Acquiring medical images at a target plane

Abstract

A method for acquiring a medical image at a target plane includes acquiring a three-dimensional 3D volume having an anatomical structure and identifying the anatomical structure within the 3D volume. The geometry of the anatomical structure within the 3D volume is analyzed, and the target plane is registered to the 3D volume based on the analysis of the geometry of the anatomical structure. A medical image is extracted from the 3D volume at the registered target plane.

Description

[Technical Field]

[0001] The present invention relates to a method for acquiring a medical image in a target plane, and in particular to extracting a medical image from a 3D volume in the target plane. [Background technology]

[0002] Longitudinal medical studies using 2D images are difficult to interpret due to differences in acquisition, e.g., angle, field of view (FOV), etc. In longitudinal studies, it is important to maximize the comparability of examinations performed at different time points. When scanning in 2D, the angle of the imaging device (e.g., ultrasound transducer) determines the anatomical plane of the resulting scan, and deviations in this angle can result in non-equivalent examinations compared to previous reference examinations. Summary of the Invention [Problem to be solved by the invention]

[0003] Users comparing exams over time in longitudinal studies must compensate for any effects of different acquisitions. Simple registration of images may not work because rigid registration does not always align views and elastic registration can destroy subtle differences in anatomy.

[0004] Therefore, there is a need to improve the comparability of tests in longitudinal studies.

[0005] U.S. Patent Application Publication No. 2021 / 338203 discloses a system for guiding a user to acquire an ideal 2D image. It utilizes 3D+t volume scanning and segmentation. The result is a single 2D projection for a given view plane determined at the time of the scan.

[0006] US Patent Application Publication No. 2020 / 13482 relates to a general approach to multi-planar reformat (MPR). [Means for solving the problem]

[0007] The invention is defined by the claims.

[0008] According to an embodiment of the present invention, there is provided a computer-implemented method for acquiring a medical image at a target plane, the method comprising: obtaining a 3D volume including an anatomical structure; identifying an anatomical structure within the 3D volume; analyzing the geometry of anatomical structures within the 3D volume; registering the target plane to the 3D volume based on an analysis of the geometry of the anatomical structure; extracting a plurality of medical images from the 3D volume near the registered target plane; A method is provided, comprising:

[0009] This allows the user to acquire a 3D volume / dataset without needing to precisely orient the imaging device when capturing the target view / plane, since the target plane can be extracted from the 3D volume regardless of the orientation of the 3D volume. 2D planes can be rendered (with very comparable image quality) by slicing a dedicated MPR from the 3D volume.

[0010] To accurately extract a target plane from a 3D volume, anatomical structures within the 3D volume are identified and their geometry is analyzed. This analysis of geometry allows the target plane to be accurately aligned / registered to the 3D volume.

[0011] The first aspect is extracting a plurality of medical images from a 3D volume near the registered target plane; determining a quality score for the extracted medical image; selecting a medical image from the plurality of extracted medical images based on the quality score; It has.

[0012] In this way, a symbolic image near the target plane is selected based on a quality assessment so that the medical image is a high quality image and captures the desired anatomical features (because they are near the target plane).

[0013] The second aspect is The method further comprises selecting a target plane, the target plane comprising a plane of a previous 2D scan or a plane of a future 2D scan relative to the time the 3D volume was acquired.

[0014] The 2D target plane may be determined at review time rather than at scan time, allowing for applications where the view plane can be later matched to match any desired plane, which may correspond to a previous or future 2D scan (relative to the time the 3D volume was imaged).

[0015] Thus, a prior 2D scan refers to a scan taken earlier than the time at which the 3D volume is acquired. A future 2D scan refers to a scan taken later than the time at which the 3D volume is acquired. However, extracting images may be performed after a later 2D scan, for example, to fill in gaps in the longitudinal analysis of the 2D images. Thus, a 3D volume can be captured at a time and analyzed at a later time to provide a 2D image corresponding to the later-acquired 2D scan.

[0016] The first and second aspects can be used alone or in combination.

