Cardiac characteristic analysis system and method

Abstract

The system described herein can be used to track and analyze cardiac features captured via MRI scans. The system can receive multiple MR slice images derived via MRI scans and present the MR slice images in a manner that allows a user to browse the MR slice images. In response to a user selecting one of the MR slice images, background and global cardiac information associated with the selected slice image can be determined and displayed. The background information can correspond to the selected slice image, and the global information can cover information collected across multiple MR slice images. The user can have the ability to browse between different display areas and evaluate cardiac health using both local and global perspectives.

Description

[0001] CROSS-REFERENCE TO RELATED APPLICATIONS

[0002] This application claims the benefit of Provisional U.S. Patent Application No. 62 / 941,198 filed on November 27, 2019 and Provisional U.S. Patent Application No. 17 / 014,609 filed on September 8, 2020, the disclosures of which are incorporated herein by reference in their entirety. Technical Field

[0003] The present application relates to the field of cardiac magnetic resonance image analysis. Background Art

[0004] Cardiovascular disease is the leading cause of death worldwide, claiming an estimated 17.9 million lives each year. Accurate assessment of cardiac characteristics and function is critical for the prevention and treatment of these diseases. In recent years, cardiac magnetic resonance imaging (cMRI) has become a powerful tool for the evaluation of cardiac characteristics including strain, strain rate, torsion and / or mechanical dispersion. cMRI allows for precise quantification of ventricular and atrial mechanics by direct assessment of myocardial fiber deformation without subjecting the patient to radiation or invasive procedures.

[0005] Although cMRI can provide a wealth of information about cardiac health, there is currently a lack of tools for interfacing with cMRI devices, understanding the information captured by cMRI devices, or organizing and presenting the information captured by cMRI devices in a manner that will allow clinicians to fully exploit the advantages of cMRI. For example, when acquiring cardiac cine images of the myocardium, clinicians are very eager to browse these images in order to evaluate specific areas of the myocardium based on the background information associated with these areas. And while focusing on a specific area, it is also desirable to maintain a global perspective of the myocardium, such as across both time and space, so that changes in the specific area can be viewed relative to other areas of the myocardium or other time points. Summary of the invention

[0006] This article describes systems, methods, and devices for tracking and analyzing cardiac features captured via MRI scans. An MRI analyzer as described herein can receive multiple MR slice images, which can be derived via an MRI scan of a patient's heart (e.g., a cardiac MR movie). The MR slice images can correspond to corresponding scan positions along a scan axis, and each MR slice image can include a visual representation of the myocardium within a period of time (e.g., one or more cardiac cycles). The MRI analyzer can, for example, present the MR slice images in a first area of ​​a display device. The presentation can be provided in a manner that allows a user of the MRI analyzer to browse the MR slice images along the scan axis. The MRI analyzer can determine background information associated with a selected slice image in a plurality of MR slice images and display the background information, for example, in a second area of ​​the display device. The background information can include images of the myocardium associated with the selected MR slice image and strains of the myocardium indicated by these images. The display of the background information can include an animated presentation of an image associated with the selected MR slice image and a graphic indicating one or more cardiac parameters (e.g., radial and / or circumferential strain curves), which are determined based on the selected MR slice image. In response to a user selecting a point on the graph (e.g., along the time axis), the MRI analyzer can adjust the animation of the myocardial image to display the myocardial image corresponding to the time position of the selected point on the graph. Further, the animation of the image can indicate the inner and outer boundaries of the myocardium, and the MRI analyzer can be configured to receive user input that marks the inner and outer boundaries of the myocardium.

[0007] The MRI analyzer described herein may also be configured to determine global information associated with the myocardium across multiple MR slice images and display the information, for example, in a third area of ​​the display device. The global information may include strain and / or deformation parameters of the myocardium determined by the MRI analyzer based on multiple MR slice images. The display of the global information may include a 3D view (e.g., a 3D grid or point cloud) of the myocardium segmented based on multiple MR slice images. The display may also include one or more graphs (e.g., bull's eye graphs) that show global strain or deformation parameters determined by the MRI analyzer for different segments of the myocardium (e.g., based on the maximum, minimum, or average strain of each segment of the myocardium during a time period associated with the MR slice image). In response to a user selecting an area of ​​the graph corresponding to a segment of the myocardium, the MRI analyzer may highlight the segment of the myocardium in the 3D view. Further, in response to a user selecting an area of ​​the 3D view corresponding to one of the multiple MR slice images, the MRI analyzer may determine background information of one of the multiple MR slice images and display the information in a second area of ​​the display device.

[0008] The MRI analyzer described herein may also be configured to determine and display a matrix indicating various states of the myocardium across space and time. The matrix may include a plurality of cells, each of which may correspond to a row and a column, the row representing a corresponding MR slice image in a plurality of MR slice images, and the column representing a time point during a time period associated with the corresponding MR slice image. Thus, each cell of the matrix may indicate a corresponding state of the myocardium, as indicated by the corresponding MR slice image and the time point associated with the cell.

