Systems and methods for cardiac stress test risk monitoring

Abstract

A cardiac stress test monitoring system including a controller is provided. The controller is configured to: receive a plurality of echocardiogram images, wherein each of the plurality of echocardiogram images may correspond to one or more stress stages; to receive measurement data corresponding to the one or more stress stages; to generate, via a cardiac wall motion tracking model, wall motion data based on the plurality of echocardiogram images; generate, via a measurement abnormality detection model, measurement abnormality data based on the measurement data; generate, via a RWMA forecasting model, peak stress RWMA forecast data based on the wall motion data and the measurement abnormality data; generate cardiac risk data based on the peak stress RWMA forecast data; and output the cardiac risk data. The cardiac risk data may include a cardiac risk dashboard comprising one or more risk visualizations.

Description

SYSTEMS AND METHODS FOR CARDIAC STRESS TEST RISK MONITORINGField of the Disclosure

[0001] The present disclosure is generally directed to cardiological monitoring, specifically to systems and methods for cardiac stress test risk monitoring, and in particular, to forecasting potential risks during early stages of cardiac stress testing.Background

[0002] According to the American College of Cardiology, approximately 1.5 million stress tests are performed annually in the United States. Stress echocardiograms are used for detecting ischemic heart disease, cardiac risk stratification, and viability analysis of various cardiac segments. Stress echocardiograms are clinically useful because elevated heart rate from stress can reveal abnormalities generally not seen at rest. The development of wall motion abnormalities during the early stages of stress may also indicate the presence of severe coronary obstruction.

[0003] A stress echocardiogram exam may be carried out using different approaches and protocols. An exercise stress echocardiogram exam elicits an electromechanical response from the treadmill or bicycle exercise. On the other hand, a pharmacological stress exam induces stress using controlled doses of drugs such as dobutamine. In both cases, the stress is induced progressively in stages, for example, either by increasing exercise workload or increasing the drug dose. Exercise stress testing is preferred for the elicitation of natural electromechanical activity and the absence of drugs.

[0004] Before the exam, a clinical examiner assesses exercise ability and various risks to decide whether to run stress testing and the type of stress testing (exercise vs pharmacologic) to be implemented. During the exam, the examiner monitors the physical response and any signs of ischemic response to decide whether to cease testing in case of severe pain. Time limitations and the subjective nature of visual assessment can make it difficult for the examiner to effectively carry out this risk analysis. Some existing solutions for evaluating stress test risk rely on electrocardiogram data. However, stress test risk analysis based on electrocardiogram data tends to be unreliable and inaccurate.Summary of the Disclosure

[0005] The present disclosure is generally directed to systems and methods for cardiac stress test risk monitoring. In particular, the present disclosure provides systems and methods for forecasting potential risks during early stages of cardiac stress testing. While a patient is undergoing stress testing, the system receives two types of data, (1) echocardiogram images (which may be provided as video or still images) and (2) measurement data (such as electrocardiogram measurements including E / A ratio, E / e’ ratio, strain rate, and / or ejection fraction). For each data type, the data is classified based on the stress stage of testing (such as resting stage, low stress stage, pre-peak stage, etc.). The echocardiogram images are processed by a cardiac wall motion tracking model to generate wall motion data descriptive of the movement of cardiac wall segments during these early stages of stress testing. The cardiac wall motion tracking model may be a three- dimensional convolutional neural network (CNN) model. The wall motion data may also include a regional wall motion abnormality (RWMA) score regarding potential abnormalities evidenced by the movement of the cardiac wall segments. The measurement data is processed by a measurement abnormality detection model to identify cardiac abnormalities in the measurement data. The measurement abnormality detection model may be an autoregressive model. The processed imaging and measurement data is then processed by an RWMA forecasting model to predict risk data during a future peak stress stage. The RWMA forecasting model may also be a CNN model. A risk dashboard is then generated and displayed to show a clinical examiner potential risks for subjecting the patient to cardiac stress testing. The potential risks may relate to a variety of conditions related to the movement of cardiac wall segments, such as ischemia, myocardial infarction, and others.

[0006] The risk dashboard may show a wide array of information. In some examples, the risk dashboard may include a risk indication on a scale of low, medium, or high. This risk indication may be accompanied by text explanations of the risk forecast, such as wall motion changes and / or measurement changes. The risk dashboard may also include visualizations of wall motion at various stress stages. The risk dashboard may also show data plots of certain types of measurement data indicative of risk. In some examples, the risk dashboard is displayed on a display screen of an ultrasound cart, enabling a health care worker to quickly evaluate the risk faced by the patient during the stress test, and determine whether or not to continue with the stress test.

[0007] Generally, in one aspect, a cardiac stress test monitoring system is provided. The cardiac stress test monitoring system includes a controller. The controller is configured to receive a plurality of echocardiogram images. Each of the plurality of echocardiogram images may correspond to one or more stress stages.