[0017] In both aspects, analyzing the geometry of the anatomical structure can include matching features / landmarks in the identified anatomical structure to predicted features in the medical image at the target plane. The geometry can include the size of the anatomical features, the distance between the anatomical features, etc.

[0018] Registering a first plane / image / volume to a second plane / image / volume generally involves determining the transformation required to transform the first plane / image / volume into the coordinate system of the second plane / image / volume.

[0019] Identifying the anatomical structure may include using a model-based segmentation algorithm trained on a model of the anatomical structure.

[0020] Model-based segmentation increases the accuracy of segmentation because the segmentation algorithm has a priori information about the anatomical structure it is segmenting. Typically, medical scans are intentionally performed on a target anatomical structure. Therefore, model-based segmentation is particularly suitable because various algorithms can be trained on the target anatomical structure (e.g., a cardiac model, a fetal model, etc.).

[0021] Registering the target plane to the 3D volume can include registering the identified anatomical structure to a model of the anatomical structure, where the target plane is pre-registered to the model of the anatomical structure.

[0022] Different models can be used for different purposes. For example, for cardiac imaging, different models may be available for different types of hearts (e.g., pediatric, adult, etc.) and / or for different times during the cardiac cycle. A general model can also be transformed for different purposes.

[0023] Extracting a plurality of medical images from the 3D volume near the registered target plane (according to the first aspect) may include extracting the medical images at the registered target plane.

[0024] The medical image extracted in the target plane may not be of adequate quality (or may not have the best quality). Therefore, it is proposed to extract medical images in other planes near the target plane. Therefore, medical images in nearby planes with higher quality scores may be more suitable for comparison with other images taken at different times, for example.

[0025] This is particularly advantageous when a user wants to compare 2D slices from two or more 3D volumes, as the 2D slices can all be extracted in planes near the target plane that provide adequate quality for all 2D slices.

[0026] Each medical image can have a single quality score, or alternatively, each medical image can have multiple quality scores.

[0027] The quality score may be based on noise level, artifact count, field of view range, visibility of anatomical structures, etc. In a first example, the quality score of a medical image is a composite score of the above criteria. In a second example, each medical image has multiple individual quality scores for the above criteria.

[0028] The 3D volume can be labeled as the first 3D volume, and the method can further include acquiring a second 3D volume including an anatomical structure; identifying the anatomical structure in the second 3D volume; analyzing the geometry of the anatomical structure in the second 3D volume; registering a target plane to the second 3D volume based on the analysis of the geometry of the anatomical structure in the second 3D volume; and extracting a second medical image from the second 3D volume at the registered target plane.

[0029] The step of extracting the second medical image may include the steps of extracting a plurality of second medical images from a second 3D volume near the registered target plane, determining quality scores of the second medical images, and selecting the second medical image from the plurality of second medical images based on the quality scores.

[0030] The steps of extracting the first medical image (from the first 3D volume) and extracting the second medical image may be based on a quality score of the extracted first medical image (of the first 3D volume) and a quality score of the second medical image. The planes of the extracted first medical image and the extracted second medical image may be the same (or within a maximum displacement threshold). This may enable comparability of adequate quality between the two extracted medical images without being limited to an exact target plane (which may be noisy, for example).

[0031] During the 3D acquisition of the first 3D volume and / or the second 3D volume, the acquisition process may sometimes be gated to acquire anatomical structures at the same point in the cycle (e.g., for cardiac images).

[0032] The method may further include obtaining a two-dimensional 2D medical scan of the anatomical structure and determining an anatomical plane from the 2D medical scan, and the target plane may be selected as the determined anatomical plane.

[0033] This allows medical images to be extracted from 3D volumes that match the plane of a separately acquired medical scan, thereby allowing medical images to be compared (e.g., comparing anatomical structures in a target plane from different exams).

[0034] The method may further include obtaining a 3D reference volume registered to the 2D medical scan, wherein determining the anatomical plane from the 2D medical scan includes identifying the anatomical plane relative to the 3D reference volume.