[0009] The MRI analyzer described herein may also be configured to generate, transmit and / or print a report including at least a portion of the background information or global information described herein. The report may be automatically or semi-automatically generated, for example, based on user input, which may include text or verbal instructions about the report. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] Examples disclosed herein may be understood in more detail from the following description given by way of example in conjunction with the accompanying drawings.

[0011] Figure 1 is a block diagram illustrating an example system including an MRI analyzer as described herein.

[0012] Figure 2 is a diagram illustrating example information that may be determined and presented by an MRI analyzer as described herein.

[0013] Figure 3 is a diagram illustrating how a 3D view of the myocardium generated by an MRI analyzer may be highlighted in response to user input.

[0014] Figure 4 is a diagram illustrating an example user interface that may be rendered by the MRI analyzer described herein.

[0015] Figure 5 is a diagram illustrating an example matrix view that may be rendered by the MRI analyzer described herein.

[0016] Figure 6 is a block diagram illustrating an example MRI analyzer described herein.

[0017] Figure 7 is a flow chart illustrating an example process that may be performed by the MRI analyzer described herein. DETAILED DESCRIPTION

[0018] The present disclosure is illustrated by way of example and not limitation in the figures of the accompanying drawings. For example, embodiments will be described herein using cardiac MRI (cMRI) and / or a human heart (e.g., left ventricle and / or myocardium) as examples, but those skilled in the art will appreciate that the techniques disclosed herein are generally applicable to other imaging modalities and other organs or tissues of the human body.

[0019] Figure 1 1 is a block diagram illustrating an example magnetic resonance imaging (MRI) feature tracking system 100 according to one or more embodiments disclosed herein. The system 100 may include an MRI acquisition device 102, an MRI image library 104, and / or an MRI analysis system or device 106. The MRI acquisition device 102 may include a scanner and a controller. The scanner may be implemented using certain types of superconducting magnets with specific apertures and / or field strengths. The magnet may generate magnetic fields that the scanner uses to acquire MR images of a patient located within a measurement space. The controller may be configured to control the operation of the MRI acquisition device 102 and may include one or more of a start unit, a receiving unit, or a data processing module. The start unit may be used to start and stop the scanner from generating a magnetic field. The receiving unit may be configured to receive and / or record MR data acquired by the scanner, which may then be prepared for storage and / or further processing by the data processing unit.

[0020] The data generated by the MRI acquisition device 102 may include one or more dynamic image sequences, such as a cardiac movie showing the motion of the heart throughout one or more cardiac cycles. A cardiac movie may include a sequence of images taken at various slice image positions along a scanning axis (e.g., short axis or long axis) and within a time frame (e.g., within one or more cardiac cycles). Each such image sequence may be referred to herein as a slice image or MR slice image, and each slice image may visually represent all or a portion of the heart (e.g., left ventricle, myocardium, etc.) within a corresponding time frame. For example, a slice image may include an image of the left ventricle, which may be used to determine systolic output and / or end-diastolic volume, from which a left ventricular ejection fraction (LVEF) may be calculated (e.g., as a ratio between systolic output and end-diastolic volume) to evaluate cardiac function. As another example, images included in the slice image may be used to determine myocardial deformation in various directions, from which radial and / or circumferential strain may be calculated. Radial strain may indicate radially oriented myocardial deformation toward the center of the LV cavity, whereas circumferential strain may indicate shortening of LV myocardial fibers along the circular circumference observed in the short axis.

[0021] The data (e.g., cardiac cine) generated by the MRI acquisition device 102 may be transmitted to and / or stored in an MRI image repository 104, which may be part of the MRI acquisition device 102 or part of a separate computing device such as a cloud-based computing device. The MRI image repository 104 may include one or more general databases or databases specifically configured to store images generated by the MRI acquisition device 102. The images may be stored in a structured manner (e.g., in a specific format and / or schema) and / or may be linked to other information about the patient, such as the patient's identity or medical history. The transmission and organization of the data generated by the MRI acquisition device 102 may be performed offline, such as when the MRI acquisition device 102 and / or the MRI image repository 104 are not in use, or online, such as when the MRI acquisition device 102 is actively collecting scan images and / or when the MRI image repository 104 is being accessed by other devices or applications.

[0022] Data (e.g., cardiac movies) generated by the MRI acquisition device 102 may also be transmitted to and / or retrieved by the MRI analyzer 106. In some examples, the MRI analyzer 106 may retrieve data directly from the MRI acquisition device 102, while in other examples, the MRI analyzer 106 may retrieve data from the MRI image library 104, for example, after the data has been transferred to the library. Data transmission and / or retrieval between the MRI acquisition device 102, the MRI image library 104, and / or the MRI analyzer 106 may be performed via a communication network 108, which may be a wired or wireless network or a combination thereof. For example, the communication network 108 may be established on a public network (e.g., the Internet), a private network (e.g., a local area network (LAN), a wide area network (WAN), etc.), a wired network (e.g., Ethernet), a wireless network (e.g., an 802.11 network, a Wi-Fi network, etc.), a cellular network (e.g., a long term evolution (LTE) or a 5G network), a frame relay network, a virtual private network (VPN), a satellite network, and / or a telephone network. The communication network 108 may include one or more network access points. For example, the communication network 108 may include wired and / or wireless network access points, such as base stations and / or Internet exchange points, through which the MRI acquisition device 102, the MRI image repository 104, and / or the MRI analyzer 106 may be connected to exchange data and / or other information. Such exchange may utilize routers, hubs, switches, server computers, and / or any combination thereof.