[0008] The controller is further configured to receive measurement data corresponding to the one or more stress stages.

[0009] The controller is further configured to generate, via a cardiac wall motion tracking model, wall motion data based on the plurality of echocardiogram images.

[0010] The controller is further configured to generate, via a measurement abnormality detection model, measurement abnormality data based on the measurement data.

[0011] The controller is further configured to generate, via a regional wall motion abnormality (RWMA) forecasting model, peak stress RWMA forecast data based on the wall motion data and the measurement abnormality data.

[0012] The controller is further configured to generate cardiac risk data based on the peak stress RWMA forecast data.

[0013] The controller is further configured to output the cardiac risk data.

[0014] According to an example, the one or more stress stages comprise a resting stage, a low stress stage, and / or a pre-peak stress stage.

[0015] According to an example, the cardiac wall motion model is a three-dimensional CNN model.

[0016] According to an example, the echocardiogram images comprise a plurality of echocardiogram views.

[0017] According to an example, the measurement abnormality detection model is an autoregressive model.

[0018] According to an example, the measurement data includes a plurality of electrocardiogram measurements.

[0019] According to an example, the wall motion data corresponds to one or more wall segments of heart chambers.

[0020] According to an example, the RWMA forecasting model is a three-dimensional CNN model.

[0021] According to an example, the wall motion data comprises one or more RWMA scores.

[0022] According to an example, the peak stress RWMA forecast data includes abnormality data for one or more cardiac wall segments.

[0023] According to an example, the cardiac risk data includes a cardiac risk dashboard comprising one or more risk visualizations. The cardiac risk dashboard is displayed on a display screen communicatively coupled to the controller. The one or more risk visualizations may include risk forecast data based on the peak stress RWMA forecast data. The one or more risk visualizations may include a wall motion visualization of a wall segment. The wall motion visualization may correspond to the one or more stress stages and a forecast stage. The one or more risk visualizations may include a measurement visualization corresponding to the one or more stress stages and a forecast stage.

[0024] Generally, in another example, a method for cardiac stress test monitoring is provided. The method includes receiving, via a controller, a plurality of echocardiogram images. Each of the plurality of echocardiogram images corresponds to one or more stress stages.

[0025] The method further includes receiving, via the controller, measurement data corresponding to the one or more stress stages.

[0026] The method further includes generating, via a cardiac wall motion tracking model of the controller, wall motion data based on the plurality of echocardiogram images.

[0027] The method further includes generating, via a measurement abnormality detection model of the controller, measurement abnormality data based on the measurement data.

[0028] The method further includes generating, via an RWMA forecasting model of the controller, peak stress RWMA forecast data based on the wall motion data and the measurement abnormality data.

[0029] The method further includes generating, via the controller, cardiac risk data based on the peak stress RWMA forecast data.

[0030] The method further includes outputting, via the controller, the cardiac risk data.

[0031] In various implementations, a processor or controller may be associated with one or more storage media (generically referred to herein as “memory,” e.g., volatile and non-volatile computer memory such as RAM, PROM, EPROM, EEPROM, floppy disks, compact disks, optical disks, magnetic tape, SSD, etc.). In some implementations, the storage media may be encoded with one or more programs that, when executed on one or more processors and / or controllers, perform at least some of the functions discussed herein. Various storage media may be fixed within aprocessor or controller or may be transportable, such that the one or more programs stored thereon can be loaded into a processor or controller so as to implement various aspects as discussed herein. The terms “program” or “computer program” are used herein in a generic sense to refer to any type of computer code (e.g., software or microcode) that can be employed to program one or more processors or controllers.

[0032] It should be appreciated that all combinations of the foregoing concepts and additional concepts discussed in greater detail below (provided such concepts are not mutually inconsistent) are contemplated as being part of the inventive subject matter disclosed herein. In particular, all combinations of claimed subject matter appearing at the end of this disclosure are contemplated as being part of the inventive subject matter disclosed herein. It should also be appreciated that terminology explicitly employed herein that also may appear in any disclosure incorporated by reference should be accorded a meaning most consistent with the particular concepts disclosed herein.

[0033] These and other aspects of the various embodiments will be apparent from and elucidated with reference to the embodiment(s) described hereinafter.Brief Description of the Drawings

[0034] In the drawings, like reference characters generally refer to the same parts throughout the different views. Also, the drawings are not necessarily to scale, emphasis instead generally being placed upon illustrating the principles of the various embodiments.

[0035] FIG. 1 is an illustration of a cardiac stress test monitoring system, in accordance with an example.

[0036] FIG. 2 is an illustration of a controller of the cardiac stress test monitoring system of FIG. 1, in accordance with an example.

