and maximum cardiac volumes, respectively. The area of the polygon at each time sample is used to generate a scalar tracking metric for the anatomical motion model.

[0086] FIG. 13 illustrates an example time series of an area-based scalar tracking metric, which has been annotated to identify times corresponding to the minimum and maximum cardiac volumes shown in FIGS. 11A / 12A and 11B / 12B, respectively. As described in this patent document, the scalar tracking metric is analyzed by the tracking algorithm to provide predictive signals that are indicative of the next time of arrival of a particular phase of the cardiac motion.

[0087] In other embodiments, the three-dimensional positions from multiple time samples are projected into a subspace simultaneously. The position vectors of each position tracking object pi = [Xi,yi,Zi]Tare used to form a 3xN matrix

[0088] The appropriate subspace is found by first performing a singular-value decomposition (SVD) of the matrix P = U VT. The subspace projections ’ = VTPTare formed using the right singular vectors of P. Since, when modelling in a two-dimensional subspace, only the two components which capture the majority of the motion are considered, only the two leading components of S’ are taken, forming the subspace vectors st= [Xi,yi]T.

[0089] In embodiments where two-dimensional points, or three-dimensional points projected into a subspace are used, the points are ordered to form a simple polygon, one that does not intersect itself and has no holes. The area of this polygon can be determined using the shoelace formula given by:

[0090] A numerical example comparing the ECG data and the scalar tracking metric is illustrated in FIG. 14. As shown therein, an area-based scalar tracking metric, obtained usingPCT ApplicationAttorney Docket No.: 123178.8010.WOOO position data from position tracking objects within a porcine heart, is shown overlaid on simultaneously obtained ECG data. There, the relative phase between the ECG R-peaks and the scalar tracking metric is maintained throughout the illustration.

[0091] In other embodiments, three-dimensional points are used to form a polyhedron whose volume serves as the scalar tracking metric. Triangular faces are formed between the points, forming a set of triplets (a^, bt, c^) for each triangle. The volume is then computed over the N triangles as:

[0092] Herein, the normal vector is defined as

[0093] 5 Examples of tracking and modeling

[0094] In some embodiments, tracking the scalar tracking metric is performed using a phase- locked loop (PLL). The PLL tracks the frequency and phase of the input metric, outputting a signal whose phase is fixed relative to the input. FIG. 15 shows an example of a PLL implementation. As shown therein, a phase detector measures the phase error between the input and the local oscillator, and generates a sine wave. The phase error is passed through a loop filter which integrates the phase error, producing a control output that is configured to adjust the phase of the local oscillator.

[0095] In other embodiments, the PLL determines the frequency and phase of the wave by measuring the timing of peak maxima in the scalar tracking metric. Frequency is measured from the time interval between successive peaks, while the phase is determined as the time offset from an arbitrary starting time. The PLL may be implemented as illustrated in FIG. 15, replacing the phase detector with a peak maximum detector.

[0096] In yet other embodiments, the motion is tracked using an extended Kalman filter. In some of these embodiments, the frequency and phase are treated as state variables that are tracked by a non-linear equation, such as that of a sine wave, and which are updated at each observation point based on the errors of the input and the state space model.

[0097] In yet other embodiments, the scalar tracking metric is tracked using a time-series forecasting model. Examples of such forecasting models include, but are not limited to,PCT ApplicationAttorney Docket No.: 123178.8010.WOOO autoregressive (AR) models, autoregressive integrated moving averages (ARIMA), boosted random forest, and neural networks such as recurrent and long short-term memory architectures.

[0098] In some of the described embodiments, the tracking loop is configured to receive one or more additional inputs, which include features generated from data or obtained from additional sensors such as an ECG sensor, force feedback sensors affixed to the invasive medical device, a breathing sensor, or a magnetoencephalography (MEG) sensor.