[0023] The MRI analyzer 106 may include one or more processors and / or one or more storage devices configured to store computer-readable instructions that, when executed by the one or more processors, cause the processors to perform one or more of the following functions. For example, the instructions may cause the one or more processors to retrieve MRI data, such as a cardiac movie, from the MRI acquisition device 102 and / or the MRI image library 104. When acquiring the MRI data, the one or more processors may also identify a plurality of MR slice images in the MRI data, which, as described herein, may visually depict the condition and / or movement of the heart (e.g., the left ventricle and / or the myocardium) along the scan axis and over a period of time. The time period may span one or more cardiac cycles, each of which may include a diastole and a systole. One or more processors of the MRI analyzer 106 can be configured to determine the beginning and / or end of diastole and systole using various techniques, including, for example, utilizing a machine learning (ML) model to automatically predict end-diastole (ED) and end-systole (ES) frames, inferring the beginning and / or end of diastole and systole based on recorded electrocardiogram (ECG) signals, receiving user input for marking ED and / or ES frames, and the like.

[0024] One or more processors of the MRI analyzer 106 may also be configured to extract background and global information related to the condition and / or motion of the heart from the MRI data. The background information may be associated with individual MR slice images in the MRI data and may include quantitative parameters such as strain (e.g., deformation), geometry (e.g., volume) and / or motion parameters of the heart, which are determined by one or more processors based on images included in the MR slice images. Global information may be derived based on multiple (e.g., all) MR slice images and may include parameters of the heart synthesized across multiple MR slice images and / or multiple time periods. It can be seen that the global information may be used by one or more processors of the MRI analyzer 106 to present a comprehensive view of the heart across both time and space (e.g., three-dimensional plus time or 3D+T).

[0025] The one or more processors of the MRI analyzer 106 may be configured to present the MR slice images, background information, and / or global information described herein on a display device 110. The display device 110 may include one or more monitors, such as one or more computer monitors, one or more TV monitors, one or more tablet computers, and / or one or more mobile devices. The display device 110 may also include one or more speakers, one or more augmented reality (AR) devices (e.g., AR goggles), and / or other accessories configured to facilitate presentations generated by the MRI analyzer 106. The display device 110 may be part of the MRI analyzer 106, or may be communicatively coupled to the MRI analyzer 106, for example, via a communication network 108 or another suitable communication link.

[0026] Figure 22 is a diagram illustrating example information that may be determined by the MRI analyzer 106 and presented on a display device such as the display device 110. In a first area 202 of the display device, the MRI analyzer 106 may present patient information (e.g., a patient identification code) next to a navigation pane that allows a user of the MRI analyzer 106 to browse through a plurality of MR slice images (e.g., a sequence of MR slice images) derived from a cardiac MRI scan (e.g., a cardiac cine) of the patient and select a slice image that the user is interested in further exploring. For example, the MR slice images may be indexed (e.g., labeled) based on respective locations of the MR slice images along a scan axis (e.g., a short axis or a long axis). Each MR slice image may include a plurality of MRI images of the heart that collectively provide a visual representation of one or more regions of the heart (e.g., a left ventricle, myocardium, etc.) within a time period during which the MRI images were taken. As described herein, such a time period may correspond to one or more cardiac cycles, and each cardiac cycle may include a diastole and a systole. For example, in response to receiving a user input indicating a switch, a plurality of MR slice images displayed in the first area 202 may be switched in and out (e.g., replaced with another set of MR slice images or MR slice image sequences). For example, the MRI analyzer 106 may obtain different MR slice image sequences from the same cardiac study of a patient. The MRI analyzer 106 may display icons in an area of ​​the display device 110 that correspond to these MR slice image sequences. As the user hovers the mouse over each icon or clicks on an icon, the MRI analyzer 106 may provide an indication on the display device that relates to where the user may cause the MR slice image sequence corresponding to the selected icon to fall. The area in which the user may cause the selected MR slice image sequence to fall may vary depending on the context of the application area in which the user is located, and in response to the user affirmatively causing the MR slice image sequence to fall into the indicated area, the MRI analyzer 106 may switch the display in the first area 202 to show the MR slice image sequence selected and caused to fall by the user.

[0027] The MRI analyzer 106 can be configured to enable browsing of the multiple MR slice images displayed in the area 202 in various ways. In an example, the MRI analyzer can enable browsing by providing a slider along one side of the first display area 202, and the user can use the slider to scroll through the multiple MR slice images. In an example, the MRI analyzer can include a drop-down menu in the portion of the first display area 202 that displays the available MR slice images. In an example (for example, when the display device is a touch screen device), the MRI analyzer can use the touch surface of the first display area 202 to allow the user to swipe the MR slice images. Selecting a specific slice image among the multiple MR slice images can also be performed in various ways. For example, a specific slice image can be selected by clicking on an icon representing a specific slice image, by selecting an item on a drop-down menu corresponding to a specific slice image, by tapping an area of ​​the touch surface that displays a specific slice image, by voice activation (for example, emitting a sound of the index of a specific slice image), etc.