[0037] FIG. 3A is a diagram of echocardiogram images to be processed by the cardiac stress test monitoring system, in accordance with an example.

[0038] FIG. 3B is a diagram of measurement data to be processed by the cardiac stress test monitoring system, in accordance with an example.

[0039] FIG. 4 is a cardiac risk dashboard showing risk forecast data, in accordance with an example.

[0040] FIG. 5 is a cardiac risk dashboard showing wall motion visualizations, in accordance with an example.

[0041] FIG. 6 is a cardiac risk dashboard showing measurement visualizations, in accordance with an example.

[0042] FIG. 7 is a schematic diagram of a controller of a cardiac stress test monitoring system, in accordance with an example.

[0043] FIG. 8 is a flow chart of a method for cardiac stress test monitoring, in accordance with an example.Detailed Description of Embodiments

[0044] The present disclosure is generally directed to systems and methods for cardiac stress test risk monitoring. In particular, the present disclosure provides systems and methods for forecasting potential risks during early stages of cardiac stress testing. While a patient is undergoing stress testing, the system receives two types of data, (1) echocardiogram images and (2) measurement data. For each data type, the data is classified based on the stress stage of testing. The echocardiogram images are processed by a cardiac wall motion tracking model to generate wall motion data descriptive of the movement of cardiac wall segments during these early stages of stress testing. The wall motion data may also include a regional wall motion abnormality (RWMA) score regarding potential abnormalities evidenced by the movement of the cardiac wall segments. The RWMA score may include sixteen individual scores, one for each of the sixteen left ventricular cardiac wall segments defined by the American Society of Echocardiography (ASE). The measurement data is processed by a measurement abnormality detection model to identify cardiac abnormalities in the measurement data. The processed imaging and measurement data is then processed by an RWMA forecasting model to predict risk data during a future peak stress stage. This risk data may correspond to forecasted abnormalities for each of the cardiac wall segments. A risk dashboard is then generated and displayed to show a clinician potential risks for subjecting the patient to cardiac stress testing. Notably, the described systems and methods may be applied to monitor risk during a variety of different stress testing protocols, such as dobutamine stress echocardiogram (DSE), exercise stress echocardiogram (ESE), and contrast-infused stress echocardiogram. For each variety of protocol, different types of echocardiogram images and measurement data may be collected. Further, the aforementioned models to process theechocardiogram images and measurement data may vary to correspond to the types of images and data collected.

[0045] Turning now to the figures, FIG. 1 illustrates a non-limiting example of a cardiac stress testing monitoring system 10 configured to monitor a heart of a patient undergoing cardiac stress testing, forecast potential heart-related issues due to the stress testing, and provide a clinician with a dashboard describing the forecasted risks due to the stress testing, according to various embodiments and implementation of the present disclosure.

[0046] As shown in FIG. 1, the system 10 includes a controller 100. The controller 100 is shown in more detail in FIGS. 2 and 7. Broadly, the controller 100 may include a processor 125 to process data and a memory 175 to store data. The controller 100 may also include a transceiver 185 to wirelessly transmit and / or receive data. In some examples, the controller 100 may be embodied as an aspect or component of a personal computer, laptop computer, patient monitoring station, or other electronic device capable of processing, storing, transmitting, and receiving data.

[0047] The controller 100 shown in FIG. 1 is configured to receive at least two modalities of data. First, the controller 100 is configured to receive a plurality of echocardiogram images 102 of the heart of the patient undergoing the cardiac stress test. As shown in FIG. 2, the echocardiogram images 102 may be captured by an ultrasound scanner 300. The echocardiogram images 102 may include a series of still images or moving video clips. The still images or video clips may be captured in a variety of different echocardiogram views 128. Aspects of the echocardiogram images 102 are shown in more detail in FIG. 3 A. The echocardiogram images 102 may be provided to the controller 100 via wired or wireless connection. As will be described in more detail in FIG. 3 A, the echocardiogram images 102 may be captured at various stages 104 throughout the stress test prior to the patient undergoing peak stress testing. For example, the electrocardiogram images 102 may represent the heart of the patient at a rest stage 122, at a low stress stage 124, and at a pre-peak stress stage 126. The echocardiogram images 102 may be tagged to indicate the stress stage 104 at which each image 102 was captured. The pre-peak stage 126 may represent a stress level where the patient is experiencing stress higher than the low stress stage 124 but has yet to reach peak stress. By evaluating the echocardiogram images 102 throughout these stress stages 104, the controller 100 can evaluate risks faced by the patient, enabling the clinician to adjust or cease testing prior to the patient experiencing maximum stress.