[0099] In some embodiments, one or more processors are configured to detect that the quasi- periodic motion is not well fitting due to abnormal motions of the anatomical features of interest. In some examples, if the anatomical feature of interest is the heart, the described embodiments can be configured to detect arrythmia. In other examples, if the anatomical feature of interest is affected by motion from breathing, the described embodiments can be configured to detect coughing or held breath.

[0100] In some embodiments, magnetic field model parameters and / or measured samples are determined to be normal or abnormal through a statistical measure such as variance or likelihood. In some examples, the variance of the past N samples is recorded. If a measured sample that is beyond some threshold proportional to the variance is detected, it is classified as an abnormal point (or an outlier). In other examples, a set of the past N samples is modeled by some probability distribution p(x), the likelihood that the current measured sample belongs to this distribution £(x|p) is determined, and samples below some likelihood threshold are classified as abnormal. In yet other examples, the magnetic field model parameters are compared to historical values of the model parameters, and may be designated as abnormal upon determining that the model parameters have deviated from historical values by a predetermined threshold. In yet other examples, statistical measures associated with the magnetic field model parameters themselves (e.g., variance of the azimuthal angle or the elevation angle).

[0101] In some embodiments, a classifier determines which tracking model is appropriate for the current motion regime. In some example cardiac applications, a classifier uses time-series data (e.g., one minute of historic heart data) to classify whether the heart is beating normally or in a state of atrial fibrillation, and accordingly selects an appropriate tracking model. In other respiratory examples, a classifier determines whether the patient is breathing normally or is hyperventilating, and uses a specific linear combination of models depending on which state the classifier determines.PCT ApplicationAttorney Docket No.: 123178.8010.WO00

[0102] 6 Examples of prediction and output

[0103] In some embodiments, where the tracking model state contains a representation of the phase, the time- series behavior of the tracking model can be represented as a single frequency tone with the form s(t) = Aocos(mt + 4>) + Adc.

[0104] The above single-frequency tone is parameterized by a phase and angular frequency m. In embodiments where the frequency is not an explicit parameter, the frequencycan be determined from the relationship GO = At a given time instant t, the phase value ofQ interest 0 G [0,2TT] is predicted to be at a future time t = - .

[0105] In other embodiments, the phase value of interest 0 is determined by extrapolation. The tracking model is evaluated for future time values and the time value t corresponding to the phase of interest is found from the extrapolated output.

[0106] In some embodiments, the tracking model output is used as an input to another system. In some examples, the output is used to trigger an X-ray image to be taken of the heart when in the particular phase of interest. This ensures that over time, the X-rays are taken of the same configuration of the heart, removing the effects of motion that would normally be seen if the images were taken at regular intervals dictated by some other parameter.

[0107] In some embodiments, the output of the predictor is a trigger, e.g., a digital logic pulse. In some examples, the digital logic pulse is used to strobe an X-ray source at the desired time. An illustration of an example discrete output based on tracking model predictions is shown in FIG. 16, where a 100ms long 5V TTL logic pulse is generated when the scalar tracking metric is at a minimum, corresponding to a phase of 7t. In other embodiments, the output is a timestamp indicating when the system predicts that the anatomical feature of interest will be in the desired configuration.

[0108] In some embodiments, an additional confidence metric indicating the confidence the predictor has in the time of arrival is also an output of the system. In some examples, the variance between the input signal and the tracking model output is used as a confidence metric. In other examples, the covariance of the state space variables is used to form the confidence metric.

[0109] In various applications, there exists some latency between when a predictor output isPCT ApplicationAttorney Docket No.: 123178.8010.WOOO received by another aspect (e.g., component or method) of the system and when that output can affect its operation. The described embodiments can be configured to compensate for this time delay (or latency). In some examples, the relevant latencies are measured during design or before system operation, and accounted for in the time that an output from the predictor is released. In an example, if a latency of 200 ms is expected between when a trigger pulse is emitted and an X- ray image can be obtained, the trigger pulse is emitted 200 ms before the predictor expects the anatomical feature of interest to be in its desired configuration. In another example, a prediction timestamp is generated, and 200 ms is subtracted from its value before emission. This timestamp then triggers the other example aspect of the system at the appropriate time to achieve the desired effect. In yet another example, the scalar tracking metric is extrapolated 200 ms into the future and if it is at the phase of interest, the other aspect of the system is triggered.

