Ultrasonic data processing

Abstract

A method and device for maintaining and updating a shared register that stores one or more parameters related to the characteristics of an anatomical structure, accessible by a plurality of different software applications adapted to derive quantitative data from an ultrasonic image using the one or more parameters, such that updates to the parameters can be shared by all applications, avoiding the need to recompute the same parameters at multiple different times and enabling the user to avoid the need to re-enter the updated parameters into each individual application.

Description

Technical Field

[0001] This method relates to the field of ultrasonic data processing.

Background Art

[0002] It is known to apply an image processing software module dedicated to ultrasonic imaging data configured to obtain a specific output based on image data. For example, there are modules for obtaining specific anatomical measurements, such as dimensions related to the heart, or standard dimensions related to a fetus, or dynamic measurements related to an organ such as the heart, such as cardiac output, from a set of ultrasonic image data. There are applications that process the data to synthesize new image views or modulate the image to better represent specific features, such as segmentation or artificial contrast enhancement.

[0003] U.S. Patent Application Publication No. 2007 / 214235 (A1) discloses a method and system for sharing intermediate medical image processing results among several different applications.

Summary of the Invention

Problems to be Solved by the Invention

[0004] In real-world clinical use, multiple such software applications are typically applied to a given data set to obtain all the necessary information. For example, for a single organ such as the heart, there can be multiple different applications that quantify different information related to the heart or generate specific images related to the heart.

[0005] Since multiple applications can utilize the same one or more parameters associated with an anatomical structure of interest, the inventors recognize that there is often a duplication of computational steps among multiple applications within this context. Therefore, in order to avoid duplication of processing, the inventors recognized that there is an opportunity to improve efficiency by providing a data sharing solution that can collectively pool the calculation and subsequent update of common parameters utilized by multiple software modules. In some cases, there is also an opportunity to improve the reliability of the output of a software module since an algorithm or processing step may fail or produce poor results if it does not have access to specific anatomical information.

Means for Solving the Problem

[0006] This invention is defined by the claims.

[0007] According to an example of one aspect of the present invention, a computer-implemented method comprising: receiving ultrasonic imaging data of a patient's anatomical structure obtained from an ultrasonic acquisition system; communicating with an anatomical feature register that stores one or more parameters related to the anatomical features of the anatomical structure; and wherein a plurality of application modules each process the acquired ultrasonic imaging data based on at least one current value of one or more parameters related to the anatomical features currently stored in the anatomical feature register to generate output quantification or segmentation data; receiving input data from a user interface is provided.

[0008] The method further comprises Updating at least one value of one or more parameters stored in the anatomical feature register based on input data received from the user interface and / or output quantification or segmentation data generated by any of the plurality of application modules having.

[0009] Accordingly, the present invention proposes a system (and related methods and computer programs) for enabling a plurality of application modules to process ultrasonic image data of a patient's structure in an efficient manner, such that any updates or corrections made to parameters related to features in the context of a given application module can be readily used by other application modules. This avoids the need for parameters to be recalculated multiple times and the need for the user to re-enter updated parameters multiple times into each individual application. In the latter case, the user can perform one data input operation to update or set the parameter value, which automatically updates or sets the parameter for all application modules. Further, in some cases, a particular algorithm or processing step may fail or produce poor results if it does not have access to specific anatomical information. For example, a heart segmentation model such as the Philips HeartModel may require the heart size as input in order to correctly segment a very small or large heart. Thus, according to some embodiments, preventing algorithm failure or poor algorithm results is a further advantage.

[0010] The term "application module" means, for example, a software module or a hardware module encoded in software, and in any case, is operable to execute the processing of ultrasonic image data to generate output quantification or segmentation data. It can include or take the form of one or more algorithms for executing the method steps attributed to it. It can include or take the form of a program or routine for executing one or more method steps attributed to it.

[0011] Output quantification data can include, as non-limiting examples, the quantification of one or more anatomical measurements such as dimensions or size parameters of anatomical structures. These can include, for example, length parameters, area parameters, or volume parameters. Output quantification data can include dynamic measurements, such as hemodynamic measurements in the case of cardiac images such as cardiac output.

[0012] In some embodiments, the method further includes generating initialization data for at least one of one or more parameters of an anatomical feature and storing the initialization data as an initial value of at least one parameter in an anatomical feature register. In some embodiments, the initialization data is generated based on the received ultrasonic imaging data. In some embodiments, the initialization data can be generated based on retrieving initialization data from a data store. In some embodiments, the initialization data is generated based on applying at least one of a plurality of application modules to the received ultrasonic image data or based on applying at least one of a plurality of application modules to historical ultrasonic image data for a patient retrieved from a data store.