[0028] In response to a user selecting a particular MR slice image from a plurality of MR slice images in the first region 202 of the display device, the MRI analyzer may be configured to determine background information associated with the selected MR slice image and display the background information in the second region 204 of the display device. The background information may include a series or multiple series of images (e.g., of the myocardium) associated with the selected MR slice image and / or quantitative parameters determined based on these images. The images may depict a cross section of the myocardium during a time period (e.g., a cardiac cycle) associated with the selected MR slice image. The quantitative parameters may indicate strain (e.g., deformation), geometry (e.g., volume), and / or motion of the myocardium during the same time period. The MRI analyzer may replay a series of images associated with the selected MR slice image in a portion of the second region 204, for example, as an animation (e.g., a movie) along a timeline of the captured images. This two-dimensional plus time (e.g., 2D+T) playback can visualize the movement and / or deformation of the myocardium during a time period associated with a selected MR slice image, and the MRI analyzer can provide controls (e.g., in-segment controllers such as buttons) on or near the playback area for the user to play, pause, rewind, and / or stop the playback.

[0029] In one or more (e.g., all) images of the 2D+T playback, the MRI analyzer can segment the endocardium and / or epicardium, and mark the boundaries of the endocardium and / or epicardium along the cardiac cycle 206. Segmentation and / or labeling can be performed using a machine learning (ML) model. An example of such an ML model can be found in co-assigned U.S. Patent Application No. 16 / 905,115, filed on June 18, 2020, entitled "Systems and Methods for Image Segmentation," the disclosure of which is hereby incorporated by reference in its entirety. The MRI analyzer can also allow a user to manually annotate the boundaries of the myocardium. For example, the MRI analyzer can allow a user to draw the entire inner and / or outer boundaries of the myocardium on one or more images of a selected MR slice image, or to mark certain locations on the inner and / or outer boundaries, and trigger the MRI analyzer to automatically connect the dotted locations to form a boundary. Once the boundaries of the myocardium are determined (e.g., based on an ML model or manual user input), the MRI analyzer can determine or adjust at least a subset of the quantitative parameters described herein, such as strain and / or thickness of the myocardium, based on the determined boundaries. Display of the myocardial boundaries and / or means for manually annotating the myocardial boundaries can be activated and deactivated (e.g., shown or hidden) by the user, for example, using in-segment controls (e.g., buttons or checkboxes) provided by the MRI analyzer.

[0030] The background information presented in the second area 204 may include one or more graphs showing the relationship between the value of the quantitative parameter determined by the MRI analyzer and time. For example, the graph may be shown in a portion of the second area 204 adjacent to the 2D+T animation of the selected MR slice image. The graph may be drawn over a time period associated with the selected MR slice image, which may include one or more cardiac cycles as described herein. The quantitative parameter values ​​shown in the graph may include, for example, radial and / or circumferential strains of the myocardium, which are determined by the MRI analyzer based on the selected MR slice image (e.g., based on an image of the myocardium included in the selected MR slice image). It can be seen that the graph may represent radial (Err) and / or circumferential (Ecc) strain curves of the myocardium over one or more cardiac cycles. The radial strain curve may indicate radially oriented myocardial deformation toward the center of the ventricular cavity (e.g., the left ventricle (LV) cavity) over time, and the circumferential strain curve may indicate LV myocardial fiber shortening along a circular circumference observed on a scanning axis (e.g., the short axis) over time. In an example, circumferential strain can be associated with the epicardium, the middle myocardium, and / or the endocardium, each of which can be displayed as a separate graph (e.g., with a unique color and / or pattern). In an example, circumferential strain can be determined for (e.g., any) specific transmural location. For example, strain values ​​can be calculated at a transmural location that has contracted a certain percentage (e.g., such as 10%) radially from the epicardial contour. As another example, strain values ​​can be calculated at a transmural location that has expanded a percentage (e.g., such as 10%) radially from the endocardial contour. Since the strain curve is drawn over a time period including one or more diastolic periods and one or more systolic periods, the curve can provide a visualization of the distribution of myocardial strain during these cardiac periods.

[0031] The MRI analyzer can be configured to link (e.g., align) the time frame of the graph to the time frame of the selected MR slice image, so that one or more points on the graph can be linked to the corresponding image of the selected MR slice image, for example, based on the alignment of the points and the images on the time axis. In this way, in response to a user selecting a point on the graph (e.g., the point can indicate an abnormality), the MRI analyzer can automatically adjust (e.g., advance or rewind) the playback of the selected MR slice image to show the image corresponding to the selected point on the graph. Thereby, the user can focus on the strain value associated with the selected point while also having the myocardial image corresponding to the selected point displayed on one side for further study.