[0110] 7 Examples and implementations of the disclosed technology

[0111] The described embodiments address the technical problem of accurate prediction of changes in the configuration of anatomical features within a patient’s body that exhibit quasi- periodic motion, such as the heart during cardiac cycles or the lungs during respiration. As discussed above, conventional medical systems often rely on indirect measurements — such as signals from electrocardiograms (ECG) or pressure sensors — to infer the position or movement of these features. However, these proxy signals are not reliably representative of the actual mechanical motion and spatial positioning of the anatomical feature of interest. The reliance on such indirect methods introduces substantial noise, artefacts, and inaccuracies, which can result in false detections, missed triggers, and ultimately, reduced reliability and safety of clinical procedures involving moving anatomy.

[0112] The following solutions overcome these limitations by directly measuring and tracking the three-dimensional positions of specific points on an anatomical motion model of the anatomical feature of interest using position-tracking objects, such as magnetic beacons or other fiducials, integrated within medical devices. These technical solutions enable real-time modeling of the anatomical configuration, deriving scalar metrics such as area or volume, and direct tracking of the scalar metric, which greatly enhances the ability to accurately predict when an anatomical feature will reach a targeted configuration, thereby optimizing the timing of medical interventions and reducing procedural complexity and risk.

[0113] SI. A system for predicting anatomical changes within a body of a patient,PCT ApplicationAttorney Docket No.: 123178.8010.WOOO comprising: a plurality of position tracking objects integrated into a medical device configured to be within the body of the patient, wherein the medical device is in a vicinity of one or more three-dimensional anatomical features of interest that are undergoing a quasi-periodic motion within the body of the patient; a sensor or imaging device external to the body of the patient; and one or more processors configured to: receive, from the sensor or imaging device, position information associated with the plurality of position tracking objects, generate, based on the position information, an anatomical motion model of at least a portion of the one or more three- dimensional anatomical features of interest, determine, based on the anatomical motion model, a scalar tracking metric associated with the quasi-periodic motion of the one or more three- dimensional anatomical features of interest, perform a tracking operation to track changes in the scalar tracking metric, and generate, based on the tracking operation, a predicted time at which the quasi-periodic motion of the one or more three-dimensional anatomical features of interest reaches a particular phase.

[0114] S2. The system of solution SI, wherein the position information comprises two- or three-dimensional positions on the one or more three-dimensional anatomical features of interest, and wherein a position tracking object comprises a beacon object, a sensing device, or a fiducial marker. Examples of position tracking objects are discussed in Section 2.

[0115] S3. The system of solution S2, wherein the beacon object comprises at least one of a permanent magnet or an electromagnet.

[0116] S4. The system of solution S3, wherein an electromagnetic field associated with the beacon object comprises a constant electromagnetic field.

[0117] S5. The system of solution S3, wherein an electromagnetic field associated with the beacon object comprises a time-varying electromagnetic field.

[0118] S6. The system of solution S5, wherein the time-varying electromagnetic field is generated based on a single-frequency signal that is static or adjustable.

[0119] S7. The system of solution S5, wherein the time- varying electromagnetic field is generated based on a multi-frequency spread-spectrum signal.

[0120] S8. The system of solution S2, wherein the beacon object comprises a permanent magnet with a first magnetic axis and an electromagnet with a second magnetic axis that is different from the first magnetic axis.

[0121] S9. The system of solution S2, wherein the beacon object comprises a permanentPCT ApplicationAttorney Docket No.: 123178.8010.WOOO magnet with a first magnetic axis and an electromagnet with a second magnetic axis that is parallel to the first magnetic axis.