[0013] In some embodiments, the method further includes, for example, receiving, from an ultrasonic acquisition system, an inspection start indicator signal indicating the start of an ultrasonic inspection session. In some embodiments, the generation and storage of initialization data are performed in response to the receipt of the inspection start indicator signal. In this way, at the start of a patient's inspection, initial values of at least one parameter are obtained. These initial values may be updated as the inspection progresses.

[0014] In some embodiments, the step of generating initialization data for at least one of one or more parameters includes applying an artificial intelligence algorithm to the received ultrasonic imaging data. In some embodiments, the artificial intelligence algorithm is a convolutional neural network.

[0015] In some embodiments, for at least one subset of a plurality of application modules, the output quantification or segmentation data may include the segmentation of at least one anatomical feature or structure. This may be the formation of a segmentation mask or mesh for the feature or structure. This may be stored in a register as a series of coordinate points corresponding to the mesh or mask vertices.

[0016] In some embodiments, at least one subset of the application modules are each adapted to generate a segmentation based on an initial shape template, the initial shape template being scaled according to a scaling parameter, the scaling parameter being at least one of or calculated based on at least one of the one or more parameters stored in the anatomical feature register.

[0017] In some embodiments, the anatomical structure is a heart structure.

[0018] In some embodiments, one or more parameters include one or more of heart size, left ventricle size, left atrium size, right ventricle size, right atrium size at end diastole, ejection fraction, and / or left ventricle length.

[0019] In some embodiments, the received ultrasonic image data is real-time image data. In some embodiments, the received ultrasonic image data is an image data stream. In some embodiments, the plurality of application modules are each adapted to operate iteratively or continuously on the received image data stream.

[0020] In some embodiments, the received ultrasonic image data includes 2D ultrasonic image data of one or a series of time frames. In some embodiments, the received ultrasonic image data includes 3D ultrasonic image data of one or a series of time frames.

[0021] In some embodiments, the anatomical feature register includes an update counter entry associated with at least one of the one or more parameters, and the update counter entry is incremented simultaneously with any update of the parameter value in the anatomical feature register based on user input data. In some embodiments, any update of the parameter in the anatomical feature register is blocked in response to the current value of the update counter register exceeding a threshold. In some embodiments, this threshold is zero. In this way, once a parameter is modified or updated, other applications are blocked from further updating it. This avoids duplication of processing and also ensures consistency in the use of the same parameter.

[0022] In some embodiments, a reset indicator signal is generated at the end or start of any ultrasonic examination session, and the method includes the step of resetting the update counter entry to zero in response to the reset indicator signal.

[0023] The present invention can also be implemented in software. Accordingly, another aspect of the present invention is a computer program product comprising code means configured to perform, when executed by a processor, a method according to any of the embodiments or examples described herein, or according to any claim of the present application.

[0024] The present invention can also be implemented in hardware form. Accordingly, another aspect of the present invention is a processing unit, comprising: an input / output unit connected to an ultrasonic data acquisition device in use for receiving ultrasonic imaging data of a patient's anatomical structure; an anatomical feature register adapted to store one or more parameters related to anatomical features of the anatomical structure; a control module operably coupled to the anatomical feature register; a plurality of application modules operably coupled to the control module, each application module being adapted to process the ultrasonic imaging data received at the input / output unit based on at least one current value of one or more parameters stored in the anatomical feature register to generate output quantification or segmentation data; wherein the foregoing control module is configured to receive user input data from a user interface, and update at least one value of one or more parameters stored in the anatomical feature register based on the user input data provided by the user via the user interface and / or output quantification or segmentation data generated by any of the plurality of application modules. is adapted to

[0025] Any of the features or options described in connection with the method aspect of the present invention can be equally applied to the software and hardware aspects of the present invention.

[0026] In some embodiments, the processing unit further comprises a register initialization module adapted to generate initialization data for at least one of one or more parameters based on received ultrasonic imaging data, the initialization data comprising an initial value for at least one of one or more parameters.

[0027] In some embodiments, the control module is further adapted to trigger the initialization module to generate initialization data and store the data as an initial value for at least one of one or more parameters in an anatomical feature register.