[0032] As described herein, the graphics in the background information of the selected MR slice image can show the characteristics of the myocardium (e.g., strain) during one or more cardiac cycles. The MRI analyzer can be configured to determine and / or indicate the corresponding boundaries of the cardiac cycle using one or more of the following techniques. The MRI analyzer can allow a user to manually mark frames (e.g., images) indicating the beginning and / or end of the cardiac cycle. For example, the MRI analyzer can allow a user to mark the end diastolic (ED) and / or end systolic (ES) frames indicating where the cardiac cycle begins and ends. The MRI analyzer can be configured to learn a model (e.g., a neural network-based model) for automatically detecting ED and / or ES frames, so that the MRI analyzer can indicate the beginning and end of the cardiac cycle in the second area 204 of the display device (e.g., on one or more graphics, such as on a strain curve displayed in the second area). The MRI analyzer can be configured to determine the ED and / or ES frames based on the recorded ECG signal. The marked ED and ES frames can be indicated using predefined flags. If an automatic detection technique is used (e.g., based on a neural network model or ECG signals), and there is an error calculation during the automatic detection, the MRI analyzer can allow the user to manually correct the error calculation (e.g., to manually mark the ED and / or ES frames). Edit the graphics corresponding to the corrected ED frames and / or the corrected ES frames (e.g., in Figure 2 A point on the radial or circumferential strain curve shown in the figure can automatically trigger the MRI analyzer to correct the tracking of strain values ​​in subsequent frames. For example, the strain analysis described herein can be performed from end diastole to end systole. As the frame marking the end diastole or end systole in a cardiac cycle is corrected, the MRI analyzer can adjust the subsequent strain analysis based on the corrected ED or ES frame. As another example, when performing myocardial segmentation on a frame-by-frame basis, the MRI analyzer can also adjust the segmentation based on the corrected ED or ES frame. As a result of the automatic correction, the errors and / or efforts associated with analyzing myocardial strain or segmenting the myocardium can be reduced.

[0033] The human heart (e.g., the left ventricle) is a 3D structure. Although the MR slice images described herein can present a 2D view of the heart slice by slice image along the scan axis, it can also be beneficial to provide a 3D representation of the heart along the time axis (e.g., within a time period associated with the MR slice images) based on the information captured in the MR slice images. The MRI analyzer can determine such global information of the heart (e.g., 3D plus time or 3D+T information) and will display the information in the third area 208 of the display device.

[0034] like Figure 2As shown in the example in , the global information may indicate deformation and / or motion of the heart (e.g., myocardium) across multiple MR slice images that are listed in the first region 202, and the MRI analyzer may be configured to display the global information in a manner that exhibits the deformation and / or motion. For example, in a portion of the global information display region (e.g., the third region 208), the MRI analyzer may present a 3D+T view (e.g., 3D point cloud plus time, 3D grid plus time, 3D sparse sample point representation plus time, etc.), which may include multiple representations of the segmented myocardium over time (e.g., indicated by dashed lines). Each representation of the segmented myocardium may correspond to an MR slice image listed in the first region 202, and the dashed lines in each representation may mark the boundaries of the myocardium as depicted by the MR slice image. The MR slice image selected in the first region 202 and displayed in the second region 204 may be highlighted in the 3D+T view to indicate the position of the selected MR slice image relative to the other slice images. And because the 3D+T view includes multiple slice images of the myocardium, deformation and / or motion of the myocardium shown by a specific slice image (eg, a selected MR slice image) can be examined compared to other slice images included in the view.

[0035] The MRI analyzer can render the 3D+T view in various ways to highlight different parts and / or characteristics of the myocardium. For example, the MRI analyzer can display the endocardium and epicardium in different colors or patterns to distinguish the two parts. When a 2D+T movie is played in the second area 204 (e.g., for a selected MR slice image), the MRI analyzer can adjust the 3D+T view according to the time lapse in the 2D+T movie to display the current state of the myocardium corresponding to the frame played in the 2D+T movie (e.g., the current boundary point group). This animated 3D+T representation of the myocardium can supplement the slice image view shown in area 204 (e.g., the view corresponds only to the current slice image of the myocardium) and allow the user to monitor in real time how the myocardium (e.g., multiple slice images of the myocardium) deforms. The user is able to pause and / or restart the animated 3D+T display of the myocardium, for example, via a button or another suitable input mechanism provided by the MRI analyzer.

[0036] A user of the MRI analyzer can browse different slice images of the myocardium via a 3D+T view, which is displayed in region 208. For example, the user can select a point on the 3D point cloud or mesh, and the MRI analyzer can adjust the display in the first region 202 and / or the second region 204 to display information about the MR slice image (e.g., showing a strain curve) that corresponds to the point selected by the user on the 3D+T view.

[0037] The MRI analyzer may also be configured to determine parameters indicative of global properties of the heart (e.g., myocardium) and display these parameters in a portion of the third region 208 to visually indicate the properties of the heart. For example, the MRI analyzer may render one or more graphs 210 (e.g., bull's eye graphs) in the third region 208 that display strain values ​​associated with different segments of the myocardium (e.g., left ventricle). Figure 2 In the example shown, the myocardium is divided into 16 segments (e.g., along horizontal and vertical directions) and projected onto a 2D plane, which produces the representation shown in Figure 210. Minimum, maximum, or average strain values ​​can then be calculated for each of the 16 segments over time (e.g., over a period of time associated with an MR slice image or movie) and displayed in corresponding areas of Figure 210, indicating the cardiac condition associated with each segment of the myocardium (e.g., deformation, motion, etc.). A value scale (e.g., with different color coding schemes or patterns) can also be provided, and Figure 210 can be color-coded or patterned according to the value scale to indicate where each specific value falls within the value range. Either or both of radial and circumferential strain can be calculated and plotted. Other myocardial function metrics such as strain rate can also be calculated and plotted. Circumferential strain can be measured at different transmural locations, including the endocardium, midmyocardium, epicardium, another predetermined transmural location described herein, or the circumferential strain can be measured as the minimum, maximum, or average value of all or a subset of these transmural locations.