[0122] S10. The system of solution S8 or 9, wherein the first magnetic axis is parallel to an axis of the medical device.

[0123] Si l. The system of solution S8 or 9, wherein the second magnetic axis is parallel to an axis of the medical device.

[0124] S12. The system of any of solutions S 8 to Si l, wherein the permanent magnet comprises a rare-earth metal or a magnetized section of the medical device.

[0125] S13. The system of solution S2, wherein the sensing device comprises a magnetic sensor.

[0126] S14. The system of solution S2, wherein the fiducial marker comprises a fiducial marker that includes a radiopaque material or an ultrasonically contrasting material.

[0127] S15. The system of solution S14, wherein the ultrasonically contrasting material (a) is metallic in nature or (b) comprises gas-filled bubbles.

[0128] S16. The system of solution S2, wherein the position tracking object comprises an electrical source.

[0129] S17. The system of solution SI, wherein the one or more processors is configured to: use an image segmentation algorithm to identify at least one position tracking object. Examples of image segmentation algorithms are discussed in Sections 2.3 and 2.4.

[0130] S18. The system of solution S17, wherein the image segmentation algorithm is based on a pixel-level analysis of images received from the sensor or imaging device.

[0131] S19. The system of solution S17, wherein the image segmentation algorithm is implemented based on a neural network architecture.

[0132] S20. A method (e.g., method 1700 illustrated in FIG. 17) of predicting anatomical changes within a body of a patient, comprising: receiving (1710), from a sensor or imaging device, position information associated with a plurality of position tracking objects integrated into a medical device within the body of the patient, the medical device being in a vicinity of one or more three-dimensional anatomical features of interest that are undergoing a quasi-periodic motion within the body of the patient; generating (1720), based on the position information, an anatomical motion model of at least a portion of the one or more three-dimensional anatomical features of interest; determining (1730), based on the anatomical motion model, a scalar trackingPCT ApplicationAttorney Docket No.: 123178.8010.WOOO metric associated with the quasi-periodic motion of the one or more three-dimensional anatomical features of interest; performing (1740) a tracking operation to track changes in the scalar tracking metric; and generating (1750), based on the tracking operation, a predicted time at which the quasi-periodic motion of the one or more three-dimensional anatomical features of interest reaches a particular phase.

[0133] S21. The method of solution S20, comprising: filtering, prior to determining the scalar tracking metric, the position information using a filter with a configurable bandwidth. In some examples, the configuration bandwidth filter in discussed in Section 3.

[0134] S22. The method of solution S21, wherein the configurable bandwidth is based on at least one of information from one or more additional sensors, an output of a tracking loop, a current system output, or one or more previous system outputs.

[0135] S23. The method of solution S20, wherein the scalar tracking metric is determined based on an area calculation or a volume calculation associated with the anatomical motion model. For example, the area calculation computes the area of the polygons illustrated in FIGS. 12A and 12B. Other examples are discussed in Section 4.

[0136] S24. The method of solution S23, wherein determining the scalar tracking metric comprises using a geometric subspace projection based on a singular value decomposition.

[0137] S25. The method of solution S20, wherein the tracking operation is based on at least one of a phase-locked loop (PLL), a peak finding algorithm, an extended Kalman filter (EKF), or a time-series forecasting model.

[0138] S26. The method of solution S20, wherein the particular phase is determined by solving a function of one or more parameters of the anatomical motion model and / or extrapolating an output of the tracking operation.

[0139] S27. The method of solution S26, wherein the one or more parameters of the anatomical motion model comprises an area of a polygon rendered on the anatomical motion model, e.g., as shown in FIGS. 12A and 12B.

[0140] S28. The method of solution S20, wherein the predicted time is configured to trigger an alternative sensor or imaging device, e.g., as described in FIG. 16.