[0048] Second, the controller 100 is configured to receive a measurement data 106 related to the heart of the patient undergoing the cardiac stress test. As shown in FIG. 2, the measurement data 106 may be captured by an electrocardiogram machine 400. Accordingly, the measurement data 106 may include a wide array of electrocardiogram measurements 130, such as E / A ratio, E / e’ ratio, strain rate, and / or ejection fraction. Aspects of the measurement data 106 are shown in more detail in FIG. 3B. The measurement data 106 may be provided to the controller 100 via wired or wireless connection. As with the electrocardiogram images 102, and as will be shown in more detail in FIG. 3B, the measurement data 106 may be captured at various stages 104 throughout the stress test prior to the patient undergoing peak stress testing, including rest stage 122, at a low stress stage 124, and at a pre-peak stress stage 126. The measurement data 106 may be tagged to indicate the stress stage 104 at which each measurement 106 was captured.

[0049] As will be described in more detail with respect to FIG. 2, the controller 100 processes echocardiogram images 102 and the measurement data 106 to determine cardiac risk data 120. The cardiac risk data 120 may include a wide range of information regarding the risk faced by the patient. In the non-limiting example of FIG. 1, the cardiac risk data 120 is conveyed to a display screen 200. In some examples, the display screen 200 may be integrated into the same device as the controller 100, such as a personal computer or patient monitoring station. In other examples, the display screen 200 is a component of a separate device, such as a smartphone or tablet computer. As shown in FIG. 1, the display screen 200 shows a cardiac risk dashboard 136. The cardiac risk dashboard provides the clinician administering the stress test with information and visuals to evaluate potential risks to the patient quickly and easily. In the non-limiting example of FIG. 1, the cardiac risk dashboard 136 indicates that the patient faces a high risk of future cardiac complications due to the cardiac stress test. Examples of the cardiac risk dashboard 136 are shown in more detail in FIG. 4-6.

[0050] Aspects of the controller 100 are shown in more detail in the non-limiting example of FIG. 2. As shown in FIG. 2, the controller 100 generally includes a cardiac wall motion tracking model 108, a measurement abnormality detection model 112, an RWMA forecasting model 116, and a cardiac risk model 148. The cardiac wall motion tracking model 108 may be a three- dimensional convolutional neural network (CNN) model configured to process the plurality of echocardiogram images 102. The cardiac wall motion tracking model 108 generates wall motion data 110 descriptive of the movement of cardiac wall segments shown in the echocardiogramimages. In particular, the wall motion data 110 may include RWMA scores 132 rating potentially abnormal cardiac wall segment movements. In some examples, one RWMA score 132 may be generated for each of the sixteen left ventricular cardiac wall segments defined by the ASE. The cardiac wall segments may include basal anterior, basal anteroseptal, basal inferoseptal, basal inferior, basal inferolateral, basal anterolateral, mid anterior, mid anteroseptal, mid inferoseptal, mid inferior, mid inferolateral, mid anterolateral, apical anterior, apical septal, apical inferior, and apical lateral segments. Within the wall motion data 110, each cardiac wall segment may be tracked over time and as the patient progresses through the stages of stress testing. Accordingly, the wall motion data 110 may be used to identify whether the motion of a particular cardiac wall segment increases, decreases, or remains constant over time. The wall motion data 110 may also track longitudinal changes of the cardiac wall segments in certain views over time. The cardiac wall motion tracking model 108 may be trained with historical wall motion data prior to implementation during a stress test.

[0051] A diagram representing the echocardiogram images 102 processed by the cardiac wall motion tracking model 108 is shown in FIG. 3 A. The example echocardiogram images 102 include images 102 captured at the resting stage 122, the low stress stage 124, and the pre-peak stage 126. In particular, the images 102 captured correspond to a plurality of echocardiogram views 128 including an apical two chamber view (AP2), an apical three chamber view (AP3), an apical four chamber view (AIM), and a parasternal long axis view (PLAX). Accordingly, if the patient is currently at rest, the cardiac wall motion tracking model 108 will only be able to analyze the echocardiogram images 102 corresponding to the resting stage 122, and the system 10 will determine the cardiac risk data 120 based only on images captured during the resting stage 122.

[0052] With further respect to FIG. 2, the measurement abnormality detection model 112 may be an autoregressive model configured to process the measurement data 106. The measurement abnormality detection model 112 generates measurement abnormality data 114 indicative of potential cardiac abnormalities. A diagram representing the measurement data 102 processed by the measurement abnormality detection model 112 is shown in FIG. 3B. The example measurement data 106 includes data 106 captured at the resting stage 122, the low stress stage 124, and the pre-peak stage 126. In this particular non-limiting example, the data 106 captured corresponds to ejection fraction (EF) andE / e’ ratio. However, the measurement data 106 may also include a wide array of other types of data related to left ventricular measurements trackingdiastolic and systolic functions. Accordingly, if the patient is currently at rest, the cardiac wall motion tracking model 108 will only be able to analyze the measurement data 106 corresponding to the resting stage 122, and the system 10 will determine the cardiac risk data 120 based only on data captured during the resting stage 122.