[0035] The method may further include acquiring a first 2D medical scan of the anatomical structure at a first time point, acquiring a second 2D medical scan of the anatomical structure at a third time point, acquiring a 3D medical volume at a second time point between the first and third time points, and determining a first anatomical plane from the first 2D medical scan and / or a second anatomical plane from the second 2D medical scan, wherein the target plane is one of the first anatomical plane or the second anatomical plane.

[0036] Thus, the target plane can be selected as the plane of a previously acquired 2D scan (at a first time in the past) or as the plane of a future 2D scan (at a third time in the future).

[0037] For example, the user can select whether the extracted image is based on an image acquired earlier (e.g., at a first time) or an image acquired later (e.g., at a third time).

[0038] Determining anatomical planes from the 2D medical scan may include using a regression network trained to identify anatomical planes from any 2D medical scan that includes an anatomical structure.

[0039] In other words, plane regression techniques can be used to identify anatomical planes in 2D medical scans.

[0040] Extracting the medical image from the 3D medical volume may include using a multiplanar reformat (MPR) on the 3D medical volume.

[0041] The 3D medical volume may be a 3D ultrasound volume, although other types of 3D medical data may also be used.

[0042] The invention also provides a computer program carrier comprising computer program code which, when executed on a processing system, causes the processing system to perform all of the steps of the above-described method.

[0043] The computer program carrier may for example be a data storage system (eg a hard drive, solid state drive, etc.) or a transitory carrier (eg a bitstream).

[0044] The present invention also provides 1. A system for acquiring a medical image at a target plane, the system comprising: obtaining a 3D volume including an anatomical structure; identifying an anatomical structure within the 3D volume; analyzing the geometry of anatomical structures within the 3D volume; registering the target plane to the 3D volume based on an analysis of the geometry of the anatomical structure; extracting a plurality of medical images from the 3D volume near the registered target plane; The present invention provides a system comprising a processor configured to execute:

[0045] In one embodiment, a plurality of medical images are extracted from a 3D volume near the registered target plane, and the processor further performs: determining a quality score for the extracted medical image; selecting a medical image from the plurality of extracted medical images based on the quality score; is configured to execute

[0046] In another aspect, the processor is further configured to receive as input a target plane, the target plane comprising a plane of a previous 2D scan or a plane of a future 2D scan relative to the time the 3D volume was acquired.

[0047] The system may also include an imaging device for acquiring the 3D volume, for example, the imaging device may be a 3D ultrasound transducer.

[0048] The processor may be configured to identify the anatomical structure by using a model-based segmentation algorithm trained on a model of the anatomical structure.

[0049] The 3D volume may be labeled as the first 3D volume, and the processor may be further configured to acquire a second 3D volume including the anatomical structure, identify the anatomical structure in the second 3D volume, analyze the geometry of the anatomical structure in the second 3D volume, register a target plane to the second 3D volume based on the analysis of the geometry of the anatomical structure in the second 3D volume, and extract a second medical image from the second 3D volume at the registered target plane.

[0050] The processor may be further configured to obtain a two-dimensional 2D medical scan of the anatomical structure and determine an anatomical plane from the 2D medical scan, wherein the target plane is the determined anatomical plane.

[0051] These and other aspects of the invention will be apparent from and elucidated with reference to the embodiments described hereinafter.

[0052] For a better understanding of the present invention and to show more clearly how it may be carried into effect, reference will now be made, by way of example only, to the accompanying drawings in which: [Brief explanation of the drawings]

[0053] [Figure 1] Shown are 2D scans of the anatomy at three separate times. [Figure 2] Shown are 3D scans of the anatomy at three separate times. [Figure 3] 3D acquisition process is shown. [Figure 4] An approach for obtaining a target plane from a 2D slice is presented. [Figure 5] 1 shows a time series of scans including a first 2D scan, a second 3D scan, a third 3D scan, a fourth 2D scan, and a fifth 3D scan. [Figure 6] A method is presented for acquiring medical images at a target plane using a three-dimensional 3D volume containing anatomical structures. DETAILED DESCRIPTION OF THE INVENTION

[0054] The present invention will now be described with reference to the drawings.