[0028] In some embodiments, the anatomical structure is a heart structure. In some embodiments, one or more parameters include one or more of the size of the heart, the size of the left ventricle, the size of the left atrium, the size of the right ventricle, the size of the right atrium at end-diastole, the ejection fraction, and / or the length of the left ventricle.

[0029] Another aspect of the present invention is a system comprising a processing unit according to any of the embodiments described herein, such as those described above, and an ultrasonic data acquisition device operably coupled to an input / output section of the processing unit. In some embodiments, the system further comprises a user interface for acquiring user input.

[0030] These and other aspects of the invention will be apparent from and will be elucidated with reference to the embodiments described hereinafter.

[0031] To better understand the present invention and to more clearly show how it can be implemented, reference is now made, by way of example only, to the accompanying drawings.

Brief Description of the Drawings

[0032]

Figure 1

Figure 2

Figure 3

[0033] The present invention will be described with reference to the drawings.

[0034] It should be understood that the detailed description and specific examples show exemplary embodiments of the apparatus, system, and method, but are for illustrative purposes only and are not intended to limit the scope of the present invention. These and other features, aspects, and advantages of the apparatus, system, and method of the present invention will be better understood from the following description, the appended claims, and the accompanying drawings. It should be understood that the figures are merely schematic and not drawn to scale. Also, it should be understood that the same reference numbers are used throughout the drawings to indicate the same or similar parts.

[0035] The present invention provides a method and device for maintaining and updating a shared register that stores one or more parameters related to the characteristics of an anatomical structure, and is accessible by a plurality of different software applications adapted to derive quantification data from ultrasonic images using the one or more parameters. As a result, updates to the parameters can be shared by all applications, avoiding the need to recalculate the same parameters at multiple different times and the need for the user to re-enter the updated parameters into each individual application.

[0036] Accordingly, the overall objective of the embodiments of the present invention is to provide improved connectivity between different applications. This is aimed at ensuring that information can flow more easily from one application to the next when modifications are made by a specific user.

[0037] FIG. 1 outlines the steps of an exemplary method according to one or more embodiments in a block diagram. The steps are summarized before being further described in the form of exemplary embodiments.

[0038] The method includes a step (12) of receiving ultrasonic imaging data of a patient's anatomical structure obtained from an ultrasonic acquisition system. The method further includes a step 14 of communicating with an anatomical feature register that stores one or more parameters related to one or more anatomical features of the anatomical structure. The method further comprises a plurality of application modules 16 that process the acquired ultrasonic imaging data respectively based on at least one current value of one or more parameters related to the anatomical features currently stored in the anatomical feature register in order to generate output quantification or segmentation data 22.

[0039] The method may further include a step (18) of receiving input data from a user interface.

[0040] The method further includes a step (20) of dynamically updating at least one value of one or more parameters stored in the anatomical feature register. This may be based on the input data 18 received from the user interface. In addition or alternatively, it may be based on the output quantification or segmentation data 22 generated by any of the plurality of application modules.

[0041] As described above, the method may also be implemented in hardware form, for example, in the form of a processing unit configured to execute the method according to any example or embodiment described in this document, or according to any claim of this application.

[0042] To further aid understanding, FIG. 2 shows a schematic diagram of an exemplary processing unit 32 configured to execute a method according to one or more embodiments of the present invention, and also schematically shows the processing flow in more detail.

[0043] The processing unit 32 includes an input / output unit 34 connected for use with an ultrasonic data acquisition device 52 for receiving ultrasonic imaging data of a patient's anatomical structure.

[0044] The processing unit 32 further includes an anatomical feature register 38 adapted to store one or more parameters related to one or more anatomical features of the anatomical structure.

[0045] The processing unit 32 further includes a control module 36 operably coupled to the anatomical feature register 38. The control module 36 includes, for example, one or more processors.

[0046] The processing unit 32 further includes a plurality of application modules 42a, 42b, …, 42n operably coupled to the control module. Each application module is adapted to process the ultrasonic imaging data received at the input / output unit 34 based on at least one current value of one or more of the parameters stored in the anatomical feature register 38 to generate output quantification or segmentation data 22.

[0047] The control module 36 may be further adapted to receive user input data from a user interface 54.

[0048] The control module 36 is adapted to dynamically update at least one value of one or more parameters stored in the anatomical feature register 38. This can be based on user input data provided by the user via the user interface 54. In addition to, or instead of, this, it can be based on output quantification or segmentation data 22 generated by any of the plurality of application modules 42a, 42b, …, 42n.