[0038] The map 210 may be rendered so that a user can select a segment on the map, and the corresponding myocardial region in the 3D+T view may be highlighted to give the user an overview of how that region is deforming, for example relative to other regions of the myocardium. Figure 3 is a simplified diagram illustrating how a portion of the myocardium may be highlighted in response to a user selecting a segment on graph 210, e.g., to indicate the transition of a key point on the myocardium from an ED period to an ES period (e.g., to indicate how much the key point has moved between periods).

[0039] Figure 4 An example user interface that can be rendered by an MRI analyzer described herein (e.g., MRI analyzer 106) is shown. The user interface can present basic patient information (e.g., height, weight, etc.) and / or a summary of cardiac parameters determined by the MRI analyzer. These parameters may be related to cardiac function analysis, bull's eye analysis, and / or specific graph analysis. For example, the cardiac function analysis portion of the display can show parameter values ​​that are related to ED volume, ES volume, ejection fraction, myocardial mass, ED volume index, ES volume index, stroke volume index, myocardial volume index, myocardial thickness, ventricular septum thickness, etc.

[0040] Figure 5 An example matrix view is shown that can be rendered by an MRI analyzer as described herein (e.g., MRI analyzer 106) based on information determined by the MRI analyzer from an MRI scan of a heart, which MRI scan can show the left ventricle (e.g., myocardium). The matrix view can be used to present information associated with multiple MR slice images obtained from the MRI scan. Each row of the matrix can represent an MR slice image (e.g., indexed by a row number), and each column of the matrix can represent an image in the MR slice image (e.g., indexed by a column number). Thus, a user of the MRI analyzer can move a cursor along a row across columns and be presented with an animated display of a beating heart (e.g., as shown in FIG. 1 ). Figure 2 204 of the MRI analyzer). Each cell of the matrix may include a visual representation of the state of the myocardium at a location and time (e.g., an analysis associated with the myocardium), the location and time being indicated by a corresponding row (e.g., an MR slice image) and column (e.g., an image in the MR slice image), respectively. For example, each cell of the matrix may include a corresponding icon representing the state of a segment of the human heart (e.g., left ventricular endocardium, epicardium, papillary muscle, right ventricle, etc.) as indicated by the analysis determined by the MRI analyzer. A user may select one or more cells from the matrix, and in response, the MRI analyzer may display an MRI image (e.g., a frame) corresponding to the selected cell (e.g., at the top of the matrix view) for further analysis by the user.

[0041] An MRI analyzer as described herein (e.g., MRI analyzer 106) may also be configured to generate, transmit, and / or print a report of information determined and / or displayed by the MRI analyzer. Such information may include, for example, an image or MR slice image of the left ventricle or myocardium, a strain map, a bull's eye map (e.g., a portion of a bull's eye map corresponding to a corresponding segment of the myocardium), a matrix view, and / or underlying data for rendering an image, slice image, chart, graph, or view. The report may be generated automatically or semi-automatically. In an example embodiment, the MRI analyzer may, for example, in response to a user selecting a menu item for report generation, provide a dialog box to the user to specify what information to include in the report. In an example embodiment, the MRI analyzer may display an icon as the user hovers the mouse over the data element to indicate that the user can add the data element to the report. For example, the MRI analyzer may display an icon in response to a user hovering the mouse over the data element. Figure 2Such an icon is displayed above the bull's eye chart 210 shown to indicate that the user can add the chart and / or the basic data for rendering the chart to the report. When the user clicks the icon, the MRI analyzer can copy the chart and / or the basic data to the clipboard. The user can then paste the copied content (e.g., using ctrl+v on the computer keyboard) into the report that the user is creating. In an example embodiment, the MRI analyzer can be configured to recognize user voice (e.g., verbal instructions) about report generation and information to be included in the report, convert the voice into text, and display the text in a conversation initiated by the user. The user can then confirm the conversion and start report generation, transmission and / or printing.