[0055] It should be understood that the detailed description and specific examples, while indicating exemplary embodiments of the devices, systems, and methods, are for purposes of illustration only and are not intended to limit the scope of the invention. These and other features, aspects, and advantages of the devices, systems, and methods of the present invention will become better understood from the following description, appended claims, and accompanying drawings. It should be understood that the figures are schematic only and are not drawn to scale. It should also be understood that the same reference numerals are used throughout the figures to indicate the same or similar parts.

[0056] The present invention provides a method for acquiring a medical image at a target plane. The method includes acquiring a three-dimensional 3D volume containing an anatomical structure and identifying the anatomical structure within the 3D volume. The geometry of the anatomical structure within the 3D volume is analyzed, and the target plane is registered to the 3D volume based on the analysis of the geometry of the anatomical structure. A medical image is extracted from the 3D volume at the registered target plane.

[0057] Figure 1 shows 2D scans at three separate times of an anatomical structure 102. In Figure 1, the anatomical structure 102 is shown as a heart for illustrative purposes only. It will be understood that other anatomical structures (e.g., lungs, liver, fetus, etc.) may be imaged instead.

[0058] To allow a user to compare 2D acquisitions (i.e., 2D scans or 2D medical images) at three separate times t1, t2, and t3, the imaging device (e.g., a transducer for ultrasound imaging) (not shown) must be aligned three times with respect to the target plane 104. This means that the angle of the imaging device must be carefully reproduced (e.g., in each separate examination) so that the field of view 106 of the imaging device captures the target plane 104 each time.

[0059] If the imaging device is not aligned correctly, the 2D acquisition may be in a different plane and therefore not comparable to the before / after acquisitions taken at the target plane.

[0060] It is proposed to solve this problem by acquiring a 3D volume of the anatomical structure 102 and then slicing 2D anatomical planes from the 3D acquisition.

[0061] Recently, ultrasound imaging has been moving towards 3D volume acquisition. 3D matrix probes are available for scanning. 2D slices can then be extracted from the 3D volume using predefined slicing or parametric slicing. However, such slicing techniques do not always provide 2D slices at the exact target plane.

[0062] FIG. 2 shows 3D scans of an anatomical structure 102 at three separate times. In this case, the angle of the imager (not shown) is not critical because the field of view 202 is much larger during 3D acquisition compared to 2D acquisition (as shown in FIG. 1). Therefore, the target plane 104 can be sliced / extracted from the 3D acquisition. In other words, slicing a 2D anatomical plane from the 3D acquisition mitigates the dependency on the angle of the imager during acquisition because a plane that is not axially aligned with the imager can be sliced ​​from the volume, as shown in FIG. 2.

[0063] Thus, the user does not need to be as precise as the position / angle of the imaging device at different times (e.g., during different examinations in a longitudinal study). In some cases, the user may want to compare a current 2D slice at the target plane 104 with a previous 2D slice. This was only possible if the user had previously acquired a 2D slice at the target plane 104. However, the user may have previously acquired a 3D volume of the anatomical structure 102. Thus, the user can extract a 2D slice from the previously acquired 3D volume at the target plane to compare with the current 2D slice.

[0064] Figure 3 illustrates the 3D acquisition process. In particular, Figure 3 shows the anatomical structure being scanned at three different times t1, t2, and t3 during three different examinations. During each examination, the angle of the imaging device (not shown) is not important because the 3D acquisition can capture all necessary information on the anatomical structure 102 and store it in a 3D volume 302 due to the large field of view 202.

[0065] The 3D volume 302 can be stored, for example, in Cartesian or polar coordinates. The 3D volume can be sliced ​​(e.g., at a later date) to acquire medical images 304 at any target plane. Thus, even if only 2D acquisition is required for a longitudinal study (i.e., multiple exams over time), storing the 3D volume 302 allows a user to extract / slice the 3D volume at a target plane on demand, thereby acquiring equivalent medical images 304.

[0066] To obtain equivalent images (i.e., the same target plane) from unregistered volumes, it is important to be able to accurately register the target plane to each volume so that the 2D slices are accurately registered to the same target plane.