[0049] In the schematic diagram of FIG. 2, the processing unit 32 is shown as a single component in which various components are arranged. However, this is not essential. The processing 32 may be a distributed processing unit in which various components are distributed in multiple locations. Further, although the various components are shown as separate hardware modules, this is also not essential. For example, the different application modules 42 may all be software modules encoded and executed by a single hardware processing module.

[0050] For the sake of explanation, each of the application modules 42 is shown communicatively coupled to a BUS 48 to facilitate communication between each of these and the input / output unit 34, the control module 36, and the anatomical feature register 38. The link to the input / output unit enables the application module in this example to directly access the ultrasonic image data coming in from the ultrasonic data acquisition device 52. The link to the control module 36 enables the control module 36 to receive the quantification data 22 generated from each of the application modules, which can in some cases be used to update parameter entries in the anatomical feature register 38. The link to the anatomical feature register 38 enables each of the application modules 42 to directly access the latest value of each parameter, and thus these can be used in the quantification performed by each module.

[0051] One aspect of the present invention is only the processing unit 32. Another aspect of the present invention is a system 30 including the processing unit 32 and the ultrasonic data acquisition device 52 and / or the user interface device 54.

[0052] Regarding the ultrasonic data acquisition device 52, this may be an ultrasonic scanner. The ultrasonic data acquisition device may include a transducer unit (for example, an ultrasonic probe or a patch). It can further include a local dedicated user interface including a display for displaying an ultrasonic image. The ultrasonic data acquisition device 52 can include a processing component for processing the acquired echo data to generate ultrasonic image data.

[0053] During operation, the processing and data flow can be executed as follows, for example.

[0054] An ultrasonic examination is started, and using the ultrasonic data acquisition device 52, ultrasonic image data begins to be acquired by the user.

[0055] This ultrasonic data is received at the input / output unit 34.

[0056] Various application modules 42 start processing the ultrasonic data to derive the quantification of anatomical structures. Some of the parameters stored in the anatomical feature register 38 are quantities calculated as outputs of one or more of the application modules. These parameters may be inputs used by other ones of the application modules. Therefore, the output quantification or segmentation data of one or more application modules can be used to update the values of one or more parameters in the anatomical feature register. These parameters can be used by other application modules to perform their own quantification.

[0057] Furthermore, some of the one or more parameters within the feature register 38 can be communicated to the user via the user interface 54 for feature verification or correction. For example, a graphical user interface can include a field that displays the current value for each of the parameters, and optionally, the source of the current value (e.g., one of the application modules, or an initial default value). Additionally, in some examples, segmentations generated by a particular application module for the purpose of quantifying the dimensions of an anatomical structure can be output to the user interface on a display. The user can utilize the user input elements of the user interface to enter corrections or amendments to the segmentation. This can then be used by the control module 36 to update the relevant dimensional parameters associated with the anatomical structure within the anatomical feature register 38.

[0058] In a preferred embodiment, it can further include a register initialization module (not shown) adapted to generate initialization data for at least one of the one or more parameters stored in the anatomical feature register 38 based on the received ultrasonic imaging data, the initialization data including an initial value for at least one of the one or more parameters. The control module 36 can be further adapted to trigger the initialization module to generate the initialization data and store the data as an initial value for at least one of the one or more parameters within the anatomical feature register 38.

[0059] For example, the initialization data may be generated at the start of an ultrasound examination. For example, the method can further include receiving, for example, an examination start indicator signal indicating the start of an ultrasound examination session from an ultrasound acquisition system, and the generation and storage of the initialization data are performed in response to the receipt of the examination start indicator signal.

[0060] Here, an exemplary implementation of a method according to a set of specific embodiments will be described as an illustration of the above concepts of the present invention. It will be understood that not all features of this specific set of embodiments are essential to the concepts of the present invention, and they are described to aid understanding and to provide examples for illustrating the concepts of the present invention.

[0061] This specific set of embodiments relates to an ultrasonic system comprising a number of application modules 42 for calculating anatomical and physiological quantities related to the heart.

[0062] Thus, in this set of embodiments, the anatomical structure is a heart structure. By way of example, one or more parameters related to anatomical features stored in a register may include one or more of heart size; left ventricle (LV) size; left atrium size; right ventricle (RV) size; right atrium size; LV length; RV length; local wall thickness; LV diameter. In some embodiments, one or more parameters may further include one or more segmentation masks (or representations thereof) for one or more structures such as the LV or RV. The segmentation mask can be stored as a contour consisting of a plurality of x / y points. These points can be processed and stored in a register as anatomical parameters (scalars) that can be placed, for example, in a vector having 20 pairs of x / y image coordinates describing the LV contour. For example, the above-mentioned "size" references to the heart or the LV or RV can be, for example, area parameters (e.g., across a 2D plane) or volume parameters (e.g., estimated from a 2D cross-section or derived from 3D data).