[0141] S29. The method of solution S28, wherein the predicted time is configured to compensate for a latency of the alternative sensor or imaging device.

[0142] S30. The method of solution S20, wherein at least one of the scalar tracking metric,PCT ApplicationAttorney Docket No.: 123178.8010.WOOO the predicted time, or the particular phase is associated with a confidence metric or interval. In some examples, the confidence metric or interval is discussed in Section 6.

[0143] S31. The method of solution S20, wherein generating the anatomical motion model is based on data from at least one of an electrocardiogram, a force feedback sensor, a breathing sensor, or a magnetoencephalogram.

[0144] S32. The method of solution S31 , wherein at least one sample of the data is associated with a classified state designation or a numerical value classifying the at least one sample as normal or abnormal based on one or more statistical features of the data.

[0145] In the above-described solutions, one or more methods of solutions S20 to S32 are implemented by the one or more processors of solution SI.

[0146] FIG. 18 shows an example of a hardware platform 1800 that can be used to implement some of the techniques described in the present document. For example, the hardware platform 1800 can implement method 1700, or implement the various modules and algorithms described herein. The hardware platform 1800 includes a processor 1802 that can execute code to implement a method. The hardware platform 1800 includes a memory 1804 that is used to store processor-executable code and / or store data. The hardware platform 1800 further includes magnets 1806 and magnetometers 1808, which can communicate with the processor 1802 using leads or a wireless protocol. The processor 1802 is configured to implement modeling, tracking and / or prediction algorithms. In some embodiments, the memory 1804 comprises multiple memories, some of which are exclusively used by the processor 1802 when implementing the modeling, tracking, and / or prediction algorithms.

[0147] Implementations of the subject matter and the functional operations described in this patent document can be implemented in various systems, digital electronic circuitry, or in computer software, firmware, or hardware, including the structures disclosed in this specification and their structural equivalents, or in combinations of one or more of them. Implementations of the subject matter described in this specification can be implemented as one or more computer program products, i.e., one or more modules of computer program instructions encoded on a tangible and non-transitory computer readable medium for execution by, or to control the operation of, data processing apparatus. The computer readable medium can be a machine- readable storage device, a machine-readable storage substrate, a memory device, a composition of matter effecting a machine-readable propagated signal, or a combination of one or more ofPCT ApplicationAttorney Docket No.: 123178.8010.WOOO them. The term “data processing unit” or “data processing apparatus” encompasses all apparatus, devices, and machines for processing data, including by way of example a programmable processor, a computer, or multiple processors or computers. The apparatus can include, in addition to hardware, code that creates an execution environment for the computer program in question, e.g., code that constitutes processor firmware, a protocol stack, a database management system, an operating system, or a combination of one or more of them.

[0148] A computer program (also known as a program, software, software application, script, or code) can be written in any form of programming language, including compiled or interpreted languages, and it can be deployed in any form, including as a stand-alone program or as a module, component, subroutine, or other unit suitable for use in a computing environment. A computer program does not necessarily correspond to a file in a file system. A program can be stored in a portion of a file that holds other programs or data (e.g., one or more scripts stored in a markup language document), in a single file dedicated to the program in question, or in multiple coordinated files (e.g., files that store one or more modules, sub programs, or portions of code). A computer program can be deployed to be executed on one computer or on multiple computers that are located at one site or distributed across multiple sites and interconnected by a communication network.

[0149] The processes and logic flows described in this specification can be performed by one or more programmable processors executing one or more computer programs to perform functions by operating on input data and generating output. The processes and logic flows can also be performed by, and devices can be implemented as, special purpose logic circuitry, e.g., an FPGA (field programmable gate array) or an ASIC (application specific integrated circuit).