[0067] The target plane can be registered to the volume by first identifying anatomical structures within the 3D volume. For example, a segmentation algorithm can be used to identify the anatomical structures within the 3D volume. Additionally, anatomical model-based segmentation can be used to more accurately identify the anatomical structures. For example, a segmentation algorithm can be trained from one or more models of anatomical structures (e.g., heart, fetus, etc.) to more accurately identify the anatomical structures within the 3D volume.

[0068] The segmented structure can be treated as an anatomical model. This means that the expected geometry of features in the target plane can be mapped to features in the segmented anatomical structure. Standard target planes can be carefully defined and validated using a combination of vertices (e.g., centroids, axes, distances, etc.) of a particular anatomical structure.

[0069] For example, in cardiac ultrasound imaging, the target plane can be defined by taking all the "mitral annulus" apexes to calculate the mitral valve center, which also forms the image center. By orienting one axis toward the left ventricular apex (defined by another set of apexes) and the second axis toward the aortic valve center (calculated as above), a coordinate system can be derived to register the target plane to the 3D volume. Finally, the size of the medical image can be given by a scaling factor used to adapt an anatomical model to the acquired 3D volume (e.g., during segmentation).

[0070] In other words, the standard target plane is defined in the cardiac coordinate system of the anatomical model and can be transformed into the 3D volume in the same way as the anatomical structure does (e.g., during model-based segmentation).

[0071] More generally, the geometry of features in the 3D volume can be matched to the geometry of features expected in the image at the target plane in order to register the target plane to the 3D volume.

[0072] The target plane can be a standard plane or a plane nearby that is already registered to an anatomical coordinate system (e.g., the coordinate system of a model of the cardiac structure). Thus, the geometry of the segmented anatomical structure can be used to register the target plane to the segmented anatomical structure.

[0073] Additionally, arbitrary planes can be mapped from one volume to another by describing the plane with reference to a segmented mesh of the anatomical structure in a first volume, transforming the planar reference to the second volume via the corresponding vertices in the mesh (which can be subject to affine, but also non-rigid, deformations), and finally deriving the corresponding plane in the second volume. For arbitrary planes, an anatomical model is preferably used to establish correspondences between vertices so that arbitrary planes can be established for all volumes.

[0074] For longitudinal studies, upon follow-up with at least one additional examination, a combinatorial optimization can be performed across all studies consisting of segmenting each 3D volume (e.g., via an anatomical model), extracting the desired target anatomical plane for review (e.g., a standard target plane or an arbitrary target plane), and selecting the slice that yields the greatest comparability across the various studies, allowing for slight deviations from the target plane.

[0075] Optimization can take into account noise levels, artifact counts, FOV coverage, visibility of anatomical structures, etc. when selecting slices to be compared. This results in an optimized series of respective 2D slices per exam / time point that are comparable, and therefore higher diagnostic confidence.

[0076] To compensate for motion, residual errors in segmentation, or noise in the extracted 2D slices, it may be preferable to search for comparable 2D slices in the vicinity of the target plane. Of course, some anatomical structures may be ambiguous, so a global search across the 3D volume is possible. This may mean, for example, finding an arbitrary target plane that provides the best comparison between the 3D volumes. However, this approach may yield suboptimal results, as the arbitrary plane may not show the desired features of the anatomical structure.

[0077] In some cases, a 2D scan of the anatomy may already exist at the target plane (e.g., from a previous study / examination). In these cases, the 2D scan can be used to acquire the target plane and thus extract further 2D slices from the 3D volume of the anatomy.

[0078] 4 shows an approach for obtaining a target plane from a 2D slice. In a longitudinal study, if at least one exam is a 2D scan 402 taken with a different technique or probe, or if 3D information is not available for the exam, it is proposed to use the 2D scan 402 to obtain a target plane 408. The target plane 408 can then be used to slice the 3D volume so that the 2D slices can be compared.

[0079] For each 2D image 402, an anatomical plane can be determined using a plane regression technique. The input 2D image 402 is segmented to identify anatomical structure boundaries 404. The plane parameters can then be derived, for example, by a recurrent convolutional neural network trained using pairs of artificial contours and plane parameters. Thus, a target plane 408 can be defined relative to an anatomical model 410 using the plane parameters.