[0063] Furthermore, parameter values recorded for each parameter may be available at both end-systole and end-diastole. The parameters can further include dynamic parameters such as, for example, ejection fraction, cardiac output, or strain parameters.

[0064] A complete set of parameters can be stored as a vector known as the heart size or heart shape vector, where each element of the vector corresponds to one of the parameters.

[0065] The heart size or heart shape vector is stored in a register and can be used by all application modules. The heart size or heart shape vector can be updated throughout the examination.

[0066] For example, the initial values of the different parameters included in the heart size / shape vector can be set, for example, based on previous patient scan data or using a separate algorithm (to be described in more detail later).

[0067] Subsequently, more refined values for at least one subset of the parameters may be obtainable from quantifications performed by one or more of the application modules 42. For example, at least one of the application modules may be adapted to output a value of the heart size or left ventricular size, which can be used to update these parameter values. Other applications of the application can calculate other quantifications such as cardiac output using the heart size and / or shape vector. A particular size or dimension parameter can be used as a basis for calculating other size or dimension parameters.

[0068] Furthermore, based on the current values of the parameters in the register, the acquisition parameters of the ultrasonic data acquisition device can be determined and communicated to the device.

[0069] As an example, in one system, there are a plurality of application modules, each receiving a 3D ultrasound image as input and generating, as output, a segmentation map of the heart (in the form of a mesh). Each of these exemplary application modules begins a process of generating a segmentation map having an initial heart shape. This heart shape can be scaled by additional inputs such as heart size. This scaling then helps each of the application modules to better converge to segmentation or prevent failure. In addition to heart size, other scaling parameters can be used, such as any of the LV size or other parameters mentioned in this disclosure.

[0070] Thus, as a more general principle of application of any embodiment of the present invention, for at least one subset of a plurality of application modules, the output quantification or segmentation data can include segmentation of at least one anatomical feature or structure, and the application module is adapted to generate the segmentation based on an initial shape template, the initial shape template is scaled according to a scaling parameter, and the scaling parameter is at least one of or calculated based on at least one of a plurality of parameters stored in an anatomical feature register. The resulting segmentation mesh or mask can be used for many different purposes. It can be used, for example, to calculate one or more quantifications and thus generate quantification data. For example, one or more quantifications can include measurements such as ejection fraction, heart size, LV size, etc. It can also be used to derive a 2D planar image from a 3D input image. Thus, in some examples, the final output from the application module can be quantification information and the segmentation is derived as an intermediate step based on one or more of the parameters in the register as input.

[0071] Additionally or alternatively, in some examples, a plurality of application modules may include one or more modules configured to quantify strain information such as overall longitudinal strain. For example, at least one module may be configured to receive a 2D ultrasound image as an input and generate strain information as an output. Here, one or more parameters in the feature register may be used to generate an initial estimate of the quantified strain information, and then the quantified strain information is refined iteratively, for example. The output is a strain measurement value.

[0072] In some examples, one or more of the application modules may be adapted to use one or more of the parameters stored in the anatomical feature register for quality control checks. For example, based on a reference to one or more parameter values in the register, a quality control check can be applied to candidate values for a particular anatomical quantification, and if the candidate value passes the quality control check, the candidate value is output as output quantification data from the application module.

[0073] For example, the application module may be configured to calculate the heart size or LV size based on the input ultrasound image. The values of the parameters in the feature register may not be required for this purpose. For example, an initial estimate of the heart size may not be required. However, after the application module calculates a candidate value for the heart size, it can check whether it is within a predefined range of the existing value of the heart size in the feature register by comparing it with the existing value of the heart size in the feature register. If it is outside the predefined range, the quality control check fails and the candidate value can be improved or discarded, for example.

[0074] Additionally or alternatively, in some embodiments, two or more of the application modules may be configured to calculate the same one of the parameters stored in the feature register, and the method includes performing a comparison of a plurality of generated values of the parameters against each other to check for consistency. If the consistency meets a predetermined consistency threshold, e.g., if the values of the parameters are within a predetermined range of each other, the register can be updated based on the generated parameter values, e.g., by selecting one of the parameter values based on a predetermined criterion or by calculating an average value. If the consistency does not meet the predetermined consistency threshold, the method can reject the generated parameter values, e.g., by waiting for the values to be recalculated by two or more application modules.