[0053] As shown in FIG. 2, the wall motion data 110 and the measurement abnormality data 114 is provided to the RWMA forecasting model 116. The RWMA forecasting model 116 may be a three-dimensional CNN configured to generate peak stress RWMA forecast data 118 indicative of the risk of abnormalities occurring during a future, peak stress stage of the current stress test. The RWMA forecast data 118 may indicate forecasted abnormalities in each of the sixteen left ventricular cardiac wall segments defined by the ASE. Accordingly, the RWMA forecasting model 116 uses data derived from two modalities, echocardiogram images and electrocardiogram measurements, to forecast the occurrence of abnormalities when the patient experiences peak stress in the future. This forecasting may be done in real time during a cardiac stress test as the stress level experienced by the patient increases from rest, to low stress, to pre-peak stress. The RWMA forecasting model 116 may be trained with historical wall motion data and historical measurement abnormality data prior to implementation during a stress test.

[0054] The peak stress RWMA forecast data 118 is then provided to the cardiac risk analyzer 148. The cardiac risk analyzer 148 translates the peak stress RWMA forecast data 118 into cardiac risk data 120 easily understood by the clinician performing the stress test. The cardiac risk data 120 may also incorporate aspects of the echocardiogram images 102 from the ultrasound scanner 300 and the measurement data 106 from the electrocardiogram machine 400. As shown in FIG. 1, the cardiac risk data 120 may be then shown on a display screen 200. In particular, and as will be shown in more detail in FIGS. 4-6, the cardiac risk analyzer 148 may generate a cardiac risk dashboard 136. The cardiac risk dashboard 136 provides the clinician with a wide array of information regarding previously recorded and forecasted risk data for the patient undergoing the stress test. The cardiac risk dashboard 136 may include one or more risk visualizations 138, including risk forecast data 140, wall motion visualizations 142, and / or measurement visualizations 146. The potential risks described by the cardiac risk data 120 may relate to a variety of conditions related to the movement of cardiac wall segments, such as ischemia, myocardial infarction, and others.

[0055] FIG. 4 shows an example cardiac risk dashboard 136 shown on the display screen 200. The cardiac risk dashboard 136 includes a risk visualization 138 in the form of risk forecast data 140. In particular, the risk forecast data 140 includes a dial indicating a high risk of ischemic heart disease. The cardiac risk dashboard 136 also includes a variety of text information regarding potential risks. In particular, a text box regarding the peak stress forecast indicates that the patient projects to have “low exercise capability” and that the patient may experience stress-induced ischemia. Another text box regarding wall motion changes indicates that mid-anterior motion is normal, while apical motion is attenuating. A further text box indicates that the ejection fraction of the heart of the patient has decreased below 40%, and that the maximum velocity of the E wave of the electrocardiogram is also decreasing. Accordingly, the cardiac risk dashboard 136 and the risk forecast data 140 enable a clinician to quickly determine how the patient may respond to increased stress testing, allowing the clinician to adjust or cease stress testing to avoid harming the patient.

[0056] FIG. 5 shows another example of a cardiac risk dashboard 136. In the non-limiting example of FIG. 5, the cardiac risk dashboard 136 includes risk visualizations 138 embodied as a series of four wall motion visualizations 142. The four wall motion visualizations 142 of FIG. 5 correspond to an apical four chamber view (AP4). As shown in FIG. 5, the wall motion visualizations 142 include electrocardiogram images 102 captured during the resting stage 122 (top left), the low stress stage 124 (top right), and the pre-peak stress stage 126 (bottom left). Additionally, the peak stress RWMA forecast data 118 is used to derive a forecasted electrocardiogram image at a peak stress, forecast stage 144 as shown in the bottom right of the four wall motion visualizations. Further, each of the wall motion visualizations 142 may also include a segment saliency map 152 tracking the motion of a specific cardiac wall segment from the resting stage 122, to the low stress stage 124, to the pre-peak stress stage 126, and to the peak stress forecast stage 144. Accordingly, these wall motion visualizations 142 enable a clinician to quickly determine how certain cardiac wall segments may respond to increased stress testing.

[0057] FIG. 6 shows another example of a cardiac risk dashboard 136. In the non-limiting example of FIG. 5, the cardiac risk dashboard 136 includes risk visualizations 138 embodied as measurement visualizations 146. The measurement visualizations 146 show a pair of plots comprising measurement data 106 and data derived from the peak stress RWMA forecast data 118. A first plot of FIG. 6 shows left ventricle ejection fraction (LVEF) at the resting stage 122, the lowstress stage 124, the peak stress stage 126, and the peak stress forecast stage 144. A second plot of FIG. 6 shows E / A ratio of an electrocardiogram reading at the resting stage 122, the low stress stage 124, the peak stress stage 126, and the peak stress forecast stage 144. Accordingly, these measurement visualizations 146 enable a clinician to quickly determine how certain measurements may respond to increased stress testing.