[0150] Processors suitable for the execution of a computer program include, by way of example, both general and special purpose microprocessors, and any one or more processors of any kind of digital computer. Generally, a processor will receive instructions and data from a read-only memory or a random-access memory or both. The essential elements of a computer are a processor for performing instructions and one or more memory devices for storing instructions and data. Generally, a computer will also include, or be operatively coupled to receive data from or transfer data to, or both, one or more mass storage devices for storing data, e.g., magnetic, magneto-optical disks, or optical disks. However, these are optional. Computer readable media suitable for storing computer program instructions and data include all forms of nonvolatilePCT ApplicationAttorney Docket No.: 123178.8010.WOOO memory, media and memory devices, including by way of example semiconductor memory devices, e.g., EPROM, EEPROM, and flash memory devices. The processor and the memory can be supplemented by, or incorporated in, special purpose logic circuitry.

[0151] While this patent document contains many specifics, these should not be construed as limitations on the scope of any invention or of what may be claimed, but rather as descriptions of features that may be specific to particular embodiments of particular inventions. Certain features that are described in this patent document in the context of separate embodiments can also be implemented in combination in a single embodiment. Conversely, various features that are described in the context of a single embodiment can also be implemented in multiple embodiments separately or in any suitable subcombination. Moreover, although features may be described above as acting in certain combinations and even initially claimed as such, one or more features from a claimed combination can in some cases be excised from the combination, and the claimed combination may be directed to a subcombination or variation of a subcombination.

[0152] Similarly, while operations are depicted in the drawings in a particular order, this should not be understood as requiring that such operations be performed in the particular order shown or in sequential order, or that all illustrated operations be performed, to achieve desirable results. Moreover, the separation of various system components in the embodiments described in this patent document should not be understood as requiring such separation in all embodiments.

[0153] Only a few implementations and examples are described and other implementations, enhancements and variations can be made based on what is described and illustrated in this patent document.

Claims

PCT ApplicationAttorney Docket No.: 123178.8010.WOOOWHAT IS CLAIMED IS:

1. A system for predicting anatomical changes within a body of a patient, comprising: a plurality of position tracking objects integrated into a medical device configured to be within the body of the patient, wherein the medical device is in a vicinity of one or more three- dimensional anatomical features of interest that are undergoing a quasi-periodic motion within the body of the patient; a sensor or imaging device external to the body of the patient; and one or more processors configured to: receive, from the sensor or imaging device, position information associated with the plurality of position tracking objects. generate, based on the position information, an anatomical motion model of at least a portion of the one or more three-dimensional anatomical features of interest, determine, based on the anatomical motion model, a scalar tracking metric associated with the quasi-periodic motion of the one or more three-dimensional anatomical features of interest, perform a tracking operation to track changes in the scalar tracking metric, and generate, based on the tracking operation, a predicted time at which the quasi- periodic motion of the one or more three-dimensional anatomical features of interest reaches a particular phase.

2. The system of claim 1, wherein the position information comprises two- or three- dimensional positions on the one or more three-dimensional anatomical features of interest, and wherein a position tracking object comprises a beacon object, a sensing device, or a fiducial marker.

3. The system of claim 2, wherein the beacon object comprises at least one of a permanent magnet or an electromagnet.

4. The system of claim 3, wherein an electromagnetic field associated with the beacon object comprises a constant electromagnetic field.PCT ApplicationAttorney Docket No.: 123178.8010.WOOO5. The system of claim 3, wherein an electromagnetic field associated with the beacon object comprises a time-varying electromagnetic field.

6. The system of claim 5, wherein the time-varying electromagnetic field is generated based on a single-frequency signal that is static or adjustable.

7. The system of claim 5, wherein the time-varying electromagnetic field is generated based on a multi-frequency spread- spectrum signal.

8. The system of claim 2, wherein the beacon object comprises a permanent magnet with a first magnetic axis and an electromagnet with a second magnetic axis that is different from the first magnetic axis.

9. The system of claim 2, wherein the beacon object comprises a permanent magnet with a first magnetic axis and an electromagnet with a second magnetic axis that is parallel to the first magnetic axis.