[0080] As described above, the 3D volume can then be segmented using a cardiac model or deep learning segmentation methods, and corresponding slices can be generated using the plane parameters determined for the target plane 408, for example, using a multiplanar reformat (MPR).

[0081] Here, longitudinal series can be presented for any plane seen in the 2D scan. In the case of multiple 2D scans, the user can select any 2D scan, and the 3D acquisition can then be reformatted to optimally review changes over time with respect to the selected scan orientation.

[0082] A similar technique can be used in a 2D workflow performed with a 3D probe. Most of the scans during the examination can still be recorded in 2D. However, at certain times (e.g., during the end-diastolic frame), the system can record a single-frame 3D image in the background, possibly at a lower resolution. These recorded 2D slices have a 3D reference that can be analyzed. In other words, the plane of the 2D slice is registered to a 3D model of the anatomical structure (i.e., via 3D reference acquisition). In this way, a 2D workflow for use by many physicians is maintained, and target planes can be acquired for later use (e.g., to acquire additional 2D slices at the target plane from a later 3D acquisition). This can be useful for not sacrificing frame rate during scanning (e.g., for valve or larger field-of-view scans).

[0083] The use of 3D fiducials can provide a more accurate target plane because the target plane is already defined relative to the 3D fiducial of the anatomy, and therefore there is no need to apply planar regression to 2D slices. For some target planes (e.g., the short-axis plane in cardiac ultrasound), planar regression may not always be accurate.

[0084] Additionally, subsequent scans can be compared to one another using the techniques described above, for example, 2D slices can be acquired from a subsequent 3D acquisition if the acquisition plane is not aligned with the previous acquisition.

[0085] If a 2D image is not acquired at the target plane, it is not possible to reformat the already acquired 2D image to best match across the longitudinal scan, however, it is still possible to derive a 2D image at the target plane using a 3D reference frame.

[0086] If knowledge of the target plane is used during the scan, the 2D parameters can be adapted to capture the corresponding target plane during the scan. Knowledge of the target plane can also be used retrospectively so that deviations from the target plane can be found, thus also finding possible defects in the measurement.

[0087] Slicing / extracting 2D slices from a 3D volume of an anatomical structure can be used to fill in gaps in a longitudinal series of 2D scans.

[0088] 5 shows a time sequence of scans including a first 2D scan 502, a second 3D scan 504, a third 3D scan 508, a fourth 2D scan 512, and a fifth 3D scan 514. The first 2D scan 502 and the fourth 2D scan 512 may be scans of anatomy in the same target plane. To fill in the gaps between the first 2D scan 502 and the fourth 2D scan 512, 3D scans obtained between (and possibly before and after) the 2D scans may be sliced ​​in the target plane corresponding to the first 2D scan 502 and / or the fourth 2D scan 512.

[0089] Extracting 2D scans from the 3D volume may include using multiplanar reformat (MPR) on the 3D scans at a target plane. The target plane may be obtained by identifying a plane of the first 2D scan 502 and / or a plane of the fourth 2D scan 512. The second 3D scan 504 may then be sliced ​​at the target plane to obtain an MPR slice 506. Similarly, the third 3D scan 508 may be sliced ​​at the target plane to obtain an MPR slice 510, and the fifth 3D scan 514 may be sliced ​​at the target plane to obtain an MPR slice 516. Thus, the first 2D scan 502 and the fourth 2D scan 512 may be compared to the MPR slices 506, 510, and 516.

[0090] Generally, if a 2D scan is missing in a time series, the target plane can be estimated from other 2D scans and then sliced ​​from the 3D volume. Thus, the sonographer can consider the equivalent slice for exams where the initial acquisition of the 2D plane was missed or forgotten.

[0091] Thus, the target plane may be selected as the plane of a previously acquired 2D scan or the plane of a future 2D scan.

[0092] The operator / user can decide to align the MPR slice to any of the 2D scans by selecting (e.g., via clicking) the MPR slice, so that the MPR slice matches the selected scan. If multiple 2D slices are selected, the matching MPRs for each of them can be displayed simultaneously. This can provide further insight into whether differences in the 2D scans result solely from different positions (e.g., if the differences are also present when displaying corresponding MPRs from a single 3D scan) or from disease progression.