[0058] FIG. 7 schematically illustrates the controller 100 previously depicted in FIGS. 2 and 4. The controller 100 includes the processor 125, the memory 175, and the transceiver 185. The memory 175 is configured to store the plurality of echocardiogram images 102 (including a plurality of echocardiogram views 128) and the measurement data 106 (including the plurality of electrocardiogram measurements 130) at the one or more stress stages 104 (including the resting stage 122, the low stress stage 124, the pre-peak stress stage 126, and the forecast stage 144). The memory 175 is also configured to store the wall motion data 110 (including the RWMA scores 132), the measurement abnormality data 114, and the peak stress RWMA forecast data 118 (including the wall segment abnormality data 134) and the cardiac risk data 120 (including a cardiac risk dashboard 136 showing one or more risk visualizations 138 such as the risk forecast data 140, the wall motion visualizations 142, and the measurement visualizations 146). The processor 125 is configured to execute the wall motion model 108, the measurement abnormality detection model 112, the RWMA forecast model 116, and the cardiac risk model 148. The transceiver 185 may be configured to transmit or receive any aspect of the aforementioned data stored in the memory 175.

[0059] FIG. 8 is a flow chart of a method 900 for cardiac stress test monitoring. The method 900 includes, in step 902, receiving, via a controller 100, a plurality of echocardiogram images 102. Each of the plurality of echocardiogram images 102 corresponds to one or more stress stages 104.

[0060] The method 900 further includes, in step 904, receiving, via the controller 100, measurement data 106 corresponding to the one or more stress stages 104.

[0061] The method 900 further includes, in step 906, generating, via a cardiac wall motion tracking model 108 of the controller 100, wall motion data 110 based on the plurality of echocardiogram images 102.

[0062] The method 900 further includes, in step 908, generating, via a measurement abnormality detection model 112 of the controller 100, measurement abnormality data 114 basedon the measurement data 106.

[0063] The method 900 further includes, in step 910, generating, via an RWMA forecasting model 116 of the controller 100, peak stress RWMA forecast data 118 based on the wall motion data 110 and the measurement abnormality data 114.

[0064] The method 900 further includes, in step 912, generating, via the controller 100, cardiac risk data 120 based on the peak stress RWMA forecast data 118.

[0065] The method 900 further includes, in step 914, outputting, via the controller 100, the cardiac risk data 120.

[0066] All definitions, as defined and used herein, should be understood to control over dictionary definitions, definitions in documents incorporated by reference, and / or ordinary meanings of the defined terms.

[0067] The indefinite articles “a” and “an,” as used herein in the specification and in the claims, unless clearly indicated to the contrary, should be understood to mean “at least one.”

[0068] The phrase “and / or,” as used herein in the specification and in the claims, should be understood to mean “either or both” of the elements so conjoined, i.e., elements that are conjunctively present in some cases and disjunctively present in other cases. Multiple elements listed with “and / or” should be construed in the same fashion, i.e., “one or more” of the elements so conjoined. Other elements may optionally be present other than the elements specifically identified by the “and / or” clause, whether related or unrelated to those elements specifically identified.

[0069] As used herein in the specification and in the claims, “or” should be understood to have the same meaning as “and / or” as defined above. For example, when separating items in a list, “or” or “and / or” shall be interpreted as being inclusive, i.e., the inclusion of at least one, but also including more than one, of a number or list of elements, and, optionally, additional unlisted items. Only terms clearly indicated to the contrary, such as “only one of’ or “exactly one of,” or, when used in the claims, “consisting of,” will refer to the inclusion of exactly one element of a number or list of elements. In general, the term “or” as used herein shall only be interpreted as indicating exclusive alternatives (i.e. “one or the other but not both”) when preceded by terms of exclusivity, such as “either,” “one of,” “only one of,” or “exactly one of.”

[0070] As used herein in the specification and in the claims, the phrase “at least one,” in reference to a list of one or more elements, should be understood to mean at least one elementselected from any one or more of the elements in the list of elements, but not necessarily including at least one of each and every element specifically listed within the list of elements and not excluding any combinations of elements in the list of elements. This definition also allows that elements may optionally be present other than the elements specifically identified within the list of elements to which the phrase “at least one” refers, whether related or unrelated to those elements specifically identified.

[0071] It should also be understood that, unless clearly indicated to the contrary, in any methods claimed herein that include more than one step or act, the order of the steps or acts of the method is not necessarily limited to the order in which the steps or acts of the method are recited.