[0075] As described above, in some embodiments, an initial value of at least one parameter can be derived, for example, using an initialization module. For example, a first estimated value of the heart size, or the left ventricular size, can be derived by applying a dedicated initialization algorithm as soon as an image covering the first apical chamber is acquired. As an example, a deep learning network can be applied to the acquired image data to obtain a first value of the heart size or the left ventricular size. As a more general principle, it is proposed that initialization data for at least one of one or more parameters can be derived by applying an artificial intelligence algorithm to the received ultrasonic image data. The artificial intelligence algorithm may advantageously be a convolutional neural network in an advantageous example.

[0076] Also, as described above, additionally or alternatively, the initialization data for at least one of the one or more parameters can be derived based on accessing data records within a data store associated with the patient being examined. In some embodiments, for example, historical image data related to the patient can be accessed, and a quantification algorithm can be applied to this historical image data to derive an initial value for at least one of the one or more parameters. As a simpler example, the data store can record the most recent value of a previously calculated parameter, which can be used as the initialization data for the parameter. For example, in the case of a longitudinal scan, the previous heart size can be determined from records within a PACS system and used as an initial estimate.

[0077] The initial values of the one or more parameters can be utilized by one or more of the plurality of application modules for initial quantification.

[0078] As already discussed, it is proposed that a functionality be provided by means of which a user can update or modify one or more of the parameters within the anatomical feature register. For example, each parameter may be assigned an initial value (in accordance with the initialization data) at the start of the examination, in which case this may be a default value, or a value obtained from data records related to the patient, or a value calculated by a dedicated algorithm or application module.

[0079] The user interface device 54 can display a graphical user interface window on its display unit, which can include fields indicating the current values of a plurality of parameters related to the anatomical features of the anatomical structure. For example, there may be a field indicating the current estimated value of any of the heart size, LV size, or other parameters mentioned above. Further, the graphical user interface can further indicate, for each parameter, the source of the parameter value, such as initialization data (e.g., a deep learning neural network), historical patient data, a specified one of the application modules, or user input data. The user interface can be configured to enable the user to input modified values for at least one subset of these values. In other words, the user can override the information. In particular, at the start of the examination, before the application module 42 generates the quantification data, this can be valuable. The various parameters are stored in registers in the background.

[0080] In the prior art ultrasonic systems, all application modules for performing quantification operate independently of each other. This means that when two or more application modules utilize the same input parameter related to the heart size, this parameter has to be updated once or multiple times for each application. Embodiments of the present invention provide, among other advantages, improved sharing of parameters.

[0081] These initial values can remain at a predetermined position in the register for use by each of the associated application modules 42 until they are updated and as long as they are not updated.

[0082] In addition or alternatively, the user can input an update or correction of one or more of the parameters, such as a manual correction for segmentation, via the user interface 54.

[0083] According to some embodiments, it is proposed that when a user updates a given parameter, the remaining part of the given examination should be locked for editing or updating. For example, this can be implemented by an update counter entry included in the anatomical feature register 38 associated with at least one of the one or more parameters. Simultaneously with any update of the parameter value in the anatomical feature register based on user input data, the update counter entry is incremented, and it is proposed that any update of the parameter in the anatomical feature register is blocked in response to the current value of the update counter register exceeding a threshold. This threshold can be set to zero, so that once the user updates or modifies a parameter in a given examination, it remains locked for the remainder of the examination.

[0084] Reset between examination sessions can be implemented by a reset indicator signal generated at the end or start of any ultrasound examination session, and the method includes resetting the update counter entry to 0 in response to the reset indicator signal.

[0085] As described above, in some embodiments, initialization data is generated to provide initial values for one or more of the parameters stored in the anatomical feature register. In some embodiments, it is proposed to use an artificial intelligence algorithm applicable to the input ultrasound image data to calculate the initialization data.

[0086] The inventors have developed a new convolutional neural network for this purpose.

[0087] The generated model is a deep learning model for estimating heart size. It can be designed as a convolutional neural network (CNN) that takes as input a 2D, 3D, 2D+t, or 3D+t ultrasound image dataset and generates as output an estimated heart size value. The convolutional neural network can be configured in an end-to-end manner such that the heart size parameters are directly regressed as continuous parameters.