[0093] 6 illustrates a method for acquiring a medical image at a target plane using a three-dimensional 3D volume containing anatomical structures. The anatomical structures are identified within the 3D volume in step 602. For example, a segmentation algorithm can be applied to the 3D volume. The segmentation algorithm can be a model-based segmentation algorithm trained on one or more models of the anatomical structures.

[0094] Then, in step 604, the target plane is registered to the 3D volume. This may be achieved by analyzing the geometry of the segmented anatomical structure. For example, the relative positions of features within the anatomical structure may be used to register the segmented anatomical structure to a model of the anatomical structure to which the target plane is already registered (e.g., a segmented anatomical structure obtained from a previous examination). The target plane may then be transformed into the segmented anatomical structure. Then, in step 606, a medical image may be extracted from the 3D volume at the registered target plane.

[0095] Note that instead of extracting a single image at the target plane, multiple images may be extracted near the registered target plane, the multiple images may be extracted at a set of parallel planes adjacent to the target plane, or non-parallel planes may be defined that intersect the target plane.

[0096] Parallel planes can be derived by shifting the original plane along the plane's normal vector, for example by shifting the plane using separate offsets in both directions, such as 1 mm, 2 mm, 3 mm, etc. along both directions.

[0097] Non-parallel planes can be derived in various ways, such as by determining a point on the plane as the rotation point, e.g., the center of the plane or the center of the anatomical structure of interest. The axis of the plane may be defined as the axis of rotation, e.g., the x- or y-axis of the plane. The original plane may, for example, be rotated around the origin and the axis of rotation in discrete steps, e.g., +-2 degrees, +-4 degrees, +-6 degrees.

[0098] This process can be repeated using different centers and axes of rotation (eg, rotating first about the x-axis, then about the y-axis, or about an axis between x and y).

[0099] A quality score is then derived for the extracted medical image.

[0100] A medical image may then be selected from the plurality of extracted medical images based on the quality score.

[0101] The final extracted 2D slices are thus not just based on matching (standard) views of the anatomy, but also on optimizing the quality scores for better comparability in longitudinal studies.

[0102] The optimization is The noise level of the image, Number of artifacts, Field of view, Anatomical structure visibility One or more of the following may be taken into consideration:

[0103] The concepts described herein generally apply to ultrasound images, however the methods also apply to other medical imaging modalities that have 3D acquisition modes.

[0104] The concepts described herein are particularly advantageous for obtaining standard views from a 3D volume. For example, standard views are particularly important in cardiac or fetal ultrasound images. The target planes described herein may correspond to said standard views.

[0105] Those skilled in the art will be able to readily develop a processor to perform the methods described herein, and therefore each step of the flowchart may represent a different action performed by a processor and may be performed by a respective module of the processor.

[0106] As described above, the system utilizes a processor to perform data processing. The processor can be implemented in a number of ways using software and / or hardware to perform the various functions required. The processor typically uses one or more microprocessors that can be programmed using software (e.g., microcode) to perform the necessary functions. The processor can also be implemented as a combination of dedicated hardware to perform some functions and one or more programmed microprocessors and associated circuitry to perform other functions.

[0107] Examples of circuitry that may 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).

[0108] In various implementations, a processor may be associated with one or more storage media, such as volatile and non-volatile computer memory, including RAM, PROM, EPROM, and EEPROM. The storage media may be encoded with one or more programs that, when executed on the one or more processors and / or controllers, perform the necessary functions. The various storage media may be fixed within the processor or controller, or may be portable, such that the one or more programs stored thereon can be loaded into the processor.

[0109] 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.

[0110] A single processor or other unit may fulfill the functions of several items recited in the claims.

[0111] The mere fact that certain measures are recited in mutually different dependent claims does not indicate that a combination of these measures cannot be used to advantage.

[0112] The computer program may 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 over the Internet or other wired or wireless telecommunications systems.

[0113] It should be noted that when the term "adapted for" is used in the claims or description, the term "adapted for" is intended to be equivalent to the term "configured for."