[0072] In the claims, as well as in the specification above, all transitional phrases such as “comprising,” “including,” “carrying,” “having,” “containing,” “involving,” “holding,” “composed of,” and the like are to be understood to be open-ended, i.e., to mean including but not limited to. Only the transitional phrases “consisting of’ and “consisting essentially of’ shall be closed or semi-closed transitional phrases, respectively.

[0073] The above-described examples of the described subject matter can be implemented in any of numerous ways. For example, some aspects may be implemented using hardware, software, or a combination thereof. When any aspect is implemented at least in part in software, the software code can be executed on any suitable processor or collection of processors, whether provided in a single device or computer or distributed among multiple devices / computers.

[0074] The present disclosure may be implemented as a system, a method, and / or a computer program product at any possible technical detail level of integration. The computer program product may include a computer readable storage medium (or media) having computer readable program instructions thereon for causing a processor to carry out aspects of the present disclosure.

[0075] The computer readable storage medium can be a tangible device that can retain and store instructions for use by an instruction execution device. The computer readable storage medium may be, for example, but is not limited to, an electronic storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any suitable combination of the foregoing. A non-exhaustive list of more specific examples of the computer readable storage medium includes the following: a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), a static random access memory (SRAM), aportable compact disc read-only memory (CD-ROM), a digital versatile disk (DVD), a memory stick, a floppy disk, a mechanically encoded device such as punch-cards or raised structures in a groove having instructions recorded thereon, and any suitable combination of the foregoing. A computer readable storage medium, as used herein, is not to be construed as being transitory signals per se, such as radio waves or other freely propagating electromagnetic waves, electromagnetic waves propagating through a waveguide or other transmission media (e.g., light pulses passing through a fiber-optic cable), or electrical signals transmitted through a wire.

[0076] Computer readable program instructions described herein can be downloaded to respective computing / processing devices from a computer readable storage medium or to an external computer or external storage device via a network, for example, the Internet, a local area network, a wide area network and / or a wireless network. The network may comprise copper transmission cables, optical transmission fibers, wireless transmission, routers, firewalls, switches, gateway computers and / or edge servers. A network adapter card or network interface in each computing / processing device receives computer readable program instructions from the network and forwards the computer readable program instructions for storage in a computer readable storage medium within the respective computing / processing device.

[0077] Computer readable program instructions for carrying out operations of the present disclosure may be assembler instructions, instruction-set-architecture (ISA) instructions, machine instructions, machine dependent instructions, microcode, firmware instructions, state-setting data, configuration data for integrated circuitry, or either source code or object code written in any combination of one or more programming languages, including an object oriented programming language such as Smalltalk, C++, or the like, and procedural programming languages, such as the “C” programming language or similar programming languages. The computer readable program instructions may execute entirely on the user’s computer, partly on the user's computer, as a standalone software package, partly on the user’s computer and partly on a remote computer or entirely on the remote computer or server. In the latter scenario, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or the connection may be made to an external computer (for example, through the Internet using an Internet Service Provider). In some examples, electronic circuitry including, for example, programmable logic circuitry, field-programmable gate arrays (FPGA), or programmable logic arrays (PLA) may execute the computer readable program instructions byutilizing state information of the computer readable program instructions to personalize the electronic circuitry, in order to perform aspects of the present disclosure.

[0078] Aspects of the present disclosure are described herein with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to examples of the disclosure. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer readable program instructions.

[0079] The computer readable program instructions may be provided to a processor of a, special purpose computer, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions / acts specified in the flowchart and / or block diagram block or blocks. These computer readable program instructions may also be stored in a computer readable storage medium that can direct a computer, a programmable data processing apparatus, and / or other devices to function in a particular manner, such that the computer readable storage medium having instructions stored therein comprises an article of manufacture including instructions which implement aspects of the function / act specified in the flowchart and / or block diagram or blocks.

[0080] The computer readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other device to cause a series of operational steps to be performed on the computer, other programmable apparatus or other device to produce a computer implemented process, such that the instructions which execute on the computer, other programmable apparatus, or other device implement the functions / acts specified in the flowchart and / or block diagram block or blocks.

[0081] The flowchart and block diagrams in the Figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various examples of the present disclosure. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of instructions, which comprises one or more executable instructions for implementing the specified logical function(s). In some alternative implementations, the functions noted in the blocks may occur out of the order noted in the Figures. For example, two blocks shown in succession may, in fact, be executed substantiallyconcurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and / or flowchart illustration, and combinations of blocks in the block diagrams and / or flowchart illustration, can be implemented by special purpose hardware-based systems that perform the specified functions or acts or carry out combinations of special purpose hardware and computer instructions.

[0082] Other implementations are within the scope of the following claims and other claims to which the applicant may be entitled.