[0088] The convolutional neural network (CNN) according to this description was implemented, trained, and tested by the inventors. The CNN was trained to predict end-diastolic (ED) and end-systolic (ES) left ventricular (LV) volumes based on an input 2D+t ultrasound image set. The 2D+t image dataset includes a series of 2D image frames each corresponding to a different time.

[0089] The CNN uses 3D convolution and consists of seven convolutional layers, a global average pooling layer, and an output layer with two output parts. The solution stage has three steps. Downsampling between steps is performed using two strides within the convolution. The model was trained using a training dataset of 25,000 ultrasound DICOM (2D+t) image datasets.

[0090] The performance of the resulting CNN model is shown in Figure 3. This shows the correlation between the predicted values of heart size (y-axis) and the ground truth values (x-axis). Quantitatively, the CNN achieves an average absolute error of 18.60 ml for the ED volume and 11.44 ml for the ES volume over a wide range of volumes (see Figure 2). The Pearson correlation coefficient is 0.864 for the ED volume and 0.899 for the ES volume. As a rough estimate of heart size, this performance is appropriate.

[0091] If the present invention is provided in a hardware implementation, there are different options regarding how this hardware can be configured. For example, as shown in FIG. 2, physically separate processing units can be provided. In other embodiments, some or all of the functions described above can be distributed among multiple processing devices in a single processing unit. In some embodiments, the function of the processing unit 32 can be integrated into the processing unit of the ultrasonic data acquisition device 52. In some embodiments, the processing unit may be a cloud-based processing unit, and communication with the ultrasonic device 52 and the user interface 54 is facilitated via an Internet link.

[0092] As described above, the present invention can be implemented in software form. Accordingly, another aspect of the present invention is a computer program product comprising code means configured to cause a processor to execute a method according to an exemplary or embodiment of the present invention described in this document or according to the claims of this application when executed on the processor.

[0093] Some of the embodiments of the present invention described above use a processing unit. A processing unit generally may comprise a single processor or multiple processors. It may be arranged within a single housing, structure, or unit, or may be distributed among multiple different devices, structures, or units. Thus, a reference to a processing unit adapted or configured to perform a particular step or task may correspond to that step or task being performed by any one or more of a plurality of processing components, alone or in combination. Those skilled in the art will understand how such distributed processing devices can be implemented. The processing unit may include a communication module or input / output section for receiving data and outputting the data to further components.

[0094] One or more processors of a processing unit can be implemented in a number of ways using software and / or hardware to perform the various functions required. A processor typically uses one or more microprocessors that can be programmed using software (e.g., microcode) to perform the required functions. A processor can be implemented as a combination of dedicated hardware for performing some functions and one or more programmed microprocessors and associated circuitry for performing other functions.

[0095] Examples of circuits that can be used in various embodiments of the present disclosure include, but are not limited to, conventional microprocessors, application specific integrated circuits (ASICs), and field programmable gate arrays (FPGAs).

[0096] In various implementations, a processor can be associated with one or more storage media such as volatile and non-volatile computer memories such as RAM, PROM, EPROM, and EEPROM. The storage media can be encoded with one or more programs that perform the required functions when executed on one or more processors and / or controllers. The various storage media can be fixed within the processor or controller or can be portable such that one or more programs stored thereon can be loaded into the processor.

[0097] Variations to the disclosed embodiments can be understood and effected by those skilled in the art in practicing the claimed invention, from a study of the drawings, the disclosure, and the appended claims. In the claims, the word "comprising" does not exclude other elements or steps, and the indefinite article "a" or "an" does not exclude a plurality.

[0098] A single processor or other unit can fulfill the functions of some of the items recited in the claims.

[0099] The mere fact that certain means are recited in mutually different dependent claims does not indicate that a combination of these means cannot be used advantageously.

[0100] The computer program can be stored / distributed on a suitable medium, such as an optical storage medium or a solid-state medium, supplied together with or as part of other hardware, but may also be distributed in other forms, such as via the Internet or other wired or wireless electrical communication systems.

[0101] It should be noted that when the term "adapted to" is used in the claims or the description, the term "adapted to" is intended to be equivalent to the term "configured to".

[0102] Any reference signs in the claims shall not be construed as limiting the scope.