[0042] Figure 6 is an illustration of an example MRI analyzer 600 as described herein (e.g., Figure 1 106). As shown, the MRI analyzer 600 may include a processor 602, which may be a central processing unit (CPU), a graphics processing unit (GPU), a microcontroller, a reduced instruction set computer (RISC) processor, an application-specific integrated circuit (ASIC), an application-specific instruction set processor (ASIP), a physical processing unit (PPU), a digital signal processor (DSP), a field programmable gate array (FPGA), or any other circuit or processor capable of performing the functions described herein. The MRI analyzer 600 may also include a communication circuit 604, a memory 606, a mass storage device 608, an input device 610, and / or a communication link 612 (e.g., a communication bus), Figure 6One or more components shown can exchange information through the communication link. The communication circuit 604 can be configured to send and receive information using one or more communication protocols (e.g., TCP / IP) and one or more communication networks, including local area networks (LANs), wide area networks (WANs), the Internet, wireless data networks (e.g., Wi-Fi, 3G, 4G / LTE, or 5G networks). The memory 606 may include a storage medium configured to store machine-readable instructions, which, when executed, causes the processor 602 to perform one or more functions described herein. Examples of machine-readable media may include volatile or non-volatile memory, including but not limited to semiconductor memory (e.g., electrically programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM)), flash memory, etc.). The mass storage device 608 may include one or more disks, such as one or more built-in hard disks, one or more removable disks, one or more magneto-optical disks, one or more CD-ROM or DVD-ROM disks, etc., on which instructions and / or data may be stored to facilitate the operation of the processor 602. Input device 610 may include a keyboard, a mouse, a voice control input device, a touch-sensitive input device (e.g., a touch screen), etc., for receiving user input to neural network system 600.

[0043] Figure 7 is an example of a method that can be used by an MRI analyzer described herein (e.g., Figure 1 The MRI analyzer 106 and / or Figure 6Flowchart of an example process 700 performed by an MRI analyzer 600 in FIG. 700. Process 700 may be initiated by an MRI analyzer at 702, for example, when the MRI analyzer is invoked by a user. At 704, the MRI analyzer may retrieve a plurality of MR slice images that may be generated by an MRI scan (e.g., a cardiac MR movie). The MR slice images may correspond to respective scan positions along a scan axis, and each MR slice image may include a visual representation of the myocardium over a period of time (e.g., one or more cardiac cycles). At 706, the MRI analyzer may present the MR slice images, for example, in a first area of ​​a display device. The presentation may be provided in a manner that allows a user of the MRI analyzer to browse the MR slice images along the scan axis. At 708, the MRI analyzer may determine background information associated with a selected slice image of the plurality of MR slice images (e.g., if no user selection is received, the first MR slice image in the series) and display the background information, for example, in a second area of ​​the display device. The background information may include images of the myocardium associated with the selected MR slice images and strain of the myocardium indicated by the images. The display of background information may include playback of a movie associated with the selected MR slice image and a graph (eg, a strain curve) indicating one or more cardiac parameters determined based on the selected MR slice image.

[0044] At 710, the MRI analyzer may determine global information associated with the myocardium across the plurality of MR slice images and display the information, for example, in a third region of the display device. The global information may include strain and / or deformation parameters of the myocardium determined by the MRI analyzer based on the plurality of MR slice images. The display of the global information may include a 3D view (e.g., a 3D mesh or point cloud) of the myocardium segmented based on the plurality of MR slice images. The display may also include one or more graphs (e.g., bull's eye graphs) showing global strain or deformation parameters determined by the MRI analyzer for different segments of the myocardium.

[0045] At 712, the MRI analyzer may determine whether a user input is received indicating that the user has selected a different MR slice image among the plurality of MR slice images. If it is determined that the user has not changed the previously selected slice image, the MRI analyzer may continue to display the background and global information based on the previously selected MR slice image. If it is determined that the user has selected a different MR slice image, the MRI analyzer may update the background information and its display based on the newly selected MR slice image at 714. The MRI analyzer may also update the global information and its display based on the newly selected MR slice image at 716.

[0046] At 718, the MRI analyzer may determine whether a user input indicating that the user desires to exit process 700 is received. If it is determined that no user input indicating a desired exit is received, the MRI analyzer may continue to display background and global information based on the currently selected MR slice image. If it is determined that the user desires to exit process 700, the MRI analyzer may end process 700 at 720.

[0047] For simplicity of explanation, the operation of the MRI analyzer may have been depicted and described in a particular order. However, it should be understood that these operations may occur in various orders, simultaneously and / or with other operations not presented or described herein. In addition, it should be noted that all operations that the MRI analyzer can perform are not depicted and described herein. It should also be noted that not all exemplified operations need to be performed by the MRI analyzer.

[0048] Although the present disclosure has been described according to certain embodiments and generally associated methods, the changes and transformations of the embodiments and methods will be apparent to those skilled in the art. Therefore, the above description of exemplary embodiments does not limit the present disclosure. Other changes, substitutions and variations are also possible without departing from the spirit and scope of the present disclosure. In addition, unless otherwise specifically stated, discussions using terms such as "analyze," "determine," "enable," "identify," "modify," etc. refer to the actions and processes of a computer system or similar electronic computing device, which manipulate and transform data represented as physical (e.g., electronic) quantities within registers and memories of a computer system into other data represented as physical quantities within a computer system memory or other such information storage, transmission or display device.

[0049] It should be understood that the above description is intended to be illustrative, rather than restrictive. After reading and understanding the above description, many other embodiments will be apparent to those skilled in the art. Therefore, the scope of the present disclosure should be determined with reference to the appended claims and the full scope of equivalents to which such claims are assigned.