[0083] While various examples have been described and illustrated herein, those of ordinary skill in the art will readily envision a variety of other means and / or structures for performing the function and / or obtaining the results and / or one or more of the advantages described herein, and each of such variations and / or modifications is deemed to be within the scope of the examples described herein. More generally, those skilled in the art will readily appreciate that all parameters, dimensions, materials, and configurations described herein are meant to be exemplary and that the actual parameters, dimensions, materials, and / or configurations will depend upon the specific application or applications for which the teachings is / are used. Those skilled in the art will recognize, or be able to ascertain using no more than routine experimentation, many equivalents to the specific examples described herein. It is, therefore, to be understood that the foregoing examples are presented by way of example only and that, within the scope of the appended claims and equivalents thereto, examples may be practiced otherwise than as specifically described and claimed. Examples of the present disclosure are directed to each individual feature, system, article, material, kit, and / or method described herein. In addition, any combination of two or more such features, systems, articles, materials, kits, and / or methods, if such features, systems, articles, materials, kits, and / or methods are not mutually inconsistent, is included within the scope of the present disclosure.

Claims

ClaimsWhat is claimed is:

1. A cardiac stress test monitoring system (10), comprising a controller (100) configured to: receive a plurality of echocardiogram images (102), wherein each of the plurality of echocardiogram images (102) corresponds to one or more stress stages (104); receive measurement data (106) corresponding to the one or more stress stages (104); generate, via a cardiac wall motion tracking model (108), wall motion data (110) based on the plurality of echocardiogram images (102); generate, via a measurement abnormality detection model (112), measurement abnormality data (114) based on the measurement data (106); generate, via a regional wall motion abnormality (RWMA) forecasting model (116), peak stress RWMA forecast data (118) based on the wall motion data (110) and the measurement abnormality data (114); generate cardiac risk data (120) based on the peak stress RWMA forecast data (118); and output the cardiac risk data (120).

2. The cardiac stress test monitoring system (10) of claim 1, wherein the one or more stress stages (104) comprise a resting stage (122), a low stress stage (124), and / or a pre-peak stress stage (126).

3. The cardiac stress test monitoring system (10) of claim 1, wherein the cardiac wall motion tracking model (108) is a three-dimensional convolutional neural network (CNN) model.

4. The cardiac stress test monitoring system (10) of claim 1, wherein the plurality of echocardiogram images (102) comprise a plurality of echocardiogram views (128).

5. The cardiac stress test monitoring system (10) of claim 1, wherein the measurement abnormality detection model (112) is an autoregressive model.

6. The cardiac stress test monitoring system (10) of claim 1, wherein the measurement data (106) comprises a plurality of electrocardiogram measurements (130).

7. The cardiac stress test monitoring system (10) of claim 1, wherein the wall motion data (110) corresponds to one or more cardiac wall segments.

8. The cardiac stress test monitoring system (10) of claim 1, wherein the RWMA forecasting model (116) is a three-dimensional convolutional neural network (CNN) model.

9. The cardiac stress test monitoring system (10) of claim 1, wherein the wall motion data (110) comprises one or more RWMA scores (132).

10. The cardiac stress test monitoring system (10) of claim 1, wherein the peak stress RWMA forecast data (118) includes abnormality data (134) for one or more cardiac wall segments.

11. The cardiac stress test monitoring system (10) of claim 1, wherein the cardiac risk data (120) comprises a cardiac risk dashboard (136) comprising one or more risk visualizations (138), and wherein the cardiac risk dashboard (122) is displayed on a display screen (200) communicatively coupled to the controller (100).

12. The cardiac stress test monitoring system (10) of claim 11, wherein the one or more risk visualizations (124) includes risk forecast data (140) based on the peak stress RWMA forecast data (H8).

13. The cardiac stress test monitoring system (10) of claim 11, wherein the one or more risk visualizations (124) includes a wall motion visualization (142) of a wall segment, wherein the wall motion visualization (142) corresponds to the one or more stress stages (104) and a forecast stage (144).

14. The cardiac stress test monitoring system (10) of claim 11, wherein the one or more risk visualizations includes a measurement visualization (146) corresponding to the one or more stress stages (104) and a forecast stage (144).

15. A method (900) for cardiac stress test monitoring, comprising: receiving (902), via a controller, a plurality of echocardiogram images, wherein each of the plurality of echocardiogram images corresponds to one or more stress stages; receiving (904), via the controller, measurement data corresponding to the one or more stress stages; generating (906), via a cardiac wall motion tracking model of the controller, wall motion data based on the plurality of echocardiogram images; generating (908), via a measurement abnormality detection model of the controller, measurement abnormality data based on the measurement data; generating (910), via a regional wall motion abnormality (RWMA) forecasting model of the controller, peak stress RWMA forecast data based on the wall motion data and the measurement abnormality data; generating (912), via the controller, cardiac risk data based on the peak stress RWMA forecast data; and outputting (914), via the controller, the cardiac risk data.

Images