Claims

1. A computer-implemented method, comprising: receiving ultrasonic imaging data of a patient's anatomical structure obtained from an ultrasonic acquisition system; communicating with an anatomical feature register that stores one or more parameters related to the anatomical features of the anatomical structure; wherein a plurality of application modules each process the acquired ultrasonic imaging data based on at least one current value of one or more parameters related to the anatomical features currently stored in the anatomical feature register to generate output quantification or segmentation data; receiving input data from a user interface; and further comprising: updating at least one value of one or more parameters stored in the anatomical feature register based on the input data received from the user interface and / or the output quantification or segmentation data generated by any of the plurality of application modules; a method.

2. generating initialization data for at least one of the one or more parameters of the anatomical features based on the received ultrasonic imaging data; storing the initialization data in the anatomical feature register as an initial value for at least one of the one or more parameters; The method according to claim 1, further comprising.

3. The method further comprises receiving, for example, from the ultrasonic acquisition system, an inspection start indicator signal indicating the start of an ultrasonic inspection session, The method according to claim 2, wherein the steps of generating and storing the initialization data are performed in response to receiving the inspection start indicator signal.

4. The method according to claim 2 or 3, wherein the step of generating initialization data for at least one of the one or more parameters comprises applying an artificial intelligence algorithm to the received ultrasonic imaging data.

5. The method according to claim 4, wherein the artificial intelligence algorithm is a convolutional neural network.

6. The anatomical structure is a cardiac structure, and the one or more parameters include one or more of the size of the heart, the size of the left ventricle, the size of the left atrium, the size of the right ventricle, the size of the right atrium at end-diastole, the ejection fraction, and / or the length of the left ventricle, for the system according to any one of claims 1 to 5.

7. The received ultrasonic image data has 2D ultrasonic imaging data for one or a series of time frames, or 3D ultrasonic imaging data for one or a series of time frames, for the apparatus according to any one of claims 1 to 6.

8. The anatomical feature register includes an update counter entry associated with at least one of the one or more parameters, and simultaneously with any update of the parameter value within the anatomical feature register based on the user input data, the update counter entry is incremented, and any update of the parameter within the anatomical feature register is blocked in response to the current value of the update counter register exceeding a threshold, for the method according to any one of claims 1 to 7.

9. The threshold is zero, for the method according to claim 8.

10. A reset indicator signal is generated at the end or start of any ultrasonic examination session, and the method has a step of resetting the update counter entry to zero in response to the reset indicator signal, for the method according to claim 8 or 9.

11. At least one subset of the application modules is each adapted to generate a segmentation based on an initial shape template, the initial shape template is scaled according to a scaling parameter, and the scaling parameter is at least one of the one or more parameters stored in the anatomical feature register or is calculated based on at least one of the one or more parameters stored in the anatomical feature register, for the method according to any one of claims 1 to 10.

12. The received ultrasonic image data is an image data stream, and the plurality of application modules are each adapted to operate repeatedly or continuously on the received image data stream, for the method according to any one of claims 1 to 11.

13. A computer program product having code means configured to execute the method according to any one of claims 1 to 12 when executed by a processor.

14. A processing unit, an input / output unit connected to an ultrasonic data acquisition device in use for receiving ultrasonic imaging data of a patient's anatomical structure, an anatomical feature register adapted to store one or more parameters related to anatomical features of the anatomical structure, a control module operably coupled to the anatomical feature register, a plurality of application modules operably coupled to the control module, each application module being adapted to process the ultrasonic imaging data received at the input / output unit based on at least one current value of one or more parameters stored in the anatomical feature register to generate output quantification or segmentation data, comprising wherein the control module receives user input data from a user interface, and updates at least one value of one or more parameters stored in the anatomical feature register based on the user input data provided by the user via the user interface and / or the output quantification or segmentation data generated by any of the plurality of application modules. A processing unit adapted to

15. A register initialization module adapted to generate initialization data for at least one of the one or more parameters based on the received ultrasonic imaging data, the initialization data comprising initial values for at least one of the one or more parameters. further comprising wherein the control module is further adapted to trigger the initialization module to generate the initialization data and store the data as initial values for at least one of the one or more parameters within the anatomical feature register. The processing unit according to claim 14.

16. The anatomical structure is a cardiac structure, and the one or more parameters include one or more of the size of the heart, the size of the left ventricle, the size of the left atrium, the size of the right ventricle, the size of the right atrium at end-diastole, the ejection fraction, and / or the length of the left ventricle, the processing unit according to claim 14 or 15.

17. A system comprising: the processing unit according to any one of claims 14 to 16; and an ultrasonic data acquisition device operably coupled to the input / output unit of the processing unit. The system further comprises, optionally, a user interface for acquiring user input. ​

Images