Claims

1. A system for analyzing cardiac characteristics, comprising: One or more processors configured to: receiving a plurality of magnetic resonance (MR) slice images derived via a magnetic resonance imaging (MRI) scan, wherein each of the MR slice images comprises a visual representation of a myocardium over a period of time; presenting the plurality of MR slice images in a first area of ​​a display device, wherein the presenting allows a user of the system to browse through the plurality of MR slice images; In response to the user selecting an MR slice image among the plurality of MR slice images in the first area of ​​the display device, determining background information and global information based on the plurality of MR slice images, the background information being associated with the selected MR slice image, and the global information being associated with the myocardium, wherein the background information includes an image of the myocardium associated with the selected MR slice image and a strain of the myocardium indicated by the image of the myocardium associated with the selected MR slice image, and wherein the global information indicates a deformation of the myocardium across the plurality of MR slice images; and displaying the background information in a second area of ​​the display device and displaying the global information in a third area of ​​the display device, wherein the display of the background information in the second area includes an animated presentation of the image of the myocardium associated with the selected MR slice image and a strain curve associated with the myocardium, and wherein the display of the global information in the third area includes a three-dimensional (3D) view showing deformation of the myocardium across the plurality of MR slice images; The display of the global information also includes a graph displaying corresponding strain values ​​associated with multiple segments of the myocardium, wherein, in response to the user selecting an area of ​​the graph corresponding to a segment of the myocardium, the one or more processors are further configured to highlight the segment of the myocardium in the 3D view.

2. The system according to claim 1, wherein: The strain curve is rendered along a timeline, and the one or more processors are further configured to adjust the animated presentation of the image of the myocardium in response to the user selecting a point on the strain curve of the myocardium to display an image of the myocardium corresponding to the temporal position of the selected point along the timeline.

3. The system according to claim 1, wherein: The animated presentation of the image of the myocardium indicates an inner boundary and an outer boundary of the myocardium, and the one or more processors are further configured to receive user input, wherein the user input marks the inner boundary and the outer boundary of the myocardium, and the one or more processors are further configured to indicate the inner boundary and the outer boundary of the myocardium in the animated presentation based on the user input.

4. The system according to claim 1, wherein: The one or more processors are further configured to calculate each of the respective strain values ​​as a maximum, minimum, or average strain of the corresponding segment of the myocardium during the time period.

5. The system according to claim 1, wherein: In response to the user selecting an area of ​​the 3D view corresponding to one of the multiple MR slice images, the one or more processors are also configured to determine background information associated with the one of the multiple MR slice images and display the information in the second area of ​​the display device.

6. The system according to claim 1, wherein: The time period corresponds to a cardiac cycle, and the strain curve indicates the strain of the myocardium during the cardiac cycle, and the one or more processors are further configured to receive a user input indicating a start or end point of the cardiac cycle.

7. The system according to claim 1, wherein: The one or more processors are also configured to display a matrix comprising a plurality of cells, wherein each of the cells is associated with a row and a column, the row representing a corresponding MR slice image among the plurality of MR slice images, the column representing a time point during the time period associated with the corresponding MR slice image, and each of the cells indicates a corresponding state of the myocardium indicated by the corresponding MR slice image at the time point.

8. The system according to claim 1, wherein: The one or more processors are also configured to receive a second set of multiple MR slice images derived via the MRI scan, indicate on the display device that the second set of multiple MR slice images are available, and in response to user input indicating a selection of the second set of multiple MR slice images, present the second set of multiple MR slice images in the first area of ​​the display device.

9. The system according to claim 1, wherein: The one or more processors are also configured to generate a report in response to receiving user input, the report including at least a portion of the context information or a portion of the global information, the user input indicating that the at least a portion of the context information or the at least a portion of the global information is to be included in the report.

10. A method for analyzing cardiac characteristics, the method comprising: receiving a plurality of magnetic resonance (MR) slice images derived from a magnetic resonance imaging (MRI) scan, wherein each of the MR slice images includes a visual representation of a myocardium over a period of time; presenting the plurality of MR slice images in a first area of ​​a display device, wherein the presenting allows a user to browse through the plurality of MR slice images; In response to the user selecting an MR slice image among the plurality of MR slice images in the first area of ​​the display device, determining background information and global information based on the plurality of MR slice images, the background information being associated with the selected MR slice image, and the global information being associated with the myocardium, wherein the background information includes an image of the myocardium associated with the selected MR slice image and a strain of the myocardium indicated by the image of the myocardium associated with the selected MR slice image, and wherein the global information indicates a deformation of the myocardium across the plurality of MR slice images; and displaying the background information in a second area of ​​the display device and displaying the global information in a third area of ​​the display device, wherein the display of the background information in the second area includes an animated presentation of the image of the myocardium associated with the selected MR slice image and a strain curve associated with the myocardium, and wherein the display of the global information in the third area includes a three-dimensional (3D) view showing deformation of the myocardium across the plurality of MR slice images, the display of the global information also including a graph showing corresponding strain values ​​associated with a plurality of segments of the myocardium; The method further comprises: In response to the user selecting a region of the map corresponding to a segment of the myocardium, the segment of the myocardium is highlighted in a 3D view.

Images