10. The system of claim 8 or 9, wherein the first magnetic axis is parallel to an axis of the medical device.

11. The system of claim 8 or 9, wherein the second magnetic axis is parallel to an axis of the medical device.

12. The system of any of claims 8 to 11, wherein the permanent magnet comprises a rare- earth metal or a magnetized section of the medical device.

13. The system of claim 2, wherein the sensing device comprises a magnetic sensor.

14. The system of claim 2, wherein the fiducial marker comprises a fiducial marker that includes a radiopaque material or an ultrasonically contrasting material.

15. The system of claim 14, wherein the ultrasonically contrasting material (a) is metallic in nature or (b) comprises gas-filled bubbles.PCT ApplicationAttorney Docket No.: 123178.8010.WOOO16. The system of claim 2, wherein the position tracking object comprises an electrical source.

17. The system of claim 1, wherein the one or more processors is configured to: use an image segmentation algorithm to identify at least one position tracking object.

18. The system of claim 17, wherein the image segmentation algorithm is based on a pixellevel analysis of images received from the sensor or imaging device.

19. The system of claim 17, wherein the image segmentation algorithm is implemented based on a neural network architecture.

20. A method of predicting anatomical changes within a body of a patient, comprising: receiving, from a sensor or imaging device, position information associated with a plurality of position tracking objects integrated into a medical device within the body of the patient, the medical device being in a vicinity of one or more three-dimensional anatomical features of interest that are undergoing a quasi-periodic motion within the body of the patient; generating, based on the position information, an anatomical motion model of at least a portion of the one or more three-dimensional anatomical features of interest; determining, based on the anatomical motion model, a scalar tracking metric associated with the quasi-periodic motion of the one or more three-dimensional anatomical features of interest; performing a tracking operation to track changes in the scalar tracking metric; and generating, based on the tracking operation, a predicted time at which the quasi-periodic motion of the one or more three-dimensional anatomical features of interest reaches a particular phase.

21. The method of claim 20, comprising: filtering, prior to determining the scalar tracking metric, the position information using a filter with a configurable bandwidth.PCT ApplicationAttorney Docket No.: 123178.8010.WOOO22. The method of claim 21, wherein the configurable bandwidth is based on at least one of information from one or more additional sensors, an output of a tracking loop, a current system output, or one or more previous system outputs.

23. The method of claim 20, wherein the scalar tracking metric is determined based on an area calculation or a volume calculation associated with the anatomical motion model.

24. The method of claim 23, wherein determining the scalar tracking metric comprises using a geometric subspace projection based on a singular value decomposition (SVD).

25. The method of claim 20, wherein the tracking operation is based on at least one of a phase-locked loop (PLL), a peak finding algorithm, an extended Kalman filter (EKF), or a timeseries forecasting model.

26. The method of claim 20, wherein the particular phase is determined by solving a function of one or more parameters of the anatomical motion model and / or extrapolating an output of the tracking operation.

27. The method of claim 26, wherein the one or more parameters of the anatomical motion model comprises an area of a polygon rendered on the anatomical motion model.

28. The method of claim 20, wherein the predicted time is configured to trigger an alternative sensor or imaging device.

29. The method of claim 28, wherein the predicted time is configured to compensate for a latency of the alternative sensor or imaging device.

30. The method of claim 20, wherein at least one of the scalar tracking metric, the predicted time, or the particular phase is associated with a confidence metric or interval.

31. The method of claim 20, wherein generating the anatomical motion model is based on data from at least one of an electrocardiogram, a force feedback sensor, a breathing sensor, or a magnetoencephalogram.PCT ApplicationAttorney Docket No.: 123178.8010.WOOO32. The method of claim 31, wherein at least one sample of the data is associated with a classified state designation or a numerical value classifying the at least one sample as normal or abnormal based on one or more statistical features of the data.

Images