[0114] Any reference signs in the claims should not be construed as limiting the scope.

Claims

1. 1. A computer-implemented method for acquiring a medical image at a target plane, comprising: obtaining a 3D volume including an anatomical structure; identifying an anatomical structure within the 3D volume; analyzing the geometry of anatomical structures within the 3D volume; registering the target plane to the 3D volume based on an analysis of the geometry of the anatomical structure; extracting a plurality of medical images from a 3D volume near the registered target plane; determining a quality score for the extracted medical image; selecting a medical image from the plurality of extracted medical images based on the quality score; A method comprising:

2. 2. The method of claim 1, further comprising selecting a target plane, the target plane comprising a plane of a previous 2D scan or a plane of a future 2D scan relative to the time at which the 3D volume was acquired.

3. 3. The method of claim 1, wherein identifying the anatomical structure comprises using a model-based segmentation algorithm trained on a model of the anatomical structure.

4. The 3D volume is a first 3D volume, and the method further comprises: acquiring a second 3D volume including the anatomical structure; identifying an anatomical structure within the second 3D volume; analyzing the geometry of anatomical structures within the second 3D volume; registering the target plane to the second 3D volume based on an analysis of the geometry of anatomical structures within the second 3D volume; extracting a second medical image from the second 3D volume at the registered target plane; A method comprising:

5. obtaining a 2D medical scan of the anatomical structure; determining an anatomical plane from the 2D medical scan, wherein the target plane is the determined anatomical plane; 5. The method of claim 1, further comprising:

6. 6. The method of claim 5, wherein obtaining a 3D reference volume registered to the 2D medical scan, and determining the anatomical plane from the 2D medical scan comprises identifying the anatomical plane relative to the 3D reference volume.

7. acquiring a first 2D medical scan of the anatomical structure at a first time; acquiring a second 2D medical scan of the anatomical structure at a third time; acquiring the 3D medical volume at a second time between the first time and the third time; determining a first anatomical plane from the first 2D medical scan and / or determining a second anatomical plane from the second 2D medical scan, wherein the target plane is one of the first anatomical plane or the second anatomical plane; 7. The method according to claim 1, comprising:

8. 8. The method of claim 1, wherein extracting the medical image from the 3D medical volume comprises using a multiplanar format on the 3D medical volume.

9. The method of claim 1 , wherein the 3D medical volume is a 3D ultrasound volume.

10. A computer program carrier comprising computer program code which, when executed on a processing system, causes said processing system to perform all of the steps of the method according to any one of claims 1 to 9.

11. 1. A system for acquiring a medical image at a target plane, the system comprising: obtaining a 3D volume including an anatomical structure; identifying an anatomical structure within the 3D volume; analyzing the geometry of anatomical structures within the 3D volume; registering the target plane to the 3D volume based on an analysis of the geometry of the anatomical structure; extracting a plurality of medical images from a 3D volume near the registered target plane; determining a quality score for the extracted medical image; selecting a medical image from the plurality of extracted medical images based on the quality score; 1. A system comprising: a processor configured to execute

12. 12. The system of claim 11, wherein the processor is configured to receive as input a target plane, the target plane comprising a plane of a previous 2D scan or a plane of a future 2D scan relative to a time at which the 3D volume was acquired.

13. 13. The system of claim 11 or 12, wherein the processor is configured to identify the anatomical structures by using a model-based segmentation algorithm trained on a model of the anatomical structures.

14. the 3D volume is a first 3D volume, and the processor further: acquiring a second 3D volume including the anatomical structure; identifying an anatomical structure within the second 3D volume; analyzing the geometry of anatomical structures within the second 3D volume; registering the target plane to the second 3D volume based on an analysis of the geometry of anatomical structures within the second 3D volume; extracting a second medical image from the second 3D volume at the registered target plane; 14. The system of claim 11, configured to:

15. The processor further comprises: obtaining a 2D medical scan of the anatomical structure; determining an anatomical plane from the 2D medical scan, wherein the target plane is the determined anatomical plane; 15. The system of any one of claims 11 to 14, configured to:

Images